Attitude monitoring method for hydraulic support in fully mechanized working face based on PSO-ELM
-
摘要: 针对基于惯性测量单元的液压支架姿态解算方法会产生累计误差、校正结果不准确的问题，提出一种基于粒子群优化（PSO）−极限学习机（ELM）的综采工作面液压支架姿态监测方法。以液压支架顶梁俯仰角为监测对象，采用倾角传感器和陀螺仪采集液压支架顶梁支护姿态实时信息，对采集到的数据进行预处理，将处理后的数据输入PSO−ELM误差补偿模型中，得到解算误差预测值；同时通过卡尔曼滤波融合进行液压支架姿态解算，得到解算值；再用误差预测值对解算值进行误差补偿，从而求得更加准确的顶梁支护姿态数据。该方法只考虑加速度和角速度数据与解算误差的关系，不依赖具体的物理模型，可有效降低姿态解算累计误差。实验结果表明：液压支架顶梁俯仰角平均绝对误差由补偿前的1.420 8°减少到0.058 0°，且误差曲线具有良好的收敛性，验证了所提方法可持续稳定地监测液压支架的支护姿态。Abstract: In response to the problems of cumulative errors and inaccurate correction results in the attitude calculation method of hydraulic supports based on inertial measurement units, a fully mechanized working face hydraulic support attitude monitoring method based on particle swarm optimization (PSO) - extreme learning machine (ELM) is proposed. Using the pitch angle of the hydraulic support top beam as the monitoring object, a tilt sensor and gyroscope are used to collect real-time information on the support attitude of the hydraulic support top beam. The collected data is preprocessed and input into the PSO-ELM error compensation model to obtain the predicted solution error. At the same time, the hydraulic support attitude is calculated through Kalman filtering fusion to obtain the calculated value. Then the method uses the error prediction value to compensate for the error in the calculated value, in order to obtain more accurate data on the top beam support attitude. This method only considers the relationship between acceleration and angular velocity data and solution errors, without relying on specific physical models. It can effectively reduce the cumulative error of attitude solution. The experimental results show that the average absolute error of the pitch angle of the top beam of the hydraulic support has been reduced from 1.420 8° before compensation to 0.058 0°. The error curve has good convergence, verifying that the proposed method can sustainably and stably monitor the support attitude of the hydraulic support.
-
图 2 基于PSO−ELM的综采工作面液压支架姿态监测方法原理
Figure 2. Attitude monitoring method principle for hydraulic support in fully mechanized mining face based on particle swarm optimization and extreme learning machin(PSO-ELM)
图 3 ELM误差预测模型结构
Figure 3. Structure of extreme learning machine(ELM) error prediction model
图 5 顶梁俯仰角解算前后误差对比
Figure 5. Comparison of errors before and after calculating the pitch angle of the top beam
图 7 液压支架姿态监测实验平台
Figure 7. Hydraulic support attitude monitoring experimental platform
表 1 不同模型的仿真结果
Table 1. Simulation results of different models
模型 MAE/（°） RMSE/（°） 卡尔曼滤波 0.094 2 0.121 0 自适应卡尔曼滤波 0.060 8 0.075 9 PSO−ELM误差补偿 0.030 5 0.038 3 
下载: 导出CSV
表 2 不同模型的实验结果
Table 2. Experimental results of different models
模型 MAE/（°） RMSE/（°） 卡尔曼滤波 1.420 8 1.867 7 自适应卡尔曼滤波 0.475 3 0.624 7 PSO−ELM误差补偿 0.058 0 0.082 1
下载: 导出CSV
-
[1] 王国法,范京道,徐亚军,等. 煤炭智能化开采关键技术创新进展与展望[J]. 工矿自动化,2018,44(2):5-12.WANG Guofa,FAN Jingdao,XU Yajun,et al. Innovation progress and prospect on key technologies of intelligent coal mining[J]. Industry and Mine Automation,2018,44(2):5-12. [2] 王国法,杜毅博,徐亚军,等. 中国煤炭开采技术及装备50年发展与创新实践——纪念《煤炭科学技术》创刊50周年[J]. 煤炭科学技术,2023,51(1):1-18.WANG Guofa,DU Yibo,XU Yajun,et al. Development and innovation practice of China coal mining technology and equipment for 50 years:commemorate the 50th anniversary of the publication of Coal Science and Technology[J]. Coal Science and Technology,2023,51(1):1-18. [3] 马旭东,许春雨,宋建成. 综采工作面液压支架姿态监测系统设计[J]. 煤炭技术,2019,38(7):174-177.MA Xudong,XU Chunyu,SONG Jiancheng. Design of attitude monitoring system for hydraulic support in fully mechanized face[J]. Coal Technology,2019,38(7):174-177. [4] 杨崇浩,白国长. 基于数字孪生的液压支架姿态监测[J]. 机床与液压,2023,51(22):39-44. doi: 10.3969/j.issn.1001-3881.2023.22.007YANG Chonghao,BAI Guochang. Attitude monitoring of hydraulic support based on digital twin[J]. Machine Tool & Hydraulics,2023,51(22):39-44. doi: 10.3969/j.issn.1001-3881.2023.22.007 [5] 杨金衡,宋单阳,田慕琴,等. 基于自适应卡尔曼滤波的双惯导采煤机定位方法[J]. 工矿自动化,2021,47(7):14-20,28.YANG Jinheng,SONG Danyang,TIAN Muqin,et al. Double inertial navigation shearer positioning method based on adaptive Kalman filter[J]. Industry and Mine Automation,2021,47(7):14-20,28. [6] 王勇,刘文江,胡军,等. 多传感器检测系统的自适应融合算法[J]. 西安电子科技大学学报(自然科学版),2004,31(3):483-487. doi: 10.3969/j.issn.1001-2400.2004.03.035WANG Yong,LIU Wenjiang,HU Jun,et al. The adaptive fusion algorithm in multiple-sensors detecion system[J]. Journal of Xidian University,2004,31(3):483-487. doi: 10.3969/j.issn.1001-2400.2004.03.035 [7] 银桥. 基于多传感器信息融合的运动系统姿态解算方法研究[D]. 桂林:桂林电子科技大学,2022.YIN Qiao. Research on attitude calculation method of motion system based on multi-sensor information fusion[D]. Guilin:Guilin University of Electronic Technology,2022. [8] 张坤,孙政贤,刘亚,等. 基于信息融合技术的超前液压支架姿态感知方法及实验验证[J]. 煤炭学报,2023,48(增刊1):345-356.ZHANG Kun,SUN Zhengxian,LIU Ya,et al. Advanced hydraulic support posture perception method based on information fusion technology and experimental verification[J]. Journal of China Coal Society,2023,48(S1):345-356. [9] 张坤. 基于信息融合技术的液压支架姿态监测方法研究[D]. 太原:太原理工大学,2018.ZHANG Kun. Research on attitude monitoring method of hydraulic support based on information fusion technology[D]. Taiyuan:Taiyuan University of Technology,2018. [10] 司垒,王忠宾,王浩,等. 基于惯性传感组件和BP神经网络的防冲钻孔机器人钻具姿态解算[J]. 仪器仪表学报,2022,43(4):213-223.SI Lei,WANG Zhongbin,WANG Hao,et al. Drilling tool attitude calculation of drilling robot for rockburst prevention based on inertial sensing assembly and BP neural network[J]. Chinese Journal of Scientific Instrument,2022,43(4):213-223. [11] 徐西华. 液压支架姿态监测关键技术研究[D]. 徐州:中国矿业大学,2018.XU Xihua. Research on key technologies of hydraulic support posture monitoring[D]. Xuzhou:China University of Mining and Technology,2018. [12] 袁祥. 液压支架位姿-负载耦合特性分析及感知基础研究[D]. 太原:太原理工大学,2022.YUAN Xiang. Analysis of position-attitude- load coupling characteristics of hydraulic support and basic research on perception[D]. Taiyuan:Taiyuan University of Technology,2022. [13] 王忠乐. 液压支架姿态监测及控制技术[J]. 工矿自动化,2022,48(增刊2):116-117,137.WANG Zhongle. Posture monitoring and control technology of fully mechanized hydraulic support[J]. Journal of Mine Automation,2022,48(S2):116-117,137. [14] 陈冬方,李首滨. 基于液压支架倾角的采煤高度测量方法[J]. 煤炭学报,2016,41(3):788-793.CHEN Dongfang,LI Shoubin. Measurement of coal mining height based on hydraulic support structural angle[J]. Journal of China Coal Society,2016,41(3):788-793. [15] 彭道刚,段睿杰,王丹豪. 两级融合的多传感器数据融合算法研究[J]. 仪表技术与传感器,2024(1):87-93. doi: 10.3969/j.issn.1002-1841.2024.01.016PENG Daogang,DUAN Ruijie,WANG Danhao. Research on multi-sensor data fusion algorithm based on two-level fusion[J]. Instrument Technique and Sensor,2024(1):87-93. doi: 10.3969/j.issn.1002-1841.2024.01.016 [16] 孙君令. 姿态数据驱动的液压支架运动状态监测技术研究[D]. 徐州:中国矿业大学,2019.SUN Junling. Research on monitoring technology of hydraulic support motion state driven by attitude data[D]. Xuzhou:China University of Mining and Technology,2019. [17] 王忠宾,司垒,王浩,等. 基于空间阵列式惯性单元的防冲钻孔机器人位姿解算方法[J]. 煤炭学报,2022,47(1):598-610.WANG Zhongbin,SI Lei,WANG Hao,et al. Position and attitude calculation method of anti-impact drilling robot based on spatial array inertial units[J]. Journal of China Coal Society,2022,47(1):598-610. [18] 常钰坤,曹港生,马振九,等. 基于PSO−LSTM模型的上肢动作识别方法[J/OL]. 华东理工大学学报(自然科学版):1-11[2024-06-20]. https://doi.org/10.14135/j.cnki.1006-3080.20231009001.CHANG Yukun,CAO Gangsheng,MA Zhenjiu,et al. Upper limb motion recognition method based on PSO-LSTM model[J]. Journal of East China University of Science and Technology (Natural Science Edition):1-11[2024-06-20]. https://doi.org/10.14135/j.cnki.1006-3080.20231009001. [19] 于海洋. 在线预测的极限学习机方法研究[D]. 长春:吉林大学,2019.YU Haiyang. Research on extreme learning machine method for online prediction[D]. Changchun:Jilin University,2019. [20] 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.LI Haifeng. Kinematics analysis of support position and posture of hydraulic support based on BP neural network[J]. Coal Engineering,2018,50(9):117-120. [21] 寇发荣,杨天祥,罗希,等. 基于ISSA−ELM算法的锂电池SOC估计 [J/OL]. 电源学报:1-8[2024-06-20]. http://kns.cnki.net/kcms/detail/12.1420.TM.20240229.1408.005.html.KOU Farong,YANG Tianxiang,LUO Xi,et al. Lithium battery SOC estimation based on ISSA-ELM algorithm[J/OL]. Journal of Power Supply:1-8[2024-06-20]. http://kns.cnki.net/kcms/detail/12.1420.TM.20240229.1408.005.html. -
点击查看大图
图(9) / 表(2)
计量
- 文章访问数: 121
- HTML全文浏览量: 32
- PDF下载量: 9
- 被引次数: 0
