Long, Jeri M.; De Coste, Melinda J. (1988, ASQC) Hydra-matic Division of General Motors, Ypsilanti, MI
Statistical process studies and ongoing control are complicated when studying machine processes that have tool wear. While such wear is a fact, it is important for processes that exhibit tool wear to be controlled in order to maintain part quality and maximize tool life.
In its simplest and most encountered form, tool wear data tend to have an upward or downward slope over time. To determine the trend of the tool wear, a best-fit line to the data is generated. For conventional control charts, the grand average and the control limits are horizontal. In contrast, when tool wear is involved, the control limits are parallel to the tool wear slope. Once control has been assessed, the capability of the process can then be determined.
Capability analysis is frequently used to further describe the process. However, the capability indices are also affected by the tool wear slope. Two capability indices used to describe the spread and the centrality of the process are Cp and Cpk, respectively. For processes that exhibit tool wear, the capability indices, Cp and Cpk, are largely dependent on the control scheme or when the tool is changed or adjusted.
This paper includes techniques for obtaining the best-fit line through the data, calculating the control limits, comparing the slopes to determine different tools, and calculating the capability of the process. These techniques are based on the assumption that tools are consistent within their tool groups.