Lean Six Sigma Notes PDF

Lean Six Sigma Process improvement, problem solving Can be defined using 3Ms: Metric – measure the capability of a process to conform to certain requirement. If a process follows a six-sigma level, it only produces 3.4 DPMO (Defects per Opportunity) Lower lean sigma le...

Lean Six Sigma Process improvement, problem solving Can be defined using 3Ms: Metric – measure the capability of a process to conform to certain requirement. If a process follows a six-sigma level, it only produces 3.4 DPMO (Defects per Opportunity) Lower lean sigma levels such as 3 sigma or 4 sigma produces more DPMO THE HIGHER THE SIGMA LEVEL THE BETTER A PROCESS IS. Methodology – follows a proven and effective step by step process depending on the type of process that you want to manage, improve, or explore DMAIC (Define, Measure, Analyze, Improve, and Control) – used for existing processes DMADV (Define Measure Analyze Design and Verify) – used for new product and processes. Management System – to cut operation costs - Specific problem-solving approach and specialized tools - Data driven - Reduce process variation (3.4 DPMO, 99.9999967% conformance) - Satisfies the customers and minimizes loses Lean Six Sigma Waste elimination Variation Reduction Taiichi Ohno Bill Smith/Mikel Harry Toyota Motorola 1940s 1980s Practical Statistical The marriage of Lean and Six Sigma makes the methodology more powerful in driving operational excellence. 5 Pillars of Lean Define Value Value is defined by the customer’s needs for a specific product or service. (Ex. What is the timeline for manufacturing and delivering?) Map the Value Stream Value stream are steps and processes involved in taking a specific product from raw materials and delivering the final product to the customer. Identifies all the actions that take a product or service through any process The goal is to identify every step that does not create value, then find ways to eliminate those wasteful steps. Value stream mapping is sometimes referred to as process reengineering Create Flow Ensure that the remaining steps flow smoothly with no interruptions, delays, or bottlenecks. May require breaking down silo thinking and making the effort to become cross- functional across all department. Establish Pull Products don’t need to be built in advance or materials stockpiled, creating expensive inventory that needs to be managed, saving money for both the manufacturer/provider and the customer. Pursuit of Perfection Making Lean thinking in process improvement part of your corporate culture Lean requires constant effort Every employee should be involved in implementing lean. Taiichi Ohno, considered the father of Toyota Production System, created a lean manufacturing framework, which was based on the idea of preserving (or increasing) value with less work. Anything that doesn’t increase value in the eye of the customer must be considered waste, or “Muda”, and every effort should be made to eliminate that waste. The 8 Wastes of Lean (Downtime) Defects Mistakes that require additional time, resources, and money to fix. In a manufacturing process, a defect might involve a defective part that has to be remade. § Poor quality controls § Poor repair § Poor documentation § Lack of Standards § Weak or missing processes § Misunderstanding customer needs § Uncontrolled inventory levels § Poor design & undocumented design changes Completely eradicating any form of waste is impossible, but defects can certainly be limited by the application of standardized work plans, more stringent quality control at all levels, a full understanding of work requirements and customer needs, and simple job aides such as checklists. Over Production In some organizations, workers just blindly keep producing, even when those who receive their output either aren’t ready for it or don’t need it. This is a big flaw as it can tie up significant working capital. It’s especially common in manufacturing, but it can occur in any workplace situation in which there’s a bottleneck § Just-in-case production § Unclear customer needs § Producing to a forecast § Long set-up times § Engineering changes § Poorly applied automation The solution to overproduction is to establish a reasonable workflow for the benefit of the customer. Be sure that there are well’-established procedures in place for every process in your organization, and if necessary, implement new processes to keep work from backing up behind bottlenecks in the organization Waiting Occurs whenever work has to stop for some reason, because the next person in line is overwhelmed, because something broke down, because you’re waiting for approval or materials, or because you’ve run out of something. § Unbalanced workloads § Unplanned downtime § Long set-up times § Producing to a forecast § Insufficient staffing § Work absences § Poor process quality § Poor communication Whatever that cause, some workers have to wait for a bottleneck to be cleared. One way to address this is the need to provide adequate staffing to handle the workload at the bottlenecks, which some managers may target as a source of monetary waste, Non-Utilized Talent Not or underutilizing people’s talents, skills and knowledge can have a detrimental effect on an organization. Companies can experience great benefits when recognizing the value of skills and improvement ideas from all levels of the business and can suffer when not effectively engaging in the process. § Assigning staff to wrong tasks § Wasteful admin tasks § Poor communication § Lack of teamwork § Poor management § Insufficient training If the above list sounds oddly familiar, it should: many of these failings are the same ones that result in a lack of employee engagement, which can hamstring any organization’s productivity. Key solutions include empowering your employees, stop micromanaging and increase training.  Transportation Waste caused by moving things around. This is less of a problem in a business office that in a manufacturing plant, since most of what white collar worker’s “transport” can be sent by email for example. Otherwise, too much transportation tends to increase costs, wastes time, increases the likelihood of product damage and deterioration, and can result in poor communication. § Poor plant/office layout § Unnecessary or excessive steps in the process § Misaligned process flow § Poorly designed systems Limiting transportation waste can be easily addressed by common-sense effort such as simplifying processes, repairing physical layouts, handling products less often, and making distances between steps as short as possible Inventory This waste occurs when there is supply in excess of real customer demand, which masks real production. § Overproduction and buffers § Poor monitoring systems § Mismatched production speeds § Unreliable suppliers § Long set-up times § Misunderstood customer needs Motion Any excess movement, whether by employees or machines, that doesn’t add value to the product, service or process. § Poor process design and controls § Poor workstation/shop layout § Shared tools and machines § Workstations congestion § Isolated and siloed operations § Lack of standards The solution here is to re-arrange layouts to decrease the distance between stations and make it easier to reach things that are often used. Extra-processing This often occurs due to the creation of multiple versions of the same task, process more than is required or long-winded poorly designed processes. § Excessive reports § Multiple signatures § Re-entering data and duplicated data § Lack of standards § Poor communication § Overdesigned equipment § Misunderstanding of the customer’s needs § Human error All of these unnecessarily increase your cost, time and resources. You must first examine and map your organization to analyze the processes in order to fix them. Standardize processes, empower employees and eliminate unnecessary documentation, sign-off processes and meetings. Systematic elimination of these wastes can result in faster processes, lower costs, higher quality, happier workers and, most importantly, happier customers. Exercise #1: Practicing 8 Wastes 1. Administering incorrect doses to patients. DEFECTS 2. Moving hospital patients from department to department. TRANSPORTATION 3. Waiting for responses from other departments. WAITING 4. People searching for materials, tools or equipment. MOTION 5. Creation of meals that are not eaten or partially eaten. OVERPRODUCTION 6. Entering the same data in more than one place on a form or in a software application. EXTRA PROCESSING 7. Cabinets full of office supplies. INVENTORY 8. People with advanced skills do routine work. NON-UTILIZED TALENT 9. Patients waiting in waiting rooms. WAITING 10. Extra report information. EXTRA PROCESSING Y = f(x) of Six Sigma Thinking Can help determine the cause and effect in the project DEFINE PHASE Goal is to establish the project’s importance, problem/opportunity, goal, scope and team. Output Deliverables: (Project Charter) A clear Business case, problem, and goal statement Selected critical to quality characteristic High level process map Steps Project Charter > SIPOC Diagram > Understand VOC (Voice of the Customer) Difference between Problem Solving and Process Improvement What is a problem? GAP = PROBLEM GAP between what is actually happening and what should be happening Therefore, the activity that we do to close that gap between the current and standard is... Problem Solving – Centers on the fundamental notion of “gap” or “deviation” from standard (e.g. cost, quality, delivery) Standard – what should be happening Current situation – what is actually happening What is an Improvement? GAP = OPPORTUNITY Improvement – focuses on achieving a new standard or level of performance. New Standard – a new level of performance that can be set based on historical performance. Current Standard – already hitting the current standard for the longest time. Baseline means current performance. THERE ARE BENEFITS IN CLOSING THE GAP. (e.g., Reduced Cost, Improved Yield, Improved Customer Satisfaction, Faster Processes) How to Choose the Right Problem? Problem Classification Matrix Simple Concern Significant Solution Only one obvious solution with alternative solutions (No other alternative solutions) Frequency of Occurrence Once Recurring Examples for Simple Concern 1. Sudden breakdown of machine for the first time 2. Sudden drop in yield due to use of unauthorized material 3. Increase in material cost due to sudden change in demand Examples for Significant Problems 1. Frequent machine breakdowns 2. Increasing rejection rate 3. Decreasing attendance rate Four Characteristics to Choose the Right Problem - Recurring or continuous - Verifiable (there is enough data to prove that the problem exists) - Can be analyzed and solved by team members (problems should be within control, so actions can impact the bottom line) - Negatively affecting the work life of team members Choosing the right problem is critical in the Define Phase because it will dictate the impact that we will generate from the completion of the project. PROJECT CHARTER - Tool barrowed from the Project Management Body of Knowledge (PMBOK). - It is a “contract” between the organization’s leadership and the project team created at the outset of the project. - It serves as a communication vehicle to establish a common understanding of the project among all involved. Stakeholders are those who will be involved and affected by the project. Project Charter Title Problem Statement Business Case & Benefits Goal Statement Preliminary Plan/Timeline Scope In/Out Team Members Project Charter Elements Business Case: Importance of doing the project. It answers the question “why are we doing the project?” Problem Statement: Description of the pain that the process experience. Goal Statement: SMART objectives. Process Scope: Process boundaries, resources. Project Timeline: Timetable of actions to achieve the goal. Consequential Metric: Metric that will be affected negatively once the primary metric of the project has been improved. Risk assessment part of the Project Charter. Team Members: People who will work together to achieve the goal. Yield is the ratio of the good output over the total output that has been produced. The higher the better. How to Write Problem and Goal Statements Tips in Writing the Problem Statement - Develop the problem statement in such a way that the problem is obvious. - Highlight the deviation from the standard or the “should” with the use of the adjectives or words such as: o High or increasing defect rate o Low or decreasing yield o Frequent machine breakdown o Many complaints o Delay in  DO NOT imply the most likely “Due to” This prevents the team from cause of the problem. “Because of” analyzing the problem thoroughly as they will tend to focus only on the stated cause. DO NOT use “lack of” in stating “Lack of” This provides instant solution. the problem. Usually, these clauses are the causes not the problems. DO NOT state the problem in “System” It will be difficult to solve a terms that are too broad or too “Communication” problem without knowing the narrow to be measured. magnitude. DO NOT state the problem as a “How to” This kind of statement prompts question. the group to formulate solutions without even analyzing causes. Tips in Writing the Goal Statement Goal Statement answers the Problem Statement - Start with an action verb. - Focus on the numbers. - Include the completion date. follows Specific Measurable Achievable Realistic Timely objective DO NOT include a solution. “By implementing” This violates the problem- “Through the application” solving process, because the team has already identified solution even without the analysis phase. Problem Statement Decreasing Process Yield at Assembly is at 98.12% since WW41 to WW52 versus factory target of 99.50% which is a gap of 1.38%. Goal Statement To increase Process Yield at Assembly from 98.12% to 99.5% which is 1.38% improvement by the end of October 2017 SIPOC DIAGRAM What is a SIPOC Diagram? tool to scope the project - It is a high-level process map that shows process boundaries. - A tool that allows a team to see their process in relation to all needed inputs, outputs and suppliers. - Identifies relationship between suppliers, inputs and the process. SUPPLIER > INPUT > PROCESS > OUTPUT > CUSTOMER SIPOC helps to answer the following questions - What is the start and end points of the work system? - What are the essential steps within the work system? - What are the main inputs and outputs? - Who are the key customers (Internal and External)? - Who are the key suppliers (Internal and External)? Guide in Answering the SIPOC Questions Supplier Input Process Output Customer Who are the What are the What is the What are the Who are the suppliers of the required inputs? process? expected customers of the inputs? outputs? outputs? Persons, Material, data, Process from start Product, yield End user, machines, workforce, to end information, etc. department, processes, etc. knowledge, etc. customer, etc. How to Create a SIPOC Diagram? 1. Describe the Process form start to end. 2. Specify the quality Output 3. Identify the Customers of the Output 4. Identify the needed Input 5. Identify who the Supplier is Define Phase Quiz 1. The Objective/Goal Statement must include the solution to the identified problem. False 2. Project charter element that describes the importance of doing the project. Business Case 3. There are benefits associated with the goals of closing the GAP. True 4. “Increasing rejection rate with an average of 5% vs target of 2% since WW20 to WW32 which is a gap of 3% due to process X operators” is a correct problem statement. False 5. A tool used to see boundaries of the process on the onset of the project. SIPOC Diagram 6. This is an activity that we do to close the gap between the current condition and target condition. Problem Solving 7. This is an activity that we do to create a new baseline or target. Improvement 8. These are types of problems that are recurring, and solutions are not known yet. Significant 9. How many process steps are recommended in creating your SIPOC Diagram? 5 -7 10. What kind of metric is said to be the risk assessment metric for your project? Consequential MEASURE PHASE Goal: To understand how the process operates, validate measurement systems, and establish baseline performance metrics. Output Deliverables: - Detailed process map - Validated measurement system - Baseline process performance - Revised project charter (if necessary) Create detailed > Identify possible > Validate > Establish baseline process map causal factors MSA process performance Process Map will help to understand current state of the process - It is used to visualize the nature and flow of the steps in a process. - It also breaks the process down into its many sub-processes. - It analyzes each of these separately minimizes the number of factors that contribute to the variation in the process. Process Mapping Symbols Symbol Name Description Start & end points Identifies process start and end Activity Process steps being done Decision Depicts decision nodes/points Arrow Represents process flow Connectors Connect process map to another flow or page Process Map Sample for Training Key Notes: - Process maps are living documents and must be changed as process. - Map what is happening to better understand the potential causes of the problem. - Should be created by individuals from the process or a subject matter expert should be involved. Deployment Process Map Sample Key Notes: - Show process steps and respective owners. - Preferred type when interested on a more detailed map and can be used to identify potential process issue. Essential Tips for Process Mapping 1. Don’t map for mapping’s sake 2. Walk the process (GEMBA Walk) 3. Map what the process really is. 4. Keep it simple. The Power of Data in Lean Six Sigma Measurement Power Y = f (X) Define Measure Analyze Improve Control Activated by Measurements Measurement – data that has been taken from the process that is being used to analyze the factors that causes the problem. All of the analysis is powered by data or measures. During define and measure phases, our concern is to analyze our Y data (effect, problem that we are trying to solve, or opportunity that we try to capture. During analyze phase our concern is to find the significant relationship between Y and X (factors and causes of the problems denoted by Y). We are trying to figure out how Y response as X change During improve and control Phases we focus on X, therefore the data that we will be leaving is coming from X or the factors, or the causes during these phases. Data Types Continuous – any data that has been captured or collected coming from what we call a continuum scale. Measurable data Discrete – data that do came from counts or categories. Generally, categories and afterward counted. Measurement Scales Data Types Knowing your data type means knowing the right tool to analyze them. Categorical – data that came from categories. If you can categorize them therefore you can count them Numerical – data coming from measurements. Continuous measurements from continuum scale. It is important to know the data type because it will dictate on what tools are we using for the analyze phase. Nominal Data Nominal values represent discrete units and are used to label variables, that have no quantitative value. Order does not matter. What is your Gender? What languages do you speak? - Female - English - German - Male - French - Spanish Ordinal Data Ordinal values represent discrete and ordered units. It is therefore nearly the same as nominal data, except that it’s ordering matters. What is Your Educational Background? - 1 – Elementary - 2 – High School - 3 – Undergraduate - 4 – Graduate 1st, 2nd, 3rd,... Interval Data Interval values represent ordered units that have the same difference. Temperature? - -10 - +5 - -5 - +10 - 0 - +15 Ratio Data Ratio values are also ordered units that have the same difference. Ratio values are the same as interval values, with the difference that they do have an absolute zero. Length (inch)? - 0 - 10 - 5 - 15 Data Collection Planning Collecting Baseline Measurement Here are the three (3) general steps when collecting and establishing baseline measurement: Select the measure(s). > Develop a data collection plan. > Go get the data! Measure(s) – refers to the metric or the data that we need to capture or collect in order for us to have a good baseline of the existing performance of the process Data Collection Plan – will serve as a guide in order for us to know what are the data that need to be collected and who will collect it and move forward. Data Gathering Procedure – the actual execution of the data collection plan. Primary and Relevant Data yield is the ratio of good Model Operator parts / total parts produced, Yield Line Source Age perish of the good service / Date, Time, Shift Tenure total no. of service rendered Gender Process Attendance Status Shift Tenure Group Primary Data – is the main metric or main KPI, it will be the basis of understanding the problem. However, having primary data is not enough that is why we need to collect relevant data. Data Collection Plan Unit of Operational Collection Data Sampling Plan In Charge Measurement Definition Method Amount of time it takes from the moment the customer Restaurant Order Lead started to Thru time Minutes Every order Systems Time order, to the studies Officer moment the order has been served to the customer. Data means the basis of the problem Basic Statistics for Lean Six Sigma Statistics is used to convert data into useful information. Probability and Statistics - It is the language of the data that are converted into information. - It is the art of collecting, classifying, presenting, interpreting and analyzing raw data as well as making inferences and conclusions about a population under study. - It provides modern decision makers a tool to arrive in a more confident business decisions. Statistics is significant in the process of value creation. The DID Approach Data > Insights > Decision Coming from several sources the data will be collected, cleaned, organized, visualized and analyzed, so that we can draw out insights about the problems and opportunities that we might have, and from that insights we will now draw decisions, we will have a better and more confident decision if we based this on data. Practical Example Given that you have seen in news that it will probably rain today, it gives you insight that you have to bring something to protect you from the rain, this will trigger you to take an umbrella with you as you go out. Accuracy Vs Precision Measures of Central Tendency Central Tendency – are measures that used to compare the center of a data set as against to a reference point. - Mean – arithmetic average of all the data values - Median – midpoint of the data values. - Mode – most frequently occurring data value. In statistics most of the time we use the mean, but in cases that there are outliers we rather used the median as this is not susceptible to bias due to outliers or unusual observations. If using continuous data, mean and median are most of the time, while using discrete data mode is more appropriate. Measures of Dispersion Dispersion – describes the characteristics of data and how far they are from each other. - Range – the difference between the maximum value and the minimum value. - Standard Deviation – distance of the values from the mean. - Variance – squared value of the Standard Deviation. Accuracy and Precision Accuracy is based on the measures of central tendency, which gives us an idea of how far the center of the data set from the target is. Precision is guided by the measures of dispersion, or how dispersed are the data values from each other. In lean six sigma, what we want to see is to give us an output that is accurate and precise. Quality is inversely proportional to variability, and dispersion and precision is the same with variability. So as we have more variability in the process, the lower the potential quality level will be. Introduction to Minitab Minitab – one of the famous statistical tool that is being used by industries and organizations when it comes to data analysis especially in lean six sigma projects. Exercise #6: Basic Using Minitab FAT ENERGY Sample ID Percent Fat Family ID Energy Cost 1 15.2 1 211 2 12.4 2 572 3 15.4 3 558 4 16.5 4 250 5 15.9 5 478 6 17.1 6 307 7 16.9 7 184 8 14.3 8 435 9 19.1 9 460 10 18.2 10 308 11 18.5 11 188 12 16.3 12 111 13 20 13 676 14 19.2 14 326 15 12.3 15 142 16 12.8 16 255 17 17.9 17 205 18 16.3 18 77 19 18.7 19 190 20 16.2 20 320 21 407 22 333 23 488 24 374 25 409 Statistics Variable N N* Mean StDev Variance Median Range Mode N for Mode Percent Fat 20 0 16.46 2.25818 5.09937 16.4 7.7 16.3 2 Statistics Variable N N* Mean StDev Variance Median Range Mode N for Mode Energy Cost 25 0 330.56 154.178 23770.8 320 599 * 0  1. Average % Fat is 16.46 2. How many data points represent the mode in the % Fat data set? 2 3. Median % Fat is 16.40 4. Mode of % Fat data set is 16.30 5. Range of % Fat is 7.70 6. Average Energy Cost is 330.6 7. Median Energy Cost is greater than Mean Energy Cost. False 8. Three (3) data points represent the Mode Energy Cost. False 9. Standard deviation of Energy Cost is 154.2 10. What central tendency is not applicable in the Energy Cost data set? Mode Measurement System Analysis (MSA) Before you do data analysis, measurement system analysis should be conducted. This seeks to answer the question “How would we know that the data we have gathered reflects a reliable source” meaning how do we know that our data is correct? Why is it important to have a good data or a clean data? Garbage in, Garbage out The collection of data will be used for decision-making Sources of Variation – measurement system error There is always variation from the output of a process. It could either be unit to unit for the true variation and worst case there are a lot of errors which can be classified as measurement system error. Using SWIPE as a guide, the possible sources are the Standard itself (no clear understanding of the standard), the Workpiece or Part (something wrong with the part or the service that we are producing or rendering), the Instrument (not calibrated or not fit to use in the specific application), the Person (doing the capturing of the data) or Procedure (the one that has been installed) or combination of both person and procedure (doesn’t know how to use the procedure), and the Environment (has an effect to the data collection process). Before analysis make sure the data is accurate and reliable. Measure Phase Quiz 1. In a process map, an ellipse designates Start and stop point 2. Tool used to validate reliability of a data source. Measurement System Analysis 3. Which of the following is NOT TRUE about measurement? Data collection is only conducted in the Measure Phase of DMAIC. 4. This give a common understanding of the how the word/term is being used in context of the project. Operational Definition 5. Which does not belong to the group? Time Series 6. Measurement scale that gives us ordered units that have the same difference and has no absolute zero. Interval 7. These are measurements from a continuum scale. Continuous 8. Which does not belong to the group? Height 9. Accuracy is to central tendency; Precision is to Dispersion 10. Preferred measure of central tendency when there is an outlier or unusual observation. Median ANALYZE PHASE Goal: To identify potential root causes and to confirm real causes using data. Output deliverables: - List of potential root causes - Confirmed root causes - List of causes for improvement Generate > Screen potential > Validate using > List validated potential root root causes data analysis root causes for causes improvement Brainstorming What is Brainstorming? - A technique used to generate ideas from a group of individuals in any stage of any problem- solving activity. - It is a means of getting a large number of ideas from a group of people in a short time. - The more alternative choices we have, the better our decision is. The fundamental basic tool that we will use in our root cause analysis Brainstorming Methods Structured – participants go in turns, one idea per turn until all ideas are exhausted. (you can get all ideas from all participants). Best used when you have a new team form, because you don’t know yet the dynamics of the team; to hedge against the risk of highly active participants that might dominate the brainstorming session. Unstructured – participant who has an idea can raise it and in no specific turn of order. (free way of brainstorming method). Used more often. Best time to use when you have the team dynamics already. Brainstorming Rules 1. Give participants a time to think about the topic to be discussed. 2. No killer phrase and no pet ideas. 3. Crazy ideas are welcome. 4. Build up on ideas previously raised. 5. The more the ideas, the better. 6. Make the ideas visual. 7. Summarize and combine ideas, if necessary. Why-Why Analysis 5 Whys (Why-Why) Analysis - It is an alternative, interrogative technique used to explore the cause-and-effect relationship underlying a particular problem. - Its primary goal is to establish the root cause of an effect by repeating the question “why?”, each answer becomes the basis of the next question. - The technique is developed by Sakichi Toyoda and was used within Toyota. As a rule of thumb, we asked five whys, with the belief that on the fifth why we can find the potential root cause. (but we can ask more or less than 5, it depends on the complexity of the problem and the context that is being put into the practice of 5 whys) Why-Why Analysis in Action #1 Problem Statement “The vehicle will not start” Why 1 The battery is dead. Why 2 The alternator is not functioning Why 3 The alternator belt has broken Why 4 The alternator belt was well beyond its useful service life and not replaced. Why 5 The vehicle was not maintained according to the recommended service schedule The vehicle will not start, because of poor maintenance schedule and attainment. Set aside, collect data to prove if its valid or not. Why-Why Analysis in Action #2 5-Why Analysis – ABC Distribution Center Problem Statement: Wrong item shipped to customer Why? The wrong item was pulled from inventory. Why? The item we pulled from inventory was mislabeled Why? Our supplier mislabeled the item prior to shipping it to our warehouse Why? The individual applying labels to our product at the supplier placed the wrong label on the product. Why? Labels for different orders are pre-printed, and it is easy to apply the wrong label. Why-Why Analysis in Action #3 Problem: Team missed the deadline for running executive reports. Why? No one was onsite to run the reports. Why? Person who regularly runs reports was on vacation, so no one was onsite to do the job. Why? No backup in place for that activity. Why? No one identified as the backup to run reports. Why-Why Analysis in Action #3 When you have sub several reasons on each of the last answer to the whys. Problem | Reason #1 – Reason #2 – Reason #3 | | | Sub Reason Sub Reason Sub Reason | | | Sub Reason Sub Reason Sub Reason You can also do tree diagram approach. How to Get Started with Why-Why. 1. Form the Team 2. Define the Problem 3. Ask Why 4. Validate 5. Take Action What is Fishbone (Cause & Effect) Diagram? - A tool used to analyze cause and effect relationship. - Use your team’s process knowledge about the entire process to create an effective cause- and-effect diagram. - This is created by Kaoru Ishikawa, 1968. 5M1E (Major Causes) Man – Machine – Method – Material – Measurement – Environment Root cause analysis must explore the flaw of the process causing the problem. Look at the man the least. How to Construct a Fishbone Diagram? 1. Generate potential causes of a problem through brainstorming. 2. Draw a horizontal arrow pointing to the right. This is the spine. 3. Decide upon the major causes categories of the event, problem, or key characteristics. 4. Write the major cause categories on the left-hand side of paper and draw lines to them off the main horizontal line. 5. Conduct a Why-Why Analysis by asking why questions that can lead to the potential root causes. These may represent root causes. Look for what you can measure in each cause so you can quantify the effects of any changes you make. Most importantly, identify and circle the causes that you can take action to. Fishbone Diagram Sample #1 Potential root causes must be stated in a negative tone. Fishbone Diagram Sample #2 Flawed fishbone diagram (arrows are not toward the spine). Should have stated it in a negative manner. Fishbone Diagram Sample #3 Technical (error?): no arrows Root Cause Analysis Tips 1. How relevant are the questions and answers to the original X or Y you are investigating? 2. Did you find a root cause that helps you control or avoid the situation? 3. Are the questions and answers significant enough, considering your project scope? 4. Can we validate the potential root cause using relevant data? Graphical Analysis Tools - These are set of tools used to validate the hypotheses or potential root causes identified from the root cause analysis. - Graphical Analysis Tools are used to examine the distribution of data, track data over time and examine potential relationship between data. Data Distribution - We will be able to understand how data is distributed based on its performance. Distribution is equivalent to variability. - We are looking for a data distribution that will support our claim, that the lower the variability the better quality level will be out of the process. Graphical tools for the distribution of data (How to choose the right graphical tool) Histogram - A histogram can also be normalized. In this case, the X axis still represents the possible values of the variables, but the Y axis represents the percentage of observations that fall into each interval on the X axis. - The total area of all rectangles in a normalized histogram is 1. - With the histogram, we have a better understanding of the shape, location, and spread of the data. Because of the value 5, which is extremely low, it tends to pull the average to the left, giving more weight to the left side of the distribution and creating noise and bias. In such cases, the median is more useful. If there is an outlier, to avoid bias (as the average is susceptible to error), consider using the median as the measure of central tendency. A normality test is a requirement before conducting any in-depth data analysis. In statistics, these are referred to as assumptions. Certain tests have the assumption that the dataset should follow a normal distribution. If it does not, you will need to use statistical tests designed for non-normally distributed data. Statistical test used for normally distributed data is called parametric test. Statistical test used for non- normally distributed data is called non-parametric test. What will you do next if the p-value indicates the data is not normally distributed? We don’t expect the data to always be normally distributed, as some datasets are inherently intended to be non- normally distributed. There’s a gray area in statistics called the Central Limit Theorem, which states that with a certain number of data points, the distribution of the data might be non-normally distributed. However, if we extend the data collection and increase the number of data points, the data will eventually follow a normal distribution. This principle is sometimes misused to justify applying parametric tests to non-normally distributed data. Boxplot What is boxplot? A box plot and whisker plot is defined as a graphical method of displaying variation in a set of data. In most cases, a histogram analysis provides a sufficient display, but a box and whisker plot can provide additional detail while allowing multiple sets of data to be displayed in the same graph. Unlike histogram boxplot can give us an idea of central tendency and dispersion better. Anatomy of a Box Plot a box plot technically divides the data set into four partitions this partitions is called a quartile, for every quartile there is 25 percent of data set within it The first partition is called the first quartile, where 25% of the data is located. The second is the second quartile, where an additional 25% (making a total of 50%) of the data is located. This is also known as the median, one of the measures of central tendency. Next is the third quartile, which contains 75% of the data after adding another 25% from the second quartile. Finally, the fourth quartile contains 100% of the data. Outliers are detected and denoted by an asterisk symbol when using a box plot. If the tails, or 'whiskers,' of the box plot cannot contain a data point (either a very high or very low value), the box plot will tag it as an outlier or an unusual observation. The mean is susceptible to outliers, which is why we use the median when employing a box plot as our graphical analysis tool. In a box plot, the central tendency is based on the median, and dispersion is measured by the interquartile range (IQR). The IQR is the difference between the third quartile and the first quartile. Practically speaking, if we have a larger IQR, the box in the plot will be grater, indicating a higher amount of variation. The smaller the size of the box the smaller the amount of the variation. Boxplot Using Minitab #1 There are 25% of data points that are equal to or less than 197, and the remaining 75% are greater than that value. For the median, it simply means that 50% of the data are above and 50% are below that number, as it represents the midpoint. Now, looking at the third quartile, 447.5, 75% of the data is below that value, and the remaining 25% is above it. Our dataset has no missing values and no outliers, as no asterisks appear on the chart that was created. If we have a target of 300, we can answer the question of how many data points are already meeting the 300 target. Since we are aiming for 'lower is better,' you will use the closest quartile value to interpret this. In this case, the closest value to 300 is the median, which is 320. Based on an estimation from the visual or graphical output of the box plot, we can say that nearly 50% of the data is meeting the 300 target, based on the median. This demonstrates how we can use a box plot to interpret the results of our data. You can use a box plot to check the distribution of your dataset against your target and assess your process capability. This will help you understand how capable you are of meeting the target and give you an idea of the magnitude of the problem you are facing. Boxplot Using Minitab #2 GrowFast, a plant fertilizer manufacturer, is attempting to develop a formula that yields the greatest plant growth. In a controlled greenhouse environment, they set up 3 groups of 50 identical seedlings, a control group with no fertilizer, a group using their product, and another group using their closest competitor, SuperPalnt. After 3 months, they measured the plants’ heights in centimeters. Source Sheet: Plant Graph > Boxplot > Multiple Y’s In a box plot, central tendency is represented by the median, which is the line inside the box, while dispersion is indicated by the height of the box. Which dataset has the highest central tendency? Since we're considering plant height and aiming for 'the higher, the better' (with values ranging from zero upward), we're looking for the median closest to the upper part of the chart, which in this case is 40 on the axis. For the central tendency measures: - For 'None,' the median is 18. - For 'GrowFast,' the median is 25.5. - For 'SuperPlant,' the median is 21. Therefore, the highest median is 'GrowFast,' making it the highest in terms of central tendency. For measures of dispersion, we need to check which has the smallest box. Using visual judgment, 'GrowFast' again appears to have the smallest box. We can confirm this by checking the interquartile range (IQR): - For 'None,' the IQR is 8. - For 'GrowFast,' the IQR is 6.25. - For 'SuperPlant,' the IQR is 8. Therefore, 'GrowFast' has the smallest amount of variation because it has the smallest IQR. Therefore, you can use a box plot to compare categories of data, but the data should be continuous. Pareto Chart and the 80-20 Rule What is a Pareto Chart? (mainly used for prioritization) - A bar chart where the bars are arranged in descending order of magnitude. The bars may represent defect categories, locations, departments, and so on. - A problem-solving tool that involves ranking all potential problem areas or sources of variation according to their contribution to cost or total variation. - Typically, 80% of the effects come from 20% of the possible causes, so efforts are best spent on these “vital few” causes, temporarily ignoring the “trivial many” causes. - Most commonly used for prioritization of resources and also for validation of root causes. Anatomy of Pareto Chart Pareto Chart Sample using Minitab #1 A quality engineer for an automotive supply company wants to decrease the number of car door panels that are rejected because of paint flaws. The engineer wants to determine whether a relationship exists between the type of paint flaws and the shift during which the door panels are made. Source Sheet: Flaws Stat > Quality Tools > Pareto Chart Defects: Flaws The vital few are those close to 80%. However, the focus here is only on peel and scratch because they represent a breaking point. Even though 85 is close to 80, other is not considered. Pareto Chart Sample using Minitab #2 A clothing manufacturer tracked the number and type of defects in a line of clothing. Source Sheet: Clothing Defect Based on defect count There is no clear breaking point, but the closest to 80% is 82.5%, which means the vital few are Missing Button, Stitching Errors, and Loose Threads. Eighty percent of the problems can be attributed to about 20% or fewer of the causes. Based on Cost Contribution Considering cost contribution, we now have a different set of vital few: Stitching Errors, Hemming Errors, and Fabric Flaws. Things to consider when you use a Pareto chart - Data collected during a short period of time, especially from an unstable process, may lead to incorrect conclusions. Because the data may not be reliable, you may get a misleading idea of the distribution of defects and causes. When the process is not in control, the causes may be unstable, and the vital few problems may change from week to week. Short periods of time may not be representative of your process as a whole. - Data collected during long periods of time may include changes. Examine the data for stratification or changes in the problem distribution over time. - Choose categories carefully. If your initial Pareto analysis does not yield useful results, you may want to ensure that your categories are meaningful and that your “other” category is not too large. - Choose weighting criteria carefully. For example, cost may be a more useful measure for prioritization than number of occurrences, especially when the costs of various defects differ. - Concentrating on the problems with the highest frequency should decrease the total number of items needing rework. Concentrating on the problems with the highest cost should increase the financial benefits of the improvement. - The goal of a Pareto analysis is to obtain maximum reward from the quality efforts, but that doesn’t mean that small, easily solved problems should be ignored until the large problems are solved. Graphical Tools to Track Data Over Time Graphical tools for variables over time |_ Control Charts If you want to monitor a KPI or performance measure in your workplace, you are probably using time series charts. Time Series What is a Time Series? A time series is a sequence of observations over regularly spaced intervals of time. As mentioned, a time series chart is used to track the performance of your data or process over time. - Monthly unemployment rates for the previous five years. - Daily production at a manufacturing plant for a month - Decade-by-decade population of a state of the previous century. Anatomy of Time Series Chart remember that you can only use line chart when you're using time series not using bar chart It’s a mistake to use bar charts when the x-axis represents a unit of time. Always use a time series chart for those types of applications. Why use time series chart? To check for patterns: Trend Shift Cycle Why do we use time series charts? Generally speaking, we use them to identify patterns or to observe how our process output behaves over time. - trend is a series of data points that is increasing or decreasing - shift means an old performance shifting to a new level of performance either because of an improvement or either because of a problem. when you detect shift there has been a sudden change of an element of the process that triggered this particular shift. - cycle is represented by waves, which can also be referred to as a season. It’s a repetitive, cyclical movement of your data points across different time periods." If we discover any of these patterns, we should ask ourselves what happened to our process and why it is producing these patterns. Time Series Sample #1 The manager of a shipping yard wants to study the amount of cargo that is transported. The manager collects the weight of all the cargo that passes through the shipping yard each month. Source Sheet: Shipping Graph > Time Series Plot > Simple Series: Weight Time/Scale: Stamp > Month Understand the behavior of our process, why it exhibits these patterns, and use it as a basis for further investigation. When you're using time series for hypothesis testing or root cause validation, you simply state your hypothesis. If you want to prove it using your data and check it over time, you can use a time series. Time Series Sample #2 The administrator of a hospital wants to examine the number of cardiac patients admitted over the past 24 months to analyzed trends in the data. Source Sheet: Patient Graph > Time Series Plot > Simple Series: No. of Patients Time/Scale: Stamp > Month Relationship Between Variables Graphical tools for relationships between variables Scatter Plot - A scatter plot is a diagram that present the relationship between two variables of a data set. - A scatter plot consists of a set of data points. - On the scatter plot, a single observation is presented by a data point with its horizontal position equal to the value of one variable and its vertical position equal to the value of the other variable. A scatter plot helps to understand: - Whether the two variables are related to each other or not. - How is the strength of their relationship. - What is the shape of their relationship. - What is the direction of their relationship. - Whether outliers are presents. The red line is called the fitted line. From this line, we draw the slope, and depending on the slope, we assess whether there is a possible positive correlation, negative correlation, or no correlation at all. This kind of slope, where the line leans to the left, indicates a possible negative correlation. What does this mean? As the weight increases, the miles per gallon decreases, which is why it's a negative correlation. A possible positive correlation occurs when, as one variable increases, the other also increases. There are also cases where no line can be drawn because the data points are too dispersed, indicating that your data shows no correlation at all." Run Chart - A run chart is a chart used to present the data in time order. It captures the process performance over time. - The X axis of the run chart indicates the time, and the Y axis indicates the observed values. - Run chart looks similar to control charts except that a run chart does not have control limits plotted. It is easier to produce a run chart than a control chart. - It is often used to identify the anomalies in the data and discover the pattern of data changing over time. 1. What is the median pulse rate for female and male? 80 & 76 2. Which Activity is the most significant contributor of Pulse Rate? Moderate 3. What is the IQR of Pulse based on Ran (Yes or No)? 30 & 13.5 4. Is there a significant difference between the distribution of Pulse based on whether the person is smoking or not smoking? No, there is none 5. What possible relationship is there between Pulse and Height? Possible Negative Correlation 6. What possible relationship is there between Pulse and Weight? Possible Negative Correlation 7. Which type of activity has an outlier Pulse? Moderate 8. How many % of the Male subjects of the study has a Pulse Rate meeting the standard of 70 to 100 BPM? 75% 9. Which bin or interval has the highest number of frequency for Pulse? 75 to 85 10. How many outliers does the Pulse data set have? 2 Validation Table When to Best Use Each Graphical Tool What is a Validation Table? Will help us to summarize the list of our root causes, and the root cause validation that we have conducted to make it valid or not valid A validation table is a simple table that summarizes the efforts done in generating and validating the potential root causes. It will give the team an idea of which has been valid root causes among all the generated potential root causes. Potential Root Causes Validation Method Conclusion (Observation, Records (Validation or Not Valid) Checking, Data/Graphical Analysis, etc.) There is high variation in Box Plot Valid preparation time affecting the lead time Lead time is higher during Time Series Valid peak hours due to surge of customer Variation (comparison of variables) Analyze Phase Quiz 1. A graphical tool used to compare distribution of the data and the location of the central tendency in terms of the median. Box Plot 2. A tool that follows the 80-20 principle stating that 80% of the effect is accounted to 20% of the factors. Pareto chart 3. A tool used to discover potential things that could impact the output of the process you are investigating. Fishbone Diagram 4. A type of histogram that is caused by natural limits in the outcome of the process. Skewed 5. High lead time is affected by high preparation time can be explained by a Positive Correlation 6. In Root Cause Analysis, this is the last major cause that we explore. Man 7. This measure of the spread or data distribution in a box plot. Inter quartile range 8. Which does not belong to the group? Histogram; Boxplot; Time Series; Pareto Chart 9. Which is not a pattern that can be highlighted by a time series chart? Limits 10. Why-why analysis is strict to asking a minimum of five (5) whys. False IMPROVE PHASE Goal: To develop, pilot, implement and evaluate solutions that address the validated root causes using data. Output Deliverables: - Tested solutions that must impact validated causes. - Comparison/evaluation of baseline versus result of implemented solution. Generate Possible Select, develop, Evaluate result solutions to > test and > of address root implement implementation cause solution Common Lean Six Sigma Improvement Tools 5S - The most fundamental tool that promotes good housekeeping as foundation of improvement. 1. Sort 3. Sweep 5. Sustain 2. Systematize 4. Standardize Cross Training - A tool used to address issues of non-utilized skill and to empower employees for job enrichment and expansion. o Avoiding the pitfall of single person risk. Parallel processing - Inspired by the SMED, it takes into account executing processes simultaneously to eliminate process waiting times. o Just what they are doing in the pit stop of car races (F1, NASCAR) Visual Management - Deploying visual management tools or labels to facilitate prevention or correction of errors in a process. o Two Types 1. Visual Display (kanban *visual card*) 2. Visual Control Standard Work - Follows the idea of making process steps easy to perform. o Variations 1. Checklist 2. Work Instruction 3. Visual Aid Mistake Proofing - Inspired by Shigeo Shingo and drives creating no or minimal opportunities for mistakes be created. (poka-yoke) o Build quality into the process. o Prevention is better than cure. What is 5S? - 5S is defined as a methodology that results in a workplace that is clean, uncluttered, safe, and well organized to help reduce waste and optimize productivity. - It’s designed to help build a quality work environment, both physically and mentally. - The 5S philosophy applies in any work area suited for visual control and lean production. - The 5S condition of a work area is critical to employees and is the basis of customers’ first impressions. What are the 5S’s? Japanese Translated English Definition Seiri Organize Sort Eliminate whatever is not needed by separating needed tools, parts, and instructions from unneeded materials. Seiton Orderliness Set in order Organize whatever remains by neatly arranging and identifying parts and tools for ease of use. Seiso Cleanliness Shine Clean the work area by conducting cleanup campaign. Seiketsu Standardize Standardize Schedule regular cleaning and maintenance by conducting seiri, seiton, and seiso daily. Shitsuke discipline Sustain Make 5S a way of life by forming the habit of always following the first four S’s 1S – Sort. Remove from the workplace what you do not need and keep what you need. 2S – Set in order. Give everything a place, and a place for any object. 3S – Shine. Simply shine, without excuses. 4S – Standardize. To maintain the workplace. 5S – Sustain. Sustain the workplace by using the standard. What are the benefits of 5S? - Improved safety - Higher equipment availability - Lower defect rates - Reduced costs - Increased production agility and flexibility - Improved employee morale - Better asset utilization - Enhanced enterprise image to customers, suppliers, employees, and management. Cross Training What is Cross Training? - Cross-Training is training different employees to perform different tasks outside of their original role. - For example, training Worker A to do Worker B’s job, and training Worker B to do the Worker A’s job. - Cross-Training improves the flow of the process, enables the sharing of best practices and increases flexibility in managing the workforce. Cross Training Benefit Improved service: When your production line grinds to a halt because the one person you need to perform the task is working on another project, your services suffer. On the other hand, when you have multiple skilled employees who are capable of many tasks, you’re far more prepared to deliver better service to your customers. Scheduling flexibility: With today’s job often coming with tight deadlines, a cross-trained workforce gives you greater choice when it comes to scheduling. And with a schedule that doesn’t overburden one or more employees, you also help prevent worker burnout – leaving you with a healthier, happier workforce and reduced absenteeism. Process improvements: With siloed employees who work separately from each other. It’s often next to impossible to envision process improvements. With a cross-trained workforce that’s encouraged to share ideas on how to eliminate waste and increase efficiency, process improvements are far more easily identified and achieved. Worker engagement: When employees see that their skills are growing and that they’re contributing to the company’s success with more than one responsibility, they feel part of the bigger picture. And when worker engagement increases, so do your employee retention rates, which goes a long way in helping your organization remain competitive in today’s labor market. What is Cross Training Matrix? Single Minute Exchange of Dies (SMED) SMED ex. Pit Stop in Action; Preventive maintenance time What is Single Minute Exchange of Die (SMED)? - The practice of dramatically reducing or eliminating the time to change from one method or unit to another where the goal is to reduce the Changeover Time to single digits or under 10 minutes. - This concept is also known as Set-up or Reduction or Changeover Reduction. - This was originally developed by Shigeo Shingo in order to reduce the time spent in setting up equipment or materials since set up does not add value. What are the benefits of applying SMED? - Lower manufacturing cost (faster changeovers mean less equipment downtime) - Smaller lot sizes (faster changeovers enable more frequent product changes) - Improved responsiveness to customer demand (smaller lot sizes enable more flexible scheduling) - Smoother startups (standardized changeover processes improve consistency and quality) How to apply SMED? SMED Steps 1. Measure total job time 2. Separate internal and external tasks; perform external ones while equipment is running. 3. Convert internal tasks into external ones wherever possible. 4. Eliminate internal waste 5. Eliminate external waste 6. Standardize and maintain best practice Internal Steps can only be one when machine is not running. External Steps can be done even the machine is running. Example Areas of Opportunity for SMED Projects VISUAL MANAGEMENT What is Visual Management? - The purpose of visual management is to improve the effectiveness of communication and reaction. This is one component of Lean Manufacturing. - Visual aids can convey messages quicker and invite more interest than written information. And this also means exposing defects and problems to allow them to be addresses sooner... bad news doesn’t get better with time. - Effective visual management involves careful thought to have the best impact. - Expose wastes and make it clear to everyone - The work area/cell/machine should “talk” to you in simple terms. - The goals should be clearly indicated. - The status of production should be found with the goals. - Simple problem-solving tools on display. - Increased communication is ultimately what all the above will do. What are the benefits of Visual Management? - Makes it Easy to Quickly Understand Information - Keeps Things Running as Designed - Prevents Mistakes or Improve Safety - Reduces Miscommunication - Improve Employee Involvement and Morale Visual Management Examples - Performance Dashboards - Floor Lines / Paints - Visual Controls (Traffic Lights and Gauges) - Andon Lights in Production - Public and Common Signages Standard Work What is Standard Work? - Standard work is the practice of setting, communicating, following, and improving standards. - Establishing standard work begins with creating, clarifying, and sharing information about the most efficient method to perform a task that is currently known with everyone performing that process. Establish Look for Create New Standard Work > Opportunities for > Baseline Improvement What are variations of the Standard Work? - Standard Operating Procedures - One Point Lessons - Best Practices - Work Instructions - Policies & Procedures - Visual Control - Automation - Modularity What does an effective Standard Work include? - Written instructions, drawings, flow chart, photographs, or checklist. - The description and scope of the work. - The exact work sequence involved in which activities are completed. - The optimal amount of time needed for each activity. - Responsibilities and work distribution. - Key points related to safety, quality and performance. - The materials, equipment and tools needed to complete the work. Standard Work Examples MISTAKE PROOFING What is Mistake Proofing? - Mistake proofing, or its Japanese equivalent poka-yoke (pronounced PO-ka yo-KAY), is the use of any device or method that either makes it impossible for an error to occur or makes the error immediately obvious once it has occurred. - Mistake Proofing can be categorized into: o Prevention o Detection o Containment Containment occurs once an error has occurred in the process. What we want to do is contain it so it does not affect other processes, and its impact is minimized. A higher level of control is detection, where you identify the likelihood of an error or defect occurring before it happens or detect whether it has already occurred. This allows you to stop the process and minimize the impact of the error or defect. Ultimately, the goal is prevention — to eliminate the possibility of the error or mistake occurring within the process. When to use Mistake proofing? - When a process step has been identified where human error can cause mistakes or defects to occur, especially in process that rely on the worker’s attention, skill, or experience. - In a service process, where the customer can make an error which affects the output. - At a hand-off step in a process, when output (or for service processes, the customer) is transferred to another worker. - When a minor error early in the process causes major problems later in the process. - When the consequences of an error are expensive or dangerous. How to use Mistake Proofing? 1. Create a process map and review each step for possible occurrence of errors. 2. For each potential error, identify the root cause or source. 3. For each error, think of ways to prevent it. 4. If it’s not possible to prevent it, think of ways on how to detect the errors as early as possible. 5. Implement the mistake proofing action items. Mistake proofing Examples Selecting the Right Solutions using PICK Matrix Impact x Effort PICK Matrix Managing the improvements using the Implementation Plan Implementation Plan – a guide on how to deploy the implementation of identified activities. This table is used to update stakeholders and team members on the current status of your project, as well as the support they can provide to help your group or project team achieve results faster. It can also highlight potential problems the team may encounter while managing their tasks alongside other daily responsibilities. Evaluation Tools Set of tools that can aid in the evaluation and display of the results of the implemented solution and improvement. https://www.youtube.com/watch?v=Zn5XsCwGf08&t=133s From the list of commonly used Lean Six Sigma improvement tools, pick the two (2) most applicable to your current situation now. Discuss what is the current situation and provide a solution in reference to your selected improvement tools. These days, I’ve been spending more time at home, so the improvement tools I find most applicable to my situation are 5S and SMED. 5S helps organize our home. In the past few months, things have been a bit messy with everyone busy with work or school. Applying the principles of 5S—Sort, Set in Order, Shine, Standardize, and Sustain—will definitely make our home more organized. Another improvement tool is SMED, which can help streamline or reduce the time spent on chores like cooking and cleaning by optimizing these tasks. Improve Phase Quiz 1. This tool can help reduce bottlenecks due to human intervention. Cross Training 2. Tool deployed to facilitate prevention or correction of errors in the process by making things obvious. Visual Management 3. 5S can be done as stand-alone improvement even outside Lean Six Sigma. True 4. Which among the following is not a variation of a standard work? SMED Worksheet 5. Arrange the following from good to best. Good: Containment; Better: Detection; Best: Prevention 6. In a PICK Matrix, you will ______ solutions with high effort but with low impact. Kill 7. In a PICK Matrix, you will ______ solutions with low effort but with high impact. Proceed 8. A guide on how to deploy the implementation of identified activities. Implementation Plan 9. Set of tools that can aid in the evaluation and display of the results of the implemented solution and improvement. Evaluation Tools 10. Which among the options given can be used for evaluation of effectiveness for implemented improvement actions? Check all that applies. Box Plot CONTROL PHASE Goal: To sustain the gains from the improvements through standardization, documentation and/or control. Output Deliverables: - Control plan and/or monitoring system to facilitate sustenance of gains - Completed documentation, communication of results and lessons learned and way forward. Design and Complete Summarize and Make Implement > documentation > communicate > recommendations Control methods and lessons learned for continuous Standardization improvement Looking in the Gains Using the Process Control Plan What is a Process Control Plan? - Process control systems include detailed measurement instruction for monitoring the process. - It helps to define the process measure target to ensure successful and continuously improving performance. Contains the step-by-step procedure or important elements that would help us to sustain and control the improvements that we have implemented coming from the improve phase. Document that we will go back into when we have problems Process Control Plan Sample What’s controlled? column contains items that we tend to control in order for us to have a more stable result. Output – what you’re trying to improve Input – factors that could affect Specs Limits/Requirements – Condition that needs to be satisfied Control Method – How can we ensure that the requirements are met Frequency – How frequent we will do the control method Person Responsible – Owners of the particular process control plan Control Charts What is a Control Charts? - A statistical control chart is a line graph of the measurements of a product or process over time that has statistically based control limits placed on it. - The points that are plotted on a control chart may be the actual measurements of a part characteristic or summary statistics from samples (subgroups) of parts taken as they are produced over time. - A control chart has control limits based upon process variation and a centerline representing the average of all measurements used to construct the control chart. Why Use a Control Chart? - To display and manage variation in process output over time. - To identify when a process changes. - To provide a basis for improvement. - To identify the causes of variation and process capability. - To distinguish special from common causes of variation (that is, when to correct sporadic problems or when to change the process). - To help assign causes of variation. Control Chart Elements Test for Special Causes of Variation Special Causes – This are causes that cause the points to fall beyond or below the control limits signaling a problem in the process. Tips in Selecting a Control Chart If you want to chart your data but have a limited number of samples, such as one sample per subgroup, you can use what is called an Individual Moving Range (I-MR) chart. This is used when your process produces an output that is difficult or expensive to measure. If you have more than eight samples, you can use what is called an X-bar S chart, or a mean and standard deviation chart. If you have less than eight samples, you can use what is called an X-bar R chart. If you are counting defective items, you can use a P chart, also known as a proportion chart. If you are counting defects per unit, you would likely use a U chart. If the primary function of a product or service cannot be performed, then it is considered defective. If this condition does not hold, the product or service simply has a defect (defect per unit). Control Chart Selection Guide Continuous Attribute Control Phase Quiz 1. It is the distance allowed for common causes of variation from the mean. +/-3sigma 2. Special test for assignable causes can be used to examine trends, cycles or shifts in the data points. True 3. If you have continuous data set and been able to collect a group size of 15, is X bar and R the best choice of control chart? No 4. It is a document that you will go back if problems are recurring from the project that you completed. Process Control Plan 5. Control charts are used to display the amount of variation present in a process. True 6. Based on the normal distribution, data should be. Randomly distributed 7. An analyst decided to count the number of defective parts with varying sample size taken daily. He should use what type of control chart? P 8. The temperature inside a facility is being monitored due to its effect to a critical process. Every day, the analyst takes 5 random temperature samples and records it. Which control chart would you advise him to be used? X Bar and R 9. Which of the following does not belong to the group? IX – MR 10. If a product or service cannot perform its intended function, then it said that it is defective 11. It is a document that you will go back if problems are recurring from the project that you completed. Process Control Plan 12. An analyst decided no count the number of defective parts with varying sample size taken daily. He should use what type of control chart? P