Manufacturing capability information for multiple product quality characteristics: a case study to precision voltage reference

摘要

Chen et al. [5] proposed a process capability analysis chart (PCAC) based on process capability indices C_(pk), C_(pl), and C_(pu) to evaluate the integrated process capability for the entire product with the nominal-the-best, the larger-the-better, and the smaller-the better characteristics. The PCAC conveys critical information of multiple characteristics of the entire product regarding accuracy, precision, and the process capability zones from one single chart, which is an effective tool for evaluating product quality/reliability. However, from a practical perspective, the PCAC chart is never considered sampling errors hence the capability information provided from this chart is often unreliable and misleading. In this paper, a manufacturing application involving multiple characteristics of precision voltage reference (PVR) is investigated. We consider the sample error by obtaining the lower confidence bounds (LCBs) of C_(pk), C_a, C_(pl), and C_(pu). The lower confidence bound presents the minimum true capability information of the process, which is essential to product reliability assurance. We employ the lower confidence bounds to PCAC to provide more reasonably reliable capability information for the product with multiple characteristics.