1

Quality Improvement Techniques

Ref. Chapter 2 - Besterfield

Pareto Diagram• A Pareto diagram is a graph that

ranks data classifications in descending order from left to right.

• Possible data classifications are types, problems, causes, nonconformities, and so forth.

• The “vital few” are on the left, and the “useful many” are on the right.

• It is sometimes necessary to combine some of the useful many into one classification called other and labeled ‘0’ . – When the “other” category is used, it

is always on the far right. The vertical scale is euro, frequency, or percent.

The data classifications are types of field failure.

data classification

2

Pareto Diagram -Cumulative • Sometimes a Pareto diagram has a

cumulative line, as shown. This line represents the sum of the data as they are added together from left to right.

• Two scales are used: The one on the left is either frequency or euro, and the one on the right is percent.

• The cumulative percentage scale, when used, must match with the euro or frequency scale such that 100% is at the same height as the (cumulative) total euro or frequency. See the arrow in the figure.

• It is noted that a quality improvement of the vital few, of say 50%, is a much greater return on investment than a 50% improvement of the useful many.

Pareto diagrams• Pareto diagrams identify the most important

problems. • Usually, 80% of the total results from 20% of the

items. • The graph has the advantage of providing a visual

impact of those vital few characteristics that need attention.

• Examples of the vital few are– A few customers account for the majority of sales.– A few products, processes, or quality characteristics

account for– the bulk of the scrap or rework cost.– A few nonconformities account for the majority of

customer complaints.

3

Construction of a Pareto diagramThere are six steps:1. Determine the method of classifying the data: by

problem, cause, type of nonconformity, and so forth.

2. Decide if euro (best) or frequency is to be used to rank the characteristics.

3. Collect data for an appropriate time interval.4. Summarize the data and rank order categories from

largest to smallest. 5. Compute the cumulative percentage if it is to be

used. 6. Construct the diagram and find the vital few.

Class Exercise1. A project team is studying the downtime cost of a soft-drink

bottling line. Data analysis in thousands of euro for a 3-month period are: back pressure regulator, 30; adjust feed worm, 15; jam copper head, 6; lost cooling, 52; valve replacement, 8; and other, 5. Construct a Pareto diagram.

2. Approximately two-thirds of all automobile accidents are due to improper driving. Construct a Pareto diagram with the cumulative line for the data:

improper turn, 3.6%; driving too fast for conditions, 28.1%; following too closely, 8.1%; right-of-way violations, 30.1%; driving left of center, .3.3%; improper overtaking, 3.2%; and other, 23.6%.

4

1. Construct a Pareto diagram for replacement parts for an electric stove.

Six-months' data are: oven door, 193; timer, 53; front burners, 460; rear burners, 290; burner control, 135; drawer rollers, 46; other, 84; and oven regulators, 265.

2. A major record-of-the-month club collected data on the reasons for re­turned shipments during a quarter. Construct a Pareto diagram when the results are:

wrong selection, 50,000; refused, 195,000; wrong address, 68,000; order canceled, 5000; and other, 15,000.

3. Nonconformities for a 1-month period for a riding lawn mower manufacturer are shown below. Construct a Pareto diagram.

blister, 212; light spray, 582, drips, 227; overspray, 109; splatter, 141; bad paint, 126; runs, 434, and other, 50.

MATRIX ANALYSIS• Matrix analysis is a simple, but effective, technique to

compare groups of categories such as operators, salespeople, machines, and suppliers. All the elements in each category must be performing the same activity.

• Actually, matrix analysis is a two-dimensional Pareto.• On the next slide we’ll see a matrix table where Column

D has the fewest non-conformities followed by A. It would be useful to discover their “knack” and teach it to the poorer performers.

5

TYPES OFNONCONFORMITY

A B C D E F TOTAL

1 0 0 1 0 2 1 4

2 1 0 0 0 1 0 2

3 0 16 1 0 2 0 19

4 0 0 0 0 1 0 1

5 2 1 3 1 4 2 13

…15 …0 …0 …0 …0 …3 …0 …3

Totals 6 20 8 3 36 7 80

Matrix of Errors Income Tax PREPARER

Operator

TIME SERIES• The series is a very simple

technique to show the change in some factor over time.

• The horizontal scale is established with a time unit such as quarters and years.

• The vertical scale is the factor under consideration, which, in this case, is percent non conforming.

• These graphs are excellent for showing trends and monitoring performance.

6

• Four cloth-weaving looms are being compared by type of nonconformity. Prepare a matrix and analyze. Data are

– Loom 24: broken string, 3; warp tension, 2; shuttle, 1; and jam, 3 Loom 36: nonconforming splice, 2; shuttle, 8; warp tension, 8; broken string, 2; and jam, 1

– Loom 28: warp tension, 5; and jam, 2– Loom 15: jam, 7; shuttle, 6; warp tension, 2; broken string, 7; and

nonconforming splice, 4

• Prepare a time series graph for nonconformities per unit for hospital Medicare claims and analyze the results. Data are:

– 1986 0.20, – 1987 0.15, – 1988 0.16, and – 1989 0.12.

Time Series Exercises

CAUSE-AND-EFFECT DIAGRAM

• A cause-and-effect (CE) diagram is a picture composed of lines and symbols designed to represent a meaningful relationship between an effect and its causes. It is some­times referred to as an Ishikawa (after its developer) or the fish-bone diagram.

Generally this tends to need improvement

Sub Categories include: training, knowledge, ability, physical characteristics etc

Categories of ‘cause’

7

CAUSE-AND-EFFECT DIAGRAM

• CE diagrams are used to investigate either– a "bad" effect and to take action to correct the causes – or a "good" effect and to learn those causes

• The effect is the quality characteristic that needs improvement.

• Causes are usually broken down into the major causes:– work methods, materials, measurement, people, and the

environment. – Management and maintenance are also sometimes used for

the major cause. – Each major cause is further subdivided into numerous minor

causes.

CAUSE-AND-EFFECT DIAGRAM• The cause-and-effect diagram has nearly unlimited

application in research, manufacturing, marketing, office operations, and so forth. – One of its strongest assets is the participation and

contribution of everyone involved in the solution process. • The diagrams are useful in

– 1. Analyzing actual conditions for the purpose of product or service quality improvement, more efficient use of resources, and reduced costs

– 2. Elimination of conditions causing nonconforming product and customer complaints

– 3. Standardization of existing and proposed operations – 4. Education and training of personnel in decision-making

and corrective-action activities

8

Cause-enumerationA particular Cause and Effect (CE) diagram

• The first step in the construction of a CE diagram is for the project team to identify the effect or quality problem. It is placed on the right side of a large piece of paper by the team leader. Next, the major causes are identified and placed on the diagram. Determining all the minor causes requires brainstorming by the project team

• The essentials elements for construction are: 1. Participation by every member of the team is facilitated 2. Quantity of ideas, rather than quality, is encouraged. 3. Criticism of an idea is not allowed. 4. Visibility of the diagram is a primary factor of participation. 5. Create a solution-oriented atmosphere and not a gripe session. Focus on

solving a problem rather than discussing how it began. The team leader should ask questions using the why, what, where, when, who, and how techniques.

6. Let the ideas incubate for a period of time (at least overnight), and then have another brainstorming session.

•Once the CE diagram is complete, it must be evaluated to determine the most likely causes.

–This activity is accomplished in a separate session. –The procedure is to have each person vote on the minor causes. Team members may vote on more than one cause. Those causes with the most votes are circled, and the four or five most likely causes of the effect are determined.

•Solutions are developed to correct the causes and improve the process. Criteria for judging the possible solutions include:

–cost, feasibility, resistance to change, consequences, training, and so forth.

•Once the solutions have been agreed to by the team, testing and implementation follow.

Cause-enumerationA particular Cause and Effect (CE) diagram

9

Other Types Cause and Effect (CE) diagrams

• There are two other types of CE diagrams that are similar to the cause enumeration. The only difference is the organization and arrangement.

– The dispersion-analysis type of CE diagram • looks just like the cause­enumeration type when both are

complete. • The difference is in the approach to constructing it.

– For this type, each major branch is filled in completely before starting work on any of the other branches. Also, the objective is to analyze the causes of dispersion or variability.

– The process-analysis type does look different from the other two.

Process-analysis A particular Cause and Effect (CE) diagram

• In order to construct this diagram, it is necessary to write each step of the production process. Steps in the production process such as load, cut, bore, countersink, chamfer, and unload become the major causes. Minor causes are then connected to the major ones. Generally its easy to construct as it follows the production sequence.

10

• Form a project team of six or seven people, elect a leader, and construct a cause-and-effect diagram for bad coffee from a 22-cup appliance used in the office.

• Form a project team of six or seven people, elect a leader, and construct a CE diagram for:– (a) Dispersion analysis type for a quality characteristic.– (b) Process analysis type for a sequence of office

activities on an insurance form.– (c) Process analysis type for a sequence of production

activities on a lathe: load 25 mm dia.-80 mm long rod, rough turn 12 mm dia.-40 mm long, UNF thread-12 mm dia., thread relief, finish turn 25 mm dia.-20 mm long, cut off, and unload.

Group Projects

CHECK SHEETS

• The main purpose of check sheets is to ensure that the data are collected carefully and accurately by operating personnel.

• Data should be presented in such a form that it can be quickly and easily used and analyzed.

• The form of the check sheet is individualized for each situation and is designed by the project team. The Figure shows a check sheet for paint non-conformities for bicycles

• Often it is useful to indicate the location of the non-confomaties.

11

Other Charts

• Histograms (Which we’ll come to again in chap 3)• Control Charts (Chap 4, 5 and 7)

– Control charts are a good technique for problem solving with resulting quality improvement.

Scatter Diagram

• The simplest way to determine if a cause-and-effect relationship exists between two variables is to plot a scatter diagram.

• The figure shows the Relationship between automotive speed and gas mileage. The figure shows that as speed increases, gas mileage decreases.

• Automotive speed is plotted on the x-axis and is the independent variable. The independent variable is usually controllable (i.e. you decide/control what speed you want to travel at)

• Gas mileage is on the y-axis and is the dependent, or response, variable (i.e. A gas-mileage figure will result from you chosen speed)

y = F(x)

Fx y

cause effect

12

Scatter Diagrams• Other examples of parings are shown here Can you

pinpoint the independent variable and the dependent variable - justify your answer.

– [tool life , cutting speed]– [moisture content, thread elongation]– [temperature, lipstick hardness]– [electrical current, striking pressure] – [percent foam in soft drinks, temperature]– [yield, concentration]– [equipment age, breakdowns]

Scatter Diagrams

– Cutting speed and tool life– Moisture content and thread elongation– Temperature and lipstick hardness– Striking pressure and electrical current– Temperature and percent foam in soft drinks– Yield and concentration– Breakdowns and equipment age

independent variable and the dependent variable

Controllable(Cause)

Response(Effect)

13

Construction of Scatter Diagrams

• There are a few simple steps in constructing a scatter diagram. Data are collected as ordered pairs (x, y). The automotive speed (cause) is controlled and the gas mileage (effect) is measured. Table 2-2 shows resulting x, y paired data.

• The horizontal and vertical scales are constructed with the higher values on the right for the x-axis and on the top for the y-axis. After the scales are labeled, the data are plotted.

• Using dotted lines, the technique of plotting sample number 1 (30, 38) is illustrated in the previous figure . The x value is 30, and the y value is 38. Sample numbers 2 through 16 are plotted, and the scatter diagram is complete. If two points are identical, concentric circles can be used, as illustrated at 60 mi/h.

Scatter Diagram Interpretation I• Once the scatter diagram is

complete, the relationship or correlation between the two variables can be evaluated.

• The figure shows different patterns and their interpretation.

• At (a), we have a positive correlation between the two variables because as x increases, y increases.

• At (b), there is a negative correlation between the two variables because as x increases, y decreases.

• At (c), there is no correlation, and this pattern is sometimes referred to as a shotgun pattern.

14

Scatter Diagram Interpretation II• At (d), there may not be a

relationship between the two variables. There appears to be a negative relationship between x and y, but it is not too strong. Further statistical analysis is needed to evaluate this pattern.

• At (e), we have stratified the data to represent different causes for the same effect.Some examples are gas mileage with the wind versus against the wind, two different suppliers of material, and two different machines. One cause is plotted with a small solid circle, and the other cause is plotted with an open triangle. When the data are separated, we see that there is a strong correlation.

• At (f), we have a curvilinear relationship rather than a linear one.

Flow Diagram

• For many products and services, it may be useful to construct a flow diagram. These diagrams show the flow of the product or service as it moves through the various processing stations.

• The diagram makes it easy to visualize the entire system, identify potential trouble spots, and locate control activities.

• Standardized symbols are used here we see a flow diagram for theorder entry activity of a made-to-order company.

15

PROBLEM-SOLVING METHOD• The project team achieves the optimal results when it operates within the

framework of the problem-solving method. • In the initial stages of a quality-improvement program, quick results are

often obtained because the solutions are obvious or someone has a brilliant idea. In the long term, a systematic approach will yield the greatest benefits.

• The problem-solving method (also called the scientific method) as applied to quality improvement has six steps:– 1. Problem identification– 2. Project team assignment– 3. Problem analysis– 4. Possible solutions– 5. Evaluation– 6. Remedial action

• These steps are not totally independent; they are sometimes interrelated. • Some techniques (such as the control chart) can be effectively utilized in

more than one step. Quality improvement is the goal, and the problem-solving process a

framework to achieve that goal.

Step 1 - Problem Identification • Problem identification should not be a reaction to a negative situation but a

constant searching for potential problems or opportunities to make significant quality improvement.

• It answers the question, What are the quality problems? – The answer leads to those problems that have the greatest potent ial for quality

improvement.• Quality problems can be identified from a variety of inputs, such as the

following: – Quality cost data– Pareto analysis of repetitive external alarm signals (field failures, complaints, ..)– Pareto analysis of repetitive internal alarm signals (scrap rework, sorting ..)– Proposals from key insiders (managers, supervisors, professionals, union..)– Field study of users' needs– Data on performance of products versus competitors (from users and from

laboratory tests)– Comments of key people outside the company (customers, vendors, journalists,

and critics)– Findings and comments of government regulators and independent laboratories

16

Step 2 & 3 -Teams and Analysis• Step 2: The quality council set up a team - sometimes permanent teams are in

place

• Step 3: In the problem-analysis step, the team mobilizes the necessary company resources to analyze the problem. All available information is collected for the project team. If this is not sufficient, then additional new information is obtained. Following are the common items of information:– Design information, such as specifications, drawings, function, bills of materials,

costs, design reviews, field data, service, and maintainability– Process information, such as routing, equipment, operators, raw materials,

component parts, and supplies– Statistical information, such as average, median, range, standard deviation,

skewness, and frequency distribution– Quality information, such as control charts, process capability, acceptance

sampling, run charts, life testing, and operator and equipment matrix analysis– Cause-and -effect diagrams

Step 4 & 5 -Solutions and Evaluation• Step 4: Once all the information is available, the team begins its search for

possible solutions. – With quality problems, more than one solution may be required to remedy a

situation. Sometimes the solutions are quite evident from a cursory analysis of the data.

– If the primary cause or causes are determined from the cause-and­effect approach, the solution might be determined quite easily. In this step, creativity plays the major role.

• Step 5: Evaluation and/or testing determines which of the possible solutions has the greatest potential for success. – Criteria for judging the possible solutions include such things as cost, feasibility,

effect, resistance to change, consequences, and training. – Solutions may be categorized into short range and long range.– It should be pointed out that one of the features of control charts is their ability to

evaluate possible solutions. Whether the idea is good, poor, or has no effect is evident from the chart.

17

Step 6 - Remedial action• The last step, actually involves three activities.

– First: there is an approval process. While the project team usually has some authority to institute remedial action, more often than not the approval of the qualitycouncilor other appropriate authority is required. If such is the case, a written and/or oral report is given.

– Second and third: The project team is also responsible for the implementation and follow-up activities.

These activities are usually included with the report that was presented for approval. If the follow-up activity does not achieve the necessary improvements, then some of the steps will need to be repeated.

• While the problem-solving method is no guarantee of success, experience has indicated that an orderly approach will yield the highest probability of success. Problem solving concentrates on quality improvement rather than quality control.

1. By means of a scatter diagram, determine if a relationship exists between product temperatures and percent foam for a soft drink.

2. By means of a scatter diagram, determine if there is a relationship between hours of machine use andmillimeters off the target. Data for 20 (x, y) pairs with hours of machine use as the x variable are;

(30,1.10), (31, 1.21), (32, 1.00), (33, 1.21), (34, 1.25), (35, 1.23), (36, 1.24), (37, 1.28), (38, 1.30), (39,1.30), (40,1.38), (41,1.35), (42, 1.38), (43, 1.38), (44,1.40), (45, 1.42), (46, 1.45), (47, 1.45), (48, 1.50), and (49, 1.58).

Draw a line for the data using eyesight only and estimate the number of millimeters off the target at 55 h.

3. Data on gas pressure (kg/cm2) and its volume (liters) are as follows: (0.5, 1.62), (1.5, 0.75), (2.0, 0.62), (3.0, 0.46), (2.5, 0.52), (1.0, 1.00), (0.8, 1.35), (1.2,0.89),(2.8, 0.48), (3.2, 0.43), (1.8, 0.71), and (0.3, 1.80).

Construct a scatter diagram and determine the relationship.