刊名：Advances in Manufacturing 2024年第1期，第6-18页
题名：A data‑driven approach to RUL prediction of tools
作者：Wei Li1,5 · Liang‑Chi Zhang2,3,4 · Chu‑Han Wu5 · Yan Wang5 · Zhen‑Xiang Cui6 · Chao Niu6
单位：1. Department of Mechanical Engineering, University College London, London WC1E 7JE, UK
2. Shenzhen Key Laboratory of Cross‑Scale Manufacturing Mechanics, Southern University of Science and Technology, Shenzhen 518055, Guangdong, People’s Republic of China
3. SUSTech Institute for Manufacturing Innovation, Southern University of Science and Technology, Shenzhen 518055, Guangdong, People’s Republic of China
4. Department of Mechanics and Aerospace Engineering, Southern University of Science and Technology, Shenzhen 518055, Guangdong, People’s Republic of China
5. School of Mechanical and Manufacturing Engineering, The University of New South Wales, Kensington, NSW 2052, Australia
6. Baoshan Iron & Steel Co., Ltd., Shanghai 200941, People’s Republic of China
摘要：An effective and reliable prediction of the remaining useful life (RUL) of a tool is important to a metal forming process because it can significantly reduce unexpected maintenance, avoid machine shutdowns and increase system stability. This study proposes a new datadriven approach to the RUL prediction for metal forming processes under multiple contact sliding conditions. The data-driven approach took advantage of bidirectional long
short-term memory (BLSTM) and convolutional neural networks (CNN). A pre-trained lightweight CNN-based network, WearNet, was re-trained to classify the wear states of workpiece surfaces with a high accuracy, then the classification results were passed into a BLSTM-based regression model as inputs for RUL estimation. The experimental results demonstrated that this approach was able to predict the RUL values with a small error (below 5%) and a low root mean square error (RMSE) (around 1.5), which was more
superior and robust than the other state-of-the-art methods.
关键词：Remaining useful life (RUL) · Bidirectional long short-term memory (BLSTM) · Data-driven approach · Metal forming
全文链接：https://link.springer.com/article/10.1007/s40436-023-00464-y