Statistical Optimization of Parameter and Tolerance Design for an Electronic Circuit

• Main Authors: Charles Liu, 劉景泰
• Other Authors: Angus Jeang
• Format: Others
• Language: en_US
• Published: 2001
• Online Access: http://ndltd.ncl.edu.tw/handle/51428691786135545875

碩士 === 逢甲大學 === 工業工程學系 === 89 === Conventionally, the parameter design is usually carried out prior to tolerance design for economic considerations. In this study, we consider parameter and tolerance design simultaneous for a circuit design. By this way can not only cost reduction but also quality improvement. At first, we generated a set of experimental data through Monte Carlo simulation based on various combination of parameter and tolerance levels as input, then the data are converted to a total cost as response value before applying the RSM for statistical analysis and optimization. The response (Total Cost) includes quality loss, tolerance cost, and failure cost, which reflect the combined effect of parameter and tolerance values being assigned. Then via numerical simulation and Response Surface Methodology (RSM). The results provide designers with optimal component parameter and tolerance values, the critical components, and the response function. Ane this function can be reuse for the correction in the future.