IE 135.pdf

IE 135 Notes 1900 Frederick Taylor introduced principles of scientific LECTURE 1 management as mass production industries began...

IE 135 Notes 1900 Frederick Taylor introduced principles of scientific LECTURE 1 management as mass production industries began to develop Quality 1924 Walter Shewhart of Bell Laboratories developed - one of the most important decision factors for the statistical control chart, which is often consumers in their selection between products and considered as the formal beginning of statistical services. quality control Late 1920s Harold Dodge and Harry Romig developed - applies to any form of consumer, from individuals to statistically based acceptance sampling as an industrial organizations to banks to military defense alternative to 100% inspection agencies. Mid 1930s Statistical quality control methods were widely - Understanding and improving quality are key to used in Western Electric (manufacturing arm of organization success, growth, and competitiveness. Bell Laboratories) WW II Greatly expanded use and acceptance of statistical THE DEFINITION OF QUALITY quality-control concepts in manufacturing Traditional Definition: Quality is fitness for use. industries - Quality of design 1950s- Emergence of reliability engineering and the o Intentional design differences in the 1960s introduction of several important textbooks in production of goods and services (e.g., statistical quality control - First introduction of material, component, specification, designed experiments in the US accessories) Late 1970s Western companies discovered that their Japanese - Quality of conformance competitors had been systematically using DOE o How well the product conforms to since the 1960s specification required by the design Problem: Quality became more associated with the MANAGEMENT ASPECTS OF QUALITY conformance aspect than the design aspect. Effective management of quality requires the execution of three activities: Modern Definition: Quality is inversely proportional to 1. Quality Planning variability (in a product’s important characteristics) a. Involves the identification of the customers 1 and their needs (often called the voice of the 𝑄𝑢𝑎𝑙𝑖𝑡𝑦 ∝ customer). 𝑉𝑎𝑟𝑖𝑎𝑏𝑖𝑙𝑖𝑡𝑦 Reducing variability (increasing quality) reduces costs and b. By first determining the needs of its improve customer perception of the product. customers, businesses can be better situated to meet or exceed expectations. c. Without a good strategic quality plan, an organization may face faulty designs, manufacturing defects, and customer complaints. d. The dimensions of quality are an important part of this process. DIMENSION OF QUALITY Garvin’s 8 Dimensions of Quality: 1. Performance Will the product do the intended job? 2. Reliability How often does it fail? A BRIEF HISTORY OF QUALITY 3. Durability How long does it last? 4. Serviceability How easy is it to fix? 5. Aesthetics What does it look like? 6. Features What else can it do? 7. Reputation What is the perception of the product/ service? 8. Conformance Is it made as the designer intended? DIMENSION OF QUALITY (SERVICE) 1. Responsiveness How long did it take the service provider to reply to your request for service? 2. Professionalism The knowledge and skills of the service provider, relates to competency “Inspect in Quality” 3. Attentiveness Caring and personalized attention from “Build in Quality” service provider “Plan in Quality” “Design in Quality” Quality has always been an integral part of products and services. But our awareness of its importance and the 2. Quality Assurance introduction of formal methods for quality control and improvement have been an evolutionary development.  a. The use of documentation to ensure quality o Control Chart levels are properly maintained and quality ▪ One of the primary techniques of issues are properly resolved statistical process control (SPC) b. Documentation of a quality system involves ▪ Control charts can detect the four components: presence of unusual sources of i. Policy – explains what is to be variability, signaling that corrective done and why action must be taken ii. Procedures – methods and ▪ Useful in monitoring processes, personnel that implement the reducing variability through policy elimination of assignable causes iii. Work instructions and ▪ An on-line technique specifications – specific instructions to carry out a task iv. Records – tracking of specific units or batches of products/services (for customer complaints handling or corrective actions) - Design of Experiments (DOE) o Discovering key factors that influence performance (e.g. factorial designs, oneway ANOVA) o Useful for process optimization 3. Quality Control and Improvement o Often conducted during development or - Quality Improvement early stages of a process o Quality improvement is the reduction of o An off-line technique variability in processes and products o Excessive variability in process performance often results in waste o Therefore, an alternative definition for quality improvement is the reduction of waste caused by variability o Reducing costs and improving quality can be done through the systematic and - Acceptance Sampling effective application of statistical quality o Closely connected with product inspection control methods. and testing - Quality control and improvement is the set of o An on-line technique for the inspection and activities to ensure products and services are classification of units randomly sampled maintained and improved upon on a continuous basis from a larger population to evaluate the - Statistical techniques such as statistical process acceptability of the greater population control and design of experiments are the major tools o With acceptance sampling, it can be for quality control and improvement determined whether to accept or reject the - Quality improvement is often done on a project-by- population (either for scrap or rework) project basis, with priority for ones with significant business impact and linked to overall business goals STATISTICAL METHODS IN QUALITY CONTROL AND IMPROVEMENT - Statistical Process Control (SPC) o Production Process Inputs and Outputs In a nutshell, the powerful collection of problem-solving tools Examples: are useful in achieving process stability and improving - A paper cup produced too thin to be able to hold a capability through the reduction of variability. reasonable amount of water QUALITY GURUS QUALITY TERMINOLOGIES W. Edwards Deming (1900-1994) - Worked for Walter Shewhart at Western Electric Quality Engineering - Long career in US government - refers to the set of operational, managerial, and - Worked with defense contractors in WW2 for engineering activities that a company uses to ensure deploying statistical methods that the quality characteristics of a product are at - Consulted at various Japanese industries, leading required levels and that the variability around these many to adopt his quality philosophies desired levels is minimum. - Japanese Union of Scientists and Engineers created Critical-to-Quality (CTQ) characteristics the Deming Prize for quality improvement - are the parameters/elements perceived to indicate - Was an active consultant and speaker until the end of quality for a particular product/service his career - TYPES: - Firmly believed the responsibility for quality rests with o Physical: length, weight, voltage, viscosity management o Sensory: taste, appearance, color o Time Oriented: reliability, durability, Deming’s 14 points serviceability 1. Create constancy of purpose towards improvement - We need to be able to measure something so we have 2. Adopt a new philosophy that recognizes being in a a baseline and determine whether we are improving new economic era or not 3. Cease reliance on mass inspection to “control” Attributes quality - Data that refers to discrete data, often taking the form 4. End the practice of awarding business based on price of counts alone and consider quality Variables 5. Focus on continuous improvement - Data that refers to continuous measurements, such 6. Institute training as length, voltage, and viscosity 7. Let leadership use modern supervision methods Specifications 8. Drive out fear (and foster openness) - Desired measurements of CTQ characteristics of 9. Break down barriers between departments components, subassemblies of the product, and the 10. Eliminate targets, slogans, and numerical goals for desired CTQ characteristics value of the final product. the workforce Target value (or nominal value) 11. Eliminate numerical quotas and work standards - is the desired value of the CTQ characteristic 12. Remove barriers that discourage employees from Upper specification limit (USL) doing their jobs - max allowable value 13. Institute an ongoing program of education for all Lower specification limit (LSL) employees - min allowable value 14. Top management must advocate the previous 13 points Examples: - Specification: The amount of sugar in milk tea order P-D-C-A should not be too much to over sweeten the drink and not too little to be unnoticeable. Deming also promoted the Shewhart Cycle as a model to guide - Target value = 10g improvement - USL = 12g - LSL = 8g Nonconforming products - Are products that fail to meet one or more of its specifications (i.e., one of the measurements of the CTQ characteristics is above its USL and below its LSL) - A specific type of failure is called a nonconformity - Note: a nonconforming product or a product with nonconformities is not necessarily unfit for use Examples: - A cleanser may contain less active ingredients than Joseph M. Juran (1904-2008) the LSL, but can still perform well if a greater amount - One of the founding fathers of the field of quality- of the product is used. control and improvement Defective products - Worked for Walter Shewhart at AT&T Bell Laboratories - Are products with one or more defects - Played an important role in simplifying administrative - A defect is a nonconformity serious enough to affect and paperwork processes in a US government agency the safe and effective use of a product during WW2  - Invited to speak to Japanese industry leaders as they began their transformation in 1950s - Co-author of the Quality Control Handbook (a standard reference for quality methods and improvement since 1957) - Emphasizes a more strategic and planning-oriented approach to quality than Deming The Juran Trilogy 1. Planning – identifying customers and determining their needs; planning on a regular basis 2. Control – activities that ensure the product/service meets requirements 3. Improvement – aim to achieve a level of performance greater than the current level; done project-by-project and is either continuous/incremental improvement or a breakthrough improvement Armand V. Feigenbaum (1922-2014) - Introduced the concept of company-wide quality control in his historic book, Total Quality Control - Influenced early philosophy of quality management in Japan in the early 1950s - Three-step approach to improving quality o 1) Quality leadership o 2) Quality technology o 3) Organizational commitment - Organizational structure and systems approach to improving quality - The technical capability for quality control should be Six Sigma (Evolved) concentrated in a specialized department - Utilize specially trained individuals called “belts” to - Quality is an essential, competitive weapon handle these projects - Management plays an important role in quality - Six sigma projects are typically 4 to 6 months in improvement length and have high potential business impact - Statistical methods are critical for “quality - Five-step problem-solving approach: DMAIC (Define, transformation” Measure, Analyze, Improve, Control) - Generation I: defect elimination & basic variability LECTURE 2 reduction - Generation II: Gen I + cost reduction Total Quality Management (TQM) - Generation III: Gen II + value creation - Implement and manage quality improvement activities organization-wide Structure of a six sigma project group - Quality is a shared responsibility that affects all aspects of the business Champions - Core Principles: - Business leaders with a conceptual understanding of o Customer focus six sigma o Employee involvement - Supports the team by removing obstacles to project o Process-approach completion o System integration Master Black Belts (MBBs) o Systematic approach - Six sigma experts with a thorough understanding of o Continuous improvement the methodology o Facts-based decisions - Mentors and coaches Black Belts o Communication - Generally plays a strategic role in an organization, ISO 9000 advising senior management on high impact - A set of international standards for quality systems improvement opportunities developed by the International Standards Black Belts (BBs) Organization (ISO) - Leads cross-divisional improvement efforts - Demonstrates a supplier’s ability to control its - Facilitates Green Belt and Yellow Belt trainings processes - Advises MBBs and Champions on local level - Heavy focus on documentation of the quality system improvements to support strategic initiatives - Coaches Green Belts in completing local level Six Sigma (departmental) improvements - Focus on reducing variability in key product quality Green Belts characteristics to the level at which failure or defects - Trained in fundamental six sigma concepts are extremely unlikely.  - Can lead improvement teams in using some six sigma - Just-In-Time (JIT) tools o In-process inventory reduction, rapid set-up, - Aware of the full potential of six sigma methodology, and a pull-type production system. so can engage BBs and MBBs in advanced tools to o Have just enough stock to produce what is support efforts they are leading needed when it is needed - Leads local improvements in their area of expertise - Poka-Yoke - Generally do not have full-time six sigma o Mistake-proofing responsibilities Quality and Productivity Yellow Belts - Have a general understanding of six sigma principles - Have no full-time six sigma responsibilities - Ideal team members for improvement initiatives because of their understanding of six sigma Six Sigma - Design for Six Sigma (DFSS) and Lean Systems are two concepts often identified with six sigma Design for Six Sigma (DFSS) - A structured and disciplined methodology for efficient commercialization of technology that results in new products, services, or processes Quality Costs - Quality costs are categories of costs associated with producing, identifying, avoiding, and repairing products that do not meet requirements Lean Systems - It is important to consider the cost of quality because: - Systems designed to eliminate waste or non-value- o Products and services are growing adding activities increasingly complex - A process is value-adding if it: ▪ Higher complexity → more quality o Brings a product/service costs closer to the final form o Businesses are now more aware of life-cycle o Changes the costs, including maintenance, spare parts, form/fit/function and field failures (i.e., failures resulting in o Is an activity the products being returned to the seller) customer is willing to o Quality engineers and managers need to pay for effectively communicate quality issues to - Otherwise, it is non-value-adding management - Four Types: o Prevention costs ▪ Costs associated with efforts in design and manufacturing directed towards the prevention of nonconformance ▪ “Make it right the first time” ▪ Examples: Quality planning and engineering – overall quality plan New products review – bid proposals and other preproduction activities Product/process design – costs related to design Other Quality Management Initiatives choices  Process control – techniques Downgrading/off-specing – to monitor and bring a process price differential of good vs into control (e.g., control nonconforming units charts) o External failure costs Burn-in – testing of products ▪ Costs when products, under extreme operating components, materials, and conditions to detect early life services fail to meet quality field failures requirements and discovered after Training (workers) – cost to delivery to the customer train those directly involved in ▪ Examples making the product Complaint adjustment – Quality data acquisition and investigation and adjustment analysis – set-up of a system for complaints to acquire data on process Returned product/material – performance receipt/ handling of o Appraisal costs nonconforming products ▪ Costs associated with measuring, Warranty charges – servicing evaluating, or auditing products, customers under warranty components, or purchased Failure analysis – cost to materials to ensure conformance determine product failure ▪ Examples Liability costs – product Inspection and testing of liability litigation incoming material – costs Indirect costs – loss of associated with inspecting business reputation, future and testing input materials business, and market share (e.g., test equipment, salary of the workers specifically for How much should quality costs be? IT DEPENDS inspection) Analyzing Quality Costs Product inspection and testing – costs associated with - Quality costs depend a lot on the type of checking conformance organization/business and the success of their quality throughout stages of improvement effort production - For some, these are at about 4-5% of sales Consumed materials/services - For others, these go as high as 35-40% of sales – costs of materials and - But in many cases, quality costs are higher than they products consumed in should be… destructive tests Maintenance of test equipment – maintenance costs to ensure effectiveness of equipment used for testing o Internal failure costs - The Cost of Poor Quality (COPQ) refer to the costs ▪ Costs when products, that would disappear if systems and processes were components, materials, and perfect services fail to meet quality - Analyzing quality costs is useful because of the requirements and discovered prior leverage effect to delivery to the customer o Investment in prevention and appraisal is ▪ Examples offset by reduction in COPQ Scrap – loss of labor/material/overhead due Costs of Poor Quality to defective products that can’t be repaired/used Rework – correcting units to meet specifications Retest – reinspection and retesting of reworked products Failure analysis – cost to determine product failures Downtime – cost of idle production facilities due to nonconforming inputs Yield losses – wastage due to variable/out-of-control processes Let’s analyze COPQ in relation to sigma capability - Suppose we have a ± 3 sigma process within specification (about 2,700 defects per million units) - Assume a cost of Php 1,000 per defect - COPQ = 2,700 x 1,000 = Php 2,700,000 for this 3 sigma process - Now what happens if the company improves its process from a 3 sigma level? - Cost increases as we go further into the process because more work is needed to affect the product as compared to doing this during design stages - Generally, the turning point is around the delivery to the customer - We can see that in this example, we have diminishing - Beyond this point, costs sharply increase because of returns the “hidden” quality costs o Sometimes the additional cost from trying to - Before delivery to the customer, impact is still improve the process may not be justified by relatively high because we can still do something the benefits gained about the product before it reaches the customer - Once delivered, the business can only do “damage Economic Balance of Quality Costs control” with the dissatisfied customers - We usually want to avoid significant COPQ because At any point in time, of generally higher costs Total (quality) costs = costs due to conformance (cost of Summary (Lec 1 and 2) attaining quality) + costs due to nonconformance (cost of poor quality) - Quality is a multi-faceted entity, incorporating several dimensions - Recognizing and selecting which dimensions to compete on is a critical part of strategic management of quality - Management must recognize that quality improvement must be a total company-wide activity wherein every organizational unit must participate - It is the responsibility of management to obtain every unit’s participation in the quality improvement effort - Strategic management of quality must involve the three components of Quality Planning, Quality Assurance, and Quality Control and Improvement - The statistical understanding, tools, and methods are essential to quality control and improvement is critical to successful implementation REVIEW: - Control limits are seen in control charts while specification limits are based on the voice of the customers. - Defect is a nonconformity while a nonconformity is a product that does not meet the standards. o Mas malala yung defect kaysa sa Product Lifecycle and Quality Costs nonconformity - It also matters when in the life cycle the quality costs LECTURE 3: DMAIC are incurred RECALL: Six Sigma - Overall, we want to ensure that benefit (impact) outweighs the cost Six Sigma - Focuses on reducing process variation and enhancing process control - Utilizes a five-step problem-solving approach: DMAIC (Define, Measure, Analyze, Improve, Control) Lean + Six Sigma = Lean Six Sigma  - Combination of two powerful quality methodologies: SAMPLE PROJECT 2: The ISP experienced a 20% lean and six sigma churn/attrition rate in 2020 - A fact-based, data-driven philosophy of improvement DMAIC PROJECT Prevent customer churn/attrition that values defect prevention over defect detection. It drives customer satisfaction and bottom-line results by reducing variation, waste, and cycle time, while promoting the use of work standardization and flow, thereby creating competitive advantage. (ASQ) LEAN SIX SIGMA - Uses visual - Uses statistical techniques techniques - Systematic - Data-driven approach to methodology to reduce/ eliminate continuous activities that do improve process to Tollgate not add value to be 99.999996% the process defect-free - Project team presents their work to managers and - Emphasis on - Emphasis on process owners waste (muda) variability - Review to ensure project is on-track reduction reduction - Opportunity to give guidance on use of specific tools or other info about the problem DMAIC Overview - Organizational problems, other barriers to success, and strategies to deal with these are identified DMAIC is a methodology for improving quality via a five-step/ phase approach that concentrates on the process that created Tools the output (instead of focusing on the output) DEFINE It can be used to: - Project Charter - Complete projects by implementing solutions that - Stakeholder Analysis solve root causes of quality and process problems - Communication Plan - Establish best practices to ensure solutions are - SIPOC Map permanent and replicable - Voice of Customer - Improve PFQT – Productivity (how many), Financial MEASURE (how much money), Quality (how well), and Time (how fast) - Operational Definitions - Data Collection Plan - Graphical Analysis (Pareto Chart, Histogram, Box Plot, Run Chart) - Detailed “As-Is” Process Maps ANALYZE - Pareto Charts - Fishbone Diagrams - Brainstorming (5 Why’s) - Non-Value Added Analysis When do we use DMAIC? IMPROVE - It should be used when a product/service is not - Brainstorming meeting customer specifications or not performing - Solution Selection Matrix adequately - “To-Be” Process Maps - It is best used when the problem is complex, or the - Piloting and Simulation risk is high. The discipline and structure prevent CONTROL teams from skipping necessary steps to solve the problem, increasing the chances of success of the - Control Charts project - Standard Operating Procedures (SOPs) - Communication Plan SAMPLE PROJECT 1: In 2020, it took on average 8 hours - Implementation Plan for hospital beds to be available after a discharge order was written - Training Plan DMAIC PROJECT Reduce the time between when a - Process Control Plans discharge order is written for a Example: Improving service quality in a bank patient and when that hospital bed becomes available again In Define and Measure, several CTQ characteristics were identified as needing to be improved: 1. Speed of service 2. Consistent service 3. An easy-to-use process 4. A pleasant environment 5. Knowledgeable staff The project team focused on two areas of improvement: 1. Improved teller and customer work stations 2. Training for the staff In Analyze and Improve, the team decided to use a designed experiment to investigate how the choses factors affect the CTQs Four branches were used to conduct actual experiments with different combinations of workstations and training programs over 30 days. Response data was collected through customer satisfaction surveys. Experiment results showed a positive difference in favor of new workstations and a new training program. Implementation of the new workstations and training program was expected to significantly improve customer satisfaction across all bank branches. 1. DEFINE PHASE The project charter is a good tool to define details of the Objective: identify the project opportunity and validate that it project. Contents include: presents a legitimate impact or potential for major improvements - Project and scope - Timeline (start and end date for each phase) Questions answered: - Primary and secondary metrics to measure success - Potential benefit to the customer 1. What is the problem? - Potential financial benefits to the organization 2. What is the goal/objective? - Milestones to be accomplished 3. Who are the customers? - Team members and their roles 4. What are the critical stages of the process? - Resources needed for the project Define the customers - CTQs impacted by the project - Who is the target audience? What are their needs? Basic Elements Their expectations? 1. Business case – why is the project important? Define the project team members 2. Problem/Opportunity statement – define the issue being resolved - Who is involved in the improvement efforts? 3. CTQs – specify the problem from a customer perspective (may not be known until the Measure Define the project boundaries Phase) - What processes are involved (the start and the end)? 4. Goal statement – describe the objective of the project 5. Project scope – what is and isn’t included? may also Define the project goal include constraints 6. Project plan – summarize milestone steps and - Example: reduce customer churn provisional dates to the goal Define the process to be improved 7. Team structure – identify who is involved and their responsibilities - Suppliers, inputs, process, outputs, customers b. SIPOC Diagram Define the problem Of the many tools that can be used in this step, we focus on these two: a. Project Charter  - Graphic aids are useful tools in this phase - With data: Last month, 20% of the company’s - The SIPOC diagram gives a simple overview of a customers unsubscribed process Many tools are useful for describing data. We only discuss a - This is useful for understanding and visualizing basic few here but your task is to identify the most appropriate tool to process elements use. - It also tells us where a process starts and ends o Suppliers – provides information, material, or other items worked on in the process o Input – the information/material provided o Process – the sequence of steps performed to do the work o Output – the product, service, or information sent to the customer o Customer – either the external customer or the next step in the business (internal customer) Tollgate Questions - Is there a comprehensive process flow chart or VSM? And are all major process steps and activities identified, along with suppliers and customers? And If appropriate, are areas where queues and work-in- process accumulate identified and queue lengths, Tollgate Questions waiting times, and work-in-progress levels reported? - Does the problem statement focus on symptoms, and - Is there a list of key process input variables (KPIVs) not on possible causes or solutions? and key process output variables (KPOVs), along with - Are all the key stakeholders identified? identification of how the KPOVs relate to customer - What evidence is there to confirm the value satisfaction or the customers CTQs? opportunity represented by this project? - Is the measurement systems capability documented? - Has the scope of the project been verified to ensure - Any assumptions that were made during data that it is neither too small nor too large? collection must be noted. - Has a SIPOC diagram or other high-level process map - Can the team answer questions such as, “Where did been completed? that data came from?”, “How did you decide what - Have any obvious barriers or obstacles to successful data to collect?”, “How valid is your measurement completion of the project been ignored? system?”, and “Did you collect enough data to provide - Is the team’s action plan for the measure step of a reasonable picture of process performance?” DMAIC reasonable? 2. MEASURE PHASE 3. ANALYZE PHASE Objective: evaluate and understand the current state of Objective: use data from Measure phase to determine cause- the process or quantify the current performance of the and-effect relationships in the process and understand the process (baseline) sources of variability Questions answered: Questions answered: - What is the current performance (baseline)? 1. What are the sources of variation? - What is the defect rate? 2. What are the root causes of defects? Know the data - Determine the root cause of variation and poor - What is available, where to source it, and develop a performance plan to gather it - Verify the root cause of variation Summarize the data - Prioritize opportunities to improve (e.g., determine - Use graphical tools which of the problems causing variation should be Describe the problem with the data addressed) - Tell the story using data - Example: Problem is higher customer churn  Other Tools: - Failure Mode and Effects Analysis (FMEA) - Pilot Testing Tollgate Questions - Is there adequate documentation of how the solution Many tools can be used to determine root causes. The task is was obtained? to identify the appropriate tools out of all that are available. - Is there documentation on the alternative solutions considered? - Are there complete results of the pilot test, including data displays, analysis, experiments, and simulation analyses? - Are there plans to implement the pilot test results on a full-scale basis? These should include dealing with any regulatory requirements, personnel concerns, or impact on other business standard practices. - Has there been an analysis of any risks of Other Tools: implementing the solution, and appropriate risk - Hypothesis testing management plans? - Fishbone diagram (Ishikawa diagram) - Confidence intervals 5. CONTROL PHASE - Regression analysis Objective: complete all remaining work on the project and - Control charts (to be discussed in IE 135) hand off the improved process to the process owner, along Note: some tools are also applicable in other phases of DMAIC, with a process control plan and other necessary depending on the purpose of their use procedures to ensure project gains are institutionalized Tollgate Questions Questions answered: - What opportunities are going to be targeted for - Are the improvements consistent over time? investigation in the Improve phase? - How do we maintain the improvements into the - What data and analysis support that investigating the future? targeted opportunities and improving/eliminating them will have the desired outcome in the KPOVs and Standardize and sustain the solutions over time customer CTQs that were the original focus of the Institutionalize the improvements through modification of project? systems and structures (staffing, training, incentives, - Are there other opportunities that are not going to be documentation) further evaluated? If so, why not? Define roles of every relevant member in maintaining the “new” - Is the project still on track with respect to time and process anticipated outcomes? Are any additional resources required at this time? Put in place a: 4. IMPROVE PHASE - Transition plan – to ensure a smooth transition to the Objective: develop and evaluate the solution/s to address the improved process problem - Process control plan – to monitor the “new” process, Questions answered: documenting elements of quality control to ensure - How do we change the process? set quality standards are met - How do we verify that the changes will improve the - Response plan – how to respond when process? nonconformities are detected Directly address the cause Brainstorm potential solutions Prioritize solutions based on the VOC Test if solutions can solve the problem (e.g., pilot study) There is also a selection of tools available from which we must pick what is most appropriate for our needs a. Best Practices Other Tools: - Transition plan - Training plan - Failure Mode and Effects Analysis (FMEA)  - Process capability analysis (to be discussed in IE 135) - CTQ is to meet contractual lead for delivery (~ 8 Tollgate Questions weeks) - Is there data illustrating that before and after results - Process map constructed for the existing process are in line with the project charter available? Were the (from PO to shipment) original objectives accomplished? - Collect both historical data and additional data over a - Is the process control plan complete? Are procedures 2-month period to monitor the process, such as control charts, in Analyze: place? - From data collected, problem areas identified were: - Is all essential documentation for the process owner 1. Supplier quality issues (causes delay in complete? testing due to premature failure) - Is a summary of lessons learned from the project 2. PO process delay (POs not promptly available? processed) - Has a list of opportunities that were not pursued in 3. Delay in customer confirmation the project been prepared? (useful for future projects; (complicates production scheduling) it is important to maintain an inventory of good Improve: potential projects to keep the improvement process - Corrective actions taken: going) 1. Supplier quality control and improvement - Has a list of opportunities to use the results of the (create internal checklist for their supplier project in other parts of the business been prepared? on required testing prior to shipment) 2. Improve internal PO process (common email address established to receive all PO notifications helped to improve transparency of the queue; designate 3 people to manage this account instead of just 1 to process more quickly) Control: - Revised the production tracking spreadsheet with firm milestone dates and provided a more visual format Signs indicating the potential for improvement - Instituted a bi-weekly updating procedure by the - High correction rates and rework levels factory to reflect up-to-date information (so project - Long processing times engineer can better monitor process and take action - Too many steps where things go back and forth accordingly should unplanned deviations occur) - Excessive delays between steps - Result: - Excessive checking o Cost savings amounted to more than - High levels of working/buffer inventory $300,000 per qtr - Processes where no standard way of doing things o Customer was satisfied and continued to exists remain confident in manufacturer’s - High volume of customer complaints capability and capacity - Late deliveries to customers LECTURE 4 Example: DESCRIBING VARIATION Improving On-Time Delivery for a Machine Tool Manufacturer A - Descriptive statistics is a simple yet effective tool to key client of the company contacted them regarding their describe the variation in a process recent poor performance in terms of delivery times. In the Objectives are to: current process, only 85% of deliveries were on-time instead of - Quantitatively express variation the ideal 100%. The customer was now requesting a penalty - Model the probability distribution of a CTQ clause in their contract with the manufacturer to reduce the characteristic paid price for the tools purchased. This meant a significant loss Descriptive Statistics Tools to the business since this customer represented a large volume - Stem-and-leaf plot of their current business. o A graphical method for summarizing and presenting data A team was formed and the project was started. o Suppose each data point is a number having at least 2 digits. One way is to use one or Define: more leading digits as the stem and the - Objective is to achieve 100% on-time delivery remaining digits as the leaf - Customers concerned with capability for on-time o Stem-and-leaf plots are useful when we are delivery (can jeopardize customer production), so a interested in the values of observations penalty clause included at cost to the manufacturer - Potential savings to meet on-time delivery requirement approx. 300K per qtr - Customer satisfaction is critical Measure:  o The stem-and-leaf plot quickly provides o A graphical display that simultaneously useful information on: displays several important features of data ▪ the shape of such as: the data ▪ central tendency ▪ the spread ▪ spread (variability) ▪ departure from symmetry of the data ▪ outliers ▪ The central tendency (i.e., middle) of the data - Histogram o A more compact summary of data than the stem-and-leaf plot o Ranges are divided into class intervals (also called cells or bins) with a defined upper - Probability distributions and lower boundary where the data will be o A mathematical model relating the value of sorted and a count is made for each bin a variable with the probability of its o Some may prefer the use of histograms with occurrence in the population the vertical scale normalized as relative o The two general types of probability frequency (i.e., y = bin frequency / total distributions are discrete and continuous observations) o Like the stem-and-leaf, the histogram quickly provides useful information on: ▪ the shape of the data o A probability distribution is associated with ▪ the spread (variability) of a mean and variance the data ▪ Mean – center of mass of the ▪ The central tendency (i.e., distribution, a measure of central middle) of the data tendency ▪ Variance – variability of the distribution; as variability increases, variance increases - Numerical summary of data FORMULA DESCRIPTION - Average of a data sample - A measure of central tendency - Average of the squared deviations Probability Distributions from the mean DISCRETE - A measure of Hypergeometric (x out of N items w/o replacement) variation (for interval Binomial (x out of n items w/ replacement) ratio variables) Poisson (x occurrences over a fixed interval) - The square root of Pascal/ Negative Binomial (rth success in the xth trial) sample variance CONTINUOUS - A measure of Normal variation (for interval Lognormal (natural log of x is normally ratio variables distributed) - Advantage vs. Exponential (time until occurrence of some variance: expressed event) in terms of the data’s Gamma (sum of r IID exponential original units distributions; time until r *interval data – has an order (scale) and magnitude, but no occurrences) absolute zero Weibull (generalization of exponential *ratio data – same as interval data but accommodates an distribution; has shape & scale) absolute zero - Box plot  o Typical causes: operator error, defective raw material, improperly adjusted or controlled machines o Large effect compared to chance causes, usually representing an unacceptable level of performance o Non-random variation, which can be reduced or eliminated by finding and addressing the cause o Action needed: investigation and corrective Importance of Normal Curve in Sampling Theory action to find and eliminate assignable - Central Limit Theorem causes o Irrespective of the shape of the distribution A process is said to be out-of-control if of a population, the distribution of average assignable causes are also present (in addition values, x-bar, of subgroups of size n, drawn to chance causes) from that population will tend toward a normal distribution as the subgroup size n grows without bounds. Statistical Methods in Q C & I Statistical Process Controls (SPC) Objectives: - To quickly detect the occurrence of assignable causes of process shifts - Elimination of variability in the process Basic SPC Tools: The Magnificent Seven 1. Histogram/stem-and-leaf plot Statistical Control 2. Check sheet - When only chance causes are present, a process is 3. Pareto chart said to be in statistical control 4. Cause-and-effect diagram - When assignable causes are also present (in addition 5. Defect concentration diagram to chance causes), a process is said to be out-of- 6. Scatter plot control 7. Control chart Note # 1: No process is truly stable forever Widely used in both the Analyze and Control steps of DMAIC - Assignable causes eventually occur, so SPC is needed to quickly detect and act upon assignable causes and reduce variability Note # 2: “Control” ≠ “Conformance” - Statistical control only means that a process is consistent and stable “Control” ≠ “Conformance” Control Limits Specification Limits Derived from natural process Determined externally by variability or the natural customers or internally by tolerance limits of a process designers “Voice of the process” “Voice of the customer” Appear on control charts Appear on histograms, box plots, probability charts Guide for process actions Separate good items from bad items What the process is doing What we want the process to do Causes of Variation - Chance (common) causes are the causes Control Charts attributable to inherent or natural variability - An on-line process-monitoring technique o Probabilistically predictable variation - A graphical display of a quality characteristic that has o Cumulative effect of many small and been measured or computed from a sample versus essentially unavoidable causes the sample number or time o Action needed: none! - Parts of a control chart A process is in statistical control or in-control when o Center line (CL) only chance causes are present o Control limits - Assignable (special) causes are the causes o Upper control attributable to new, unanticipated, emergent or limit (UCL) previously neglected phenomena within the system  o Lower control limit (LCL) 2. Establishing parameters o Measurement of the quality characteristic a. First exam scores would be the initial gauge (sample points are often connected by to check students’ foundation of IE 135 straight-line segments for easier 3. Collection of Data visualization) a. Administering the first exam - Control limits are computed in such a way that nearly 4. Construction of Control Charts all of the sample points will fall between them (only freak occurrences will not) - When points fall out of the control limits, then we can say that something has occurred, or the process has shifted to make it out of control - But this is not the only instance when we can conclude a process is out-of-control; a process may be within control limits but still be out of control if it is behaving in a particularly unlikely manner (e.g., 18 of the last 20 points plot above the centerline) FUNDAMENTAL USES OF CONTROL CHARTS - Reduction of process variability - Monitoring and surveillance of a process - Estimation of product or process parameters Benefits of Using Control Charts: 5. Capability analysis (initial) - Effective in preventing nonconformities - Provide diagnostic information - Prevent unnecessary process adjustments - Provide information about process capability - Improve productivity Control Charts and Hypothesis Testing - Control charts have a close connection to hypothesis testing o HO : the process is in-control o HA : the process is out-of-control - The concept of Type I and Type II error applies in analyzing a control chart o Type I error: conclude a process is out-of- control when it is really in-control 6. Monitoring and correction o Type II error: conclude a process is in- a. 2 possible points: Exam, Students control when it is out-of-control 7. Revision General Model of Control Charts a. Examine exam results and questions Let b. Give another test to see if consistent - w = a sample statistic that measures some quality of Using Control Charts to Improve Processes interest - Most processes are not operating in a state of - L = “distance” of control limits from the CL expressed statistical control in stdev units - Routine and attentive use of control charts helps identify the presence of any assignable causes (once eliminated, variability is reduced and the process is improved) Steps to Applying Control Charts 1. Selection of response variable 2. Establishing parameters 3. Collection of data 4. Construction of control charts 5. Capability analysis (initial) 6. Monitoring and correction - An important part of the corrective action process of 7. Revision using control charts is use of the out-of-controlaction Example: plan (OCAP) - I want to determine the “quality” of IE 135 students o Flowchart of activities following detection of 1. Selection of response variable an out-of-control signal a. Exam performance to gauge “quality” o Consists of:  ▪ Checkpoints – potential assignable Designing Control Charts causes - Control chart design includes the choice of: ▪ Terminators – actions taken to o Control limits resolve the out-of-control o Sample size condition by eliminating the o Sampling frequency assignable cause For example, in this control chart, we specified a sample size of o The OCAP should be as complete as five measurements (each point is an average of five possible in its checkpoints and terminators measurements), three sigma control limits, and the sampling and are arranged in an order that facilitates frequency to be every hour. process diagnostic activities Choice of Control Limits - Specifying the control limits is one of the critical decisions that must be made in designing a control chart - Wider control limits → lower Type I error, but higher Type II error o *if narrower control limits, the effect is reversed - We use 3 sigma limits (i.e., L = 3) because it yields good results in practice and it is difficult to determine the true distribution of a process Choice of Sample Size and Sampling Frequency - Sample size is generally chosen with consideration to the size of the shift we are trying to detect - In general, larger samples will make it easier to detect small shifts in the process Types of Control Charts - Ideally, we would like to take large samples at short 1. Variables control charts intervals, however this is not economically feasible a. For continuous quality characteristics - Usually, we either take small samples at short b. Usually involves measurements intervals or larger samples at longer intervals c. E.g., dimension, volume, weight - Industry practice tends to favor smaller, more 2. Attributes control charts frequent samples, particularly in high volume a. For discrete quality characteristics manufacturing processes, or industries where many b. Usually involves counted data or types of assignable causes can occur proportions Choice of Sample Size and Sampling Frequency c. E.g., # of defects, # of mistakes, % of non- - Average Run Length (ARL) is the average number of conforming units points that must be plotted before a point indicates an out-of-control condition o It can be used to evaluate the decisions regarding sample size and sampling frequency ▪ ARL = 1/p ▪ where p = probability a point exceeds control limits o For 3 sigma limits, p = 0.0027. Therefore, ARL = 1/0.0027 = 370. Therefore, even when in-control, an out-of-control signal is generated every 370 samples on average - Average Time to Signal (ATS) is the average time it takes to detect a shift in the process o ATS is occasionally used to express the performance of the control chart  ▪ ATS = ARL x h based upon rational hypotheses is therefore inherently better ▪ where h corresponds to the fixed off in the long run than the one who is not thus successful.” interval of time between two points (Walter A. Shewhart) Rational Subgrouping - The concept of rational subgroups means that Objective subgroups or samples should be selected such that if - Select subgroups in a way that minimizes the assignable causes are present, the chance for opportunity for variation within a subgroup while differences between subgroups is maximized while maximizing it across subgroups the chance for difference within subgroups is - It is desirable for subgroups to be as small as possible minimized Ideal subgroup size - Control charts provide a statistical test to determine if - According to Shewhart, n = 4 variation between subgroups is consistent with - In industry, common subgroup size = 5 variations within subgroups Factors to consider - Time order is frequently a good basis for forming - Statistics (subgroup size of 4 is better than 2 or 3) subgroups because it allows us to detect assignable - Computation causes occurring over time - Cost of measurement - Order of production is one logical basis for - Sensitivity to small variations (larger subgroup size → subgrouping but other factors also influence the narrower control limits) choice of subgroups - Resources required Two schemes proposed by Grant (1999): 1. Each subgroup is as homogenized as possible by Sources of variability in rational subgroups taking samples of consecutive units 1. Cyclical/stream-to-stream variation a. Essentially gives a snapshot of the process a. Variation between consecutive units from a at the point in time a sample is collected process in the same general time frame b. Gives the best estimate of σ if assignable b. Variation among groups of units (e.g., batch causes can be eliminated to batch, lot to lot, machine to machine, c. Gives more sensitive measurement of shifts operator to operator, line to line, plant to in process average plant) 2. Each subgroup is representative of all units produced 2. Temporal/time-to-time variation (in terms of quality level/process performance) since a. E.g., hour to hour, shift to shift, day to day, the last sample by taking a random sample of all week to week outputs over the sampling interval 3. Positional/piece positional variation a. Reflects changes when process shifts a. Variations within a single unit (e.g., left side happen between subgroups vs. right side, top vs. bottom, center vs. b. Preferred when one purpose of control edge, taper, out of round) charting is to influence decisions on product b. Variations across a single unit containing rejection/acceptance on all units since the many parts (e.g., wafer with many chips) last sample c. Variations by location or position in a batch - Considerable care must be taken in interpreting loading process (e.g., cavity to cavity control charts in the 2nd scheme position in a mold press) - If process mean drifts over the sampling interval 4. Piece-to-piece variation between samples, this may cause variability within 5. Error of measurement samples to be large, resulting in wider control limits - Other bases for forming rational subgroups exist - Proper selection of samples requires careful consideration of the process, with the objective of obtaining as much useful information as possible from the control chart analysis Example: We want to use a control chart for a process that utilizes several machines and pools their output into a common stream of output - It’s difficult to monitor if any particular machine is out-of-control if we monitor the common stream, so a logical approach to rational subgrouping is to apply control charting to each individual machine - It depends on the context of the problem being analyzed what is a good basis for establishing subgroupings “The ultimate object is not only to detect trouble but also to find it, and such discovery naturally involves classification. The engineer who is successful in dividing his data initially into rational subgroups