Abstract:In view of the practical engineering problem that the load cannot be obtained directly and effectively due to the adverse working conditions of the crawler travel system of coal mining robot, a method of vibration signal load identification based on genetic neural network is proposed. A genetic algorithm optimized BP(back propagation) neural network load identification model was constructed. The road test method was used to collect 5 sets of vibration acceleration data and a single set of stress load data of the crawler travel system. Discussed the influence of road roughness frequency and driving wheel meshing frequency on the vibration and stress load of crawler travel system. Used fast Fourier transform to denoise the original stress load data. According to the ride comfort index of the crawler travel system, the sym8 wavelet function was used to extract the five-layer feature of the vibration acceleration signal to improve the accuracy of load identification. Then 5 groups of wavelet transform decomposed acceleration data and filtered stress load data were used as the input and output of the GA-BP neural network for training and verification, revealing the relationship between vibration and stress load in the moving process of the crawler travel system. The results show that road roughness frequency, meshing frequency, and rotating frequency are the main frequency components of crawler vibration, the vibration frequency caused by road roughness is 13.765 Hz, the meshing frequency of the driving wheel is 68.25 Hz, and the rotating frequency is 3.25 Hz. After many tests, the best hidden layer neurons number of BP neural network is 63. The stress load identified by the GA-BP neural network is highly consistent with the expected stress load, and the relative error is 4.5%, which verifies the effectiveness of the method. It provides a good theoretical basis for the reliability research of the crawler travel system of coal mine machinery.
张志宏,张宏,陈有,李直,李国华,付政. 基于遗传神经网络的履带行驶系统载荷识别方法[J]. 振动与冲击, 2022, 41(3): 54-61.
ZHANG Zhihong, ZHANG Hong, CHEN You, LI Zhi, LI Guohua, FU Zheng. Load identification method of track driving system based on genetic neural network. JOURNAL OF VIBRATION AND SHOCK, 2022, 41(3): 54-61.
[1] 张宏,康鹏,宋扬,等. 滑动式履带行走系统动力学建模方法与试验[J]. 振动.测试与诊断,2015(01):70-75+188.
ZHANG Hong, KANG Peng, SONG Yang, et al. Dynamic modeling method and experiment of sliding track walking system[J]. Vibration, Measurement and Diagnosis, 2015, 35(1): 70–75.
[2] 张宏,张晓鹍,石涛. 连采机履带行走机构动力学特性与疲劳寿命分析[J]. 煤炭科学技术,2016,44(11):110-115.
ZHANG Hong,ZHANG Xiaokun,SHI Tao. Analysis on dynamics features and fatigue life of crawler walking mechanism applied in continuous miner[J]. Coal Science and Technology, 2016,44(11): 110-115.
[3] 马星国,潘仕卫,尤小梅,等. 履带行驶系统数学模型及张紧力计算[J]. 振动与冲击,2014,33(03):186-190.
MA Xingguo,PAN Shiwei,YOU Xiaomei, et al. Mathema -tical models for a caterpillar driving system and its tension calculation[J]. Journal of Vibration and Shock, 2014,33(03):186-190.
[4] 袁永伟,弋景刚,吴红雷,等. 多功能农用底盘结构设计及关键技术研究[J]. 江苏农业科学,2017,45(13):173-176.
YUAN Yongwei,YI Jinggang,WU Honglei,et al. Research on structure design and key technology of multifunctional agricultural chassis[J]. Jiangsu Agricultural Sciences, 2017, 45(13):173-176.
[5] 金守峰. 连续采煤机履带销磨损的数值预测研究[J]. 中国机械工程,2010,21(22):2714-2716+2754.
JIN Shoufeng. Research on Wear Simulation of Track Pin of Continuous Miner[J]. China Mechanical Engineering, 2010,21(22): 2714-2716+2754.
[6] 姚继权,李晓豁,朱宇,等. 纵轴式掘进机履带行走系统张紧力仿真研究[J]. 矿山机械,2012,40(06):18-21.
YAO Jiquan,LI Xiaohuo,ZHU Yu,et al. Simulation study on tension of track walking system in longitudinal roadheader[J]. Mining & Processing Equipment, 2012, 40(06):18-21.
[7] 王锦红,林勇,李海林. 基于Recurdyn履带式海底行走机构不同工况性能分析[J]. 机械传动,2017,41(05):45-52.
Wang Jinhong,Lin Yong,Li Hailin. Performance Analysis of the Tracked Traveling Mechanism in Deep Sea Bed Under Different Operating Conditions based on Recurdyn[J]. Journal of Mechanical Transmission,2017, 41(05):45-52.
[8] Jiang D. Dynamic simulation of crawler excavator walking mechanism[J]. Acta Technica, 2017, 62(2): 255-264.
[9] 高伟,于开平,盖晓男. L∞范数拟合正则化方法在飞行器动态载荷识别中的应用[J].振动与冲击,2017,36(09): 101-107.
GAO Wei,YU Kaiping,GAI Xiaonan. Application of L∞ norm fitting regularization method in dynamic load identification of space-crafts[J]. Journal of Vibration and Shock, 2017,36(09): 101-107.
[10] 周玙,刘莉,周思达,等. 基于应变模态参数的结构瞬态载荷识别方法研究[J]. 振动与冲击,2019,38(06):199-205.
ZHOU Yu,LIU Li,ZHOU Sida, et al. Transient load identification of structural dynamic systems based on strain modal parameters[J]. Journal of Vibration and Shock, 2019,38(06): 199-205.
[11] 王能建,任春平,刘春生. 一种新型分数阶Tikhonov正则化载荷重构技术及应用[J]. 振动与冲击, 2019,38(06):121-126+158.
WANG Nengjian,REN Chunping,LIU Chunsheng. Novel fractional order Tikhonov regularization load reconstruction technique and its application[J]. Journal of Vibration and Shock,2019,38(06): 121-126+158.
[12] 张玉良,杨飞,岳洪浩,等. 基于频域法的星箭连接分离装置的冲击载荷识别[J]. 振动与冲击,2018,37(17):79-85.
ZHANG Yuliang,YANG Fei,YUE Honghao,et al. Impact load identification of connection-separation device between satellite and rocket with frequency domain method based on EEMD[J]. Journal of Vibration and Shock, 2018,37(17): 79-85.
[13] SUN Y, LUO L, CHEN K,et al. A time-domain method for load identification using moving weighted least square technique[J]. Computers & Structures, 2020, 234: 106254.
[14] WANG L, HAN X, XIE Y. A new conjugate gradient method for solving multi-source dynamic load identification problem[J]. International Journal of Mechanics and Materials in Design, 2013, 9(3): 191-197.
[15] KIM S J, LEE S K. Experimental identification for inverse problem of a mechanical system with a non-minimum phase based on singular value decomposition[J]. Journal of mechanical science and technology,2008,22(8): 1504-1509.
[16] 张猛,魏强,石焕成,等. 钢制闸门冰载荷识别与静强度分析[J]. 哈尔滨工程大学学报,2019,40(09):1543-1548.
ZHANG Meng,WEI Qiang,SHI Huancheng,et al. Ice load identification and static strength analysis of a steel gate[J]. Journal of Harbin Engineering University,2019,40(09): 1543-1548.
[17] ZHOU J M, DONG L, GUAN W,et al. Impact load identification of nonlinear structures using deep Recurrent Neural Network[J]. Mechanical Systems and Signal Processing, 2019, 133: 106292.
[18] MARANO G C, QUARANTA G, MONTI G. Modified genetic algorithm for the dynamic identification of structural systems using incomplete measurements[J]. Computer‐Aided Civil and Infrastructure Engineering, 2011, 26(2): 92-110.
[19] 安东诺夫. 履带行驶装置原理[M]. 魏宸官,译. 北京:国防工业出版社,1957.
[20] 金虎,楼文娟,陈勇. 基于自适应BP神经网络的桥梁结构荷载识别[J]. 浙江大学学报(工学版), 2005(10):138-144.
JIN Hu,LOU Wenjuan,CHEN Yong. Load identification for bridge structures based on self-adaptive BP neural networks[J]. Journal of Zhejiang University(Engineering Science) ,2005(10):138-144.
[21] LIU Z, LIU X, WANG K, et al. GA-BP Neural Network-Based Strain Prediction in Full-Scale Static Testing of Wind Turbine Blades[J]. Energies, 2019, 12(6): 1026.
[22] LI Z, FENG Z, CHU F. A load identification method based on wavelet multi-resolution analysis[J]. Journal of Sound and Vibration, 2014, 333(2): 381-391.
[23] 陈洪月,魏玉峰,毛君,等. 刨煤机刨刀截割载荷与刨头振动特性实验分析研究[J]. 振动与冲击,2020,39(19): 149-155.
CHEN Hongyue,WEI Yufeng,MAO Jun,et al. Tests for a coal planer knives’ cutting loads and its head’s vibration characteristics. Journal of Vibration and Shock,2020, 39(19): 149-155.
[24] 林慕义,张福生.车辆底盘构造与设计[M].北京:冶金工业出版社.2007.
[25] 翟文鹏,张小内,侯惠让,等. 基于小波能量矩的嗅觉脑电信号识别[J]. 生物医学工程学杂志, 2020,37(03): 399-404.
ZHAI Wenpeng,ZHANG Xiaonei,HOU Huirang, et al. Olfactory electroencephalogram signal recognition based on wavelet energy moment[J]. Journal of Biomedical Engineering,2020,37(03):399-404.
[26] 董长虹,高志,余啸海. MATLAB小波分析工具箱原理与应用[M]. 北京:国防工业出版社,2004.
[27] 周士栋,薛扬,马晓晶,等. 基于SCADA数据的风电机组关键载荷预测[J]. 农业工程学报,2018,34(02):219-225.
ZHOU Shidong,XUE Yang,MA Xiaojing,et al. Prediction of wind turbine key load based on SCADA data[J]. Transactions of the Chinese Society of Agricultural Engineering,2018,34(02): 219-225.