Study On High Temperature Wear Law And Wear Prediction Method Of Hot Forging Die Steel H13

Hot forging dies are commonly encountered process equipment in the industrial setting. Due to repeated mechanical and alternating loads under high temperature for an extended period of time, these dies are prone to wear and tear, which can impact their service life and drive up production costs for enterprises. To address this issue, it is crucial to investigate the high temperature wear law and wear prediction methodology of hot forging dies. In this paper, hot forging die steel H13 (HFDS - H13) that has undergone heat treatment is employed for experimental research. The results demonstrate that within the range of experimental temperature and load, as the temperature rises, the material's hardness decreases. Elevated temperatures and loads result in an overall decrease in the average friction coefficient, while the wear volume increases. Based on the test data, prediction models are designed using the modified Archard model and BP neural network. Both models display great prediction accuracy. However, under certain conditions, the BP neural network prediction model is superior. After utilizing interpolation algorithms to enhance the data, the BP neural network model demonstrates improved prediction accuracy by 2.11% and exhibits better stability.The article provides a reference for the study of high temperature wear law and wear prediction of other materials.