基于BP神经网络的轴承套圈沟道磨削粗糙度识别
|
摘要
针对轴承套圈沟道磨削监测方法间接、监控信号偏少、识别效率不高、准确率偏低等不足,采用相关分析初选8个与粗糙度相关性较高的信号特征,再采用主成分分析,根据主成分贡献率以及累积贡献率,进一步将8个信号特征转化为3个主成分,采用BP神经网络建立主成分与沟道磨削粗糙度之间的映射关系模型,利用Matlab软件进行训练和验证,粗糙度识别正确率超过95%,能够提高轴承套圈沟道磨削过程的质量监控能力。
For the less monitoring signal, indirect monitoring mode, lower accuracy and efficiency of quality monitoring, the correlation analysis method is used to select 8 signal features which have higher correlation with surface roughness of bearing ring groove. According to the contribution rate of the main components and the cumulative contribution rate, the principal component analysis(PCA) Method is adopted to convert 8 signal features to 3 principal components. The BP neural network is used to establish the mapping relationship between the principal components and the surface roughness of groove grinding. The MATLAB software is used to train and identify the surface roughness of ring groove, and the recognition accuracy is more than 95%, this method can improve quality monitoring capability of the bearing grinding process.
For the less monitoring signal, indirect monitoring mode, lower accuracy and efficiency of quality monitoring, the correlation analysis method is used to select 8 signal features which have higher correlation with surface roughness of bearing ring groove. According to the contribution rate of the main components and the cumulative contribution rate, the principal component analysis(PCA) Method is adopted to convert 8 signal features to 3 principal components. The BP neural network is used to establish the mapping relationship between the principal components and the surface roughness of groove grinding. The MATLAB software is used to train and identify the surface roughness of ring groove, and the recognition accuracy is more than 95%, this method can improve quality monitoring capability of the bearing grinding process.
引文
[ 1 ] 宋荣.面向轴承制造过程的质量知识学习系统的研究与开发[D].杭州:浙江大学,2006.
[ 2 ] JEMIELNIAK K,ARRAZOLA P J.Application of AE and cutting force signals in tool condition monitoring in micro-milling [J].CIRP Journal of Manufacturing Science and Technology,2008,1(2):97-102.
[ 3 ] ARUN A,RAMESHKUMAR K.Tool condition monitoring of cylindrical grinding process using acoustic emission sensor[J].Materials Today,2018,5(5):11888-11899.
[ 4 ] VENKATA K R.Prediction of cutting tool wear,surface roughness and vibration of work piece in boring of AISI 316 steel with artificial neural network [J].Measurement,2014,51(3):63-70.
[ 5 ] MAURICIO E N.Evaluation of neural models applied to the estimation of tool wear in the grinding of advanced ceramics [J].Expert Systems with Applications,2015,42(20):7026-7035.
[ 6 ] 常舟,陈耀龙.基于全因子试验的轴承沟道磨削工艺研究[J].航空制造技术,2018,61(9):52-58.
[ 7 ] 周佳,雷贤卿.轴承沟道形状误差的最小二乘评定[J].机械工程与自动化,2012(6):123-128.
[ 8 ] 高作斌,郭章计,马伟.轴承沟道超精研加工中的原理性沟形误差[J].轴承,2011 (7):7-12.
[ 9 ] 肖健华,吴今培,熊焕庭.基于支持向量机的滚动轴承质量检测方法[J].计算机工程与应用,2004(1):201-204.
[10] 王哲,胥利.沟道形状误差对深沟球轴承振动和噪音的影响[J].哈尔滨轴承,2009,30(4):23-24.
[11] 黎慧,张国文.基于灰色模型的滚动轴承剩余寿命预测[J].机械设计与研究,2018,34(1):113-116.
[12] 荆双喜,杨晓雨,罗志鹏.基于自适应时频分析的滚动轴承故障诊断[J].机械设计与研究,2018,34(4):85-88.
[13] 柏文峰,胡德金,刘玉文.磨削参数对硫化氢应力腐蚀试样表面质量的影响分析与优化[J].机械设计与研究,2010,26(1):84-86.
[14] 高世龙,安立宝.基于神经网络的车削加工表面粗糙度智能预测[J].机械设计与研究,2016,32(1):96-99.
[ 2 ] JEMIELNIAK K,ARRAZOLA P J.Application of AE and cutting force signals in tool condition monitoring in micro-milling [J].CIRP Journal of Manufacturing Science and Technology,2008,1(2):97-102.
[ 3 ] ARUN A,RAMESHKUMAR K.Tool condition monitoring of cylindrical grinding process using acoustic emission sensor[J].Materials Today,2018,5(5):11888-11899.
[ 4 ] VENKATA K R.Prediction of cutting tool wear,surface roughness and vibration of work piece in boring of AISI 316 steel with artificial neural network [J].Measurement,2014,51(3):63-70.
[ 5 ] MAURICIO E N.Evaluation of neural models applied to the estimation of tool wear in the grinding of advanced ceramics [J].Expert Systems with Applications,2015,42(20):7026-7035.
[ 6 ] 常舟,陈耀龙.基于全因子试验的轴承沟道磨削工艺研究[J].航空制造技术,2018,61(9):52-58.
[ 7 ] 周佳,雷贤卿.轴承沟道形状误差的最小二乘评定[J].机械工程与自动化,2012(6):123-128.
[ 8 ] 高作斌,郭章计,马伟.轴承沟道超精研加工中的原理性沟形误差[J].轴承,2011 (7):7-12.
[ 9 ] 肖健华,吴今培,熊焕庭.基于支持向量机的滚动轴承质量检测方法[J].计算机工程与应用,2004(1):201-204.
[10] 王哲,胥利.沟道形状误差对深沟球轴承振动和噪音的影响[J].哈尔滨轴承,2009,30(4):23-24.
[11] 黎慧,张国文.基于灰色模型的滚动轴承剩余寿命预测[J].机械设计与研究,2018,34(1):113-116.
[12] 荆双喜,杨晓雨,罗志鹏.基于自适应时频分析的滚动轴承故障诊断[J].机械设计与研究,2018,34(4):85-88.
[13] 柏文峰,胡德金,刘玉文.磨削参数对硫化氢应力腐蚀试样表面质量的影响分析与优化[J].机械设计与研究,2010,26(1):84-86.
[14] 高世龙,安立宝.基于神经网络的车削加工表面粗糙度智能预测[J].机械设计与研究,2016,32(1):96-99.