基于PNN神经网络的掘进机截齿磨损程度识别研究
|
摘要
针对掘进机截齿磨损在线识别问题,提出一种基于PNN神经网络的截齿磨损程度多特征信号识别方法,提取不同磨损程度的截齿在截割过程中的振动和声发射特征信号,分别分析振动加速度、声发射信号峰值以及2种特征信号频域图的均方根这4个特征参数,获取振动信号、声发射信号与不同磨损程度截齿的变化规律。建立5种不同磨损程度截齿的多特征信号样本数据库,采用多特征信号样本对PNN神经网络进行学习和训练,建立截齿磨损程度的识别模型,实现截齿磨损程度的精确识别。结果表明:基于PNN神经网络的截齿预测磨损状态识别模型识别精度较高,识别准确率和预测准确率约为93.3%和95.0%,与BP神经网络方法相比分别提高了3.3%和15.0%。因此该神经网络具有良好的可靠性与精确性。
In view of the problem of on-line identification of cutting wear of roadheader,a multi-feature signals recognition method based on PNN neural network is proposed.The vibration and acoustic emission characteristic signals of the picks with different pick wear degrees during the cutting process are extracted and analyzed separately.The four characteristic parameters of the vibration acceleration,the peak value of acoustic emission signal and the root mean square of the frequency domain diagram of two characteristic signals were used to obtain the variation of vibration signal,acoustic emission signal and pick of different wear degrees.A Multi-feature signal sample database for five different pick wear degree were established.The multi-feature signal samples were used to study and train the PNN neural network,the recognition model of pick wear degree was established to realize the accurate identification of pick wear degree.The results show that the recognition accuracy of model based on PNN neural network has higher recognition accuracy,and the accuracy of recognition and prediction are about 93.3% and 95%,which is 3.3% and 15% higher than that of BP neural network.The results provide an important technical means for identifying the wear degree of picks precisely and improving the work efficiency.
In view of the problem of on-line identification of cutting wear of roadheader,a multi-feature signals recognition method based on PNN neural network is proposed.The vibration and acoustic emission characteristic signals of the picks with different pick wear degrees during the cutting process are extracted and analyzed separately.The four characteristic parameters of the vibration acceleration,the peak value of acoustic emission signal and the root mean square of the frequency domain diagram of two characteristic signals were used to obtain the variation of vibration signal,acoustic emission signal and pick of different wear degrees.A Multi-feature signal sample database for five different pick wear degree were established.The multi-feature signal samples were used to study and train the PNN neural network,the recognition model of pick wear degree was established to realize the accurate identification of pick wear degree.The results show that the recognition accuracy of model based on PNN neural network has higher recognition accuracy,and the accuracy of recognition and prediction are about 93.3% and 95%,which is 3.3% and 15% higher than that of BP neural network.The results provide an important technical means for identifying the wear degree of picks precisely and improving the work efficiency.
引文
[1]张强,韩东,张旭,等.掘进机负压降尘装置设计及性能分析[J].煤炭科学技术,2018,46(12):1-7.ZHANG Qiang,HAN Dong,ZHANG Xu,et al.Design and performance analysis of negative pressure dust control device of roadheader[J].Coal Science and Technology,2018,46(12):1-7.
[2]张强,刘志恒,王海舰,等.基于BP神经网络的截齿磨损程度在线监测[J].中国机械工程,2017(9):1062-1068.ZHANG Qiang,LIU Zhiheng,WANG Haijian,et al.On-line monitoring of pick’s wear degrees based on BP neural network[J].China Mechanical Engineering,2017(9):1062-1068
[3]张强,张石磊,王海舰,等.基于声发射信号的煤岩界面识别研究[J].电子测量与仪器学报,2017,31(2):230-237.ZHANG Qiang,ZHANG Shilei,WANG Haijian,et al.Study on identification of coal-rock interface based on acoustic emission signal[J].Journal of Electronic Measurement and Instrumention,2017,31(2):230-237.
[4]张强,刘志恒,王海舰,等.BP神经网络在截齿合金头失效识别中的应用[J].振动·测试与诊断,2018,38(3):508-516.ZHANG Qiang,LIU Zhiheng,WANG Haijian,et al.Application of bp neural network in failure identification of gear cutting alloy head[J].Journal of Vibration,Measurement&Diagnosis,2018,38(3):508-516.
[5]李晓豁,何洋,焦丽,等.基于参数识别的截割头纵向随机振动响应优化[J].中国机械工程,2015,26(6):818-823.LI Xiaohuo,HE Yang,JIAO Li,et al.Optimization of longtidinal random vibration response of cutting head based on parameter identification[J].China Mechanical Engineering,2015,26(6):818-823.
[6]王雁翔,杨道龙,王凌翔.镐形截齿截割磨损研究[J].煤矿机械2014,35(2):47-49.WANG Yanxiang,YANG Daolong,WANG Lingxiang.Study on wear perfor mance of pick cutting[J].Coal Mine Machinery,2014,35(2):47-49.
[7]孙汝继,王水生,王海舰.掘进机截齿磨损程度分析及识别方法[J].工矿自动化,2016,42(12):68-71.SUN Ruji,WANG Yongsheng,WANG Haijian.Analysis and recognition method of wear degree of roadheader cutting picks[J].Industry and Mine Automation.2016,42(12):68-71
[8]张强,顾颉颖,刘峻铭,等.基于小波包与SOM神经网络的截齿磨损状态识别[J].煤炭学报,2018,43(7):2077-2083.ZHANG Qiang,GU Jieying,LIU Junming,et al.Pick wear condition identification based on wavelet packet and SOM neural network[J].Journal of China Coal Society,2018,43(7):2077-2083.
[9]袁一鸣.基于数据融合的掘进机截齿磨损状态监测[J].科技创新导报,2016,13(21):36-37.YUAN Yiming.Monitoring of cutting wear status of roadheader based on data fusion[J].Science and Technology Innovation Herald,2016,13(21):36-37.
[10]王小敏,谢文俊.PNN网络在入侵检测中的应用研究[J].软件导刊,2016,15(10):152-154.WANG Xiaomin,XIE Wenjun,Research on the application of PNN network in intrusion detection[J].Software Guide,2016,15(10):152-154.
[11]韩凤华,谢峰.基于多参数指标的刀具磨损状态在线监测[J].制造技术与机床,2018(2):141-146.XIE Fenghua,XIE Feng.On-line monitoring of tool wear status based on multi-parameter indexes[J].Manufacturing Technology&Machine Tool,2018(2):141-146.
[12]徐彦伟,陈立海,袁子皓,等.基于信息融合的刀具磨损状态智能识别[J].振动与冲击,2017,36(21):257-264.XU Yanhua,CHEN Lihai,YUAN Zihao,et al.Intelligent recognition of tool wear conditions based on the information fusion[J].Journal of Vibration and Shock,2017,36(21):257-264.
[13]刘宇,汪惠芬,刘庭煜.一种基于多特征和支持向量机的刀具磨损状态识别技术[J].制造业自动化,2016,38(5):132-138.LIU Yu,WANG Huifen,LIU Tingyu.An intelligent tool wear estimation technology based on multi-feature and support vector machine[J].Manufacturing Automation,2016,38(5):132-138.
[14]张锴锋,袁惠群,聂鹏.基于切削声信号与优化SVM的刀具磨损状态监测[J].振动·测试与诊断,2015,35(4):727-732,801.ZHANG Kaifeng,YUAN Huiqun,NIE Peng.Tool wear monitoring based on cutting acoustic signal and optimized SVM[J].Journal of Vibration,Measurement&Diagnosis,2015,35(4):727-732,801.
[15]任艺,张蕾.基于概率神经网络的TSI发动机故障识别方法[J].天津职业技术师范大学学报,2017,27(3):34-38.REN Yi,ZHANG Lei.Research on the recognizing method of TSIengine trouble based on probabilistic neural net[J].Journal of Tianjin University of Technology and Education,2017,27(3):34-38.
[16]宋伟,尹涛.基于概率神经网络(PNN)的矿井提升机故障诊断研究[J].电子测量技术,2016,39(11):187-189,194.SONG Wei,YIN Tao.Research on fault diagnosis of mine hoist based on probabilistic neural network[J].Electronic Measurement Technology,2016,39(11):187-189,194.
[17]刘智键,刘宝林,胡远彪.刀具磨损状态检测方法的分析与验证[J].工具技术,2018,52(2):116-118.LIU Zhijian,LIU Baolin,HU Yuanbiao.Analysis on method of detecting tool wear state[J].Tool Engineering,2018,52(2):116-118.
[18]林伟,王昕,郑益慧,等.基于概率神经网络的局部放电信号特征提取与识别研究[J].电气自动化,2018,40(3):60-63.LIN Wei,WANG Xin,ZHENG Yihui,et al.Research of feature extraction and recognition of partial discharge based on the probabilistic neural network[J].Electrical Automation,2018,40(3):60-63.
[19]李慧莹,胡西川.基于概率神经网络的手写体数字特征提取[J].现代计算机,2018(15):59-63.LI Huiying,HU Xichuan,Handwritten digital feature extraction based on probabilistic Neural network[J].Modern Computer,2018(15):59-63.
[20]唐航,周绍骑,周殷涛,等.基于奇异值分解和FSVM的声发射信号识别[J].自动化与仪器仪表,2017(5):205-207.TANG Hang,ZHOU Saiqi,ZHOU Yintao,et al.Acoustic Emission signal recognition based on singular value decomposition and FSVM[J].Automation&Instrumentation,2017(5):205-207.
[2]张强,刘志恒,王海舰,等.基于BP神经网络的截齿磨损程度在线监测[J].中国机械工程,2017(9):1062-1068.ZHANG Qiang,LIU Zhiheng,WANG Haijian,et al.On-line monitoring of pick’s wear degrees based on BP neural network[J].China Mechanical Engineering,2017(9):1062-1068
[3]张强,张石磊,王海舰,等.基于声发射信号的煤岩界面识别研究[J].电子测量与仪器学报,2017,31(2):230-237.ZHANG Qiang,ZHANG Shilei,WANG Haijian,et al.Study on identification of coal-rock interface based on acoustic emission signal[J].Journal of Electronic Measurement and Instrumention,2017,31(2):230-237.
[4]张强,刘志恒,王海舰,等.BP神经网络在截齿合金头失效识别中的应用[J].振动·测试与诊断,2018,38(3):508-516.ZHANG Qiang,LIU Zhiheng,WANG Haijian,et al.Application of bp neural network in failure identification of gear cutting alloy head[J].Journal of Vibration,Measurement&Diagnosis,2018,38(3):508-516.
[5]李晓豁,何洋,焦丽,等.基于参数识别的截割头纵向随机振动响应优化[J].中国机械工程,2015,26(6):818-823.LI Xiaohuo,HE Yang,JIAO Li,et al.Optimization of longtidinal random vibration response of cutting head based on parameter identification[J].China Mechanical Engineering,2015,26(6):818-823.
[6]王雁翔,杨道龙,王凌翔.镐形截齿截割磨损研究[J].煤矿机械2014,35(2):47-49.WANG Yanxiang,YANG Daolong,WANG Lingxiang.Study on wear perfor mance of pick cutting[J].Coal Mine Machinery,2014,35(2):47-49.
[7]孙汝继,王水生,王海舰.掘进机截齿磨损程度分析及识别方法[J].工矿自动化,2016,42(12):68-71.SUN Ruji,WANG Yongsheng,WANG Haijian.Analysis and recognition method of wear degree of roadheader cutting picks[J].Industry and Mine Automation.2016,42(12):68-71
[8]张强,顾颉颖,刘峻铭,等.基于小波包与SOM神经网络的截齿磨损状态识别[J].煤炭学报,2018,43(7):2077-2083.ZHANG Qiang,GU Jieying,LIU Junming,et al.Pick wear condition identification based on wavelet packet and SOM neural network[J].Journal of China Coal Society,2018,43(7):2077-2083.
[9]袁一鸣.基于数据融合的掘进机截齿磨损状态监测[J].科技创新导报,2016,13(21):36-37.YUAN Yiming.Monitoring of cutting wear status of roadheader based on data fusion[J].Science and Technology Innovation Herald,2016,13(21):36-37.
[10]王小敏,谢文俊.PNN网络在入侵检测中的应用研究[J].软件导刊,2016,15(10):152-154.WANG Xiaomin,XIE Wenjun,Research on the application of PNN network in intrusion detection[J].Software Guide,2016,15(10):152-154.
[11]韩凤华,谢峰.基于多参数指标的刀具磨损状态在线监测[J].制造技术与机床,2018(2):141-146.XIE Fenghua,XIE Feng.On-line monitoring of tool wear status based on multi-parameter indexes[J].Manufacturing Technology&Machine Tool,2018(2):141-146.
[12]徐彦伟,陈立海,袁子皓,等.基于信息融合的刀具磨损状态智能识别[J].振动与冲击,2017,36(21):257-264.XU Yanhua,CHEN Lihai,YUAN Zihao,et al.Intelligent recognition of tool wear conditions based on the information fusion[J].Journal of Vibration and Shock,2017,36(21):257-264.
[13]刘宇,汪惠芬,刘庭煜.一种基于多特征和支持向量机的刀具磨损状态识别技术[J].制造业自动化,2016,38(5):132-138.LIU Yu,WANG Huifen,LIU Tingyu.An intelligent tool wear estimation technology based on multi-feature and support vector machine[J].Manufacturing Automation,2016,38(5):132-138.
[14]张锴锋,袁惠群,聂鹏.基于切削声信号与优化SVM的刀具磨损状态监测[J].振动·测试与诊断,2015,35(4):727-732,801.ZHANG Kaifeng,YUAN Huiqun,NIE Peng.Tool wear monitoring based on cutting acoustic signal and optimized SVM[J].Journal of Vibration,Measurement&Diagnosis,2015,35(4):727-732,801.
[15]任艺,张蕾.基于概率神经网络的TSI发动机故障识别方法[J].天津职业技术师范大学学报,2017,27(3):34-38.REN Yi,ZHANG Lei.Research on the recognizing method of TSIengine trouble based on probabilistic neural net[J].Journal of Tianjin University of Technology and Education,2017,27(3):34-38.
[16]宋伟,尹涛.基于概率神经网络(PNN)的矿井提升机故障诊断研究[J].电子测量技术,2016,39(11):187-189,194.SONG Wei,YIN Tao.Research on fault diagnosis of mine hoist based on probabilistic neural network[J].Electronic Measurement Technology,2016,39(11):187-189,194.
[17]刘智键,刘宝林,胡远彪.刀具磨损状态检测方法的分析与验证[J].工具技术,2018,52(2):116-118.LIU Zhijian,LIU Baolin,HU Yuanbiao.Analysis on method of detecting tool wear state[J].Tool Engineering,2018,52(2):116-118.
[18]林伟,王昕,郑益慧,等.基于概率神经网络的局部放电信号特征提取与识别研究[J].电气自动化,2018,40(3):60-63.LIN Wei,WANG Xin,ZHENG Yihui,et al.Research of feature extraction and recognition of partial discharge based on the probabilistic neural network[J].Electrical Automation,2018,40(3):60-63.
[19]李慧莹,胡西川.基于概率神经网络的手写体数字特征提取[J].现代计算机,2018(15):59-63.LI Huiying,HU Xichuan,Handwritten digital feature extraction based on probabilistic Neural network[J].Modern Computer,2018(15):59-63.
[20]唐航,周绍骑,周殷涛,等.基于奇异值分解和FSVM的声发射信号识别[J].自动化与仪器仪表,2017(5):205-207.TANG Hang,ZHOU Saiqi,ZHOU Yintao,et al.Acoustic Emission signal recognition based on singular value decomposition and FSVM[J].Automation&Instrumentation,2017(5):205-207.