TRAININGONTHE SEVEN QC TOOLS

BY N.K.GUPTA

THE SEVEN Q.C. TOOLS

THE SEVEN

Q.C.

TOOLS

THE SEVEN Q.C. TOOLS

Q.C. approach to problem solving stresses onCollecting data that represent the true facts.Analyzing these data in order to make judgmentTaking counter measures.Dr. kaoru Ishikawa, the leading figure in development of Q.C. in Japan said Everybody could solve 95% of problems around them by using Q.C. Tools successfully.QC tools are instruments for handling data and diagnostic tools for Problem Solving

FACTSCollect DataProcess DataProcess DataACTQ.C. APPROACH

WHAT ARE THE QC TOOLS

QC Tools are technique used in QC activities forDiscovering Problem Organizing InformationGenerating ideas.Analyzing causes.Taking actions.Effecting ImprovementsEstablishing controlb)Any technique that can be used effectively in Quality Control for dealing with data is defined as a QC Tools

SIGNIFICANCE OF QC TOOLS

You cannot build a house without hammer and nails.Base for every thing on the facts.Judgment and conclusion on numerical data.Helps in finding out exactly what is going wrong.Unearthing ProblemAnalyzing Problem Taking Counter measuresEstablishing Control e)Most important weapons in solving problem in workplace.

THE SEVEN QC TOOLS

Cause & effect diagram Pareto diagram.Graph & ChartsCheck SheetHistogramScatter DiagramControl Chart

AdditionalRun ChartFlow Chart

1: CAUSE & EFFECT DIAGRAM A Diagram shaped like the bones of a fish for systematically summarizing the relationship between quality characteristics, defects etc and their causes.MethodMaterialMachineryManpowerQualityFISH BONE DIAGRAMMaterialEquipmentMeasurementMethodQualityEnvironmentCAUSEEFFECTWhen you need to explore and display all of the possible cause of a specific problem or condition

USEFULNESS OF CAUSE & EFFECT DIAGRAM (ISHIKAWA DIAGRAM)

For searching out factors that affect the characteristics.

Sorting out the relationship between these factors (Causes) and the characteristic (The results).

Depicting above systematically

Gather the opinion of as many people as possible in order flush out all the relevant factors.

STEPS IN CONSTRUCTING A FISH BONE DIAGRAM

Placing problem statement in box on the right.

Drawing the traditional major cause categories steps in the production process or any cause that are helpful in organizing the most important factors.

Placing the brain stormed ideas in the appropriate major categories.

For each cause ask Why does it happen and list response as branches of the major causes.

Generate ideas through structured brain storming about possible causes without previous preparation.

2: PARETO DIAGRAMPARETO CHART When you need to display the relative importance of all the problems of conditions in order to choose the starting point for problem solving monitor success or identify the basic cause of a problem.A Diagram on which undesirable events are stratifed according to their causes or manifestation and plotted in vertical bar graph in order of importance.0102030405060708090100

3: GRAPH & CHARTS A diagram for plotting data and showing temporal changes and relationship between different quantities.Line GraphBar GraphPie Chart

It help in comparing quantities

Simply graph in which the entire circle represents 100% (Not 360 degrees) of data to be displayed.The circle (Pie) is divided into percentage slices that show the largest shares of data.Shows relative proportiory.

PIE CHARTSURVEY - FEELING ON WEIGHT. This is useful in the same way as pareto chart.400People75% Over weight8% too thin

18% just right

1% dont care

4: CHECK SHEETCheck sheets are simply an easy to understand Form used to answer the question How often are certain events happening?It starts the process of translating Opinions into factsForms specially prepared to enable data to be collected simply by Making check marks.

. Check sheet are used fortifying the occurrences of the defects or causes being adverse and graphing or charting them directly.Check sheets have the systematic recording and compiling of data from historical or current observations. This information can indicate pattern and trends.

ProblemMonths123Total AIIIII5BIIIIIIII8CIIIIIIIIII IIII17Total971430

5: HISTOGRAMIt is graphical picture of a frequency table prepared by dividing the data range into sub groups and counting the no.of points in each sub-group. The no. of points (The frequency) is then plotted as a height on the diagram in bar graph form.

A Histogram takes measurement data temprature, dimension etc. and displays its distribution.A Histogram reveals the amount of variation that any process has with in it.A Histogram gives a Bird Eye Viewof the variation in a data set and provides us a quick picture of the distribution for the measured characteristics. HISTOGRAMWhen you need to discover and display the distribution of data by bar graphing the no. of units in each category.

SMALL VARIABILITYHISTOGRAM - VARIABLITYLARGE VARIABILITYPOSITIVELY OF SKEWEDNEGATIVELY SKEWED

STEP IN CONSTRUCTING A HISTOGRAMStep 1 : Count the no. of data points in the set of data.Step 2 : Determine the range, R for the entire data set.Step 3 : Divide the range value into a certain no. of classes. No. of Data Points No. of Classes (K) Under 50 5 7 50-100 6 10 100-250 7 12 Over 250 10 20Step 4 : Determine the class width, H. R H = Range KStep 5 : Determine the class boundary, or end point.Step 6 : Construct a frequency table based on the values (No. of classes, width and class boundary) The frequency table is actually a Histogram in a tabular form.Step 7 : Construct the Histogram based on the frequency table

STEP IN CONSTRUCTING A HISTOGRAMThere will be more detailed instructions for constructing histograms than most of the other tools. This is being stressed because of the confusion that seems to be crated when deciding on the nmo. Of classes (bars), in the class boundaries, etc.These no. refer to the thickness of a certain key material in process

Step 1 : Counter the no. of data points in the set of data. For our example above there are 125 data points (n=125) Step 2 : Determine the range, R for the entire data set. The range is the smallest value in the set of data subtracted from the largest value. In our case, the range is equal to 10.7 minus 9.0. Thus, the range equals 1.7. Step 3 : Divide the range value into a certain no. of classes, referred to as K. the table below provides an approximate guideline for dividing your set of data into a points would be broken down into 7-12 classes. We will use K=10 classes. No. of Data Points N. of Classes (K)Under 505-750-1006-10100-2507-12Over 25010-20

Step 4 : Determine the class width, H. A convenient formula is as follows. R 1.7H = = = .17 K 10 In this case, as in most, it helps to round off H to some convenient no. for our purposes, .20 would appear appropriate.Step 5 : Determine the class boundary, or end point. Take the smallest individual measurement and look at the right most decimal place. Subtract half the right most decimal place from this measurement. In our example the smallest individual measurement was 9.0. Thus, subtract 0.05 from 9.0 to obtain the lowest class boundary of 8.95. Finally, consecutively add the class width 0.20 (i.e. 8. 95, 9.15, 9.35) to lowest class boundary unit the correct no. of classes, 10, obtained.

Step 6 : Construct a frequency table based on the values (i.e. no. of classes, class width. Class boundary) computed above. The frequency table is actually a histogram in a tabular form. A frequency table based on the thickness. Data is shown below:

ClassClass BoundariesMid PointFrequencyTotal18.95-9.159.051129.15-9.359.251111 1111939.35-9.559.451111 1111 1111 11649.55-9.759.651111 1111 1111 1111 1111 1 2759.75-9.959.85 1111 1111 1111 1111 1111 1111 13169.95-10.1510.051111 1111 1111 11123710.15-10.3510.251111 1111 11 12810.35-10.5510.45112910.55-10.7510.65111141010.75-10.9510.850

Step 7 : Construct the histogram based on the frequency table. A histogram is a graphical picture of a frequency table. It provides us with a quick picture of the distribution for the measured characteristic. A Histogram for our example is shown below :

As point out earlier, the histogram is an important diagnostic tool because it gives a Bird-eye-view of the variation in a data set. In our case, the data appears to have a central tendency around 9.75 to 9.95. It also appears the data creates close to a normal curve. The specification for the thickness characteristic is 7.5 to 10.5, with a target of 9. Thus, we can see that our histogram indicates the process is targeted high and that 3% may be above the upper specification limit.

6 : SCATTER DIAGRAMA Scatter diagram is a plot to access the relationship between two variables.It is prepared by plotting paired sets of data such as hardness and tensile strength and temperature & yield etc. against each other on X and Y axis.A Scatter diagram is set up whereby the horizontal axis (X-axis) represent the measurement values of one variable and the vertical axis (y-axis) represent the measurement of second variable.A Scatter diagram is used to study the possible relationship between one variable and another.The Scatter diagram is used to test for possible causes and effect relationship. It can not prove that one variable causes the other but it does make it clear whether a relationship exists and the and the strength of that relationship.

METHOD OF USECollect paired sets of data on causes and effects and use scatter diagram to check for correction between the sets of data.Use atleast 30 values, preferably around 100.

Variable 2Variable 1

VRIATION PATTERN OF SCATTER DIAGRAMxyxyxyxyxyHeight vs wt.Trg. Vs performancePositive CorrelationNegative CorrelationPossible Negative CorrelationNo CorrelationPossible Positive Correlation

8: RUN CHARTA run chart or time series plot permits the study of observed data for trends or patterns over time, where X-axis is time and Y-axis, The measured variable.Run charts are employed to visually represent data they are used to monitor a system to see whether or not the long range average is changing.Run charts are simplest tool to construct and use point are plotted on the graph in order in which they become available.Run charts are used when you need to do the simplest possible display of trends within observation points over a specified time period.Run chart is common to graph the result of a process such as machine down time, yield, scrap, and productivity as they very over time.MEASUREMENTTIME OR SEQUENCE