PTTE 434 Quality Organization & Management Lecture 7 Ch 11: Statistical Tools for Analyzing Data (Process Control Charts)

PTTE 434Quality Organization & Management Lecture 7

Ch 11: Statistical Tools for Analyzing Data (Process Control Charts)

2

Chapter Overview

Statistical Fundamentals Process Control Charts Some Control Chart Concepts Process Capability Other Statistical Techniques in Quality

Management

3

Some useful URLs on Control Charts

Stat Soft Quality Control Charts:http://www.statsoft.com/textbook/stquacon.html

Free Quality. Org (Many free tools)http://www.freequality.org

(Please Note: These tools are supported by MS Excel and Access and download best when MS Internet Explorer is used.)

Wikipidia on Control Chartshttp://en.wikipedia.org/wiki/Control_chart

Six Sigma on Control Chartshttp://www.isixsigma.com/st/control_charts/

Univariant and Multivariant Control Chartshttp://www.itl.nist.gov/div898/handbook/pmc/section3/pmc3.htm

4

Process Control ChartsSlide 1 of 37

Process Charts Tools for monitoring process variation. The figure on the following slide shows a

process control chart. It has an upper limit, a center line, and a lower limit.

5

Process Control ChartsSlide 2 of 37

Control Chart (Figure 10.3 in the Textbook)

Upper ControlLimit (UCL)

Lower ControlLimit (LCL)

CenterLine (CL)

The UCL, CL, andLCL are computed

statisticallyEach point representsdata that are plotted

sequentially

6

Process Control ChartsSlide 3 of 37

Variables and Attributes To select the proper process chart, we must

differentiate between variables and attributes. A variable is a continuous measurement such

as weight, height, or volume. An attribute is the result of a binomial process

that results in an either-or-situation. The most common types of variable and attribute

charts are shown in the following slide.

7

Process Control ChartsSlide 4 of 37

Variables and Attributes

Variables Attributes

X (process population average) P (proportion defective)

X-bar (mean for average) np (number defective)

R (range) C (number conforming)

MR (moving range) U (number nonconforming)

S (standard deviation)

8

Process Control ChartsSlide 5 of 37

Central Requirements for Properly Using Process Charts

1. You must understand the generic process for implementing process charts.

You must know how to interpret process charts.

You need to know when different process charts are used.

You need to know how to compute limits for the different types of process charts.

4.

3.

2.

9

Process Control ChartsSlide 6 of 37A Generalized Procedure for

Developing Process Charts Identify critical operations in the process

where inspection might be needed. These are operations in which, if the operation is performed improperly, the product will be negatively affected.

Identify critical product characteristics. These are the attributes of the product that will result in either good or poor function of the product.

10

Process Control ChartsSlide 7 of 37

A Generalized Procedure for Developing Process Charts (continued) Determine whether the critical product characteristic

is a variable or an attribute. Select the appropriate process control chart from

among the many types of control charts. This decision process and types of charts available are discussed later.

Establish the control limits and use the chart to continually improve.

11

Process Control ChartsSlide 8 of 37

A Generalized Procedure for Developing Process Charts (continued) Update the limits when changes have been

made to the process.

12

Process Control ChartsSlide 9 of 37

Understanding Control Charts A process chart is nothing more than an

application of hypothesis testing where the null hypothesis is that the product meets requirements.

An X-bar chart is a variables chart that monitors average measurement.

An example of how to best understand control charts is provided under the heading “Understanding Control Charts” in the textbook.

13

Process Control ChartsSlide 10 of 37 X-bar and R Charts

The X-bar chart is a process chart used to monitor the average of the characteristics being measured. To set up an X-bar chart select samples from the process for the characteristic being measured. Then form the samples into rational subgroups. Next, find the average value of each sample by dividing the sums of the measurements by the sample size and plot the value on the process control X-bar chart.

14

Process Control ChartsSlide 11 of 37

X-bar and R Charts (continued) The R chart is used to monitor the variability or

dispersion of the process. It is used in conjunction with the X-bar chart when the process characteristic is variable. To develop an R chart, collect samples from the process and organize them into subgroups, usually of three to six items. Next, compute the range, R, by taking the difference of the high value in the subgroup minus the low value. Then plot the R values on the R chart.

15

Process Control ChartsSlide 12 of 37

X-bar and R Charts

16

Process Control ChartsSlide 13 of 37

Interpreting Control Charts Before introducing other types of process charts, we

discuss the interpretation of the charts. The figures in the next several slides show different

signals for concern that are sent by a control chart, as in the second and third boxes. When a point is found to be outside of the control limits, we call this an “out of control” situation. When a process is out of control, the variation is probably not longer random.

17

Process Control ChartsSlide 14 of 37

18

Process Control ChartsSlide 15 of 37

Control Chart Evidence for Investigation (Figure 10.10 in the textbook)

19

Process Control ChartsSlide 16 of 37

Control Chart Evidence for Investigation (Figure 10.10 in the textbook)

20

Process Control ChartsSlide 17 of 37

Control Chart Evidence for Investigation (Figure 10.10 in the textbook)

21

Process Control ChartsSlide 18 of 37

Implications of a Process Out of Control If a process loses control and becomes

nonrandom, the process should be stopped immediately.

In many modern process industries where just-in-time is used, this will result in the stoppage of several work stations.

The team of workers who are to address the problem should use a structured problem solving process.

22

Process Control ChartsSlide 19 of 37

X and Moving Range (MR) Charts for Population Data At times, it may not be possible to draw

samples. This may occur because a process is so slow that only one or two units per day are produced.

If you have a variable measurement that you want to monitor, the X and MR charts might be the thing for you.

23

Process Control ChartsSlide 20 of 37

X and Moving Range (MR) Charts for Population Data (continued) X chart. A chart used to monitor the mean of

a process for population values. MR chart. A chart for plotting variables when

samples are not possible. If data are not normally distributed, other

charts are available.

24

Process Control ChartsSlide 21 of 37 g and h Charts

A g chart is used when data are geometrically distributed, and h charts are useful when data are hypergeometrically distributed.

The next slide presents pictures of geometric and hypergeometric distributions. If you develop a histogram of your data, and it appears like either of these distributions, you may want to use either an h or a g chart instead of an X chart.

25

Process Control ChartsSlide 22 of 37

h and g Distributions (Figure 10.12 in the textbook)

26

Process Control ChartsSlide 23 of 37

Control Charts for Attributes We now shift to charts for attributes. These charts deal

with binomial and Poisson processes that are not measurements.

We will now be thinking in terms of defects and defectives rather than diameters or widths.

A defect is an irregularity or problem with a larger unit.

A defective is a unit that, as a whole, is not acceptable or does not meet specifications.

27

Process Control ChartsSlide 24 of 37

p Charts for Proportion Defective The p chart is a process chart that is used to graph the

proportion of items in a sample that are defective (nonconforming to specifications)

p charts are effectively used to determine when there has been a shift in the proportion defective for a particular product or service.

Typical applications of the p chart include things like late deliveries, incomplete orders, and clerical errors on written forms.

28

Process Control ChartsSlide 25 of 37

np Charts The np chart is a graph of the number of

defectives (or nonconforming units) in a subgroup. The np chart requires that the sample size of each subgroup be the same each time a sample is drawn.

When subgroup sizes are equal, either the p or np chart can be used. They are essentially the same chart.

29

Process Control ChartsSlide 26 of 37

np Charts (continued) Some people find the np chart easier to use

because it reflects integer numbers rather than proportions. The uses for the np chart are essentially the same as the uses for the p chart.

30

Process Control ChartsSlide 27 of 37

c and u Charts The c chart is a graph of the number of

defects (nonconformities) per unit. The units must be of the same sample space; this includes size, height, length, volume and so on. This means that the “area of opportunity” for finding defects must be the same for each unit. Several individual unites can comprise the sample but they will be grouped as if they are one unit of a larger size.

31

Process Control ChartsSlide 28 of 37

c and u Charts (continued) Like other process charts, the c chart is used

to detect nonrandom events in the life of a production process. Typical applications of the c chart include number of flaws in an auto finish, number of flaws in a standard typed letter, and number of incorrect responses on a standardized test

32

Process Control ChartsSlide 29 of 37

c and u Charts (continued) The u chart is a graph of the average number of

defects per unit. This is contrasted with the c chart, which shows the actual number of defects per standardized unit.

The u chart allows for the units sampled to be different sizes, areas, heights and so on, and allows for different numbers of units in each sample space. The uses for the u chart are the same as the c chart.

33

Process Control ChartsSlide 30 of 37

Other Control Charts s Chart. The s (standard deviation) chart is

used in place of the R chart when a more sensitive chart is desired. These charts are commonly used in semiconductor production where process dispersion is watched very closely.

34

Process Control ChartsSlide 31 of 37 Other Control Charts (continued)

Moving Average Chart. The moving average chart is an interesting chart that is used for monitoring variables and measurement on a continuous scale.

The chart uses past information to predict what the next process outcome will be. Using this chart, we can adjust a process in anticipation of its going out of control.

35

Process Control ChartsSlide 32 of 37

Other Control Charts (continued) Cusum Chart. The cumulative sum, or cusum,

chart is used to identify slight but sustained shifts in a universe where there is no independence between observations.

36

Process Control ChartsSlide 33 of 37

Summary of Chart Formulas (Table 10.2 in the textbook)

37

Process Control ChartsSlide 34 of 37

Some Control Chart Concepts Choosing the Correct Control Chart

Obviously, it is key to choose the correct control chart. Figure 10.19 in the textbook shows a decision tree for the basic control charts. This flow chart helps to show when certain charts should be selected for use.

38

Process Control ChartsSlide 35 of 37

Some Control Chart Concepts (continued) Corrective Action. When a process is out of control,

corrective action is needed. Correction action steps are similar to continuous improvement processes. They are

Carefully identify the problem. Form the correct team to evaluate and solve the

problem. Use structured brainstorming along with fishbone

diagrams or affinity diagrams to identify causes of the problem.

39

Process Control ChartsSlide 36 of 37

Some Control Chart Concepts (continued) Corrective Action (continued)

Brainstorm to identify potential solutions to problems.

Eliminate the cause. Restart the process. Document the problem, root causes, and

solutions. Communicate the results of the process to all

personnel so that this process becomes reinforced and ingrained in the operations.

40

Process Control ChartsSlide 37 of 37

Some Control Chart Concepts (continued) How Do We Use Control Charts to Continuously

Improve? One of the goals of the control chart user is to

reduce variation. Over time, as processes are improved, control limits are recomputed to show improvements in stability. As upper and lower control limits get closer and closer together, the process improving.

The focus of control charts should be on continuous improvement and they should be updated only when there is a change in the process.

41

Process CapabilitySlide 1 of 4

Process Stability and Capability Once a process is stable, the next emphasis is to

ensure that the process is capable. Process capability refers to the ability of a process to

produce a product that meets specifications. Six-sigma program such as those pioneered by

Motorola Corporation result in highly capable processes.

42

Process CapabilitySlide 2 of 4

Six-Sigma Quality (Figure 10.21 in the textbook)

43

Process CapabilitySlide 3 of 4 Process Versus Sampling Distribution

To understand process capability we must first understand the differences between population and sampling distributions.

Population distributions are distributions with all the items or observations of interest to a decision maker.

A population is defined as a collection of all the items or observations of interest to a decision maker.

A sample is subset of the population. Sampling distributions are distributions that reflect the distributions of sample means.

44

Process CapabilitySlide 4 of 4

The Difference Between Capability and Stability? Once again, a process is capable if individual

products consistently meet specifications. A process is stable if only common variation is

present in the process.

45

Determine characteristicto be charted.

Is the datavariable?

Is it homogeneous,or not conducive to

subgroup sampling?(e.g., chemical

bath, paintbatch, etc.)

Non-conformingunits? (% bad

parts)

Constantsample size?

Nonconformities? (I.e., discrepancies

per part.)

Use np orp chart.

Usep chart.

Can subgroupaverages beconvenientlycomputed?

Usec or chart.

Is samplespace

constant?

Use

chart.

Usemedian chart.

NONO

NONO

NONONONO

NONO

NONO

YESYES YESYES

YESYES

YESYES

YESYES

Next slide.

YESYES

Use X - MR chart.Use X - MR chart.

YESYES

How to choose the correct control chart

46

Is the subgroupsize < 9?

Can subgroupaverages beconvenientlycomputed?

YESYES

Can s be calculatedfor each group?

Usemedian chart.

Usemedian chart.

Use.

Use. X - R chart

Use.

Use. X - R chart

Use.

Use. X - s chart

YESYES

YESYES

NONO

NONO

NONO

How to choose the correct control chart

(from previous page)