Cross-Process Chain Analysis on Gear Quality and Sustainability

The aim of this study is to use a Shapley value-based machine learning algorithm to investigate the cross-process chain impacts of the processes involved in a pinion shafts manufacturing chain on final gear quality with sustainability considerations. Process data is collected during gear hobbing and profile grinding and analyzed using a neural network model to calculate Shapley values. The results quantify the influence of process parameters and trace data of each process on the gear quality, thereby improving understanding and leading to better control and sustainability of processes within the manufacturing chain. By achieving better process control and evaluating sustainability, this study not only helps to save time, energy, and material resources but also promotes sustainable manufacturing practices that minimize waste and the environmental impact of gear production. Overall, this study provides valuable insights into the importance of processes in the gear manufacturing chain, aiding in its optimization.