7110406 Quality Tools Doc

8/8/2019 7110406 Quality Tools Doc

1/48

Kano Analysis


2/48

A Brief Tutorial on Mistake-proofing, Poka-Yoke, andZQC

Work Instructions for Mistake Proofing

1. Use CFT approach to Mistake proofing.

2. Selection of process for Mistake proofing.During the third phase of APQP, the CFT shall identify the processes, where, dueto avoidable human errors, the rating of "Occurrence" and/or "Detection" haveincreased thereby increasing the RPN for the process. Poka Yoke techniques of

mistake proofing are applied to these processes in order to lower the ratings of Occurrence and / or detection.

Analysis of Customer complaints also reveals activities which are in need of mistake proofing, in order to achieve 'Zero Defect' level of working. CFT willundertake application of Poka Yoke techniques to these processes.

3. The selected mistake proofing technique should qualify the following criteria:o Inexpensive.o Based upon common sense, preferably of the operator or the 1st line

employee.o It MUST eliminate Occurrence / Detection of the problem at the source

itself.

4. Occurrence oriented Poka Yoke should follow the procedure as below:A) First classify the source of 'Occurrence' as follows:

1. Required action is NOT performed or is performed incorrectly.2. Undesired action is exercised.3. Information essential for performing the action is mis-interpreted.4. Mistake occurs due to complexity.

B) After having classified the source, apply one of the following techniques, asappropriate, to prevent the occurrence:

o Use of 100% prevention devices such as Fouling Pins, Contoured locators

or templates, Proximity or Photo-electric sensors, Limit or Micro switches,Warning lights or Buzzers, Pressure transducers.o Design to modify to ensure that in assembly the parts shall not join if

aligned wrongly.Machine will not run if operators' hands or feet are notoutside or if the job & tooling are not in right position.

o These techniques should be integral part of the process.The devices areplaced sufficiently close to where the mistakes occur, providing fastfeedback to the operator, of mistakes occurring.


3/48

5. Detection oriented Poka Yoke should use one of the following techniques for ensuring 100% detection of the mistake:

o It should be autonomous inspection occurring without intervention.o It should be 100% inspection which occurs without intervention.o It should determine 'before the fact' whether the conditions for 100%

quality exist or not.o It should make the error visible to the operator.o Consider supply of exactly made kits of components to the assembler, so

that any balance part will signal error in assembly.o Consider use of electronic sensors to activate warning lights or buzzers.o Use color coded parts or graphics.o Make use of contact devices e.g. Fixtures, Limit switches, probes or Non-

contact devices e.g. LEDs, Pressure transducers etc.

6. Effectiveness of the applied Poka Yoke technique should be judged after observing the performance, for a period on minimum one month.


4/48

Histograms

A histogram is a specialized type of bar chart. Individual data points are grouped together inclasses, so that you can get an idea of how frequently data in each class occur in the data set. High

bars indicate more points in a class, and low bars indicate less points. In the histogram show

above, the peak is in the 40-49 class, where there are four points.The strength of a histogram is that it provides an easy-to-read picture of the location and variation in a data set. There are, however, two weaknesses of histograms that you should bear inmind:The first is that histograms can be manipulated to show different pictures. If too few or too many

bars are used, the histogram can be misleading. This is an area which requires some judgment,and perhaps some experimentation, based on the analyst's experience.Histograms can also obscure the time differences among data sets. For example, if you looked atdata for #births/day in the United States in 1996, you would miss any seasonal variations, e.g.peaks around the times of full moons. Likewise, in quality control, a histogram of a process runtells only one part of a long story. There is a need to keep reviewing the histograms and controlcharts for consecutive process runs over an extended time to gain useful knowledge about aprocess.

Histogram statistics:

For histograms, the following statistics are calculated:

Mean The average of all the values.

Minimum The smallest value.

Maximum The biggest value.

Std Dev An expression of how widely spread the values are around the mean.

Class Width The x-axis distance between the left and right edges of each bar in thehistogram.

Number of Classes

The number of bars (including zero height bars) in the histograms.

Skewness Is the histogram symmetrical? If so, Skewness is zero. If the left hand tail islonger, skewness will be negative. If the right hand tail is longer, skewness will


5/48

be positive. Where skewness exists, process capability indices are suspect. Forprocess improvement, a good rule of thumb is to look at the long tail of yourdistribution; that is usually where quality problems lie.

Kurtosis Kurtosis is a measure of the pointiness of a distribution. The standard normalcurve has a kurtosis of zero. The Matterhorn, has negative kurtosis, while a

flatter curve would have positive kurtosis. Positive kurtosis is usually more of aproblem for quality control, since, with "big" tails, the process may well be wider than the spec limits.

Specification Limits and Batch Performance

Where relevant, you should display specification limits on your histograms. The specificationsinclude a target value, an upper limit and a lower limit. For example, if Michael Jordan isshooting a basketball at a hoop, his target is the middle of the hoop. His spec limits are thosepoints in the circle of the hoop that will just allow the ball to bounce through the basket. If theshot is outside spec limits, the ball doesn't go in.

When you overlay specification limits on a histogram, you can estimate how many items are beingproduced which do not meet specifications. This gives you an idea of batch performance, that is,of how the process performed during the period that you collected data. PathMaker calculates theactual percentage of items in the sample that fall outside specification limits.

When you have added target, upper and lower limit lines, you can examine your histogram to seehow your process is performing.

If the histogram shows that your process is wider than the specification limits, then it is notpresently capable of meeting your specifications. This means the variation of the process should

be reduced. Also, if the process is not centered on the target value, it may need to be adjusted so that it can, onaverage, hit the target value. Sometimes, the distribution of a process could fit between thespecification limits if it was centered, but spreads across one of the limits because it is notcentered. Again, the process needs to be adjusted so that it can hit the target value most often.

Center of a Distribution

Processes have a target value, the value that the process should be producing, where most output

of the process should fall. The center of the distribution in a histogram should, in most cases, fallon or near this target value. If it does not, the process will often need to be adjusted so that thecenter will hit the target value.

Spread of a Distribution

The spread, or width of a process is the distance between the minimum and maximum measured values. If the spread of the distribution is narrower than the specification limits, it is an indication


6/48

of small variability in the process. This is almost always the goal, since consistency is important inmost processes. If the distribution is wider than the specification limits the process has too much

variability. The process is generating products that do not conform to specifications, i.e. junk.

Shape: Skewness and Kurtosis

A "normal" distribution of variation results in a specific bell-shaped curve, with the highest pointin the middle and smoothly curving symmetrical slopes on both sides of center. Thecharacteristics of the standard normal distribution are tabulated in most statistical reference

works, allowing the relatively easy estimation of areas under the curve at any point.Many distributions are non-normal. They may be skewed, or they may be flatter or more sharply peaked than the normal distribution.

A "skewed" distribution is one that is not symmetrical, but rather has a long tail in one direction.If the tail extends to the right, the curve is said to be right-skewed, or positively skewed. If the tailextends to the left, it is negatively skewed. PathMaker calculates the skewness of a histogram, anddisplays it with the other statistics. Where skewness is present, attention should usually befocused on the tail, which could extend beyond the process specification limits, and where muchof the potential for improvement generally lies.

Kurtosis is also a measure of the length of the tails of a distribution. For example, a symmetricaldistribution with positive kurtosis indicates a greater than normal proportion of product in thetails. Negative kurtosis indicates shorter tails than a normal distribution would have. Again,PathMaker calculates the kurtosis of histograms.Taken together, the values for process center, spread, skewness and kurtosis can tell you a greatdeal about your process. However, unless you have a solid statistics background, you willprobably learn more from looking at the histogram itself than from looking at the statistics. Justremember that, where there is data in the tails near a specification limit, chances are that somenon-conforming product is being made. If your process is actually making 5 bad parts in every thousand, and you are sampling 20 in every thousand, it will take some time before you find any out-of-spec parts. There are three things you should do:

1. keep tracking data2. get help in fitting a curve to your distribution3. make sure your sampling plan is efficient.

PathMaker can help with the first, but not (yet) with the other two.

Distributions you may encounter

The standard normal distribution, with its zero skewness and zero kurtosis.

A skewed distribution, with one tail longer than the other.


7/48

A double-peaked curve often means that the data actually reflects two distinct processes with different centers. You

will need to distinguish between the two processes to get a clear view of what is really happening in either individualprocess.

A truncated curve, with the peak at or near the edge while trailing gently off to the other side, often means that part of the distribution has been removed through screening, 100% inspection, or review. These efforts are usually costly andmake good candidates for improvement efforts.

A plateau-like curve often means that the process is ill-defined to those doing the work, which leaves everyone on theirown. Since everyone handles the process differently, there are many different measurements with none standing out.The solution here is to clearly define an efficient process.

Outliers in a histogram bars that are removed from the others by at least the width of one bar sometimes indicatethat perhaps a separate process is included, but one that doesn't happen all the time. It may also indicate that specialcauses of variation are present in the process and should be investigated, though if the process is in control before the

histogram is made as it should be, this latter option is unlikely.


8/48

Histogram Interpretation: Normal

Histogram Interpretation: Symmetric, Non-Normal,Short-Tailed

Histogram Interpretation: Symmetric, Non-Normal,Long-Tailed


9/48

Histogram Interpretation: Symmetric and Bimodal

1.2.3.4.5.

Histogram Interpretation: Bimodal Mixture of 2Normals
http://www.itl.nist.gov/div898/handbook/eda/section3/runseqpl.htmhttp://www.itl.nist.gov/div898/handbook/eda/section3/scatterp.htmhttp://www.itl.nist.gov/div898/handbook/eda/section3/lagplot.htmhttp://www.itl.nist.gov/div898/handbook/eda/section3/spectrum.htmhttp://www.itl.nist.gov/div898/handbook/eda/section3/ppccplot.htmhttp://www.itl.nist.gov/div898/handbook/eda/section3/eda3661.htmhttp://www.itl.nist.gov/div898/handbook/eda/section3/eda3669.htm


10/48

p

Histogram Interpretation: Skewed (Non-Normal)Right

3.

Histogram Interpretation: Skewed (Non-Symmetric)Left
http://www.itl.nist.gov/div898/handbook/eda/section3/eda3668.htmhttp://www.itl.nist.gov/div898/handbook/eda/section3/eda366b.htmhttp://www.itl.nist.gov/div898/handbook/eda/section3/eda3666.htmhttp://www.itl.nist.gov/div898/handbook/eda/section3/eda3669.htmhttp://www.itl.nist.gov/div898/handbook/eda/section3/eda366e.htmhttp://www.itl.nist.gov/div898/handbook/eda/section3/boxcoxno.htm


11/48

Histogram Interpretation: Symmetric with Outlier

1.2.
http://www.itl.nist.gov/div898/handbook/eda/section3/boxplot.htmhttp://www.itl.nist.gov/div898/handbook/eda/section3/eda35h.htm


12/48

Scatter Plots

Scatter Plots (also called scatter diagrams) are used to investigate the possible relationship between two variables that both relate to the same "event." A straight line of best fit (using theleast squares method) is often included.Things to look for:

If the points cluster in a band running from lower left to upper right, there is a positive correlation (if x increases, y increases).

If the points cluster in a band from upper left to lower right, there is a negative correlation (if x increases, y decreases). Imagine drawing a straight line or curve through the data so that it "fits" as well as possible. The more the points cluster

closely around the imaginary line of best fit, the stronger the relationship that exists between the two variables. If it is hard to see where you would draw a line, and if the points show no significant clustering, there is probably no

correlation.

Caution!There is a maxim in statistics that says, "Correlation does not imply causality." In other words,

your scatter plot may show that a relationship exists, but it does not and cannot prove that one variable is causing the other. There could be a third factor involved which is causing both, someother systemic cause, or the apparent relationship could just be a fluke. Nevertheless, the scatterplot can give you a clue that two things might be related, and if so, how they move together.

Scatter Plot statistics:For scatter plots, the following statistics are calculated:

Mean X and Y: the average of all the data points in the series.

Maximum X and Y: the maximum value in the series.

Minimum X and Y the minimum value in the series.

Sample Size the number of values in the series.

X Range and Y Range the maximum value minus the minimum value.

Standard Deviations for Indicates how widely data is spread around the mean.


13/48

X and Y values

Line of Best Fit - Slope The slope of the line which fits the data most closely (generally usingthe least squares method).

Line of Best Fit - Y

Intercept

The point at which the line of best fit crosses the Y axis.


14/48

Creating a Scatter Plot in Excel

Table of Contents

Introduction

Part 1 - Beer's Law Scatter Plot and Linear Regression1. Entering and Formatting the Data in Excel2. Creating the Initial Scatter Plot3. Creating a Linear Regression Line4. Using the Regression Equation to Calculate Concentration5. Adjusting the Chart Display

Part 2 - Titration Data Plotting1. Creating a Scatter Plot of Titration Data2. Curve Fitting to Titration Data3. Changing the Scatter Plot to a Line Graph4. Adding a Reference Line5. Modifying the Chart Axis Scale

IntroductionBeer's Law states that there is a linear relationship between concentration of a coloredcompound in solution and the light absorption of the solution. This fact can be used to

calculate the concentration of unknown solutions, given their absorption readings. First, aseries of solutions of known concentration are tested for their absorption level. Next, ascatter plot is made of this empirical data and a linear regression line is fitted to the data.This regression line can be expressed as a formula and used to calculate the concentrationof unknown solutions.

Part 1 - Beer's Law Scatter Plot and Linear Regression

Entering and Formatting the Data in ExcelOpen Excel. On Unity/Eos computers, the program will be located on the ApplicationLauncher. On other computers, it will probably be located under the Start Menu.Your data will go in the first two columns in the spreadsheet (see Figure 1a).

Title the spreadsheet page in cell A1 Label Column A as the concentration of the known solutions in cell A3 . Label Column Bas the absorption readings for each of the solutions in cell B3 .

Begin by formatting the spreadsheet cells so the appropriate number of decimal placesare displayed (see Figure 1a).
http://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#eaf#eafhttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#cti#ctihttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#cal#calhttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#utr#utrhttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#atc#atchttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#cas#cashttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#cft#cfthttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#cts#ctshttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#aaf#aafhttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#mtc#mtchttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#eaf#eafhttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#cti#ctihttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#cal#calhttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#utr#utrhttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#atc#atchttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#cas#cashttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#cft#cfthttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#cts#ctshttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#aaf#aafhttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#mtc#mtc


15/48

Click and drag over the range of cells that will hold the concentration data (A5through A10 for the sample data)

Choose Format > Cells... (this is shorthand for choosing Cells... from the Formatmenu at the top of the Excel window)

Click on the Number tab

Under Category choose Number and set Decimal places to 5 Click OK Repeat for the absorbance data column (B5 through B10 for the sample data),

setting the decimal places to 4

If you do not have your own data, you can copy the data seen in Figure 1b. Enter your data below the column titles You can also place the absorption readings for the unknown solutions below the

other data.


16/48

The concentration data is probably better expressed in scientific notation. Highlight the concentration data and choose Format > Cells... . Choose the Scientific Category and set the Decimal places to 2.

The last step before creating the graph is to choose the data you want to graph. Highlight the data in both the concentration and absorbance columns (but not the

unknown data) This is shown in Figure 2.


17/48

Creating the Initial Scatter PlotWith the data you want graphed, start the chart wizard

Choose the Chart Wizard icon from the tool bar (Figure 3). If the Chart Wizard

is not visible, you can also choose Insert > Chart...

The first dialogue of the wizard comes up Choose XY (Scatter) and the unconnected points icon for the Chart sub-type

(Figure 4a)


18/48

Click Next > The Data Range box should reflect the data you highlighted in the spreadsheet. TheSeries option should be set to Columns, which is how your data is organized (see Figure4b).


19/48

Click Next > The next dialogue in the wizard is where you label your chart (Figure 4c)

Enter Beer's Law for the Chart Title Enter Concentration (M) for the Value X Axis Enter Absorbance for the Value Y Axis


20/48

Click on the Legend tab Click off the Show Legend option (Figure 4d)

Click Next >

Keep the chart as an object in the current sheet (Figure 4e). Note : Your current sheet is probably named with the default name of "Sheet 1".


21/48

Click Finish The initial scatter plot is now finished and should appear on the same spreadsheet page asyour original data. Your chart should look like Figure 5. A few items of note:

Your data should look as though it falls along a linear path Horizontal reference lines were automatically placed in your chart, along with a

gray background Your chart is highlighted with square 'handles' on the corners. When your chart is

highlighted, a special Chart floating palette should also appear, as is seen inFigure 5. Note: If the Chart floating palette does not appear, go toTools>Customize... , click on the Toolbars tab, and then click on the Chartcheckbox.If it still doesn't show up as a floating palette, it may be 'docked' on oneof your tool bars at the top of the Excel window.With your graph highlighted, you can click and drag the chart to a wherever youwould like it located on the spreadsheet page. Grabbing one of the four corner handles allows you to resize the graph. Note: the graph will automatically adjust anumber of chart properties as you resize the graph, including the font size of thetext in the graph. You may need to go back and alter these properties. At the end

of the first part of this tutorial, you will learn how to do this.


22/48

Creating a Linear Regression Line (Trendline)When the chart window is highlighted, besides having the chart floating palette appear, aChart menu also appears. From the Chart menu, you can add a regression line to thechart.

Choose Chart > Add trendline... A dialogue box appears (Figure 6a).

Select the Linear Trend/Regression type


23/48

Choose the Options tab and select Display equation on chart (Figure 6b)

Click OK to close the dialogueThe chart now displays the regression line (Figure 7)


24/48

Using the Regression Equation to Calculate ConcentrationsThe linear equation shown on the chart represents the relationship between Concentration(x) and Absorbance (y) for the compound in solution. The regression line can beconsidered an acceptable estimation of the true relationship between concentration andabsorbance. We have been given the absorbance readings for two solutions of unknownconcentration.Using the linear equation (labeled A in Figure 8), a spreadsheet cell can have an equationassociated with it to do the calculation for us. We have a value for y (Absorbance) andneed to solve for x (Concentration). Below are the algebraic equations working out thiscalculation:y = 2071.9x + 0.111y - 0.0111 = 2071.9x(y - 0.0111) / 2071.9 = x

Now we have to convert this final equation into an equation in a spreadsheet cell. Theequation associated with the spreadsheet cell will look like what is labeled C in Figure 8.'B12' in the equation represents y (the absorbance of the unknown). The solution for x(Concentration) is then displayed in cell 'C12'.

Highlight a spreadsheet cell to hold 'x', the result of the final equation (cell C12,labeled B in Figure 8).

Click in the equation area (labeled C, figure 8) Type an equal sign and then a parentheses Click in the cell representing 'y' in your equation (cell B12 in Figure 8) to put this

cell label in your equation Finish typing your equation

Note: If your equation differs for the one in this example, use your equationDuplicate your equation for the other unknown.


25/48

Highlight the original equation cell (C12 in Figure 8) and the cell below it (C13) Choose Edit > Fill > Down

Note that if you highlight your new equation in C13, the reference to cell B12 has alsoincremented to cell B13.

Adjusting the Chart DisplayThe readability and display of the scatterplot can be further enhanced by modifying anumber of the parameters and options for the chart. Many of these modifications can beaccessed through the Chart menu, the Chart floating palette, and by double-clicking theelement on the chart itself. Let's start by creating a better contrast between the data points

and regression line and the background. Double-click in the gray background area of the chart or by selecting Chart

Area in the Chart floating palette and then clicking on the Format icon (Figure9a).


26/48

In the Chart Area Format dialogue, set the border and background colors (see Figure 9b)

Choose None for a Border Choose the white square from the color palette for an Area color Click OK

Now, delete the horizontal grid lines Click on the horizontal grid lines in the chart and press the Delete key

Now, adjust the color and line weight of the regression line and the color of the data points

Double-click on the regression line (or choose Series 1 Trendline 1 from theChart floating palette and then click the Format icon)


27/48

Choose a thinner line for the Line Weight Click on the word Automatic next to Line Color and the color palette appears.

Choose dark blue from the color palette Click OK Double-click on one of the data points (or choose Series 1 and click the Format

icon) Choose dark red from the color palette for the Marker Foreground and

Background Click OK

Finally, you can move the regression equation to a more central location on the chart Click and drag the regression equation

If necessary, resize the font size for text elements in the graph. Either double click the text element or choose it from the floating palette Click on the Fonts tab Choose a different font size

The results can be seen in Figure 9c.

Part 2 - Titration Data Plotting

Creating a Scatter Plot of Titration DataIn this next part of the tutorial, we will work with another set of data. In this case, it is of a strong acid-strong base titration (see Figure 10). With this titration, a strong base(NaOH) of known concentration is added to a strong acid (also of known concentration,in this case). As the strong base is added to solution, its OH- ions bind with the freeH+ions of the acid. An equivalence point is reached when there are no free OH- nor H+ions in the solution. This equivalence point can be found with a color indicator in the


28/48

solution or through a pH titration curve. This part of the tutorial will show you how to dothe latter.

Note that there should be two columns of data in your spreadsheet:Column A: mL of 0.1 M NaOH addedColumn B: pH of the 0.1 M HCl / 0.1M NaOH mixture

Using a new page in the spreadsheet, enter your titration data. If you do not haveyour own data, use the data shown in Figure 10. Return to the beginning of the tutorial if you need hints on formatting the cells to

the proper number of decimal places

Now, create a scatter plot of titration data, just as you did with the Beer's Law

plot .(Figure 11). Highlight the titration data and the Column headers Click on the Chart wizard icon Choose XY (Scatter) and the scatter Chart sub-type
http://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#eaf#eafhttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#cti#ctihttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#cti#ctihttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#eaf#eafhttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#cti#ctihttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#cti#cti


29/48

Continue through steps 2 through 4 of the Chart wizard:

The defaults for step 2 should be fine if you properly highlighted the data In step 3 enter the chart title and x and y axis labels and turn off the legend In step 4 , leave as an object in the current page

The resulting plot should look like Figure 12:


30/48

Curve Fitting to Titration DataThe next logical question that you might ask is whether a linear regression line or acurved regression line might help us interpret the titration data. You may remember thatour goal with this plot is to calculate the equivalence point, that is, what amount of NaOHis needed to change the pH of the mixture to 7 (neutral)?Create a linear regression line:

Choose Chart > Add Trendline... Pick Linear sub-type

Looking at the data (Figure 13a), it is clear that the first 45 ml of NaOH do little to alter the pH of the mixture. Then between 45 ml and 55 ml, there is a sharp rise in pH beforeleveling off again. The data trend does not seem linear at all and, in fact, a linear regression line does not fit the data well at all.


31/48

The next approach might be to choose a different type of trendline (Figure 13b): Click on the linear regression line in the plot and press the delete key to delete

the line Choose Chart > Add Trendline... Pick Polynomial subtype Set the Order of the curve to 2


32/48

You can see that a second order polynomial curve does not capture the steep rise of thedata well. A higher order curve might be tried (Figure 13c):

Double-click on the curved regression line Set the Order of the curve to 3

Still, the third order polynomial does not capture the steep part of the curve where it passes through a pH of 7. Even higher order curves could be created to see if they fit thedata better. Instead, a different approach will be taken for this data. Go ahead and deletethe regression curve:

Click on the curved regression line in the plot and press the delete key

Changing the Scatter Plot to a Line GraphInstead of adding a curved regression line, all of the points of the titration data areconnected with a smooth curve. With this approach, the curve is guaranteed to go throughall of the data points. This is both good and bad. This option can be used if you have onlyone pH reading per amount of NaOH added . If you have multiple pH readings for each amount added on the scatter plot, you will not end up with a smooth curve. Tochange the scatter plot is a (smoothed) line graph (Figure 14a):

Choose Chart > Chart Type... Select the Scatter connected by smooth lines Chart subtype


33/48

The result should look like Figure 14b:


34/48

This smooth, connected curve helps locate where the steep part of the curve passesthrough pH 7.

Adding a Reference LineThe chart can be enhanced by adding a reference line at pH 7. This clearly marks the

point where the curve passes through this pH. A set of drawing tools should be visible at the bottom of the window. If not, click

on the Draw icon two to the right of the Chart wizard icon. Make sure your chart is highlighted Choose the line tool at the bottom of the window Draw a horizontal line at pH 7 across the width of the chart by clicking and

dragging a line across the chart area. With the horizontal line still highlighted, choose a 3/4 pt line thickness and a

dashed line type at the bottom of the windowFurther refinements in the chart can be made by (as you did with the Beer's law chart ):

removing the other horizontal grid lines turning off the border changing chart colors Thickening the curve and shrinking the data points emphasizes the fitted curve

over the individual data pointsThe result should look like Figure 15.
http://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#atc#atchttp://www.ncsu.edu/ncsu/chemistry/resource/excel/excel.html#atc#atc


35/48

Modifying the Chart Axis ScaleThe above chart gives a good overview of the entire titration. If you would like to focusexclusively on the steep part of the curve between 45 and 55 ml of added NaOH, a newchart can be created which limits the X Axis range. Start by making a copy of the currentchart:

Select the current chart by clicking near its border Choose Edit > Copy Click a spreadsheet cell about 10 rows below the current chart Choose Edit > Paste

With the new chart highlighted (Figure 16): Choose Value (X) Axis from the Chart floating palette Click on the Format icon Set the Minimum to 45 , Maximum to 55 Set the Major unit to 1 and Minor unit to 0.25 Click OK


36/48

Next, both vertical and horizontal gridlines can be added to more accurately locate the

equivalency point (Figure 17): Choose Chart > Chart Options... Click on the Gridlines tab Select X axis Major gridlines and Y axis Major gridlines Click OK


37/48

With enhancements similar to what you did to the other chart, the result will look likeFigure 18.

Even with this smooth curve passing through all of the data points, it is still an estimationof what intermediate mL added/pH data points would be. A clear inaccuracy is where thecurve moves in a negative X direction between the 50 and 51 mL data points. More data

points collected between 49 and 51 mL would both better smooth the curve and give amore accurate estimation of the equivalency point.


38/48

Cause & Effect Diagram

The cause & effect diagram is the brainchild of Kaoru Ishikawa, who pioneered quality management processes in the Kawasaki shipyards, and in the process became one of the foundingfathers of modern management. The cause and effect diagram is used to explore all the potentialor real causes (or inputs) that result in a single effect (or output). Causes are arranged accordingto their level of importance or detail, resulting in a depiction of relationships and hierarchy of events. This can help you search for root causes, identify areas where there may be problems, andcompare the relative importance of different causes.Causes in a cause & effect diagram are frequently arranged into four major categories. While thesecategories can be anything, you will often see:

manpower, methods, materials, and machinery (recommended for manufacturing) equipment, policies, procedures, and people (recommended for administration and service).

These guidelines can be helpful but should not be used if they limit the diagram or areinappropriate. The categories you use should suit your needs. At SkyMark, we often create the

branches of the cause and effect tree from the titles of the affinity sets in a preceding affinity diagram.

The C&E diagram is also known as the fishbone diagram because it was drawn to resemble theskeleton of a fish, with the main causal categories drawn as "bones" attached to the spine of thefish, as shown below.

Cause & effect diagrams can also be drawn as tree diagrams, resembling a tree turned on its side.From a single outcome or trunk, branches extend that represent major categories of inputs orcauses that create that single outcome. These large branches then lead to smaller and smaller

branches of causes all the way down to twigs at the ends. The tree structure has an advantage overthe fishbone-style diagram. As a fishbone diagram becomes more and more complex, it becomesdifficult to find and compare items that are the same distance from the effect because they aredispersed over the diagram. With the tree structure, all items on the same causal level are aligned

vertically.


39/48

To successfully build a cause and effect diagram: 1. Be sure everyone agrees on the effect or problem statement before beginning.2. Be succinct.3. For each node, think what could be its causes. Add them to the tree.4. Pursue each line of causality back to its root cause.

5. Consider grafting relatively empty branches onto others.6. Consider splitting up overcrowded branches.7. Consider which root causes are most likely to merit further investigation.

Determine The Root Cause: 5 Whys

Asking "Why?" may be a favorite technique of your three year old child in driving you crazy, but itcould teach you a valuable Six Sigma quality lesson. The 5 Whys is a technique used in theAnalyze phase of the Six Sigma DMAIC methodology. It's a great Six Sigma tool that doesn't

involve data segmentation , hypothesis testing , regression or other advanced statistical tools , andin many cases can be completed without a data collection plan .By repeatedly asking the question "Why" (five is a good rule of thumb), you can peel away thelayers of symptoms which can lead to the root cause of a problem. Very often the ostensiblereason for a problem will lead you to another question. Although this technique is called "5 Whys,"you may find that you will need to ask the question fewer or more times than five before you findthe issue related to a problem.

Benefits Of The 5 Whys

Help identify the root cause of a problem. Determine the relationship between different root causes of a problem. One of the simplest tools; easy to complete without statistical analysis.

When Is 5 Whys Most Useful?

When problems involve human factors or interactions. In day-to-day business life; can be used within or without a Six Sigma project.

How To Complete The 5 Whys

1. Write down the specific problem. Writing the issue helps you formalize the problem anddescribe it completely. It also helps a team focus on the same problem.2. Ask Why the problem happens and write the answer down below the problem.3. If the answer you just provided doesn't identify the root cause of the problem that you wrotedown in step 1, ask Why again and write that answer down.4. Loop back to step 3 until the team is in agreement that the problem's root cause is identified.Again, this may take fewer or more times than five Whys.

5 Whys Examples

Problem Statement: Customers are unhappy because they are being shipped products thatdon't meet their specifications.1. Why are customers being shipped bad products?
http://www.isixsigma.com/library/content/six_sigma_dmaic_quickref_analyze.asphttp://www.isixsigma.com/me/dmaic/http://www.isixsigma.com/me/dmaic/http://www.isixsigma.com/st/data/http://www.isixsigma.com/st/hypothesis_testing/http://www.isixsigma.com/st/regression/http://www.isixsigma.com/st/http://www.isixsigma.com/st/http://www.isixsigma.com/library/content/c010422a.asphttp://www.isixsigma.com/dictionary/Root_Cause-61.htmhttp://www.isixsigma.com/library/content/six_sigma_dmaic_quickref_analyze.asphttp://www.isixsigma.com/me/dmaic/http://www.isixsigma.com/st/data/http://www.isixsigma.com/st/hypothesis_testing/http://www.isixsigma.com/st/regression/http://www.isixsigma.com/st/http://www.isixsigma.com/library/content/c010422a.asphttp://www.isixsigma.com/dictionary/Root_Cause-61.htm


40/48

- Because manufacturing built the products to a specification that is different from what thecustomer and the sales person agreed to.2. Why did manufacturing build the products to a different specification than that of sales?

- Because the sales person expedites work on the shop floor by calling the head of manufacturing directly to begin work. An error happened when the specifications were beingcommunicated or written down.3. Why does the sales person call the head of manufacturing directly to start work instead of following the procedure established in the company?

- Because the "start work" form requires the sales director's approval before work can begin andslows the manufacturing process (or stops it when the director is out of the office).4. Why does the form contain an approval for the sales director?

- Because the sales director needs to be continually updated on sales for discussions with theCEO.In this case only four Whys were required to find out that a non-value added signature authority ishelping to cause a process breakdown.Let's take a look at a slightly more humorous example modified from Marc R.'s posting of 5 Whysin the iSixSigma Dictionary.Problem Statement: You are on your way home from work and your car stops in the middle of the road.1. Why did your car stop?

- Because it ran out of gas.2. Why did it run out of gas?

- Because I didn't buy any gas on my way to work.3. Why didn't you buy any gas this morning?

- Because I didn't have any money.4. Why didn't you have any money?

- Because I lost it all last night in a poker game.5. Why did you lose your money in last night's poker game?

- Because I'm not very good at "bluffing" when I don't have a good hand.As you can see, in both examples the final Why leads the team to a statement (root cause) thatthe team can take action upon. It is much quicker to come up with a system that keeps the salesdirector updated on recent sales or teach a person to "bluff" a hand than it is to try to directlysolve the stated problems above without further investigation.

5 Whys And The Fishbone Diagram

The 5 Whys can be used individually or as a part of the fishbone (also known as the cause andeffect or Ishikawa) diagram . The fishbone diagram helps you explore all potential or real causesthat result in a single defect or failure. Once all inputs are established on the fishbone, you canuse the 5 Whys technique to drill down to the root causes.

Fishbone DiagramA Problem-Analysis Tool

What is a Fishbone diagram?Dr. Kaoru Ishikawa, a Japanese quality control statistician, invented the fishbone diagram.Therefore, it may be referred to as the Ishikawa diagram. The fishbone diagram is an analysistool that provides a systematic way of looking at effects and the causes that create or contributeto those effects. Because of the function of the fishbone diagram, it may be referred to as acause-and-effect diagram. The design of the diagram looks much like the skeleton of a fish.Therefore, it is often referred to as the fishbone diagram.
http://www.isixsigma.com/dictionary/5_Whys-377.htmhttp://www.isixsigma.com/library/content/t000827.asphttp://www.isixsigma.com/library/content/t000827.asphttp://www.isixsigma.com/dictionary/5_Whys-377.htmhttp://www.isixsigma.com/library/content/t000827.asphttp://www.isixsigma.com/library/content/t000827.asp


41/48

Whatever name you choose, remember that the value of the fishbone diagram is to assist teamsin categorizing the many potential causes of problems or issues in an orderly way and inidentifying root causes.

When should a fishbone diagram be used? Does the team...

Need to study a problem/issue to determine the root cause? Want to study all the possible reasons why a process is beginning to have difficulties,

problems, or breakdowns? Need to identify areas for data collection? Want to study why a process is not performing properly or producing the desired results?

How is a fishbone diagram constructed? Basic Steps:

1. Draw the fishbone diagram....2. List the problem/issue to be studied in the "head of the fish".

3. Label each ""bone" of the "fish". The major categories typically utilized are:The 4 Ms: Methods, Machines, Materials, Manpower

The 4 Ps: Place, Procedure, People, Policies

The 4 Ss: Surroundings, Suppliers, Systems, Skills

Note: You may use one of the four categories suggested, combine them in any fashion or makeup your own. The categories are to help you organize your ideas.

4. Use an idea-generating technique (e.g., brainstorming) to identify the factors withineach category that may be affecting the problem/issue and/or effect being studied. Theteam should ask... "What are the machine issues affecting/causing..."

5. Repeat this procedure with each factor under the category to produce sub-factors.Continue asking, "Why is this happening?" and put additional segments each factor andsubsequently under each sub-factor.6. Continue until you no longer get useful information as you ask, "Why is thathappening?"7. Analyze the results of the fishbone after team members agree that an adequateamount of detail has been provided under each major category. Do this by looking for those items that appear in more than one category. These become the 'most likelycauses".8. For those items identified as the "most likely causes", the team should reachconsensus on listing those items in priority order with the first item being the mostprobable" cause.

The Cause and Effect Diagram (a.k.a. Fishbone)When utilizing a team approach to problem solving, there are often many opinions as to theproblem's root cause. One way to capture these different ideas and stimulate the team'sbrainstorming on root causes is the cause and effect diagram, commonly called a fishbone. Thefishbone will help to visually display the many potential causes for a specific problem or effect. Itis particularly useful in a group setting and for situations in which little quantitative data isavailable for analysis.


42/48

The fishbone has an ancillary benefit as well. Because people by nature often like to get right todetermining what to do about a problem, this can help bring out a more thorough exploration of the issues behind the problem - which will lead to a more robust solution.To construct a fishbone, start with stating the problem in the form of a question, such as 'Why isthe help desk's abandon rate so high?' Framing it as a 'why' question will help in brainstorming,as each root cause idea should answer the question. The team should agree on the statement of the problem and then place this question in a box at the 'head' of the fishbone.The rest of the fishbone then consists of one line drawn across the page, attached to the problemstatement, and several lines, or 'bones,' coming out vertically from the main line. These branchesare labeled with different categories. The categories you use are up to you to decide. There are afew standard choices:

Table 1: Fishbone Suggested Categories Service Industries

(The 4 Ps)Manufacturing Industries

(The 6 Ms)Process Steps(for example)

Policies Procedures People Plant/Technology

Machines Methods Materials Measurements Mother Nature

(Environment) Manpower

(People)

Determine Customers Advertise Product Incent Purchase Sell Product Ship Product Provide Upgrade

You should feel free to modify the categories for your project and subject matter.

Once you have the branches labeled, begin brainstorming possible causes and attach them tothe appropriate branches. For each cause identified, continue to ask 'why does that happen?' andattach that information as another bone of the category branch. This will help get you to the truedrivers of a problem.

Once you have the fishbone completed, you are well on your way to understanding the rootcauses of your problem. It would be advisable to have your team prioritize in some manner thekey causes identified on the fishbone. If necessary, you may also want to validate theseprioritized few causes with a larger audience.


43/48

SIPOC DiagramSIPOC stands for suppliers, inputs, process, output, and customers. You obtain inputs fromsuppliers, add value through your process, and provide an output that meets or exceeds your

customer's requirements.

Supplier-Input-Process-Output-Customer: Method that helps you not to forget something whenmapping processes.

SIPOC DiagramMany recent inquiries and discussions have focused on the SIPOC diagram -- a tool used in theSix Sigma methodology. Because of the interest level, a further explanation is presented herealong with a sample and template for your use.

A SIPOC diagram is a tool used by a team to identify all relevant elements of a processimprovement project before work begins. It helps define a complex project that may not be wellscoped, and is typically employed at the Measure phase of the Six Sigma DMAIC methodology. Itis similar and related to Process Mapping and 'In/Out Of Scope ' tools, but provides additionaldetail.The tool name prompts the team to consider the Suppliers (the 'S' in SIPOC) of your process, theInputs (the 'I') to the process, the Process (the 'P') your team is improving, the Outputs (the 'O') of the process, and the Customers (the 'C') that receive the process outputs. In some cases,Requirements of the Customers can be appended to the end of the SIPOC for further detail.The SIPOC tool is particularly useful when it is not clear: Who supplies Inputs to the process? What specifications are placed on the Inputs? Who are the true Customers of the process? What are the Requirements of the customers?

Sample SIPOC Diagram A SIPOC diagram is a tool used by a team to identify all relevant elements of a processimprovement project before work begins. It helps define a complex project that may not be wellscoped, and is typically employed at the Measure phase of the Six Sigma DMAIC methodology
http://www.isixsigma.com/me/dmaic/http://www.isixsigma.com/tt/process_mapping/http://www.isixsigma.com/tt/process_mapping/http://www.isixsigma.com/library/content/c010218b.asphttp://www.isixsigma.com/library/content/c010218b.asphttp://www.isixsigma.com/library/content/c010218b.asphttp://www.isixsigma.com/me/dmaic/http://www.isixsigma.com/tt/process_mapping/http://www.isixsigma.com/library/content/c010218b.asp


44/48

Steps To Complete The SIPOC Diagram1.7. Optional
http://www.isixsigma.com/library/content/c010429d.asp


45/48

Pareto Charts

Things to look for:

Pareto chart statistics:

Mean:

Sum:

If you are using the AutoPareto mode, the followingstatistics are also calculated for each class of data:

Total:

Percentage:

80/20 Rule (aka 80:20 Rule or 80 20 Rule)Vilfredo Pareto was an economist who is credited with establishing what is now widelyknown as the Pareto Principle or 80/20 rule. When he discovered the principle, itestablished that 80% of the land in Italy was owned by 20% of the population. Later, hediscovered that the pareto principle was valid in other parts of his life, such as gardening:80% of his garden peas were produced by 20% of the peapods. Some Sample 80/20 Rule Applications


46/48

80% of process defects arise from 20% of the process issues. 20% of your sales force produces 80% of your company revenues. 80% of delays in schedule arise from 20% of the possible causes of the delays. 80% of customer complaints arise from 20% of your products or services.(The above examples are rough estimates.)


47/48


48/48

Arranging items in a compilation table

Causes for Late Arrival(Decreasing Order)

Number of Occasions Percentage

CumulativePercentage

Traffic tie-up 32 44 44Woke up late 20 28 71Family problems 8 10 82Sick 6 8 90

Had to take the bus 4 6 96Bad weather 3 4 100 Step 6List the items on the horizontal axis of a graph from highest to lowest. Label the left vertical axis with the numbers(frequency, time or cost), then label the right vertical axis with the cumulative percentages (the cumulative totalshould equal 100 percent). Draw in the bars for each item.Step 7Draw a line graph of the cumulative percentages. The first point on the line graph should line up with the top of thefirst bar. Excel offers simple charting tools you can use to make your graphs, or you can do them with paper andpencil.Step 8Analyze the diagram by identifying those items that appear to account for most of the difficulty. Do this by lookingfor a clear breakpoint in the line graph, where it starts to level off quickly. If there is not a breakpoint, identify thoseitems that account for 50 percent or more of the effect. If there appears to be no pattern (the bars are essentially allof the same height), think of some factors that may affect the outcome, such as day of week, shift, age group of patients, home village. Then, subdivide the data and draw separate Pareto charts for each subgroup to see if apattern emerges.

7110406 Quality Tools Doc

Documents

Transcript of 7110406 Quality Tools Doc