大数据在设备健康预测和备件补货中的应用
|
摘要
提出了一种设备健康预测和库存优化方法。使用自编码器提取监测信号特征,基于深度神经网络模型进行时序预测,构建设备健康度指标;采用统计分布判定和参数拟合的预测方法实现库存优化;最后,根据设备健康状态与备件数量实现生产主动预警。实例结果表明,该方法预测精度高于LSTM算法,可对设备故障进行精确预警,且备件库存优化模型的可靠性高达90.4%,可有效减少备件库存。
A equipment health prediction and inventory optimization method was proposed herein.Firstly,a self-encoder was used to extract the features of monitoring signals.Based on that,a deep neural network model was used to predict the time series outcomes,and a equipment health indicator was also constructed.Secondly,a statistical distribution and parameter fitting prediction methods was used to achieve inventory optimization.Finally,the system provided active warnings for productions based on the information about the device health status and the number of spare parts.Example results show that the prediction accuracy of this method is higher than that of LSTM algorithm,which may accurately predict equipment failure.Early warning,and the reliability of the spare parts inventory optimization model is of 90.4%,which may effectively reduce spare parts inventory.
A equipment health prediction and inventory optimization method was proposed herein.Firstly,a self-encoder was used to extract the features of monitoring signals.Based on that,a deep neural network model was used to predict the time series outcomes,and a equipment health indicator was also constructed.Secondly,a statistical distribution and parameter fitting prediction methods was used to achieve inventory optimization.Finally,the system provided active warnings for productions based on the information about the device health status and the number of spare parts.Example results show that the prediction accuracy of this method is higher than that of LSTM algorithm,which may accurately predict equipment failure.Early warning,and the reliability of the spare parts inventory optimization model is of 90.4%,which may effectively reduce spare parts inventory.
引文
[1]许秀,肖军,王莉.石油化工自动化及仪表[M].北京:清华大学出版社,2013.XU Xiu,XIAO Jun,WANG Li.Automation and Instrumentation of Petrochemical Industry[M].Beijing:Tsinghua University press,2013:3-4.
[2]简祯富,许嘉裕.大数据分析与数据挖掘[M].北京:清华大学出版社,2016.JIAN Zhenfu,XU Jiayu.Big Data Analysis and Data Mining[M].Beijing:Tsinghua University Press,2016.
[3] LEE Jay,WU Fangji,ZHAO Wenyu,et al.Prognostics and Health Management Design for Rotary Machinery Systems—Reviews, Methodology and Applications[J].Mechanical Systems and Signal Processing,2014,42(1/2):314-334.
[4]彭宇,刘大同,彭喜元.故障预测与健康管理技术综述[J].电子测量与仪器学报,2010,24(1):1-9.PENG Yu,LIU Datong,PENG Xiyuan.A Review:Prognostics and Health Management[J].Journal of Electronic Measurement and Instrument,2010,24(1):1-9.
[5]廖雯竹,潘尔顺,王莹,等.统计模式识别和自回归滑动平均模型在设备剩余寿命预测中的应用[J].上海交通大学学报,2011,45(7):1000-1005.LIAO Wenzhu,PAN Ershun,WANG Ying,et al.Application of Statistical Pattern Recognition and Autoregressive Sliding Average Model in Prediction of Remaining Life of Equipment[J].Journal of Shanghai Jiaotong University,2011,45(7):1000-1005.
[6]赵玉刚,鞠建波,张经伟.基于LIB-SVM的电子设备故障预测方法研究[J].计算机测量与控制,2015,23(6):1888-1891.ZHAO Yugang,JU Jianbo,ZHANG Jingwei.Research on Fault Prediction Methods of Electronic Device Based on LIB-SVM[J].Computer Measurement&Control,2015,23(6):1888-1891.
[7] HEIMES F O.Recurrent Neural Networks for Remaining Useful Life Estimation[C]//First International Conference on Prognostics and Health Management(PHM 2008).Denver,2008:1-6.
[8]王洪斌,王红何,群王跃,等.基于深度信念网络的风机主轴承状态监测方法[J].中国机械工程,2018,29(8):948-953.WANG Hongbin, WANG Honghe,QUN Wangyue,et al.Condition Monitoring Method for Wind Turbine Main Bearings Based on DBN[J].China Mechanical Engineering,2018,29(8):948-953.
[9]吴魁,孙洁,蒋波,等.基于LSTM的风洞设备健康状态评估方法研究[J].计算机测量与控制,2018,26(3):288-291.WU Kui,SUN Jie,JIANG Bo,et al.Study of Health Assessment for Wind Tunnel Based on LSTM[J].Computer Measurement&Control,2018,26(3):288-291.
[10]张洁,秦威,鲍劲松.制造业大数据[M].上海:上海科学技术出版社,2016.ZHANG Jie,QIN Wei,BAO Jinsong.Big Data of Manufacturing Industry[M].Shanghai:Shanghai Science and Technology Press,2016.
[11]吕飞,李延晖.备件物流系统选址库存路径问题模型及算法[J].工业工程与管理,2010,15(1):82-86.LYU Fei,LI Yanhui.Model and Algorithm for Location Inventory-routing Problem of Spare Parts Logistics System in Time-based Competition[J].Industrial Engineering and Management,2010,15(1):82-86.
[12]黄照协,高崎,葛阳,等.典型串并联系统的备件库存优化模型[J].数学的实践与认识,2012,42(18):195-201.HUANG Zhaoxie,GAO Qi,GE Yang,et al.Optimization Model of Spares Inventory Based on Typical Series-Paurallel Connection System[J].Mathmatics in Practice and Theory,2012,42(18):195-201.
[13]罗祎,阮旻智,袁志勇.多级维修供应下可修复备件库存建模与优化[J].系统工程理论与实践,2013,33(10):2623-2630.LUO Yi,RUAN Minzhi,YUAN Zhiyong.Modeling and Optimization of Repairable Spare Parts under the Multi-echelon Maintenance Supply[J].Systems Engineering-Theory&Practice,2013,33(10):2623-2630.
[14]聂涛,盛文,王晗中.装备备件两级闭环供应链库存优化与分析[J].系统工程理论与实践,2010(12):2309-2314.NIE Tao,SHENG Wen,WANG Hanzhong.Optimizing and Analyzing Two-echelon Closed Loop Supply Chain Storage System for Equipment Spare Parts[J].Systems Engineering-Theory&Practice,2010(12):2309-2314.
[2]简祯富,许嘉裕.大数据分析与数据挖掘[M].北京:清华大学出版社,2016.JIAN Zhenfu,XU Jiayu.Big Data Analysis and Data Mining[M].Beijing:Tsinghua University Press,2016.
[3] LEE Jay,WU Fangji,ZHAO Wenyu,et al.Prognostics and Health Management Design for Rotary Machinery Systems—Reviews, Methodology and Applications[J].Mechanical Systems and Signal Processing,2014,42(1/2):314-334.
[4]彭宇,刘大同,彭喜元.故障预测与健康管理技术综述[J].电子测量与仪器学报,2010,24(1):1-9.PENG Yu,LIU Datong,PENG Xiyuan.A Review:Prognostics and Health Management[J].Journal of Electronic Measurement and Instrument,2010,24(1):1-9.
[5]廖雯竹,潘尔顺,王莹,等.统计模式识别和自回归滑动平均模型在设备剩余寿命预测中的应用[J].上海交通大学学报,2011,45(7):1000-1005.LIAO Wenzhu,PAN Ershun,WANG Ying,et al.Application of Statistical Pattern Recognition and Autoregressive Sliding Average Model in Prediction of Remaining Life of Equipment[J].Journal of Shanghai Jiaotong University,2011,45(7):1000-1005.
[6]赵玉刚,鞠建波,张经伟.基于LIB-SVM的电子设备故障预测方法研究[J].计算机测量与控制,2015,23(6):1888-1891.ZHAO Yugang,JU Jianbo,ZHANG Jingwei.Research on Fault Prediction Methods of Electronic Device Based on LIB-SVM[J].Computer Measurement&Control,2015,23(6):1888-1891.
[7] HEIMES F O.Recurrent Neural Networks for Remaining Useful Life Estimation[C]//First International Conference on Prognostics and Health Management(PHM 2008).Denver,2008:1-6.
[8]王洪斌,王红何,群王跃,等.基于深度信念网络的风机主轴承状态监测方法[J].中国机械工程,2018,29(8):948-953.WANG Hongbin, WANG Honghe,QUN Wangyue,et al.Condition Monitoring Method for Wind Turbine Main Bearings Based on DBN[J].China Mechanical Engineering,2018,29(8):948-953.
[9]吴魁,孙洁,蒋波,等.基于LSTM的风洞设备健康状态评估方法研究[J].计算机测量与控制,2018,26(3):288-291.WU Kui,SUN Jie,JIANG Bo,et al.Study of Health Assessment for Wind Tunnel Based on LSTM[J].Computer Measurement&Control,2018,26(3):288-291.
[10]张洁,秦威,鲍劲松.制造业大数据[M].上海:上海科学技术出版社,2016.ZHANG Jie,QIN Wei,BAO Jinsong.Big Data of Manufacturing Industry[M].Shanghai:Shanghai Science and Technology Press,2016.
[11]吕飞,李延晖.备件物流系统选址库存路径问题模型及算法[J].工业工程与管理,2010,15(1):82-86.LYU Fei,LI Yanhui.Model and Algorithm for Location Inventory-routing Problem of Spare Parts Logistics System in Time-based Competition[J].Industrial Engineering and Management,2010,15(1):82-86.
[12]黄照协,高崎,葛阳,等.典型串并联系统的备件库存优化模型[J].数学的实践与认识,2012,42(18):195-201.HUANG Zhaoxie,GAO Qi,GE Yang,et al.Optimization Model of Spares Inventory Based on Typical Series-Paurallel Connection System[J].Mathmatics in Practice and Theory,2012,42(18):195-201.
[13]罗祎,阮旻智,袁志勇.多级维修供应下可修复备件库存建模与优化[J].系统工程理论与实践,2013,33(10):2623-2630.LUO Yi,RUAN Minzhi,YUAN Zhiyong.Modeling and Optimization of Repairable Spare Parts under the Multi-echelon Maintenance Supply[J].Systems Engineering-Theory&Practice,2013,33(10):2623-2630.
[14]聂涛,盛文,王晗中.装备备件两级闭环供应链库存优化与分析[J].系统工程理论与实践,2010(12):2309-2314.NIE Tao,SHENG Wen,WANG Hanzhong.Optimizing and Analyzing Two-echelon Closed Loop Supply Chain Storage System for Equipment Spare Parts[J].Systems Engineering-Theory&Practice,2010(12):2309-2314.