Capability Analysis: What is it?Capability analysis is a set of statistical calculations performed on a set of data in order to determine the capability of the system. The capability of the system refers to the ability of the system to perform in comparison to its specification limits. A system is said to be "capable" if it is producing approximately 100% within specification limits. Specification limits are set by customers, engineering, or management. They are sometimes called requirements, goals, objectives, or standards. Specification limits are the upper and lower boundaries within which the system must operate. They are not to be confused with control limits, which are based on the data collected from a system. The set of calculations for capability analysis presented here is based on the assumption that the data is normally distributed. The shape given by the histogram will tell you if the data is normally distributed. Many, but not all, dimensional values in manufacturing behave normally. Another assumption for capability analysis is that the system being studied is stable. In other words, there are no special causes of variation present. Information obtained from an unstable system would be unreliable over time. A control chart of the system should be made to determine stability before capability analysis is performed. Capability indices allow one to monitor and report the improvement of the system over time. The capability indices to be used are Cp and Cpk. The Cp is used to summarize a system's ability to meet two-sided specification limits (upper and lower). A drawback of the Cp index is that it really evaluates only process spread and ignores the process average. If the system is not centered at the middle of the specifications, the Cp index may be misleading. Assuming the system is centered, a Cp value of 1 indicates that the system is producing 99.73% of output within specification limits. The Cpk tells how well a system can meet specification limits while accounting for the location of the average. The Cpk index modifies the Cp index to account for the location of the average (or center). A Cpk of 1 indicates that the system is producing at least 99.73% within the specification limits. If the system is centered on its target value, the values for Cp and Cpk will be equal. Cp and Cpk values of 1 for some organizations have become the minimum requirements for a system. However, the larger the Cp and Cpk values the better, and many organizations are requiring Cp and Cpk values well in excess of 1. For example, Motorola, a National Quality Award winner, has a goal of 6 sigma which equates to a Cpk of 2. Capability indices help to change the focus of improvement. The focus of improvement has traditionally been to reduce the proportion of product or service not meeting the specification, using measures such as percent rework. Capability indices help focus on the target value, the value most desired by the customers. The farther a product deviates from the target value, the more loss it contributes. This loss can be in terms of customer dissatisfaction, high warranty costs, and lost sales. Often the value of these losses is unknown and unknowable. Thus, the idea is to shrink the variation around the target value. This relates to increasingly higher Cp and Cpk values. A team uses capability analysis to assess the current situation and to study the results of improvement efforts. In order to propose a theory for improvement, the team must first know the performance of the system. When the system's performance is assessed, the team then generates theories for improvement. For instance, they may propose to shift the central location of the system up or down or search for ways to reduce the variability around the target value. After an improvement theory is implemented, a team uses capability analysis to study the results (or to see if the theory worked). In other words, they continue to collect data on the system and calculate its capability. � � |
