Applying machine learning and GA for process parameter optimization in car steering wheel manufacturing.

The wrapping layer's foaming process of the car steering wheel industry usually relies on the manual parameter setting by experienced engineers, but the reliability and validity are usually hard to control due to many foaming factors that affect the hardness of steering wheel wrapping layer (e.g., vulcanization time, mold temperature, material liquid temperature, material discharge pressure, humidity). This paper first proposes an intelligent process parameter recommendation system architecture, then develops a neural network-based hardness prediction (NNHP) model to predict the car steering wheel's wrapping hardness. Consequently, we combine NNHP and genetic algorithm (GA) to develop a foaming process parameter recommendation model (NNHP-GA) to effectively recommend the most suitable combinations of process parameters for achieving the desired wrapping hardness in an IoT-based intelligent manufacturing environment. An empirical study is applied in Taiwan's world-leading car steering wheel company. By analyzing the 16 important process sensor data installed in each casting machine, the five experimental results show that the NNHP-GA recommendation system can successfully predict the hardness of the steering wheel's wrapping layer and recommend appropriate process parameters (e.g., sensors S1-vulcanization time, S2-mold temperature, S5-A.P. pressure, S6-B.I. pressure, and "pressurization time") under a specific hardness target. The manufacturing company may employ the NNHP-GA model to build a process parameter recommendation system and increase the quality of process parameter setting. [ABSTRACT FROM AUTHOR]