Lean_Six_Sigma_GB_MS_AFS

Line Balancing

Line balancing helps to see where continuous flow might be possible among multiple processes, the idea being that continuous flow can only be achieved when each process operates at the optimal Takt time. It helps improve the process throughput while reducing lead time, inventory and costs.

Just-in-Time

Low inventory production system, also known as Stockless Production, using Pull Scheduling to replenish downstream operations with work-in-process inventory as demanded. ____ matches the pace of production closely with customer demand to minimize inventory levels and reduce Cycle Times. ____ aims to deliver products and services to the customer only as they are requested or needed.

6 M's

Manpower Methods Machine Material 'Mother Nature' (or Environment) Measurements ... Used mainly in manufacturing *Categories for ANALYZE phase of Fishbone / Cause & Effect Diagram / Ishikawa Diagram*

Continuous measurements

Measurement derived from a scale or continuum that is infinitely-divisible [e.g. time, temperature, weight, height, voltage, miles per hour, etc.] and provide the greatest possible information content (within the boundaries of measurement device resolution) because values are represented directly, not classified into categories. Also called variable measurements.

Discrete measurements

Measurement representations of categories or attributes E.g. good/bad, boy/girl, black/white, or a discrete number of items or objects that only come in whole units: people, cars, animals, cities, computer terminals, etc. Rating scales and indexes are another example of discrete measurement systems, for example: customer satisfaction rated on a scale of 1 to 5, grading of a course from F to A. Also called Attribute Measurements

Coefficient of Determination

Measures the proportion of variance in one variable that is explained by another variable. In multiple regression analysis, R gives the proportion of variance in the response (output) variable that is attributable to the set of explanatory (input) variables in the model. It is interpreted as a measure of the strength of the linear association between the output and input variables and serves as an indicator of how well the regression model fits the data.

Kanban

_____ is used to request materials replenishment between linked operations along the production line. _____ is a commonly used tool in Just-in-time production systems. On a factory floor, carts are used to transport parts from one site to another. An empty cart at the downstream site signals a need for replenishment of the parts and the cart is moved back up to the source to be filled. The filled cart is moved once again to the 'customer' site, signaling the 'order' fulfillment. ... Japanese for 'signal',

Measurement System Analysis (MSA)

A procedure used to estimate the percentage of variation in a measurement that is due to the measurement system (gages, operators, fixtures) itself. The actual method employed depends on the nature of the measurements, whether they're continuous or attribute-based. Gage R&R (Repeatability and Reproducibility) is the name given to the MSA for continuous data.

Defects Per Million Opportunities (DPMO)

A quality metric used in the calculation of the sigma level. It facilitates direct comparisons between processes with varying levels of complexity. ____ = (Number of Defects x 1,000,000) / ((Number of Defect Opportunities per Unit) x Number of Units)

Affinity Diagram

A team-based tool used to organize and categorize large amounts of non-numerical information into logical, cohesive groups. This technique is used to group like ideas together during problem-solving or idea-generation brainstorming sessions, resulting in separate groupings with coherent central themes. Also referred to as KJ Analysis.

Force Field Analysis

A tool to assist in examining *the driving and restraining forces of change*, help a team understand the forces that keep things the way they are, and build organizational consensus concerning the forces for and the barriers to change To force creative thinking focused on the issues of change and provide an entry point into process improvement initiatives.

Sigma

A measure that represents the standard deviation.

Pareto Principle

"20% of the actions produce 80% of the gains" or "80% of our problem can be explained by just 20% of the causes" ... find the vital few categories that account for most of the variation or problems

Genichi Taguchi's Loss Function

*The total loss to society from poor quality increases in a geometric fashion as variability increases* (is proportional to the square of the deviation of the performance characteristic from its target value or L(y) = k(y-T)^2, where T=the target value and k = a constant). Accordingly, *products produced near the upper or lower specification are less "good" than products produced at the process target value, and there is little difference between products that are marginally acceptable and those that are marginally defective.* This interpretation of quality requires continuous measures of the quality characteristic.

Uptime

100% minus losses for all causes, including equipment failures, set-ups, adjustments, start-ups, and stoppages. ____ does not measure actual speed vs. engineered speed.

Cpk

A measure of the actual process capability. It calculated by dividing the distance of the process mean to the nearest tolerance limit by 3 standard deviations of the process. Again, the process must be in control before assessing ____.

Efficiency

A measure of the amount of input necessary to achieve a given output. It is a productivity metric measuring the speed and cost of doing a job.

Systematic random sampling

Involves selecting one unit on a random basis and choosing consecutive units at evenly spaced intervals until the desired number of units is obtained. This plan could be useful when selecting manufactured units moving along a production line.

(Pearson's) Correlation Coefficient

A measure of the degree to which two quantitative variables are linearly associated. The correlation coefficient (r) Ranges between -1 (perfect negative linear association) and +1 (perfect positive linear association). A coefficient value of zero indicates that there is no linear association between the two variables (note: it does NOT rule out a non-linear relationship).

The Empirical Rule

68% of the values under the normal curve fall within one standard deviation of the mean, 95% within two standard deviations and 99.7% within three standard deviations of the mean. Also called the 68-95-99.7% rule.

Voice Of The Customer (VOC)

A compilation of data on the needs and wants of a company's internal and/or external customers, obtained through various channels such as comment/suggestion boards, focus groups, interviews and market research. Process: Identify > Gather > Sort > Develop > Translate

Lean Six Sigma

A comprehensive and flexible system for achieving, sustaining and maximizing business success. ______ is uniquely driven by close understanding of customer needs, disciplined use of facts, data, and statistical analysis, and diligent attention to managing, improving, and reinventing business processes.

Histogram

A graphical display of the distribution of a set of continuous data. The x-axis of the graph represents the measurement scale of the dataset. The y-axis represents the frequencies (counts) of observations falling in the different intervals. Because the measurement scale is continuous, the bars representing the intervals are connected, unlike those in a bar chart. The ____ gives a good idea of the shape, centering and spread of a dataset.

Value Stream Map

A graphical representation of the series of activities the organization follows in producing and delivering its end product or service. It shows the flow of information and material and the occurrence of actions using easy-to-understand symbols.

Boxplot

A graphical tool used to display the centering, spread and shape of a continuous dataset. It essentially gives a pictorial representation of the five point summary descriptive statistics: the minimum value, lower quartile, median (sometimes includes the mean), upper quartile and maximum value. Also known as 'Box and Whiskers' plot because the lines extending from either end of the box to the maximum and minimum are called 'whiskers'.

SIPOC

A high-level Process Map that shows the relationships between Suppliers, Inputs, Process, Outputs and Customers. SIPOC Maps are useful in defining the scope of an improvement project, so they are employed when developing or refining the project charter. Because SIPOC Maps also identify the process inputs, they can also be used as the first cut at identifying potential key process inputs (KPIs).

Kaizen

A highly focused, short-term rapid improvement event performed by cross-functional teams at the work-group level that identifies and removes waste from a process.

Critical-To-Quality-Characteristics (CTQC)

A measurable characteristic of a process or product which expresses a key requirements of the customer - either internal or external. A ____ characteristic should be determined through analysis of Voice of Customer (VOC) data to have a significant impact on customer satisfaction. Sometimes referred to at Critical Customer Requirement (CCR)

Cp

A measure of potential process capability. It is the ratio of the six-sigma spread of a process distribution to the tolerance of that distribution. The process must be stable in order to assess ___. ___ gives the maximum process capability (Cpk) if the process is centered exactly in the middle of the tolerance.

Effectiveness

A measure of the ability of the product or service to meet customer expectations. In other words, it is a measure of quality - how well the job gets done. The advantage of Effectiveness metrics is that they speak to the customer's experience, unlike Efficiency metrics. If effectiveness measurements turn south, improved efficiency will have little long term value because the top line - sales revenue - will be negatively impacted.

Central Limit Theorem

According to this theorem, the sampling distribution of the sample mean is approximated by a Normal distribution as the sample size increases, irrespective of the shape of the original distribution.

1.5 Sigma Shift

All processes exhibit increasing instability over time. Thus, a process that in the short term has only common cause (random) variation will tend to 'shift and drift' in the long term because of special cause variation. According to Motorola, this shift could be as much as 1.5. The 1.5 sigma shift was proposed as an 'adjustment factor' to account for this long term process drift. The idea is that a process becomes less capable over time, so that if it is performing at 6 sigma capability today, the long-term sigma is really (6-1.5=) 4.5 after accounting for the shift.

Bias

Also referred to as Accuracy, ___ is a measure of the distance between the measured value and the "True" or "Actual" value of the sample or part. If the distance is greater than zero, we say there is a positive ___; if it is smaller than zero, the ___ is negative. Thus, ___ is related to the quality of the measurements (how close they are to the standard) as opposed to precision which has to do with the consistency of the measurements (how close they are to each other).

Operational Definition

An unambiguous, observable, and if at all possible, measurable standard of acceptance for a product/process characteristic [aim is a] common set of rules for evaluating a characteristic that everyone can follow independently, without any opportunity for misinterpretation. The process for creating _____ _____ involves three elements: a criterion, validation test and decision. The criterion establishes the objective for the key quality characteristic against which the test results can be evaluated. The test provides a specific procedure for measuring the characteristic. Finally, the decision is a determination as to whether or not the characteristic meets the criterion.

Defect

Any failure of a product or service to meet customer requirements. The "customer" may be the external consumer, or may be the next step of an internal process

Constraint

Any restrictation, financial, physical or otherwise, that limits the capacity of a process to produce higher throughput. ALSO, A time trap that is unable to produce at the exit rate required to meet customer demand rate.

Continuous Flow

Continuous or one-piece flow eliminates all waste in a process by improving the movement of material or information through a process. This is in contrast to the traditional batch-and-queue processing setup which causes extra handling and buildup of work-in-process (WIP). Reducing cycle time requires achieving a more continuous flow, which in turn requires a reduction in lot size to more closely match the pace of demand with the pace of production. Achieving continuous flow of either materials or information requires a combination of conditions and activities: reducing the lot size (batch size) as close to one as possible. [Visibility > Flow > Pull > Perfection]

Prevention Cost

Cost (Investment) to do it right the first time. Training, error-proofing, pre-production pilots, design for capability (DFSS - Design For Six Sigma).

Appraisal Cost

Cost of testing and inspection to detect defects internally.

External Failure Cost

Defects detected by customers, including warranty, replacements, allowances, product liability, customer dissatisfaction and lost revenue.

Internal Failure Cost

Defects detected internally: Scrap, rework, and "Seconds" sold off-price.

ABC Part Stratification

Divides inventoried items (individual part numbers) into three classifications on the basis of dollar volume: Class A items = 80% of the dollar volume Class B items = 15% of the dollar volume Class C items = 5% of the dollar volume AKA the Pareto Principle - "Critical few and trivial many" Dollar Volume = Annual Production Volume x Cost per Item Dollar Volume is also known as "Extended Cost"

Failure Modes and Effects Analysis (FMEA), Part A

Failure Modes and Effects Analysis is used to evaluate all possible ways in which a product/process may fail and to assess their effect down stream. It is used primarily as a tool to prioritize improvement actions based on the scores assigned for the *severity*, *occurrence* and *detection* likelihood associated with each failure mode. A *Risk Priority Number (RPN) is obtained by taking the product of these scores* and the failure mode with the highest RPN is considered the highest priority for improvement.

Linearity

Gage ____ is a measure of the consistency of Bias over the operating range of the measurement device (gage). For example, if a bathroom scale is under by 1.0 pound when measuring a 150 pound person, but is off by 5.0 pounds when measuring a 200 pound person, then the scale of Bias is not constant and it may help to understand the extent of changes in Bias over the range of weights being measured.

Repeatability

Gage _______ assesses the ability of the gage or measurement system to give consistent readings when the same appraiser measures the same part multiple times with the same device. It is a measure of the inherent precision of the gage. _____ is a part of Gage _______and Reproducibility (R&R) studies performed on continuous data.

Reproducibility

Gage ________ assesses the ability of the gage to give consistent readings when different appraisers measure the same part/sample with the same device or system. It is a measure of how well the appraisers conform to the measurement procedure.

Stratified random sampling

If the population consists of naturally different segments (strata) such as different machines, groups, shifts, product variations, etc., consider using a stratified sampling plan. For example, a pizza delivery chain might want to collect data on average delivery time, and stratify the sampling to look at different times (weekdays vs. weekends, hour by hour in the evening), or different geography (different neighborhoods served). In this case units would be randomly sampled from within each stratum to form the sample and all units in a stratum would have an equal chance of being selected. Be sure to associate the data with the stratum it came from so you can connect the dots to possible root causes when you see a pattern.

Little's Law (equation)

PLT = WIP / ER Process Lead Time = Work-in-progress / Exit Rate The equation states: Throughput Volume Per Unit of Time = Items-In-Process/Cycle Time Or, solving for the other components: Items-In-Process = Throughput Volume Per Unit of Time x Cycle Time Or: Cycle Time = Items-In-Process / Throughput Volume Per Unit of Time

4 P's

People Process / Plant Procedure Policies ... preferred by service organizations *Categories for ANALYZE phase of Fishbone / Cause & Effect Diagram / Ishikawa Diagram*

First Pass Yield

Percentage of units that meet specifications without any rework or repair. This is a commonly used measurement, but has dubious value for two reasons: A) rework and repair is often "hidden" - takes place up the line but is not recorded, and B) multiple defects occurring on a single unit are not captured.

Value Added Cycle Time

Portion of the total cycle time where value is actually added to the product or service - excludes all wait time and transit time through a plant

Process Cycle Efficiency (PCE) formula

Process Cycle Efficiency = Value Added Time / Process Lead Time or PCE = VA / PLT

Single Minute Exchange of Die (SMED)

Process of quick die changes (nine minutes or less) developed by Shigeo Shingo and Toyota. The process is based heavily on completing setup operations in advance (external setup) of the actual changeover that takes place when the machine is down (internal setup).

Preventive Maintenance %

Proportion of total maintenance time spent on preventive actions vs. unplanned actions.

Regression Analysis

Regression analysis is a statistical technique for estimating the relationship between a response variable (Y) and one or more independent explanatory variables (X's). Simple regression gives the relation between one Y and one X, multiple regression models the relation between one Y and multiple X's and multivariate regression involves multiple Y's. Regression analysis is also called 'curve fitting', because it essentially fits an equation of a line (linear) or curve (non-linear) to the data that best explains the relationship between the Y's and X's. This is called a Regression equation. The Least squares or Maximum likelihood methods are commonly used to obtain the regression equation

Standard Deviation

Roughly the arithmetic average distance of the observed values from the mean. It is the square root of the variance, and represents the spread of a distribution. Its advantage over the variance is that it is expressed in the original measurement Units (the variance is expressed in squared units).

Sigma Level

____ is a quality metric that measures the level of performance of a process based on the number of defects per million opportunities (DPMO) in that process, compared to the near-perfection level of Six Sigma, which equates to 3.4 defects per million opportunities. **uses the standard deviation and the customers' specification limit to determine process capability**

Theory of Constraints (TOC)

TOC optimizes resource utilization by identifying, exploiting, subordinating, elevating and reassessing constraints in the process. Scientific principles are applied as a set of logical thinking processes to develop transformational, breakthrough business solutions. A constraint is any resource whose capacity is less than the demand placed upon it. TOC attacks constraints and barriers (a restriction or other block to increases in output). PRIMARY RULE: balance flow, not capacity

Key Process Output Variable (KPOV)

The "big Y" or CTQC of interest.

Value Stream

The complete sequence of activities an organization performs in order to produce and deliver its end product or service. It encompasses suppliers, internal processes, customers and end-users. This toolset focuses on the flow from customer demand backward through the process to supplier delivery of raw material or information

Cost of Poor Quality (COPQ)

The cost incurred by producing non-conforming product/service. It includes the categories of appraisal (inspection, audit), internal failure (defectives, rework, scrap, ineffective use of resources), external failure (repairs, service calls, warranty claims, write-offs, lost business and lost opportunities) and prevention (costs incurred trying to minimize the cost of appraisal and failures). Poor quality in the supply chain also compounds these costs

Error-Proofing / Poka-Yoke

The design and implementation of fail-safe mechanisms to prevent a process from producing Defects. This activity is also know by the Japanese term poka-yoke, from poka (inadvertent errors) and yokeru (to avoid). The emphasis here is on error prevention rather than resolution, where efforts are made to reduce or eliminate the opportunities for committing errors.

Process Cycle Efficiency (PCE)

The efficiency of a process based upon the amount of value added to the product vs. the time the product spends in the process. PCE is a measure of the relative efficiency in a process. It represents the percentage of time that's spent adding value to the product, to the total time the product spends in the process; PCE is the performance indicator for any given process.

Stability

____ refers to the capacity of a measurement system to produce the same values over time when measuring the same sample. As with statistical process control charts, ___ means the absence of "Special Cause Variation", leaving only "Common Cause Variation" (random variation).

Capacity

The maximum amount of product (output) a process can deliver (produce) over a continuous period of time.

Parts Per Million Defective (PPM)

The number of defective parts (or operations in a service example) out of each one million parts or operations. The calculation is straightforward: Number of Defects / Number of Units (or Operations) x 1,000,000.

Time Trap (Bottleneck)

The operation or step that inserts the largest amount of time delay into a process. There can be only one time trap at a time in a process. **A timetrap is not always a process constraint.

Lead Time

The time (in days) from receiving raw material to shipping product

Takt Time

The time it should take to produce one unit if production is matched to demand. It gives the pace of customer demand. ___ time = net available production time (after breaks) per period divided by customer demand during that same period. ___ time is commonly referred to as the "drum beat" of the process.

Variance

The variance of a distribution is a measure of the dispersion, or amount of scatter about the mean. For the population distribution, the variance is roughly the average squared distance between the mean and the individual observations. The sample variance of a set of data is calculated as the sum of squared deviations of the individual observations from the mean divided by the Degrees of Freedom, (n-1).

Simple random sampling

This is a method of selecting n units from a population such that every possible sample of size n has an equal chance of being drawn.

Central Tendency

_____ _____ is the property that data tends to group around a "center" point This "center" may be the a) mathematical average = MEAN b) the data point in the center of the data set = MEDIAN or, c) the most frequently occurring data value = MODE

Defects Per Unit

Total number of defects identified on all units divided by the number of units. This metric gives a better measure of quality than First Pass Yield because it captures all defects. Care must be taken to capture "hidden" rework and repairs that may take place up the line or prior to the reporting point. This metric is also more readily convertible to Defects Per Million Opportunities for Six Sigma projects.

Total Cycle Time

Total time to complete a physical process, including wait time and inventory time. Also known as Dock to Dock Time.

Seven Forms of Waste

Transportation (moving items from one place to another) Inventory (items/paperwork/information waiting to be processed) Motion (excess movement and/or poor ergonomics) Waiting (delays caused by shortages, approvals, downtime) Overproduction (producing more than is needed) Overprocessing (adding more value than the customer is willing to paying for) Defects (rework & scrap - doing the same job more than once)

Cluster or multi-stage random sampling

Used when a list of the population units themselves is not available, but a list of clusters of units such as households, cities, departments, etc. is. In this case a sample of clusters is selected at random and all units belonging to the selected clusters are included in the sample. If units from each cluster are further selected by random sampling, this becomes a two (multi) stage sampling plan.

Value Add Time (VA Time)

Useful activities/features in a process that a customer will pay for. Value Added activities are ones that give the product/process a competitive advantage by making it more innovative or revenue-enhancing.

Z-Score

Value calculated by subtracting the sample mean from the observed value and dividing the difference by the sample standard deviation: (X - mean)/std. dev. It gives the number of Standard Deviations between the observed value and the mean. It relates the data point to the Standard Normal Distribution, with Mean=0 and standard deviation=1. (Also called standard score) Helps answer the question "how many standard deviations away is the observed value from the mean?'' by mapping the observed value onto the standard normal distribution.

Little's Law (definition)

___ is an equation that expresses the relationship between the processing speed, work-in-process inventory and cycle time for a stable process. This relation provides the basis for using lean methods to reduce processing, either by reducing the items in inventory, or by increasing the throughput rate or processing capacity.

Scatter Plot

___ provide a visual display of the relationship between two variables, showing how one variable increases or decreases as another variable increases or decreases. If changes in one variable are linked to changes in another, they are said to be "correlated". Correlation may provide some insight into a possible cause & effect relationship between two variables, although correlation alone does not prove a causal relationship