毛清华;赵健博;李亚周;马宏伟;薛旭升;

• 1:西安科技大学机械工程学院
• 2:西安科技大学陕西省矿山机电装备智能监测重点实验室
• 3:陕西榆林能源集团郭家滩矿业有限公司

摘要(Abstract)：

采煤机是煤矿综采工作面的关键设备,由于煤层结构复杂,导致截割载荷复杂多变,并且截割载荷难以直接测量。因此,针对采煤机截割载荷难以直接检测难题,研究了采煤机交流异步电机的机械特性,提出了基于软测量建模技术的截割载荷预测方法。首先,通过分析采煤机交流异步电机的机械特性,得出截割载荷与截割电机的转速、电流符合非线性关系,运用软测量建模方法可以预测截割载荷。然后,以截割电机的转速和电流作为输入变量,运用ELM神经网络的软测量建模方法建立采煤机截割载荷软测量模型。最后,运用ELM,BP,RBF3种神经网络软测量建模方法对采煤机电机载荷进行预测,以均方误差和相关系数作为预测评价指标,结果表明:ELM神经网络软测量建模方法在预测精度和预测速度方面都优于BP神经网络和RBF神经网络软测量建模方法。运用ELM神经网络软测量建模方法能够准确、快速预测采煤机截割载荷,为采煤机恒功率截割和牵引智能调速提供了理论基础。

关键词(KeyWords)： 采煤机;截割载荷;软测量建模;ELM

Abstract:

Keywords:

基金项目(Foundation): 陕西省科技厅陕煤联合基金面上项目(2019JLM-39);; 煤矿机电设备智能检测与控制创新团队(2018TD-032)

作者(Author): 毛清华;赵健博;李亚周;马宏伟;薛旭升;

Email:

DOI: 10.13800/j.cnki.xakjdxxb.2020.0503

参考文献(References)：

• [1] 周元华,马宏伟,吴海燕.基于RBF神经网络的采煤机姿态预测控制[J].煤矿机械,2014,35(9):43-45.ZHOU Yuan-hua,MA Hong-wei,WU Hai-yan.Predictive control of shearer vertical steering system based on RBF neural network[J].Coal Mining Machinery,2014,35(9):43-45.
• [2] 刘丹丹,赵灿,汤春瑞.基于磁流变阀的采煤机恒功率控制应用[J].煤炭学报,2009,34(7):988-992.LIU Dan-dan,ZHAO Can,TANG Chun-rui.Application of constant power control of shearer based on magneto-rheological valve[J].Journal of China Coal Society,2009,34(7):988-992.
• [3] 葛帅帅,秦大同,胡明辉.突变工况下滚筒式采煤机调速控制策略研究[J].煤炭学报,2015,40(11):2569-2578.GE Shuai-shuai,QIN Da-tong,HU Ming-hui.Research on drum shearer speed control strategies under impact conditions[J].Journal of China Coal Society,2015,40(11):2569-2578.
• [4] 张梦奇,郝建生,马健康,等.锥形截齿旋转破岩截割力预测方法试验研究[J].煤炭科学技术,2015,43(12):98-103.ZHANG Meng-qi,HAO Jian-sheng,MA Jian-kang,et al.Experimental study on rock cutting force by rotational moving for coal mining equipment conical pick[J].Coal Science and Technology,2015,43(12):98-103.
• [5] 马香明.基于煤岩截割阻抗预知的采煤机滚筒运动参数控制策略研究[D].重庆:重庆大学,2016.MA Xiang-ming.Research on control strategy of shearer drum kinematical parameters based on the prediction of coal and rock[D].Chongqing:Chongqing University,2016.
• [6] XU Z P.Characteric analysis of current spectrum of shearer cutting load[J].Journal of Theoretical and Applied Information Technology,2013,50(3):595-600.
• [7] 郭卫,张武刚,赵栓峰,等.不同工况下采煤机滚筒截割阻力矩的仿真[J].煤矿机械,2014,35(4):54-56.GUO Wei,ZHANG Wu-gang,ZHAO Shuan-feng,et al.Resistant-torque simulation of miner cutting drum under different working conditions[J].Coal Mine Machinery,2014,35(4):54-56.
• [8] 李强,毛君,张明玉,等.采煤机截齿三向力测试方案设计及实验研究[J].工程设计学报,2016,23(5):506-512.LI Qiang,MAO Jun,ZHANG Ming-yu,et al.Three-axis force testing scheme design and experimental study of shearer cutter[J].Journal of Engineering Design,2016,23(5):506-512.
• [9] 王育龙.基于电流信号的煤岩识别方法研究[D].西安:西安科技大学,2012.WANG Yu-long.Research on coal-rock recognition method based on current signal[D].Xi’an:Xi’an University of Science and Technology,2012.
• [10] 刘春生,李德根,任春平.基于熵权的正则化神经网络煤岩截割载荷谱预测模型[J].煤炭学报,2020,45(1):474-483.LIU Chun-sheng,LI De-gen,REN Chun-ping.Regularized neural network load spectrum prediction model of coal-rock cutting based on entropy weight[J].Journal of China Coal Society,2020,45(1):474-483.
• [11] 曹鹏飞,罗雄麟.化工过程软测量建模方法研究进展[J].化工学报,2013,64(3):788-800.CAO Peng-fei,LUO Xiong-lin.Modeling of soft sensor for chemical process[J].Journal of Chemical Industry and Engineering,2013,64(3):788-800.
• [12] 傅永峰.软测量建模方法研究及其工业应用[D].杭州:浙江大学,2007.FU Yong-feng.Studys on soft sensor modeling methods and their applications in industry[D].Hangzhou:Zhejiang University,2007.
• [13] 贺敏,支恩玮,程兰,等.基于多工况迁移学习的磨机负荷参数软测量[J].控制工程,2019,26(11):1994-1999.HE Min,ZHI En-wei,CHENG Lan,et al.Soft sensor of ball mill load parameters based on multi-mode transfer learning[J].Control Engineering,2019,26(11):1994-1999.
• [14] 邱禹,刘乙奇,吴菁,等.基于深层神经网络的多输出自适应软测量建模[J].化工学报,2018,69(7):3101-3113.QIU Yu,LIU Yi-qi,WU Jing,et al.A self-adaptive multi-output soft sensor modeling based on deep neural network[J].Journal of Chemical Industry and Engineering,2018,69(7):3101-3113.
• [15] 丁华,常琦,杨兆建,等.基于极限学习机的采煤机功率预测算法研究[J].煤炭学报,2016,41(3):794-800.DING Hua,CHANG Qi,YANG Zhao-jian,et al.Research on the algorithm of shearer power prediction based on extreme learning machine[J].Journal of China Coal Society,2016,41(3):794-800.
• [16] 马勇,黄德先,金以慧.基于支持向量机的软测量建模方法[J].信息与控制,2004,33(4):34-38.MA Yong,HUANG De-xian,JIN Yi-hui.Soft-sensor modeling method based on support vector machine[J].Information and control,2004,33(4):34-38.
• [17] 耿洁.采煤机高效截割的自适应调速研究[D].徐州:中国矿业大学,2017.GENG Jie.Research on self-adaptive speed regulation principle for high efficiency cutting of shearer[D].Xuzhou:China University of Mining and Technology,2017.
• [18] DENG W Y,BAI Z,HUANG G B,et al.A fast SVD-hidden-nodes based extreme learning machine for large-scale data analytics[J].Neural Networks,2016,77(1):14-28.
• [19] 高彩云,高宁.改进极限学习机的不同类型滑坡位移预测[J].西安科技大学学报,2018,38(4):683-689.GAO Cai-yun,GAO Ning.Various types of landslide displacement prediction based on improved extreme learning machine[J].Journal of Xi’an University of Science and Technology,2018,38(4):683-689.
• [20] 苏涛,潘红光,黄向东,等.基于改进PSO-SVM的燃煤电厂烟气含氧量软测量[J].西安科技大学学报,2020,40(2):342-348.SU Tao,PAN Hong-guang,HUANG Xiang-dong,et al.Soft sensor of flue oxygen content based on improved PSO-SVM in coal-fired power plant[J].Journal of Xi’an University of Science and Technology,2020,40(2):342-348.