8-1 Quality Improvement and StatisticsDefinitions of Quality Quality means fitness for use - quality of design - quality of conformance Quality is inversely proportional to variability. 8-1 Quality Improvement and StatisticsQuality ImprovementQuality improvement is the reduction ofvariability in processes and products. Alternatively, quality improvement is also seen as waste reduction. 8-1 Quality Improvement and StatisticsStatistical process control is a collection of tools that when used together can result in process stability and variance reduction. 8-2 Statistical Process Controlhe seven ma!or tools are"# $istogram%# &areto 'hart(# 'ause and )ffect *iagram+# *efect 'oncentration *iagram,# 'ontrol 'hart -# Scatter *iagram .# 'hec/ Sheet 8-3 Introduction to Control Charts8-3.1 asic PrinciplesA process that is operating with only chance causes of variation present is said to be in statistical control.A process that is operating in the presence of assignable causes is said to be out of control.he eventual goal of S&' is the elimination of variability in the process. 8-3 Introduction to Control Charts8-3.1 asic PrinciplesA typical control chart has control limits set at values such that if the process is in control, nearly all points will lie within the upper control limit 01'2# and the lower control limit 02'2#. 8-3 Introduction to Control Charts8-3.1 asic Principles 8-3 Introduction to Control Charts8-3.1 asic Principles 8-3 Introduction to Control Charts8-3.1 asic PrinciplesImportant uses of the control chart". 3ost processes do not operate in a state of statistical control%. 'onsequently, the routine and attentive use of control charts will identify assignable causes.4f these causes can be eliminated from the process, variability will be reduced and the process will be improved5. he control chart only detects assignable causes.3anagement, operator,and engineering action will be necessary to eliminate the assignable causes. 8-3 Introduction to Control Charts8-3.1 asic Principles!ypes the control chart6ariables 'ontrol 'harts7hese charts are applied to data that follow a continuous distribution.Attributes 'ontrol 'harts7hese charts are applied to data that follow a discrete distribution. 8-3 Introduction to Control Charts8-3.1 asic PrinciplesPopularity of control charts"# 'ontrol charts are a proven technique for improving productivity.%# 'ontrol charts are effective in defect prevention.5# 'ontrol charts prevent unnecessary process ad!ustment.(# 'ontrol charts provide diagnostic information.+# 'ontrol charts provide information about process capability. 8-3 Introduction to Control Charts8-3.2 Desi"n of a Control ChartSuppose we have a process that we assume the true process mean is 8 -( and the process standard deviation is 8 9.9".Samples of si:e + are ta/en giving a standard deviation of the sample average,is 99(+ . 9+9" . 9n;= == 8-3 Introduction to Control Charts8-3.2 Desi"n of a Control Chart'ontrol limits can be set at 5 standard deviations from the mean in both directions.5-Sigma 'ontrol 2imits 1'2 8 -( < 509.99(+# 8 -(.9"5+'28 -( 2'2 8-( - 509.99(+# 8 -5.=.,+ 8-3 Introduction to Control Charts8-3.2 Desi"n of a Control Chart 8-3 Introduction to Control Charts8-3.2 Desi"n of a Control Chart'hoosing the control limits is equivalent to setting up the critical region for hypothesis testing $9> 8 -($"> -( 8-3 Introduction to Control Charts8-3.3 #ational Su$"roupsSubgroups or samples should be selected so that if assignable causes are present, the chance for differences between subgroups will be ma;imi:ed, while the chance for differences due to these assignable causes within a subgroup will be minimi:ed. 8-3 Introduction to Control Charts8-3.3 #ational Su$"roupsConstructin" #ational Su$"roupsSelect consecutive units of production.7&rovides a snapshot of the process.7?ood at detecting process shifts. Select a random sample over the entire sampling interval.7?ood at detecting if a mean has shifted 7out-of-control and then bac/ in-control. 8-3 Introduction to Control Charts8-3.% &nalysis of Patterns on Control Charts2oo/ for runs - this is a sequence of observations of the same type 0all above the center line, or all below the center line#@uns of say . observations or more could indicate an out-of-control situation.7@un up> a series of observations are increasing7@un down> a series of observations are decreasing 8-3 Introduction to Control Charts8-3.% &nalysis of Patterns on Control Charts 8-3 Introduction to Control Charts8-3.% &nalysis of Patterns on Control Charts 8-3 Introduction to Control Charts8-3.% &nalysis of Patterns on Control Charts 8-3 Introduction to Control Charts8-3.% &nalysis of Patterns on Control Charts 8-3 Introduction to Control Charts8-3.% &nalysis of Patterns on Control Charts 8-% '-$ar and R Control Charts 8-% '-$ar and R Control Charts 8-% '-$ar and R Control Charts 8-% '-$ar and R Control Charts 8-% '-$ar and R Control Charts 8-% '-$ar and R Control Charts 8-% '-$ar and R Control ChartsComputer Construction 8-(Control Charts for Individual )easurementsAhat if you could not get a sample si:e greater than " 0n 8"#B );amples include7Automated inspection and measurement technology is used, and every unit manufactured is analy:ed.7he production rate is very slow, and it is inconvenient to allow samples si:es of C D " to accumulate before analysis7@epeat measurements on the process differ only because of laboratory or analysis error, as in many chemical processes.he individual control charts are useful for samples of si:es n 8 ". 8-(Control Charts for Individual )easurementshe moving range 03@# is defined as the absolute difference between two successive observations>3@i 8 E;i - ;i-"Ewhich will indicate possible shifts or changes in the process from one observation to the ne;t. 8-(Control Charts for Individual )easurements 8-(Control Charts for Individual )easurements 8-(Control Charts for Individual )easurementsF 'harts can be interpreted similar tocharts.3@ charts cannot be interpreted the same asor @ charts.Since the 3@ chart plots data that are correlated with one another, then loo/ing for patterns on the chart does not ma/e sense. 3@ chart cannot really supply useful information about process variability.3ore emphasis should be placed on interpretation of the F chart.Interpretation of the Charts;; 8-*Process Capa$ilityProcess capa$ility refers to the performance of the process when it is operating in control.wo graphical tools are helpful in assessing process capability>!olerance chart 0or tier chart#+isto"ram 8-*Process Capa$ility 8-*Process Capa$ility 8-*Process Capa$ility 8-*Process Capa$ility 8-*Process Capa$ility 8-,&ttri$ute Control Charts8-,.1 P Chart -Control Chart for Proportions. and nP Chart 8-,&ttri$ute Control Charts8-,.1 P Chart -Control Chart for Proportions. and nP Chart 8-,&ttri$ute Control Charts8-,.1 P Chart -Control Chart for Proportions. and nP Chart 8-,&ttri$ute Control Charts8-,.1 P Chart -Control Chart for Proportions. and nP Chart 8-,&ttri$ute Control Charts8-,.2 U Chart (Control Chart for Average Number of Defects per Unit) and C Chart 8-,&ttri$ute Control Charts8-,.2 U Chart (Control Chart for Average Number of Defects per Unit) and C Chart 8-,&ttri$ute Control Charts8-,.2 U Chart (Control Chart for Average Number of Defects per Unit) and C Chart 8-,&ttri$ute Control Charts8-,.2 U Chart (Control Chart for Average Number of Defects per Unit) and C Chart 8-8Control Chart Performance&vera"e #un /en"thhe average run length 0A@2# is a very important way of determining the appropriate sample si:e and sampling frequency.2et p 8 probability that any point e;ceeds the control limits.hen, 8-8Control Chart Performance 8-8Control Chart Performance 8-8Control Chart Performance 8-0)easurement Systems Capa$ility 8-0)easurement Systems Capa$ility 8-0)easurement Systems Capa$ility 8-0)easurement Systems Capa$ility 8-0)easurement Systems Capa$ility 8-0)easurement Systems Capa$ility 8-0)easurement Systems Capa$ility 8-0)easurement Systems Capa$ility