Presentation on theme: "Slide 1 Choosing the Appropriate Control Chart Attribute (counts)Variable (measurable) Defect Defective (MJ II, p. 37) The Lean Six Sigma Pocket Toolbook,"— Presentation transcript:
Slide 1 Choosing the Appropriate Control Chart Attribute (counts)Variable (measurable) Defect Defective (MJ II, p. 37) The Lean Six Sigma Pocket Toolbook, p. 123.
Slide 2 Different types of control charts Variables (or measurement ) data Situation Chart Control Limits Variables data, sets of measurements Xbar and R Charts source: Brian Joiner, Fourth Generation Management, p X-”BAR” CHART R CHART See MJ II p. 42 for constants A 2, D 3 and D 4. Lean Six Sigma Pocket Toolbook, p. 127.
Slide 3 Parameters for Creating X-bar Charts Lean Six Sigma Pocket Toolbook, p. 128.
Slide 4 X Bar Chart Average X bar = 82.5 psi Standard Deviation of X bar = 1.6 psi Control Limits= Avg X bar + 3 Std of X bar = (3)(1.6) = [77.7, 87.3] Process is “In Control” (i.e., the mean is stable) UCL LCL
Slide 5 Range (R) Chart Average Range R = 10.1 psi Standard Deviation of Range = 3.5 psi Control Limits: (3)(3.5) = [0, 20.6] Process Is “In Control” (i.e., variation is stable) UCL LCL
Slide 6 Exercise An automatic filling machine is used to fill 16 ounce cans of a certain product. Samples of size 5 are taken from the assembly line each hour and measured. The results of the first 25 subgroups are shown in the attached file with selected rows shown below. Does the process appear to be in statistical control? Source: Shirland, Statistical Quality Control, problem 5.2. If the specification limits are USL = and LSL = is the process capable?
Slide 7 Different types of control charts Attribute (or count) data Situation Chart Control Limits Fraction of defectives fraction of orders not processed perfectly on first trial (first pass yield) fraction of requests not processed within 15 minutes p np source: Brian Joiner, Fourth Generation Management, p Lean Six Sigma Pocket Toolbook, p. 132.
Slide 8 UCL= + 3 ˆ LCL= - 3 ˆ ˆ = Estimate average defect percentage Estimate Standard Deviation Define control limits Divide time into: - calibration period (capability analysis) - conformance analysis =0.052 =0.013 =0.091 =0.014 Period n defects p Attribute Based Control Charts: The p-chart
Slide 9 Consider a data entry operation that makes numerous entries daily. On each of 24 consecutive days subgroups of 200 entries are inspected. Develop a p control chart for this process. Gitlow, Openheim, Openheim & Levine, Quality Management, 3ed.
Slide 11 Revised Data
Slide 13 Control, Capability and Design: Review Every process displays variation in performance: normal or abnormal Do not tamper with a process that is “in control” with normal variation Correct an “out of control” process with abnormal variation Control charts monitor process to identify abnormal variation Control charts may cause false alarms (or missed signals) by mistaking normal (abnormal) variation for abnormal (normal) variation Local control yields early detection and correction of abnormal variation Process “in control” indicates only its internal stability Process capability is its ability to meet external customer needs Improving process capability involves (a) changing the mean in the short run, and (b) reducing normal variability in the long run, requiring investment Robust, simple, standard, mistake - proof design improves process capability Joint, early involvement in design by all improves product quality, speed, cost
Slide 14 Capability and Design: Review Process capability measures its precision in meeting processing requirements Improving capability involves reducing variation and its impact on product quality Simplicity, standardization, and mistake - proofing improve process capability Joint design and early involvement minimizes quality problems, delays, cost