One of the most important features of the modern ma ch ining system in an "unmanned" factory is to change tools that have been subjec ted to wear and damage. An integrated tool condition monitoring system co...One of the most important features of the modern ma ch ining system in an "unmanned" factory is to change tools that have been subjec ted to wear and damage. An integrated tool condition monitoring system composed of multi-sensors, signal processing devices and intelligent decision making pla ns is a necessary requirement for automatic manufacturing processes. An intellig ent tool wear monitoring system will be introduced in this paper. The system is equipped with power consumption, vibration, AE and cutting force sensors, signal transformation and collection apparatus and a microcomputer. Tool condition monitoring is a pattern recognition process in which the characte ristics of the tool to be monitored are compared with those of the standard mode ls. The tool wear classification process is composed of the following parts: fea ture extraction; determination of the fuzzy membership functions of the features ; calculation of the fuzzy similarity; learning and tool wear classification. Fe atures extracted from the time domain and frequency domain for the future patter n recognition are as follows. Power consumption signal: mean value; AE-RMS sign al: mean value, skew and kutorsis; Cutting force, AE and vibration signal: mean value, standard deviation and the mean power in 10 frequency ranges. These signa l features can reflect the tool wear states comprehensively. The fuzzy approachi ng degree and the fuzzy distance between corresponding features of different obj ects are combined to describe the closeness of two fuzzy sets more accurately. A unique fuzzy driven neural network based pattern recognition algorithm has bee n developed from this research. The combination of Artificial Neural Networks (A NNs) and fuzzy logic system integrates the strong learning and classification ab ility of the former and the superb flexibility of the latter to express the dist ribution characteristics of signal features with vague boundaries. This methodol ogy indirectly solves the automatic weight assignment problem of the conventiona l fuzzy pattern recognition system and let it have greater representative power, higher training speed and be more robust. The introduction of the two-dimensio nal weighted approaching degree can make the pattern recognition process more re liable. The fuzzy driven neural network can effectively fuse multi-sensor i nformation and successfully recognize the tool wear states. Armed with the advan ced pattern recognition methodology, the established intelligent tool condition monitoring system has the advantages of being suitable for different machini ng conditions, robust to noise and tolerant to faults. Cooperated with the contr ol system of the machine tool, the optimized machining processed can be achieved .展开更多
文摘One of the most important features of the modern ma ch ining system in an "unmanned" factory is to change tools that have been subjec ted to wear and damage. An integrated tool condition monitoring system composed of multi-sensors, signal processing devices and intelligent decision making pla ns is a necessary requirement for automatic manufacturing processes. An intellig ent tool wear monitoring system will be introduced in this paper. The system is equipped with power consumption, vibration, AE and cutting force sensors, signal transformation and collection apparatus and a microcomputer. Tool condition monitoring is a pattern recognition process in which the characte ristics of the tool to be monitored are compared with those of the standard mode ls. The tool wear classification process is composed of the following parts: fea ture extraction; determination of the fuzzy membership functions of the features ; calculation of the fuzzy similarity; learning and tool wear classification. Fe atures extracted from the time domain and frequency domain for the future patter n recognition are as follows. Power consumption signal: mean value; AE-RMS sign al: mean value, skew and kutorsis; Cutting force, AE and vibration signal: mean value, standard deviation and the mean power in 10 frequency ranges. These signa l features can reflect the tool wear states comprehensively. The fuzzy approachi ng degree and the fuzzy distance between corresponding features of different obj ects are combined to describe the closeness of two fuzzy sets more accurately. A unique fuzzy driven neural network based pattern recognition algorithm has bee n developed from this research. The combination of Artificial Neural Networks (A NNs) and fuzzy logic system integrates the strong learning and classification ab ility of the former and the superb flexibility of the latter to express the dist ribution characteristics of signal features with vague boundaries. This methodol ogy indirectly solves the automatic weight assignment problem of the conventiona l fuzzy pattern recognition system and let it have greater representative power, higher training speed and be more robust. The introduction of the two-dimensio nal weighted approaching degree can make the pattern recognition process more re liable. The fuzzy driven neural network can effectively fuse multi-sensor i nformation and successfully recognize the tool wear states. Armed with the advan ced pattern recognition methodology, the established intelligent tool condition monitoring system has the advantages of being suitable for different machini ng conditions, robust to noise and tolerant to faults. Cooperated with the contr ol system of the machine tool, the optimized machining processed can be achieved .
