稀有金属快锻机液压机组状态监测预警系统
|
摘要
稀有金属快锻机作为国之重器,在国防工业材料加工领域具有重要作用,其液压机组可靠工作是关键。针对稀有金属快锻机液压机组结构与故障特点,提出一种快锻机液压机组状态监测预警系统。系统采集液压主系统压力、液压缸压力、液压油油温、主机泵振动信号与主机泵温度等运行状态参数,构建基于BP神经网络的状态预警模型,结合钛及钛合金锻造运行状态参数与状态知识库进行BP神经网络训练,在Matlab统实现对快锻机液压机组危险运行状态实时诊断与预警,对稀有金属快锻机安全可靠运行具有典型应用价值。
The rare metal fast forging machine plays an important role in the material processing field of national defense industry,and its normal operation depends on the reliable running of its hydraulic machine set. In allusion to the structure and fault characteristics for the hydraulic machine set of the rare metal fast forging machine,a state monitoring and early-warning system for the hydraulic machine set of the fast forging machine is proposed. In the system,the operation state parameters such as pressure of main hydraulic system,pressure of hydraulic cylinder,temperature of hydraulic oil,vibration signals and temper-ature of main pump motor are collected,so as to build a state early-warning model based on the BP neural network. The BP neu-ral network is trained and simulated on the Matlab platform by combining with the titanium and titanium alloy forging operation state parameters,and the state knowledge base. The actual operation results show that the state monitoring and early-warning sys-tem can realize real-time diagnosis and early-warning for the dangerous operation state of the hydraulic machine set of the fast forging machine,which has a typical application value for the safe and reliable operation of the rare metal fast forging machine.
The rare metal fast forging machine plays an important role in the material processing field of national defense industry,and its normal operation depends on the reliable running of its hydraulic machine set. In allusion to the structure and fault characteristics for the hydraulic machine set of the rare metal fast forging machine,a state monitoring and early-warning system for the hydraulic machine set of the fast forging machine is proposed. In the system,the operation state parameters such as pressure of main hydraulic system,pressure of hydraulic cylinder,temperature of hydraulic oil,vibration signals and temper-ature of main pump motor are collected,so as to build a state early-warning model based on the BP neural network. The BP neu-ral network is trained and simulated on the Matlab platform by combining with the titanium and titanium alloy forging operation state parameters,and the state knowledge base. The actual operation results show that the state monitoring and early-warning sys-tem can realize real-time diagnosis and early-warning for the dangerous operation state of the hydraulic machine set of the fast forging machine,which has a typical application value for the safe and reliable operation of the rare metal fast forging machine.
引文
[1]施锦丹,王凯,王伯成,等.液压系统故障诊断方法综述[J].机床与液压,2008,36(11):175-179.SHI Jindan,WANG Kai,WANG Bocheng,et al.An overview of fault diagnosis technology for hydraulic system[J].Machine tool&hydraulics,2008,36(11):175-179.
[2]刘涛,朱达荣,汪方斌,等.物联网环境下的大型立磨状态监测及损伤预警系统模型[J].机械设计与制造,2017(10):168-170.LIU Tao,ZHU Darong,WANG Fangbin,et al.Large vertical mill condition monitoring and damage early warning system model under Internet of Things environment[J].Machinery design&manufacture,2017(10):168-170.
[3]李文伟.25MN快锻机液压故障诊断专家系统研究[D].西安:西安建筑科技大学,2015.LI Wenwei.Research on hydraulic fault diagnosis expert system of 25MN rapid forging machine[D].Xi’an:Xi’an University of Architectural Science and Technology,2015.
[4]BODROV V V,BAGAUTDINOV R M,GOIDO M E,et al.Modernization of the hydraulic system of an 8-MN radial forging machine[J].Metallurgist,2002,46(11):392-395.
[5]曹凤才,岳凤英.基于BP神经网络的液压系统故障诊断研究[J].中北大学学报(自然科学版),2010,31(6):596-599.CAO Fengcai,YUE Fengying.Fault diagnosis of hydraulic system based on BP neural network[J].Journal of North University of China(Natural science edition),2010,31(6):596-599.
[6]张乃禄,王伟,李伟强,等.钛及钛合金真空自耗熔炼爆炸预警系统研制[J].钛工业进展,2018,35(2):42-45.ZHANG Nailu,WANG Wei,LI Weiqiang,et al.Research on explosion early-warning system for titanium and titanium alloys vacuum consumption melting[J].Titanium industry progress,2018,35(2):42-45.
[7]颜瑾,张乃禄,张钰哲,等.基于物联网制造企业电能综合监控系统[J].现代电子技术,2016,39(16):159-162.YAN Jin,ZHANG Nailu,ZHANG Yuzhe,et al.IoT-based electric energy integrated monitoring system for manufacturing enterprise[J].Modern electronics technique,2016,39(16):159-162.
[8]郭文行,陈柏金,胡彦兵.快锻液压机远程监测与故障诊断系统构建[J].机械科学与技术,2015,34(5):748-751.GUO Wenxing,CHEN Baijin,HU Yanbing.Remote monitoring and construction of fault diagnosis system for rapid forging hydraulic press[J].Mechanical science and technology for aerospace engineering,2015,34(5):748-751.
[9]刘保杰,杨清文,吴翔,等.基于神经网络与改进证据理论融合的故障诊断方法[J].火炮发射与控制学报,2017,38(4):92-97.LIU Baojie,YANG Qingwen,WU Xiang,et al.Fault diagnosis method based on the fusion of neural network and improved evidence theory[J].Journal of gun launch&control,2017,38(4):92-97.
[10]梁华.基于模糊神经网络的凝汽器真空故障诊断方法[J].仪器仪表用户,2015,22(4):72-76.LIANG Hua.Condenser vacuum fault diagnosis method based on fuzzy neural network[J].Instrumentation customer,2015,22(4):72-76.
[2]刘涛,朱达荣,汪方斌,等.物联网环境下的大型立磨状态监测及损伤预警系统模型[J].机械设计与制造,2017(10):168-170.LIU Tao,ZHU Darong,WANG Fangbin,et al.Large vertical mill condition monitoring and damage early warning system model under Internet of Things environment[J].Machinery design&manufacture,2017(10):168-170.
[3]李文伟.25MN快锻机液压故障诊断专家系统研究[D].西安:西安建筑科技大学,2015.LI Wenwei.Research on hydraulic fault diagnosis expert system of 25MN rapid forging machine[D].Xi’an:Xi’an University of Architectural Science and Technology,2015.
[4]BODROV V V,BAGAUTDINOV R M,GOIDO M E,et al.Modernization of the hydraulic system of an 8-MN radial forging machine[J].Metallurgist,2002,46(11):392-395.
[5]曹凤才,岳凤英.基于BP神经网络的液压系统故障诊断研究[J].中北大学学报(自然科学版),2010,31(6):596-599.CAO Fengcai,YUE Fengying.Fault diagnosis of hydraulic system based on BP neural network[J].Journal of North University of China(Natural science edition),2010,31(6):596-599.
[6]张乃禄,王伟,李伟强,等.钛及钛合金真空自耗熔炼爆炸预警系统研制[J].钛工业进展,2018,35(2):42-45.ZHANG Nailu,WANG Wei,LI Weiqiang,et al.Research on explosion early-warning system for titanium and titanium alloys vacuum consumption melting[J].Titanium industry progress,2018,35(2):42-45.
[7]颜瑾,张乃禄,张钰哲,等.基于物联网制造企业电能综合监控系统[J].现代电子技术,2016,39(16):159-162.YAN Jin,ZHANG Nailu,ZHANG Yuzhe,et al.IoT-based electric energy integrated monitoring system for manufacturing enterprise[J].Modern electronics technique,2016,39(16):159-162.
[8]郭文行,陈柏金,胡彦兵.快锻液压机远程监测与故障诊断系统构建[J].机械科学与技术,2015,34(5):748-751.GUO Wenxing,CHEN Baijin,HU Yanbing.Remote monitoring and construction of fault diagnosis system for rapid forging hydraulic press[J].Mechanical science and technology for aerospace engineering,2015,34(5):748-751.
[9]刘保杰,杨清文,吴翔,等.基于神经网络与改进证据理论融合的故障诊断方法[J].火炮发射与控制学报,2017,38(4):92-97.LIU Baojie,YANG Qingwen,WU Xiang,et al.Fault diagnosis method based on the fusion of neural network and improved evidence theory[J].Journal of gun launch&control,2017,38(4):92-97.
[10]梁华.基于模糊神经网络的凝汽器真空故障诊断方法[J].仪器仪表用户,2015,22(4):72-76.LIANG Hua.Condenser vacuum fault diagnosis method based on fuzzy neural network[J].Instrumentation customer,2015,22(4):72-76.