Intelligent process control in manufacturing industry with sequential processes

Quality control and improvement using statistical process control is very difficult to set up the best condition of manufacturing specification in plants with complex sequential processes. The inductive learning and neural network can acquire rules from the monitored data and show decision trees or new operating rules of the given attributes of the input variables. In this paper, a hybrid method, in combination with the inductive learning and neural network, is presented to extract rules, to control and generate better operating manufacturing conditions. Also, the method is applied to an intelligent process control system in the manufacturing processes of color-CRT and semiconductor. (C) 1999 Elsevier Science B.V. All rights reserved.