Research On The Machining Status Monitoring Of CNC Machine Tools Based On Ubiquitous Manufacturing

Characterized by awareness and intelligence, new technologies are emerged and mutually integrated. Ubiquitous manufacturing, which is based on ubiquitous network and centers on ubiquitous awareness, is becoming the new driving force of manufacturing technology. Furthermore, it promotes the development of the equipment status monitoring. Based on ubiquitous sensor networks, the operators can collect the information related to machining parameters quickly and comprehensively, With fusion algorithm the information can be analyzed deeply. According to the analysis result, the relevant management staff and operators can know well the machining status of CNC machine tools via ubiquitous network.According to the architecture of ubiquitous manufacturing, this paper established a system of machining status monitoring of CNC machine tools. By installing relevant sensors, the signals of machining were transmitted to the monitoring center by wireless network. In the monitoring center, the signals were analyzed by time domain analysis method. The features were selected by synthesis coefficient method. Then the neural network method was used to identify the processing status of CNC machine tools. At last, the results were transmitted to PDA or remote server by ubiquitous network.As an example for the test of built monitoring system, the experimentation was carried out to monitor the condition of tool wear, which was related with the machining process closely. Firstly, the vibrancy and acoustic emission signals were collected and analyzed by time domain analysis. Secondly, as inputting data for neural network, the characteristic of vibrancy and acoustic emission signals were extracted by synthesis coefficient method. According to experimentation results, the static mean and average energy value of the time domain characteristics were selected for tool wear status recognition and wearing prediction. In pattern recognition, using the nonlinear mapping function of neural network, a three-layer BP artificial neural network was selected to carry out the mapping between the processing status and related signal features. In this way, the monitoring of machining processing was implemented. The Matlab Script node of LabVIEW software was used to call the neural network package of Matlab, which reduced the program development and increased the reliability of the program. According to the experimentation, BP artificial neural network can effectively recognize the wear status of finger cutter and accomplish the wear prediction.The thesis carried out deep exploration on experiment design, signal analyzing, feature selecting, pattern recognition and other aspects. It implemented the wear monitoring and wearing prediction of finger cutters in the experimentation through wireless network, which laid the foundation for the practical application of ubiquitous manufacturing-based machining status monitoring of CNC machine tools.