Neural networks based in process tool wear prediction system in milling wood operations

摘要：

Neural networks in process tool wear prediction system has been proposed and evaluated in this study. A total of 100 experimental data have been received for training through a back-propagation neural networks model. The input variables for the proposed neural networks system were feed rate, cutting speed from the cutting parameters, and the force in the x,y-direction collected online using a dynamometer. After the proposed neural networks system had been established, two experimental testing cuts were conducted to evaluate the performance of the system. From the test results, it was evident that the system could predict the tool wear online with an average error of ±0.037 mm.

关键词： Artificial neural networks cutting force dynamometer milling tool wear

作者: Krzysztof Szwajka Joanna Zieliska-Szwajka Jarosaw Górski

作者单位: Institute of Technology, University of Rzeszow, Poland Faculty of Wood Technology, SGGW, Nowoursynowska 159, 02-776 Warsaw, Poland

会议类型: 国际会议

会议名称: 第五届仪器科学与技术国际学术会议(ISIST 2008)Fifth International Symposium on Instrmentation Science and Technology

会议地点: 沈阳

会议语种:英文

页码: 1-9

在线出版日期: 2008-09-15（万方平台首次上网日期，不代表论文的发表时间）