A PCA-FBPN Approach for Job Cycle Time Estimation in a Wafer Fabrication Factory

摘要: Variable replacement is a well-known technique to improve the forecasting performance, but has not been applied job cycle time forecasting, which critical task semiconductor manufacturer. To this end, in study, principal component analysis PCA enhance performance of fuzzy back propagation network FBPN approach. First, replace original variables, form variables that are independent each other, and become new inputs FBPN. Subsequently, constructed estimate times jobs. According results case hybrid PCA-FBPN approach was more efficient, while achieving satisfactory estimation performance.