A Knowledge-Embedded End-to-End Intelligent Reasoning Method for Processing Quality of Shaft Parts
Published in November 26-28, 2021
Contribution
In this article, a knowledge-embedded end-to-end intelligent reasoning method for processing quality of shaft parts is proposed. Using this method, knowledge in SSM can be embedded in simulation data sets. In addition, an end-to-end intelligent inference model based on ANFIS was developed to achieve final WTD pre-awareness based on current measurements. The average training RMSE and MAE for the four process prediction models were 2.21 μm and 1.75 μm, respectively, and the average test RMSE and MAE were 3.77 μm and 2.89 μm, respectively. Finally, by analyzing the MFs, it is possible to specify the appropriate size range for each section, which ensuring that the WTD meets the requirements.
Recommended citation: T. Zhang, B. Li, H. Sun, S. Zhao, F. Peng, L. Zhou, R. Yan. (2022). A Knowledge-Embedded End-to-End Intelligent Reasoning Method for Processing Quality of Shaft Parts. In: Liu, H., et al. Intelligent Robotics and Applications. ICIRA 2022. Lecture Notes in Computer Science(), vol 13458. Springer, Cham. https://doi.org/10.1007/978-3-031-13841-6_39 https://doi.org/10.1007/978-3-031-13841-6_39