Intelligent Recognition Method of Turning Tool Wear State Based on Information Fusion Technology and BP Neural Network

Abstract

The multi-information data acquisition system of tool wear condition of CNC lathe is built by acquiring the acoustic emission and vibration acceleration signals. The data of acoustic emission and vibration acceleration signals during the process of CNC machine tool processing under the conditions of different tool wear degrees and different cutting conditions are acquired and analyzed using the orthogonal experimental method. The optimum characteristic frequency band of acoustic emission and vibration acceleration signals was extracted by the wavelet envelope decomposition method so as to recognize tool wear condition as the characteristic parameters. The characteristic information of acoustic emission and vibration acceleration signals during the process of CNC machine tool processing was fused. In addition, the intelligent recognition of tool wear condition during the process of machine tool processing was researched.