Statistical Process Control Chapter 6, Part 2 Specification Limits The target for a process is the ideal value –Example: if the amount of beverage in a bottle should be 16 ounces, the target is 16 ounces Specification limits are the acceptable range of values for a variable Example: the amount of beverage in a bottle must be at least 15.8 ounces and no more than 16.2 ounces. –Range is 15.8 – 16.2 ounces. –Lower specification limit = 15.8 ounces or LSL = 15.8 ounces –Upper specification limit = 16.2 ounces or USL = 16.2 ounces
Process is Capable UCL LCL X Lower specification limit Upper specification limit
Process is Not Capable UCL LCL X Lower specification limit Upper specification limit UCL outside specification limits not capable
Capability and Conformance Quality (1) A process is capable if –It is in control and –It consistently produces outputs that meet specifications. –This means that both control limits for the mean must be within the specification limits*** A capable process produces outputs that have conformance quality (outputs that meet specifications).
Capable Transformation Process Inputs Facilities Equipment Materials Energy Outputs Goods & Services that meet specifications
Capability and Conformance Quality (2) If the process is capable and the product specification is based on current customer requirements, outputs will meet customer expectations.
Customer Satisfaction Capable Transformation Process + Product specification that meets current customer requirements = Customer satisfaction
Process Capability Ratio Use only when the mean = the target. The process is capable when
Process Capability Index C pk = process mean (or estimated mean) LSPEC = lower specification limit USPEC = upper specification limit C pk = Smaller {(USPEC- )/3 – LSPEC)/ 3 } If C pk >= 1, process meets customer requirements 99.74% of the time. Use C pk when the mean does not equal the target value
3-Sigma Quality Uses 3 control limits for x Corresponds to 3 defects per 1,000 units. If a product has 250 parts and each has 3 control limits, P[at least 1 bad part] = 0.528
6-Sigma Quality Use 6- control limits for x. Control limits are (X- 2A 2 R, X + 2A 2 R). Corresponds to 3.4 defects per million If a product has 250 parts and each has 6 control limits, P[at least 1 bad part] <0.001
Customer Requirements Product Specifications Statistical Process Control: Measure & monitor quality Meets Specifications? Process Specifications Yes Conformance Quality Fix process or inputs No Product launch activities: Revise periodically Ongoing Activities