基于BP神经网络的高速开关阀多级电压控制策略
|
摘要
为了提高液压系统控制精度,通过分析几种常用驱动策略下阀芯的动态特性以及进油口压力对动态特性的影响,提出了一种可适应进油口压力变化的多级电压激励驱动策略,与常用的双电压激励策略相比具有更好的动态特性,阀芯开启、关闭时间分别降至2. 2、1. 7 ms,线圈热功率降低了68. 5%。设计了一种通过PWM调制、可输出0～60 V之间任一电压的驱动电路。采用BP神经网络对PID参数进行整定,可实现液压缸位移的精确控制。在自适应电压激励与BP神经网络联合控制策略下,恒流量液压系统液压缸位移误差在-0. 3～0. 3 mm之间,变流量液压系统液压缸位移误差在-0. 5～0. 5 mm之间。
In order to improve the control precision of hydraulic system,the following two aspects were done. Firstly, in terms of driving strategy, the driving strategy was considered and the dynamic characteristics of the valve core under several common driving strategies were analyzed. After considering the following aspects, a multi-stage adaptive voltage excitation driving strategy was put forward accordingly. The strategy had better dynamic characteristics than the commonly used dual voltage excitation strategy. Under this multi-stage adaptive voltage excitation driving strategy,the valve core and the closing time were reduced to 2. 2 ms and 1. 7 ms,respectively. At the same time,the coil thermal power was reduced by 68. 5%. Moreover,a driving circuit which can output any voltage between 0 V and60 V through PWM modulation was designed. Secondly,in terms of control strategy,the BP neural network was used to adjust the PID parameters to achieve precise control of hydraulic cylinder displacement. The network PID controller of BP neural had the characteristics of short response time,small overshoot and good robustness and so on. Under the combined control of adaptive voltage excitation and BP neural network,the hydraulic cylinder displacement error of constant flow hydraulic system was controlled within-0. 3 ～ 0. 3 mm. Meanwhile,thanks to the combined control of adaptive voltage excitation and BP neural network,the hydraulic cylinder displacement error of variable flow hydraulic system was controlled within-0. 5 ～ 0. 5 mm. The research had a great promotion to the study of this field.
In order to improve the control precision of hydraulic system,the following two aspects were done. Firstly, in terms of driving strategy, the driving strategy was considered and the dynamic characteristics of the valve core under several common driving strategies were analyzed. After considering the following aspects, a multi-stage adaptive voltage excitation driving strategy was put forward accordingly. The strategy had better dynamic characteristics than the commonly used dual voltage excitation strategy. Under this multi-stage adaptive voltage excitation driving strategy,the valve core and the closing time were reduced to 2. 2 ms and 1. 7 ms,respectively. At the same time,the coil thermal power was reduced by 68. 5%. Moreover,a driving circuit which can output any voltage between 0 V and60 V through PWM modulation was designed. Secondly,in terms of control strategy,the BP neural network was used to adjust the PID parameters to achieve precise control of hydraulic cylinder displacement. The network PID controller of BP neural had the characteristics of short response time,small overshoot and good robustness and so on. Under the combined control of adaptive voltage excitation and BP neural network,the hydraulic cylinder displacement error of constant flow hydraulic system was controlled within-0. 3 ～ 0. 3 mm. Meanwhile,thanks to the combined control of adaptive voltage excitation and BP neural network,the hydraulic cylinder displacement error of variable flow hydraulic system was controlled within-0. 5 ～ 0. 5 mm. The research had a great promotion to the study of this field.
引文
[1]GIOUSOUF M,KOVACS G.Dielectric elastomer actuators used for pneumatic valve technology[J].Smart Materials and Structures,2013,22(10):104-110.
[2]KONG Xiaowu,LI Shizhen.Dynamic performance of high speed solenoid valve with parallel coils[J].Chinese Journal of Mechanical Engineering,2014,27(4):816-821.
[3]TU H,RANNOW M B,WANG M,et al.Modeling and validation of a high speed rotary PWM on/off valve[C]∥Proceeding of the ASME Dynamic Systems and Control Conference,2009:629-636.
[4]苏明.电磁高速开关阀控制特性方法研究[D].贵阳:贵州大学,2010.SU Ming.Study on control characteristics and method of high speed on/off solenoid valve[D].Guiyang:Guizhou University,2010.(in Chinese)
[5]黄卫春,苏利杰.PWM高速开关阀驱动电路仿真设计[J].制造业自动化,2010,32(6):168-171.HUANG Weichun,SU Lijie.Simulation design of driver circuit for the PWM high speed on-off valve[J].Manufacturing Automation,2010,32(6):168-171.(in Chinese)
[6]LIU Yugang,SU Ming.Design of switch valve control system to adapt the pressure of the fuel supply port[J].Application of Electronic Technique,2012,38(10):65-67.
[7]詹仲强,余金,郭志,等.基于自组织映射的改进BP神经网络短期光伏出力预测研究[J].四川电力技术,2018,41(2):24-28,67.ZHAN Zhongqiang,YU Jin,GUO Zhi,et al.Study on prediction of short-term photovoltaic output power with improved BPneural network based on self-organizing mapping[J].Sichuan Electric Power Technology,2018,41(2):24-28,67.(in Chinese)
[8]LAJUNEN A.Evaluation of energy storage system requirements for hybrid mining loader[C]∥IEEE Computer Society,Chicago,USA,2011.
[9]SUN Hui,JING Junqing.Research on the system configuration and energy control strategy for parallel hydraulic hybrid loader[J].Automation in Construction,2010,19(2):213-220.
[10]HUANG Li,HUANG Jian,WANG Wei.The sustainable development assessment of reservoir resettlement based on a BPneural network[J].International Journal of Environmental Research&Public Health,2018,15(1):146-152.
[11]向忠,陶国良,谢建蔚,等.气动高速开关阀动态压力特性仿真与试验研究[J].浙江大学学报(工学版),2008,42(5):845-849.XIANG Zhong,TAO Guoliang,XIE Jianwei,et al.Simulation and experimental investigation on pressure dynamics of pneumatic high-speed on/off valve[J].Journal of Zhejiang University(Engineering Science),2008,42(5):845-849(in Chinese)
[12]孔晓武.高速开关阀动态性能试验装置及其应用研究[J].机电工程,2005,22(8):41-43.KONG Xiaowu.Dynamic performance test device for high speed on/off valve and its application[J].Journal of Mechanical&Electrical Engineering,2005,22(8):41-43.(in Chinese)
[13]高钦和,刘志浩,牛海龙,等.高速开关阀控液压缸的位置控制[J].中国机械工程,2014,25(20):2775-2781.GAO Qinhe,LIU Zhihao,NIU Hailong,et al.Position control of high speed on-off valve controlled hydraulic cylinder[J].China Mechanical Engineering,2014,25(20):2775-2781.(in Chinese)
[14]贺娟,袁颂岳.基于DSP的高速开关阀控液压缸位置控制系统研究[J].中国机械工程,2010,21(24):2929-2931.HE Juan,YUAN Songyue.High speed on/off valve hydraulic position control system based on DSP[J].China Mechanical Engineering,2010,21(24):2929-2931.(in Chinese)
[15]易继锴,候媛彬.智能控制技术[M].北京:北京工业大学出版社,2007.
[16]赵泽昆,韩晓娟,马会萌.基于BP神经网络的储能电池衰减容量预测[J].电器与能效管理技术,2016(19):68-72.ZHAO Zekun,HAN Xiaojuan,MA Huimeng.Capacity fade prediction model of battery energy storage system based on BPneural network[J].Electrical&Energy Management Technology,2016(19):68-72.(in Chinese)
[17]张珂斐,郭江,聂德鑫,等.基于化学反应优化神经网络与融合DGA算法的油浸式变压器模型研究[J].高电压技术,2016,42(4):1275-1281.ZHANG Kefei,GUO Jiang,NIE Dexin,et al.Diagnosis model for transformer fault based on CRO-BP neural network and fusion DGA method[J].High Voltage Engineering,2016,42(4):1275-1281.(in Chinese)
[18]李明生,叶进,谢斌,等.双泵合流系统电-液联控合流阀设计与试验[J/OL].农业机械学报,2018,49(9):353-360.LI Mingsheng,YE Jin,XIE Bin,et al.Design and test of electric hydraulic confluence valve in double pump confluence system[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2018,49(9):353-360.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20180941&flag=1.DOI:10.6041/j.issn.1000-1298.2018.09.041.(in Chinese)
[19]RADER T.Method and device for driving a solenoid valve:USA,6504699BI[P].2003-07-01.
[20]王新,候风艳.基于改进的PSO-BP神经网络的无刷直流电机控制[J].电子测量技术,2017,40(2):10-14.WANG Xin,HOU Fengyan.Control of brushless DC motor based on improved PSO-BP neural network[J].Electronic Measurement Technology,2017,40(2):10-14.(in Chinese)
[21]陈龙,朱斌,孙晓东,等.基于模型预测控制的多电机驱动系统能量最优分配策略[J/OL].农业机械学报,2018,49(10):403-409.CHEN Long,ZHU Bin,SUN Xiaodong,et al.Optimal allocation strategy for multi-motor drive system based on model predictive control[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2018,49(10):403-409.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20181047&flag=1.DOI:10.6041/j.issn.1000-1298.2018.10.047.(in Chinese)
[22]王权,李军,戴立.基于BP神经网络的电动伺服加载算法研究[J].工业仪表与自动化装置,2017(2):8-13.WANG Quan,LI Jun,DAI Li.Research on electric servo loading algorithm based on BP neural network[J].Industrial Instrumentation&Automation,2017(2):8-13.(in Chinese)
[23]孙成伟,初亮,郭建华,等.电磁阀阶梯减压控制方法[J/OL].农业机械学报,2017,48(12):380-385.SUN Chengwei,CHU Liang,GUO Jianhua,et al.Stepped decompression control method of solenoid valve[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2017,48(12):380-385.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20171247&flag=1.DOI:10.6041/j.issn.1000-1298.2017.12.047.(in Chinese)
[2]KONG Xiaowu,LI Shizhen.Dynamic performance of high speed solenoid valve with parallel coils[J].Chinese Journal of Mechanical Engineering,2014,27(4):816-821.
[3]TU H,RANNOW M B,WANG M,et al.Modeling and validation of a high speed rotary PWM on/off valve[C]∥Proceeding of the ASME Dynamic Systems and Control Conference,2009:629-636.
[4]苏明.电磁高速开关阀控制特性方法研究[D].贵阳:贵州大学,2010.SU Ming.Study on control characteristics and method of high speed on/off solenoid valve[D].Guiyang:Guizhou University,2010.(in Chinese)
[5]黄卫春,苏利杰.PWM高速开关阀驱动电路仿真设计[J].制造业自动化,2010,32(6):168-171.HUANG Weichun,SU Lijie.Simulation design of driver circuit for the PWM high speed on-off valve[J].Manufacturing Automation,2010,32(6):168-171.(in Chinese)
[6]LIU Yugang,SU Ming.Design of switch valve control system to adapt the pressure of the fuel supply port[J].Application of Electronic Technique,2012,38(10):65-67.
[7]詹仲强,余金,郭志,等.基于自组织映射的改进BP神经网络短期光伏出力预测研究[J].四川电力技术,2018,41(2):24-28,67.ZHAN Zhongqiang,YU Jin,GUO Zhi,et al.Study on prediction of short-term photovoltaic output power with improved BPneural network based on self-organizing mapping[J].Sichuan Electric Power Technology,2018,41(2):24-28,67.(in Chinese)
[8]LAJUNEN A.Evaluation of energy storage system requirements for hybrid mining loader[C]∥IEEE Computer Society,Chicago,USA,2011.
[9]SUN Hui,JING Junqing.Research on the system configuration and energy control strategy for parallel hydraulic hybrid loader[J].Automation in Construction,2010,19(2):213-220.
[10]HUANG Li,HUANG Jian,WANG Wei.The sustainable development assessment of reservoir resettlement based on a BPneural network[J].International Journal of Environmental Research&Public Health,2018,15(1):146-152.
[11]向忠,陶国良,谢建蔚,等.气动高速开关阀动态压力特性仿真与试验研究[J].浙江大学学报(工学版),2008,42(5):845-849.XIANG Zhong,TAO Guoliang,XIE Jianwei,et al.Simulation and experimental investigation on pressure dynamics of pneumatic high-speed on/off valve[J].Journal of Zhejiang University(Engineering Science),2008,42(5):845-849(in Chinese)
[12]孔晓武.高速开关阀动态性能试验装置及其应用研究[J].机电工程,2005,22(8):41-43.KONG Xiaowu.Dynamic performance test device for high speed on/off valve and its application[J].Journal of Mechanical&Electrical Engineering,2005,22(8):41-43.(in Chinese)
[13]高钦和,刘志浩,牛海龙,等.高速开关阀控液压缸的位置控制[J].中国机械工程,2014,25(20):2775-2781.GAO Qinhe,LIU Zhihao,NIU Hailong,et al.Position control of high speed on-off valve controlled hydraulic cylinder[J].China Mechanical Engineering,2014,25(20):2775-2781.(in Chinese)
[14]贺娟,袁颂岳.基于DSP的高速开关阀控液压缸位置控制系统研究[J].中国机械工程,2010,21(24):2929-2931.HE Juan,YUAN Songyue.High speed on/off valve hydraulic position control system based on DSP[J].China Mechanical Engineering,2010,21(24):2929-2931.(in Chinese)
[15]易继锴,候媛彬.智能控制技术[M].北京:北京工业大学出版社,2007.
[16]赵泽昆,韩晓娟,马会萌.基于BP神经网络的储能电池衰减容量预测[J].电器与能效管理技术,2016(19):68-72.ZHAO Zekun,HAN Xiaojuan,MA Huimeng.Capacity fade prediction model of battery energy storage system based on BPneural network[J].Electrical&Energy Management Technology,2016(19):68-72.(in Chinese)
[17]张珂斐,郭江,聂德鑫,等.基于化学反应优化神经网络与融合DGA算法的油浸式变压器模型研究[J].高电压技术,2016,42(4):1275-1281.ZHANG Kefei,GUO Jiang,NIE Dexin,et al.Diagnosis model for transformer fault based on CRO-BP neural network and fusion DGA method[J].High Voltage Engineering,2016,42(4):1275-1281.(in Chinese)
[18]李明生,叶进,谢斌,等.双泵合流系统电-液联控合流阀设计与试验[J/OL].农业机械学报,2018,49(9):353-360.LI Mingsheng,YE Jin,XIE Bin,et al.Design and test of electric hydraulic confluence valve in double pump confluence system[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2018,49(9):353-360.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20180941&flag=1.DOI:10.6041/j.issn.1000-1298.2018.09.041.(in Chinese)
[19]RADER T.Method and device for driving a solenoid valve:USA,6504699BI[P].2003-07-01.
[20]王新,候风艳.基于改进的PSO-BP神经网络的无刷直流电机控制[J].电子测量技术,2017,40(2):10-14.WANG Xin,HOU Fengyan.Control of brushless DC motor based on improved PSO-BP neural network[J].Electronic Measurement Technology,2017,40(2):10-14.(in Chinese)
[21]陈龙,朱斌,孙晓东,等.基于模型预测控制的多电机驱动系统能量最优分配策略[J/OL].农业机械学报,2018,49(10):403-409.CHEN Long,ZHU Bin,SUN Xiaodong,et al.Optimal allocation strategy for multi-motor drive system based on model predictive control[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2018,49(10):403-409.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20181047&flag=1.DOI:10.6041/j.issn.1000-1298.2018.10.047.(in Chinese)
[22]王权,李军,戴立.基于BP神经网络的电动伺服加载算法研究[J].工业仪表与自动化装置,2017(2):8-13.WANG Quan,LI Jun,DAI Li.Research on electric servo loading algorithm based on BP neural network[J].Industrial Instrumentation&Automation,2017(2):8-13.(in Chinese)
[23]孙成伟,初亮,郭建华,等.电磁阀阶梯减压控制方法[J/OL].农业机械学报,2017,48(12):380-385.SUN Chengwei,CHU Liang,GUO Jianhua,et al.Stepped decompression control method of solenoid valve[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2017,48(12):380-385.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20171247&flag=1.DOI:10.6041/j.issn.1000-1298.2017.12.047.(in Chinese)