Tool life prediction based on multi-source feature PSO-SVR neural network

Abstract With the continuous improvement of modern manufacturing automation and process intensification, the complexity of tools and machined parts has greatly increased, and their performance directly affects the quality of workpieces and production efficiency. Accurate prediction of tool life is conducive to improving production efficiency and reducing enterprise costs. In this paper, a tool life prediction method based on multi-source feature PSO-SVR neural network is proposed. By monitoring and collecting the current and vibration signals of the tool during the machining process of CNC machine tools, the time-frequency eigenvalues are extracted. The effective features are extracted by feature selection technology as the input of support vector regression (SVR) neural network, and the parameters of the network are optimized by particle swarm optimization (PSO), so as to improve the accuracy of the predict, and finally predict the remaining useful life(rul) of the tool.