基于PSO−BP神经网络的临时支架支撑力自适应控制

田劼; 李阳; 张磊; 刘振

doi:10.13272/j.issn.1671-251x.2022100017

基于PSO−BP神经网络的临时支架支撑力自适应控制

doi: 10.13272/j.issn.1671-251x.2022100017

田劼^{1, 2,},
李阳^{1, 2},
张磊^{1, 2},
刘振^{1, 2}

1.
中国矿业大学(北京) 机电与信息工程学院, 北京　100083
2.
中国矿业大学(北京) 煤矿智能化与机器人创新应用应急管理部重点实验室, 北京　100083

基金项目: 国家自然科学基金面上项目（51774293）；中央高校基本科研业务−重点领域交叉创新项目（2022JCCXJD02）。

详细信息

作者简介:
田劼 (1982—)，女，山西太原人，教授，博士，主要研究方向为机器人化矿山综掘智能控制，E-mail：tianj@cumtb.edu.cn

中图分类号: TD355.4
计量
- 文章访问数: 190
- HTML全文浏览量: 50
- PDF下载量: 23
- 被引次数: 0
出版历程
- 收稿日期: 2022-10-10
- 修回日期: 2023-07-16
- 网络出版日期: 2023-08-03

Adaptive control of temporary support force based on PSO-BP neural network

TIAN Jie^{1, 2
,},
LI Yang^{1, 2},
ZHANG Lei^{1, 2},
LIU Zhen^{1, 2}

1.
School of Mechanical Electronic and Information Engineering, China University of Mining and Technology-Beijing, Beijing 100083, China
2.
Key Laboratory of Coal Mine Intelligence and Robot Innovative Application, Ministry of Emergency Management, China University of Mining and Technology-Beijing, Beijing 100083, China

摘要

摘要: 为了使临时支架的支撑力更好地与矿压相适应，提高支架的支护能力，以双联自移式临时支架为研究对象，提出了基于粒子群优化（PSO）−BP神经网络的临时支架支撑力自适应控制方法。利用PSO算法的全局搜索能力及快速收敛特性对BP神经网络的初始权值进行优化，提高BP神经网络的收敛速度；再通过优化后的BP神经网络实现PID参数在线自调整，构建PSO−BP神经网络优化PID控制器，使临时支架的支撑力更快速、准确地达到预定值，实现临时支架支撑力自适应控制，避免因支护力和顶板压力不匹配而对顶板造成破坏。用单位阶跃信号模拟临时支护支架的期望初撑力进行实验验证，结果表明，与BP神经网络优化PID控制器及传统PID控制器相比，PSO−BP神经网络优化PID控制器可以更快、更准确地达到预期的初撑力，调整时间仅为0.5 s且基本不存在超调。根据实际地质条件仿真模拟开挖支护过程中支架受到的顶板压力，研究3种控制器的支撑力自适应控制效果，结果表明，在PSO−BP神经网络优化PID控制器的控制下，系统误差仅为0.02 MPa，误差最小，控制效果最好。
- 综掘工作面 /
- 临时支护 /
- 支撑力自适应控制 /
- PSO−BP神经网络 /
- PID控制
Abstract: In order to make the temporary support force better adapt to the mine pressure and improve the support capacity of the support, taking the dual self-moving temporary support as the research object, an adaptive control method of temporary support force based on particle swarm optimization (PSO) - BP neural network is proposed. The initial weights of the BP neural network are optimized by using the global search capability and fast convergence features of the PSO algorithm to improve the rate of convergence of the BP neural network. Then, the optimized BP neural network is used to achieve online self-adjustment of PID parameters. The PSO-BP neural network is constructed to optimize the PID controller. This enables the temporary support force to reach the predetermined value more quickly and accurately, achieving adaptive control of the temporary support force. It avoids damage to the roof due to the mismatch between support force and roof pressure. The expected initial support force of the temporary support is simulated using unit step signals for experimental verification. The results show that compared with the BP neural network optimized PID controller and traditional PID controller, the PSO-BP neural network optimized PID controller can achieve the expected initial support force faster and more accurately. The adjustment time is only 0.5 s and there is almost no overshoot. Based on actual geological conditions, the roof pressure on the support during excavation support is simulated. The adaptive control effect of three controllers for support force is studied. The results show that under the control of the PSO-BP neural network optimized PID controller, the system error is only 0.02 MPa, with the smallest error and the best control effect.
- fully mechanized excavation working face /
- temporary support /
- adaptive control of support force /
- PSO-BP neural network /
- PID control

HTML全文

图 1 双联自移式临时支护支架结构

1—底座；2—支架护帮板；3—护帮板千斤顶；4—顶板千斤顶；5—上顶板；6—下顶板；7—液压支撑油缸；8—推移油缸。

Figure 1. Structure of dual self-moving temporary support

下载: 全尺寸图片幻灯片

图 2 临时支撑力控制系统结构

1—油箱；2—滤油器；3—电动机；4—液压泵；5—电液伺服阀；6—液压锁；7—油液压力传感器；8—支撑液压缸；9—溢流阀。

Figure 2. Structure of support force control system of temporary support

下载: 全尺寸图片幻灯片

图 3 临时支架支撑力控制系统原理

Figure 3. Principle of support force control system of temporary support

下载: 全尺寸图片幻灯片

图 4 临时支架支撑力控制系统性能曲线

Figure 4. Performance curves of support force control system of temporary support

下载: 全尺寸图片幻灯片

图 5 调整后系统Bode图

Figure 5. Bode diagram of the adjusted system

下载: 全尺寸图片幻灯片

图 6 BP神经网络结构

Figure 6. BP neural network structure

下载: 全尺寸图片幻灯片

图 7 初撑力响应曲线

Figure 7. Response curves of initial support force

下载: 全尺寸图片幻灯片

图 8 初撑力误差曲线

Figure 8. Error curves of initial support force

下载: 全尺寸图片幻灯片

图 9 巷道地质仿真模型

Figure 9. Roadway geological simulation models

下载: 全尺寸图片幻灯片

图 10 临时支架支撑力自适应控制曲线

Figure 10. Support force adaptive control curves of temporary support

下载: 全尺寸图片幻灯片

图 11 临时支架支撑力自适应控制误差曲线

Figure 11. Error curves of support force adaptive control of temporary support

下载: 全尺寸图片幻灯片

表 1 临时支架支撑力控制系统参数

Table 1. Parameters of support force control system of temporary support

参数	数值
液压缸内腔直径/mm	130
液压缸活塞杆外径/mm	80
k_q/(L∙min⁻¹∙m⁻¹)	27 000
k_ce/(L∙min⁻¹∙MPa⁻¹)	0.06
A_q/cm²	84.425
ω_n/Hz	502.4
ω_h/Hz	0.13
ω₀/Hz	842.5
ζ₀	0.15
k_v/(m∙A⁻¹)	0.056
ω_v/Hz	110
ζ_v	0.7
k_a/(A∙V⁻¹)	0.007
k_f/(V∙N⁻¹)	100

下载: 导出CSV

表 2 煤矿地质参数

Table 2. Coal mine geological parameters

顶底板名称	岩层名称	厚度/m	平均厚度/m
基本顶	砂岩	2.28~11.97	7.29
直接顶	泥岩	0.5~13.8	5.4
煤层	煤	0.66~3.24	3
直接底	泥岩	2.8	2.8
基本底	泥岩	4	4

下载: 导出CSV

表 3 各岩层力学参数

Table 3. Mechanical parameters of each rock layer

岩层名称	密度/ (kg·m⁻³)	体积模量/GPa	剪切模量/GPa	黏聚力/MPa	内摩擦角/(°)
砂岩	2650	6	3.6	3.0	35
泥岩	2550	5	2.3	1.2	28
煤	1650	4	2.5	1.0	24
砂质泥岩	2000	5	3.0	2.0	33

下载: 导出CSV

参考文献(21)

[1]	秦海忠,付玉凯,王涛. 深部复合顶板巷道变形破坏特征及支护技术[J]. 工矿自动化,2020,46(10):80-86. doi: 10.13272/j.issn.1671-251x.2020020009 QIN Haizhong,FU Yukai,WANG Tao. Deformation and failure characteristics and support technology of deep roadway with composite roof[J]. Industry and Mine Automation,2020,46(10):80-86. doi: 10.13272/j.issn.1671-251x.2020020009
[2]	朱俊福. 深部层状岩体巷道围岩松动圈形成机理及其工程应用研究[D]. 徐州: 中国矿业大学, 2021. ZHU Junfu. Study on the formation mechanism and its engineering application of broken rock zone in deep bedded rock mass[D]. Xuzhou: China University of Mining and Technology, 2021.
[3]	张铁军,李伟涛,尹松阳. 深部开采巷道掘进工作面受力特征及合理空顶距分析[J]. 煤炭科技,2022,43(5):50-53,57. ZHANG Tiejun,LI Weitao,YIN Songyang. Analysis of the stress characteristics and reasonable space between roadway and roof in deep mining[J]. Coal Science & Technology Magazine,2022,43(5):50-53,57.
[4]	郭文孝. 交叉迈步式快速掘进临时支护支架组的研究[J]. 煤矿机械,2014,35(12):187-189. doi: 10.13436/j.mkjx.201412079 GUO Wenxiao. Research on rapid excavation and temporary support of moving cross-type support group[J]. Coal Mine Machinery,2014,35(12):187-189. doi: 10.13436/j.mkjx.201412079
[5]	薛光辉,管健,程继杰,等. 深部综掘巷道超前支架设计与支护性能分析[J]. 煤炭科学技术,2018,46(12):15-20. doi: 10.13199/j.cnki.cst.2018.12.003 XUE Guanghui,GUAN Jian,CHENG Jijie,et al. Design of advance support for deep fully-mechanized heading roadway and its support performance analysis[J]. Coal Science and Technology,2018,46(12):15-20. doi: 10.13199/j.cnki.cst.2018.12.003
[6]	卢进南. 综掘巷道迈步式超前支护系统力学特性研究[D]. 阜新: 辽宁工程技术大学, 2014. LU Jinnan. Study on mechanical properties of stepping advance support system in fully mechanized roadway [D]. Fuxin: Liaoning University of Engineering and Technology, 2014.
[7]	王国法,庞义辉,李明忠,等. 超大采高工作面液压支架与围岩耦合作用关系[J]. 煤炭学报,2017,42(2):518-526. doi: 10.13225/j.cnki.jccs.2016.0699 WANG Guofa,PANG Yihui,LI Mingzhong,et al. Hydraulic support and coal wall coupling relationship in ultra large height mining face[J]. Journal of China Coal Society,2017,42(2):518-526. doi: 10.13225/j.cnki.jccs.2016.0699
[8]	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. doi: 10.16579/j.issn.1001.9669.2017.04.001 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. doi: 10.16579/j.issn.1001.9669.2017.04.001
[9]	胡相捧,刘新华,庞义辉,等. 基于BP神经网络PID的液压支架初撑力自适应控制[J]. 矿业科学学报,2020,5(6):662-671. doi: 10.19606/j.cnki.jmst.2020.06.009 HU Xiangpeng,LIU Xinhua,PANG Yihui,et al. Adaptive control of setting load of hydraulic support based on BP neural network PID[J]. Journal of Mining Science and Technology,2020,5(6):662-671. doi: 10.19606/j.cnki.jmst.2020.06.009
[10]	薛光辉,管健,柴敬轩,等. 基于神经网络PID综掘巷道超前支架支撑力自适应控制[J]. 煤炭学报,2019,44(11):3596-3603. doi: 10.13225/j.cnki.jccs.2018.1688 XUE Guanghui,GUAN Jian,CHAI Jingxuan,et al. Adaptive control of advance bracket support force in fully mechanized roadway based on neural network PID[J]. Journal of China Coal Society,2019,44(11):3596-3603. doi: 10.13225/j.cnki.jccs.2018.1688
[11]	姜磊,叶圣超,李飞龙. 基于PSO−BP神经网络的采煤机电动机故障诊断研究[J]. 矿山机械,2020,48(9):59-64. doi: 10.16816/j.cnki.ksjx.2020.09.012 JIANG Lei,YE Shengchao,LI Feilong. Research on fault diagnosis of shearer motor based on PSO-BP neural network[J]. Mining & Processing Equipment,2020,48(9):59-64. doi: 10.16816/j.cnki.ksjx.2020.09.012
[12]	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. CHEN Lan. Modeling and simulation of hydraulic support hydraulic system[D]. Xi'an: Xi'an University of Science and Technology, 2011.
[13]	冯玉芳,卢厚清,殷宏,等. 基于BP神经网络的故障诊断模型研究[J]. 计算机工程与应用,2019,55(6):24-30. FENG Yufang,LU Houqing,YIN Hong,et al. Study on fault diagnosis model based on BP neural network[J]. Computer Engineering and Applications,2019,55(6):24-30.
[14]	邵建浩,张婷. 基于BP神经网络的SCARA机器人故障诊断[J]. 机床与液压,2022,50(14):166-170. doi: 10.3969/j.issn.1001-3881.2022.14.030 SHAO Jianhao,ZHANG Ting. Fault diagnosis of SCARA robot based on BP neural network[J]. Machine Tool & Hydraulics,2022,50(14):166-170. doi: 10.3969/j.issn.1001-3881.2022.14.030
[15]	袁建平,施一萍,蒋宇,等. 改进的BP神经网络PID控制器在温室环境控制中的研究[J]. 电子测量技术,2019,42(4):19-24. doi: 10.19651/j.cnki.emt.1802034 YUAN Jianping,SHI Yiping,JIANG Yu,et al. Research on improved BP neural network PID controller in greenhouse environment control[J]. Electronic Measurement Technology,2019,42(4):19-24. doi: 10.19651/j.cnki.emt.1802034
[16]	谢宇希,颜拥军,李翔,等. 基于BP神经网络的核探测器故障诊断方法研究[J]. 原子能科学技术,2021,55(10):1857-1864. doi: 10.7538/yzk.2020.youxian.0716 XIE Yuxi,YAN Yongjun,LI Xiang,et al. Study of nuclear detector fault diagnosis method based on BP neural network[J]. Atomic Energy Science and Technology,2021,55(10):1857-1864. doi: 10.7538/yzk.2020.youxian.0716
[17]	XU Xianzhen, CAO Dan, ZHOU Yu, et al. Application of neural network algorithm in fault diagnosis of mechanical intelligence[J]. Mechanical Systems and Signal Processing, 2020, 141. DOI: 10.1016/j.ymssp.2020.106625.
[18]	WU Yanmin, SONG Qipeng. Improved particle swarm optimization algorithm in power system network reconfiguration[J]. Mathematical Problems in Engineering, 2021, 2021. DOI: 10.1155/2021/5574501.
[19]	田劼,银晓琦,文艺成. 基于混合IWO−PSO算法的掘进机截割轨迹规划方法[J]. 工矿自动化,2021,47(12):55-61. TIAN Jie,YIN Xiaoqi,WEN Yicheng. Method of cutting trajectory planning of roadheader based on hybrid IWO-PSO algorithm[J]. Industry and Mine Automation,2021,47(12):55-61.
[20]	施昕昕,费军. 基于PSO−BP的直线电机轨迹跟踪自抗扰控制器设计[J]. 组合机床与自动化加工技术,2023(6):132-135. doi: 10.13462/j.cnki.mmtamt.2023.06.030 SHI Xinxin,FEI Jun. Design of active disturbance rejection controller for linear motor trajectory tracking based on PSO-BP[J]. Modular Machine Tool & Automatic Manufacturing Technique,2023(6):132-135. doi: 10.13462/j.cnki.mmtamt.2023.06.030
[21]	KAHOULI O, ALSAIF H, BOUTERAA Y, et al. Power system reconfiguration in distribution network for improving reliability using genetic algorithm and particle swarm optimization[J]. Applied Sciences, 2021, 11（7）. DOI: 10.3390/app11073092.