TA的首页吾一日三省乎其身-20080330
双边规格的CPK如何计算
昨天（3/29）与IQC的部分同仁一起探讨了双边规格的CPK如何计算。今天想起来，仍然觉得意味尤尽，特意在此再温习一遍.
Quality assurance and improvement
Compatibility of mechanical parts:
•To save money by minimizing scrap
•To save time by minimizing inspection
To collect data from part dimension variation during the life cycle of the mould.
•To establish a data bank of process outputs and capability analyses
•Impact on design and mechanical solutions
•Statistical dimensioning/tolerance design (VSA - simulation tool)
• Cumulative know-how - feedback from previous projects。
What is the difference between Cp&Pp,Cpk&Ppk
Standard deviation is calculated differently :
Process capability:Cp&Cpk--Short term standard deviation.
(common causes).
sST doesn’t account for the long time variation (e.g. tool wear, material changes).
Process performance:Pp&Ppk-->Long term standard deviation.
(common and special causes).
Capability index: Cp -->the process is capable of reproducing the characteristic. Cpk-->The process is actually reporducing the characteristic within desired limits.
Most of companies requirement :Cpk should not be less than 1.33.
If these indexes are small we may have to consider some of the following:
•are the tolerance limits set correctly
• to use for example Design of Experiments to improve the process
• to invest in new technology
The difference between Cpk and Ppk indexes indicates how much we can possibly improve our process by using process control.
What Do These Indexes Tell Us ?
Simple numerical values to describe the quality of the process
Requirement for Cpk is 1.67
This leaves us some space for the variation
• Are we able to improve our process by using SPC
If index is low, following things should be given a thought:
•Is the product design OK?
Are tolerance limits set correctly?
Too tight?
Is the process capable of producing good quality products?
Process variations?
•Is the measuring system capable?
Porcess capability accurancy ：Ca=（Average-Mean)/(Torlance/2).
Porcess capability precision ：Cp=Torlance/(6*standard deviation).
Standard deviation = SQRT([(X1-M)^2+(X2-M)^2+(X3-M)^2+...+(Xn-M)^2]/(n-1))
Cpk=(|Ca|)*Cp=Min{Cpu,Cpl}.
昨天（3/29）与IQC的部分同仁一起探讨了双边规格的CPK如何计算。今天想起来，仍然觉得意味尤尽，特意在此再温习一遍.
Quality assurance and improvement
Compatibility of mechanical parts:
•To save money by minimizing scrap
•To save time by minimizing inspection
To collect data from part dimension variation during the life cycle of the mould.
•To establish a data bank of process outputs and capability analyses
•Impact on design and mechanical solutions
•Statistical dimensioning/tolerance design (VSA - simulation tool)
• Cumulative know-how - feedback from previous projects。
What is the difference between Cp&Pp,Cpk&Ppk
Standard deviation is calculated differently :
Process capability:Cp&Cpk--Short term standard deviation.
(common causes).
sST doesn’t account for the long time variation (e.g. tool wear, material changes).
Process performance:Pp&Ppk-->Long term standard deviation.
(common and special causes).
Capability index: Cp -->the process is capable of reproducing the characteristic. Cpk-->The process is actually reporducing the characteristic within desired limits.
Most of companies requirement :Cpk should not be less than 1.33.
If these indexes are small we may have to consider some of the following:
•are the tolerance limits set correctly
• to use for example Design of Experiments to improve the process
• to invest in new technology
The difference between Cpk and Ppk indexes indicates how much we can possibly improve our process by using process control.
What Do These Indexes Tell Us ?
Simple numerical values to describe the quality of the process
Requirement for Cpk is 1.67
This leaves us some space for the variation
• Are we able to improve our process by using SPC
If index is low, following things should be given a thought:
•Is the product design OK?
Are tolerance limits set correctly?
Too tight?
Is the process capable of producing good quality products?
Process variations?
•Is the measuring system capable?
Porcess capability accurancy ：Ca=（Average-Mean)/(Torlance/2).
Porcess capability precision ：Cp=Torlance/(6*standard deviation).
Standard deviation = SQRT([(X1-M)^2+(X2-M)^2+(X3-M)^2+...+(Xn-M)^2]/(n-1))
Cpk=(|Ca|)*Cp=Min{Cpu,Cpl}.
RSS Feed