Title :
Experimental study of tool wear monitoring based on neural networks
Author :
Gao, Hongli ; Xu, Mingheng ; Su, Yanchen ; Fu, Pan ; Liu, Qingjie
Author_Institution :
Sch. of Mech. Eng., Southwest Jiaotong Univ., Chengdu
Abstract :
The influence of experimental design on modeling of tool condition monitoring system based on different neural networks was investigated. The orthogonal experiments and complete parameter combination experiments were carried out on a Vertical Machining Centre, and BPNN and CSGFFNN were adopted to model the mapping relations between tool condition and features extracted from different sensor signals by using experimental data. The research results show the orthogonal experiments canpsilat meet the need of modeling of TCMS based on different NN and the classifying error is high above 87%, complete parameter combination experiments can provide enough data for modeling of NN for TCMS and realize reliable monitoring of tool condition or tool wear.
Keywords :
backpropagation; condition monitoring; design of experiments; feature extraction; machine tools; machining; neural nets; sensors; wear; backpropagation neural network; experimental design; feature extraction; sensor signal; tool condition monitoring system modeling; tool wear monitoring; vertical machining centre; Acoustic sensors; Condition monitoring; Design for experiments; Feature extraction; Machining; Milling; Neural networks; Sampling methods; Signal mapping; Vibration measurement; BPNN; CSGFFNN; Experiment; Tool Condition Monitoring;
Conference_Titel :
Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on
Conference_Location :
Chongqing
Print_ISBN :
978-1-4244-2113-8
Electronic_ISBN :
978-1-4244-2114-5
DOI :
10.1109/WCICA.2008.4593985
