基于LSTM-RF的电动钻机绞车齿轮箱故障诊断

刘光星1, 2, 马一豪1

振动与冲击 ›› 2024, Vol. 43 ›› Issue (21) : 156-162.

PDF(2145 KB)
PDF(2145 KB)
振动与冲击 ›› 2024, Vol. 43 ›› Issue (21) : 156-162.
论文

基于LSTM-RF的电动钻机绞车齿轮箱故障诊断

  • 刘光星1,2,马一豪1
作者信息 +

Fault diagnosis of electric drill winch gearbox based on LSTM-RF

  • LIU Guangxing1,2, MA Yihao2
Author information +
文章历史 +

摘要

针对提高石油电动钻机绞车齿轮箱故障诊断的准确性和效率,提出了一种基于长短期记忆网络(long short-term memory,LSTM)和随机森林(random forest,RF)融合模型。首先,运用LSTM能够从大规模数据中学习复杂特征,将这些特征作为随机森林的输入,然后通过随机森林处理非线性和高维数据以及对特征的分类,以实现对齿轮不同故障状态的识别。最后,利用电动钻机绞车齿轮箱运行过程中的实时数据,建立了一个包含多种齿轮故障类型的综合数据集。实验结果表明,LSTM齿轮故障诊断准确率为94.67%,RF齿轮故障诊断准确率为94.34%,支持向量机齿轮故障诊断准确率为82.00%,K近邻齿轮故障诊断准确率88.33%,而融合模型LSTM-RF在齿轮故障诊断准确率方面达到了98.33%,克服了单一模型的局限性,提高了诊断准确性,研究表明了融合模型具有更优的电动钻机绞车齿轮箱故障诊断能力。

Abstract

To improve the accuracy and efficiency of fault diagnosis in the gearbox of petroleum electric drill winches, a fusion model based on Long Short-Term Memory (LSTM) and Random Forest (RF) is proposed. Firstly, LSTM is employed to learn complex features from large-scale data, using these features as input to the Random Forest. The Random Forest then processes nonlinear and high-dimensional data, classifying features to identify different gear fault states. Finally, a comprehensive dataset containing various gear fault types is established using real-time data from the operation of electric drill winch gearboxes. Experimental results show that the diagnosis accuracy of LSTM for gear faults is 94.67%, RF achieves a diagnosis accuracy of 94.34%, Support Vector Machine (SVM) reaches 82.00%, and KNN achieves a diagnosis accuracy of 88.33%. In contrast, the fusion model LSTM-RF achieves a gear fault diagnosis accuracy of 98.33%, overcoming the limitations of individual models, and improving diagnostic accuracy. The research demonstrates that the fusion model exhibits superior fault diagnosis capabilities for the gearbox of electric drill winches. 

关键词

电动钻机 / 齿轮箱 / 故障诊断 / 长短期记忆预测 / 随机森林算法 /

Key words

Electric drill winch / Gearbox / Fault diagnosis / Long Short-Term Memory / Random Forest algorithm.

引用本文

导出引用
刘光星1, 2, 马一豪1. 基于LSTM-RF的电动钻机绞车齿轮箱故障诊断[J]. 振动与冲击, 2024, 43(21): 156-162
LIU Guangxing1, 2, MA Yihao2. Fault diagnosis of electric drill winch gearbox based on LSTM-RF[J]. Journal of Vibration and Shock, 2024, 43(21): 156-162

参考文献

[1] 张幼振,刘若君,姚克等.煤矿坑道钻机状态监测与故障诊断技术研究现状及展望[J].科学技术与工程,2023,23(07):2683-2693.
Zhang Youzhen, Liu Ruojun, Yao Ke, etc. Current Status and Prospect of Coal Mine Roadway Drilling Rig State Monitoring and Fault Diagnosis Technology [J]. Science Technology and Engineering, 2023, 23(07): 2683-2693.
[2] 田亮,袁存波.基于LSTM和证据理论的引风机轴承故障诊断[J].动力工程学报,2023,43(05):614-621.
Tian Liang, Yuan Cunbo. Fault Diagnosis of Fan Bearings Based on LSTM and Evidence Theory [J]. Journal of Power Engineering, 2023, 43(05): 614-621.
[3] 张硕,田慕琴,霍鹏飞等.基于一维卷积神经网络的定向钻机故障诊断专家系统设计[J].煤炭技术,2023,42(06):221-224. 
Zhang Shuo, Tian Muqin, Huo Pengfei, et al. Design of Directional Drilling Rig Fault Diagnosis Expert System Based on One-Dimensional Convolutional Neural Network [J]. Coal Technology, 2023, 42(06): 221-224.
[4] 李兆奎,田慕琴,宋建成.基于故障树的定向钻机故障诊断专家系统设计[J].现代电子技术,2022,45(22):121-125.
Li Zhaokui, Tian Muqin, Song Jiancheng. Design of Expert System for Fault Diagnosis of Directional Drilling Rig Based on Fault Tree [J]. Modern Electronic Technology, 2022, 45(22): 121-125.
[5] Huang, T., Zhang, Q., Tang, X. et al. A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systems. Artificial Intelligence Review,55, 1289–1315 (2022). 
[6] 游达章,陶加涛,许文俊等.基于CNN-RF的嵌入式数控系统故障诊断研究[J].机床与液压,2022,50(19):167-172. 
You Dazhang, Tao Jiatao, Xu Wenjun, et al. Research on Fault Diagnosis of Embedded Numerical Control System Based on CNN-RF [J]. Machine Tool & Hydraulics, 2022, 50(19): 167-172.
[7] 汪军, 颜世铛, 郝建旭, 闫团刚, 杨勇. 石油钻采装备齿轮箱技术发展现状及分析[J]. 机械设计, 2022, 39 (S1): 89-92.
Wang Jun, Yan Shichang, Hao Jianxu, Yan Tuangang, Yang Yong. Current Status and Analysis of Technical Development of Gearboxes for Petroleum Drilling and Production Equipment [J]. Mechanical Design, 2022, 39 (S1): 89-92.
[8] Xiao B ,Miao S ,Xia D , et al.Detecting the backfill pipelineblockage and leakage through an LSTM-based deep learning model[J].International Journal of Minerals,Metallurgy and Materials,2023,30(08):1573-1583.
[9] Alex Sherstinsky.Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network[J]. Physica D: Nonlinear Phenomena,2020.
[10] 闫鹏程,张孝飞,尚松行等.LIF结合LSTM神经网络的矿井水源识别[J].光谱学与光谱分析,2022,42(10):3091-3096.
Yan Pengcheng, Zhang Xiaofei, Shang Songxing, et al. Identification of Mine Water Sources Using LIF Combined with LSTM Neural Network [J]. Spectroscopy and Spectral Analysis, 2022, 42(10): 3091-3096.
[11] 姚鹏飞,涂亚楠,王瑞红.基于随机森林算法拖拉机齿轮箱故障诊断研究[J].农机化研究,2022,46(03):246-251.
Yao Pengfei, Tu Yanan, Wang Ruihong. Research on Fault Diagnosis of Tractor Gearbox Based on Random Forest Algorithm [J]. Journal of Agricultural Mechanization Research, 2022, 46(03): 246-251.
[12] 葛阳, 郭兰中, 牛曙光, 窦岩. 基于t-SNE和LSTM的旋转机械剩余寿命预测[J]. 振动与冲击, 2020, 39 (07): 223-231+273.
Ge Yang, Guo Lanzhong, Niu Shuguang, Dou Yan. Remaining Life Prediction of Rotating Machinery Based on t-SNE and LSTM [J]. Journal of Vibration and Shock, 2020, 39 (07): 223-231+273.
[13] 王进花,周德义,曹洁等.基于多特征融合与RF的球磨机滚动轴承故障诊断[J/OL].北京航空航天大学学报:1-19[2023-08-07].
Wang Jinhua, Zhou Deyi, Cao Jie, et al. Fault Diagnosis of Ball Mill Rolling Bearings Based on Multi-feature Fusion and RF [J/OL]. Journal of Beijing University of Aeronautics and Astronautics: 1-19 [2023-08-07].
[14] 张月平,田伟华,刘艳红.柱塞泵滑靴磨损信号随机森林算法故障诊断[J/OL].[2023-07-24](2023-12-06). https://doi.org/10.19356/j.cnki.1001-3997.20230724.031.
[15] 贾哲宇,温华兵,朱军超等.基于随机森林方法的柴油机涡轮增压器故障诊断[J].舰船科学技术,2023,45(06):109-113.
Jia Zheyu, Wen Huabing, Zhu Junchao, et al. Fault Diagnosis of Diesel Engine Turbocharger Based on Random Forest Method [J]. Ship Science and Technology, 2023, 45(06): 109-113.
[16] Lei Y ,ShaoBo L ,ChuanJiang L , et al.Data-driven unsupervised anomaly detection and recovery of unmanned aerial vehicle flight data based on spatiotemporal correlation[J].Science China(TechnologicalSciences),2023,66(05):1304-1316.
[17] 林涛,张达,王建君.改进LSTM-RF算法的传感器故障诊断与数据重构研究[J].计算机工程与科学,2021,43(05):845-852.
Lin Tao, Zhang Da, Wang Jianjun. Research on Sensor Fault Diagnosis and Data Reconstruction with Improved LSTM-RF Algorithm [J]. Computer Engineering and Science, 2021, 43(05): 845-852.
[18] Yulin Shen, Benoît Mercatoris, Zhen Cao, Paul Kwan, Leifeng Guo, Hongxun Yao, Qian Cheng.Improving Wheat Yield Prediction Accuracy Using LSTM-RF Framework Based on UAV Thermal Infrared and Multispectral Imagery[J].Agriculture ( IF 2.072 ) PubDate : 2022-06-20.

PDF(2145 KB)

161

Accesses

0

Citation

Detail

段落导航
相关文章

/