Adaptive control of setting load of hydraulic support based on BP neural network PID
-
摘要: 液压支架初撑力对顶板的控制具有重要作用,采用三位四通手动操纵阀的开环控制或两位三通电磁换向阀的先导控制,很难使初撑力达到设定值并保持稳定,即使达到设定值也存在压力降和波动现象。基于此,建立了立柱电液力控制系统数学模型,利用MATLAB分析了系统的稳定性,得到系统的Pole-Zero图右半S平面不存在开环零点和极点,系统为最小相位系统;Nyquist图逆时针绕(-1,j0)的圈数为0,系统相位裕度为941°,幅值裕度为107 dB,系统稳定;阶跃响应115 s趋于稳定,脉冲响应90 s趋于稳定。提出了基于BP神经网络的PID初撑力自适应控制方法,并建立了三层神经网络控制模型,误差控制采用二次型性能指标;采用有监督的Hebb学习规则和梯度下降法对输出层和隐含层的权值系数进行更新,经训练得到PID控制器的三个控制参数。仿真结果表明:期望输入为阶跃信号时,立柱达到初撑力并稳定需要约885 s,期望输入为方波信号时,立柱达到初撑力并稳定需要约91 s,相比没有采用BP神经网络PID控制,其响应时间提高了约13倍。Abstract: The setting load of hydraulic support plays an important role in the roofcontrolThere are two methods to control the setting load of hydraulic support,one is openloop control by manual control valve of three position four port,the other is pilot control by solenoid directional control valve of two position three portHowever,these two methods can hardly make the setting load reach the expected value and remain stableEven when the expected value is reached,pressure drop and fluctuation generally existBased on this,a mathematical model of electrohydraulic force control system is established,then the stability of the system is analyzed by using MATLABIt is obtained that there are no openloop zeros and poles in the right half S plane of the PoleZero diagram of the system,so the system is a minimum phase system;the number of cycles of counterclockwise winding(-1,j0) from the Nyquist diagram is 0,and the system phase margin is 941° and the amplitude margin is 107 dB,so the system is stable;the step response is stable for 115 s,the impulse response is stable for 90 sAn adaptive PID control method based on BP Neural Network is proposed,and a threelayer neural network control model is establishedQuadratic performance index is used to control errorThe weight coefficients of the output and hidden layers are updated by using supervised Hebb learning rules and gradient descent algorithmThen three control parameters of the PID controller are obtained by trainingThe simulation results show that:it takes about 885 s for the setting load to reach the expected value and maintain stability when the expected input is step signal,and 91 s when the expected input is the square wave signalCompared with no BP neural network PID control,the response time is increased by about 13 times.
-
Key words:
- hydraulic support /
- leg /
- setting load /
- Neural Network /
- selfadaption
-
[1] 钱鸣高,石平五,许家林矿山压力与岩层控制[M]. 徐州:中国矿业大学出版社,2010:157 [2] 刘强,苏学贵,郝佩,等基于大采高综采支架工况的煤壁片帮控制研究[J]. 矿业研究与开发,2018,38(11):61-65 [3] Liu Qiang,Su Xuegui,Hao Pei,et al. Study on the control of rib fall of coal wall based on the working state of large mining hydraulic support[J]. Mining Research and Development,2018,38(11):61-65 [4] 刘闯,李化敏,张群磊大采高液压支架初撑力与额定工作阻力合理比值研究[J]. 采矿与安全工程学报,2018,35(4):725-733 [5] Liu Chuang,Li Huamin,Zhang QunleiResearch on reasonable ratio of setting load and yield load of shield in large mining height coal mine [J]. Journal of Mining & Safety Engineering,2018,35(4):725-733 [6] 薛光辉,程继杰,管健,等深部综掘巷道机器人化超前支护方案与最佳支护时机研究[J]. 矿业科学学报,2019,4(4):349-356 [7] Xue Guanghui,Cheng Jijie,Guan Jian,et al. Robotized advance support scheme and optimum support opportunity for deep fully mechanized roadway[J]. Journal of Mining Science and Technology,2019,4(4):349-356 [8] 邱常青提高放顶煤工作面液压支架初撑力的研究[J]. 煤,2018,27(2):75-76 [9] Qiu ChangqingStudy on improving the initial support force of hydraulic support in caving face[J]. Coal,2018,27(2):75-76 [10] 曹连民,郭震,仲崇涛,等液压支架初撑力手动增压装置设计与应用[J]. 工矿自动化,2017,43(6):10-14 [11] Cao Lianmin,Guo Zhen,Zhong Chongtao,et al. Design and application of manual pressurization device for initial support force of hydraulic support[J]. Industry and Mine Automation,2017,43(6):10-14 [12] 何勇,郭一楠,巩敦卫液压支护平台的异步自抗扰平衡控制[J]. 控制理论与应用,2019,36(1):151-163 [13] He Yong,Guo Yinan,Gong DunweiAsynchronous active disturbance rejection balance control for hydraulic support platforms[J]. Control Theory and Applications,2019,36(1):151-163 [14] 栾丽君,赵慧萌,谢苗,等超前支架速度、压力稳定切换控制策略研究[J]. 机械强度,2017,39(4):747-753 [15] Luan Lijun,Zhao Huimeng,Xie Miao,et al. Research on speed and pressure control strategy of stable switch about forepoling equipment[J]. Journal of Mechanical Strength,2017,39(4):747-753 [16] Cao Lianmin,Sun Shijiao,Zhang Yazhu,et al. The research on characteristics of hydraulic support advancing control system in coal mining face[J]. Wireless Personal Communications,2018,102(4):2667-2680 [17] 李明,封航,张延顺基于UMAC的RBF神经网络PID控制[J]. 北京航空航天大学学报,2018,44(10):2063-2070 [18] Li Ming,Feng Hang,Zhang YanshunRBF neural network tuning PID control based on UMAC[J]. Journal of Beijing University of Aeronautics and Astronautics,2018,44(10):2063-2070 [19] 乔俊飞,张力,李文静基于尖峰自组织模糊神经网络的需水量预测[J]. 控制与决策,2018,33(12):2197-2202 [20] Qiao Junfei,Zhang Li,Li WenjingPrediction of water demand based on spiking selforganizing fuzzy neural network[J]. Control and Decision,2018,33(12):2197-2202 [21] 杨小彬,王逍遥,周世禄,等基于改进广义回归神经网络的工作面低氧预测模型研究[J]. 矿业科学学报,2019,4(5):434-440 [22] Yang Xiaobin,Wang Xiaoyao,Zhou Shilu,et al. Prediction model of working face hypoxia based on improved generalized regression neural network[J]. Journal of Mining Science and Technology,2019,4(5):434-440 [23] 赵红泽,王宇新,李淋,等基于灰色关联分析与GA-BP神经网络的拉斗铲生产能力预测[J]. 矿业科学学报,2020,5(1):58-66 [24] Zhao Hongze,Wang Yuxin,Li Lin,et al. Production capacity prediction of dragline based on grey correlation analysis and GA-BP neural network[J]. Journal of Mining Science and Technology,2020,5(1):58-66 [25] 李海锋基于BP神经网络的液压支架支护位姿运动学分析[J]. 煤炭工程,2018,50(9):117-120 [26] Li HaifengKinematics analysis of support position and posture of hydraulic support based on BP neural network[J]. Coal Engineering,2018,50(9):117-120 [27] 王邦祥,陆金桂,王京涛,等神经网络近似模型在液压支架顶梁轻量化设计中的应用[J]. 轻工学报,2018,33(2):87-94 [28] Wang Bangxiang,Lu Jingui,Wang Jingtao,et al. Application of neural network approximate model in lightweight design of hydraulic support top beam[J]. Journal of Light Industry,2018,33(2):87-94 [29] 丁飞,金鑫,王春华,等小样本事件下液压支架可靠性评估[J]. 煤炭科学技术,2016,44(11):116-120 [30] Ding Fei,Jin Xin,Wang Chunhua,et al. Evaluation on reliability of hydraulic powered support under small sample event[J]. Coal Science and Technology,2016,44(11):116-120 [31] 王磊,曾庆良,万丽荣,等液压支架立柱控制系统建模与仿真研究[J]. 煤矿机械,2009,30(4):51-53 [32] Wang Lei,Zeng Qingliang,Wan Lirong,et al. Modelling and simulation on prop controlling system of hydraulic support[J]. Coal Mine Machinery,2009,30(4):51-53 [33] 丁少华,贾春强液压支架立柱系统动态压力仿真分析[J]. 煤矿机械,2014,35(2):68-70 [34] Ding Shaohua,Jia ChunqiangDynamic pressure simulation analysis of hydraulic support column system[J]. Coal Mine Machinery,2014,35(2):68-70 [35] 王相亭液压支架液压系统建模及仿真分析[J]. 液压气动与密封,2014,34(2):58-60 [36] Wang XiangtingModeling and simulation of hydraulic system for hydraulic support[J]. Hydraulics Pneumatics & Seals,2014,34(2):58-60 [37] 陈兰液压支架液压系统的建模与仿真[D]. 西安:西安科技大学,2011 [38] 王春行液压控制系统[M]. 北京:机械工业出版社,1999:134-139 [39] 常同立液压控制系统[M]. 北京:清华大学出版社,2014:224-229 [40] 赵雄鹏,李永堂,仉志强,等综采面支架液压系统的压力损失研究[J]. 煤矿机械,2017,38(6):51-53 [41] Zhao Xiongpeng,Li Yongtang,Zhang Zhiqiang,et al. Study on pressure loss of hydraulic support system in fully mechanized face[J]. Coal Mine Machinery,2017,38(6):51-53 [42] 丛爽面向MATLAB工具箱的神经网络理论与应用[M]. 合肥:中国科学技术大学出版社,2009:63-101 [43] [25]刘金琨先进PID控制MATLAB仿真[M]. 北京:电子工业出版社,2016:311-328
点击查看大图
计量
- 文章访问数: 389
- HTML全文浏览量: 93
- PDF下载量: 69
- 被引次数: 0