基于LSTM−Adam的刮板输送机链传动系统故障预警方法

李博; 郭星燃; 李娟莉; 王学文; 夏蕊

doi:10.13272/j.issn.1671-251x.18086

基于LSTM−Adam的刮板输送机链传动系统故障预警方法

doi: 10.13272/j.issn.1671-251x.18086

李博^{1, 2,},
郭星燃^{1, 2},
李娟莉^{1, 2, ,},
王学文^{1, 2},
夏蕊¹

1.
太原理工大学机械与运载工程学院，山西太原　030024
2.
煤矿综采装备山西省重点实验室，山西太原　030024

基金项目: 国家自然科学基金项目（52204149）；山西省科技重大专项计划“揭榜计划”项目（202101020101021）；山西省基础研究计划项目（202103021223080）；山西省研究生实践创新项目（2023SJ052）；太原理工大学校基金项目（2022QN006）。

详细信息

作者简介:
李博（1988—），男，山西太原人，副教授，博士，研究方向为煤机装备结构与性能优化，E-mail：libo@tyut.edu.cn

通讯作者:
李娟莉（1979—），女，山西寿阳人，教授，博士，研究方向为煤机装备故障诊断，E-mail： lijuanli@tyut.edu.cn。

中图分类号: TD528/634
计量
- 文章访问数: 850
- HTML全文浏览量: 79
- PDF下载量: 42
- 被引次数: 0
出版历程
- 收稿日期: 2023-03-15
- 修回日期: 2023-09-24
- 网络出版日期: 2023-09-28

A fault warning method for scraper conveyor chain transmission system based on LSTM-Adam

LI Bo^{1, 2
,},
GUO Xingran^{1, 2},
LI Juanli^{1, 2
, ,},
WANG Xuewen^{1, 2},
XIA Rui¹

1.
College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan 030024, China
2.
Shanxi Key Laboratory of Fully Mechanized Coal Mining Equipment, Taiyuan 030024, China

摘要

摘要: 刮板输送机链传动系统由于承受复杂载荷作用导致故障频发，然而传统的故障诊断需要大量的先验知识和主观干预，对技术人员要求高。为实现刮板输送机链传动系统故障预警的自主性、准确性与高效性，利用深度学习强大的数据挖掘能力，提出了基于LSTM−Adam的刮板输送机链传动系统故障预警方法。首先，基于组态技术搭建刮板输送机工况监测系统，采集减速器输出轴转矩及转速、中部槽中板压力、刮板竖直方向振动加速度及刮板链运行方向应变等刮板输送机实时运行数据，并对数据进行清洗和min−max归一化处理，为故障预警提供数据支撑；然后，基于LSTM搭建预测模型，并采用Adam优化算法对其进行训练和优化，得到最优LSTM−Adam预测模型；最后，将刮板输送机实时运行数据导入LSTM−Adam预测模型，得到刮板输送机运行参数预测值，使用滑动加权平均法计算预测值与真实值之间的残差，并将正常运行工况下同类数据的最大残差作为预警阈值，当残差超过预警阈值时进行预警。试验结果表明：LSTM−Adam预测模型能够准确预测出刮板链应变数据的变化趋势，并对卡链与断链故障准确做出预警。
- 刮板输送机 /
- 链传动系统 /
- 故障预警 /
- LSTM /
- Adam /
- 滑动加权平均法
Abstract: The scraper conveyor chain transmission system is prone to frequent faults due to its complex load bearing capacity. However, traditional fault diagnosis requires a large amount of prior knowledge and subjective intervention, which requires high technical personnel. In order to achieve the autonomy, accuracy, and efficiency of fault warning for the scraper conveyor chain transmission system, a fault warning method for the scraper conveyor chain transmission system based on LSTM-Adam is proposed using the powerful data mining capability of deep learning. Firstly, a monitoring system for the working conditions of the scraper conveyor is built based on configuration technology. The system collects real-time operating data of the scraper conveyor, such as the torque and speed of the output shaft of the reducer, the pressure of the middle groove plate, the vibration acceleration in the vertical direction of the scraper, and the strain in the running direction of the scraper chain. The data is cleaned and normalized in min-max to provide data support for fault warning. Secondly, a prediction model is built based on LSTM and trained and optimized using the Adam optimization algorithm to obtain the optimal LSTM Adam prediction model. Finally, the real-time operating data of the scraper conveyor is imported into the LSTM-Adam prediction model to obtain the predicted values of the scraper conveyor operating parameters. The sliding weighted average method is used to calculate the residual between the predicted value and the true value. The maximum residual of the same type of data under normal operating conditions is used as the warning threshold. When the residual exceeds the warning threshold, an early warning is given. The experimental results show that the LSTM-Adam prediction model can accurately predict the trend of strain data of the scraper chain and provide accurate warnings for stuck chain and broken chain faults.
- scraper conveyor /
- chain transmission system /
- fault warning /
- LSTM /
- Adam /
- sliding weighted average method

HTML全文

图 1 基于LSTM−Adam的刮板输送机故障预警框架

Figure 1. Fault warning framework of scraper conveyor based on LSTM-Adam

下载: 全尺寸图片幻灯片

图 2 刮板输送机试验台

Figure 2. Test platform of scraper conveyor

下载: 全尺寸图片幻灯片

图 3 刮板输送机工况监测系统

Figure 3. Working condition monitoring system of scraper conveyor

下载: 全尺寸图片幻灯片

图 4 数据采集设备

Figure 4. Data acquisition equipment

下载: 全尺寸图片幻灯片

图 5 LSTM单元结构

Figure 5. LSTM unit structure

下载: 全尺寸图片幻灯片

图 6 LSTM−Adam预测模型建立流程

Figure 6. Build process of LSTM-Adam prediction model

下载: 全尺寸图片幻灯片

图 7 刮板链应变

Figure 7. Scraper chain strain

下载: 全尺寸图片幻灯片

图 8 预警判断流程

Figure 8. Warning judgment process

下载: 全尺寸图片幻灯片

图 9 正常运行工况下刮板链应变数据残差分析结果

Figure 9. Residual analysis results of scraper chain strain data under normal working condition

下载: 全尺寸图片幻灯片

图 10 卡链工况下的残差

Figure 10. Residual under stuck chain condition

下载: 全尺寸图片幻灯片

图 11 断链工况下的残差

Figure 11. Residual under broken chain condition

下载: 全尺寸图片幻灯片

表 1 不同模型节点数下的均方误差

Table 1. Mean square error under different model node numbers

模型节点数	32	64	128
均方误差	0.004 8	0.004 6	0.004 2

下载: 导出CSV

参考文献(21)

[1]	于林. 矿用重型刮板输送机断链故障监测传感器研究[J]. 煤炭学报,2011,36(11):1934-1937. YU Lin. Research on sensor used to detect chain-broken on armoured face conveyor[J]. Journal of China Coal Society,2011,36(11):1934-1937.
[2]	赵驭阳. 基于DAG−SVM的煤矿井下输送装置故障在线检测[J]. 机床与液压,2021,49(10):189-194. doi: 10.3969/j.issn.1001-3881.2021.10.038 ZHAO Yuyang. On-line fault detection of coal mine underground conveyor device based on DAG-SVM[J]. Machine Tool & Hydraulics,2021,49(10):189-194. doi: 10.3969/j.issn.1001-3881.2021.10.038
[3]	崔宏尧,刘敏智. 基于混沌差分进化FCM的刮板输送机故障诊断[J]. 煤矿机械,2020,41(10):172-174. CUI Hongyao,LIU Minzhi. Fault diagnosis of scraper conveyor based on chaotic differential evolution FCM[J]. Coal Mine Machinery,2020,41(10):172-174.
[4]	LIN Yi,WU Yuankai,GUO Dongyue,et al. A deep learning framework of autonomous pilot agent for air traffic controller training[J]. IEEE Transactions on Human-Machine Systems,2021,51(5):442-450. doi: 10.1109/THMS.2021.3102827
[5]	ZHU Xiaoxun,HANG Xinyu,GAO Xiaoxia,et al. Research on crack detection method of wind turbine blade based on a deep learning method[J]. Applied Energy,2022,328. DOI: 10.1016/j.apenergy.2022.120241.
[6]	WU Rui,LIU Chao,HAN Te,et al. A planetary gearbox fault diagnosis method based on time-series imaging feature fusion and a transformer model[J]. Measurement Science and Technology,2023,34(2). DOI: 10.1088/1361-6501/ac9e6c.
[7]	文成林,吕菲亚. 基于深度学习的故障诊断方法综述[J]. 电子与信息学报,2020,42(1):234-248. WEN Chenglin,LYU Feiya. Review on deep learning based fault diagnosis[J]. Journal of Electronics & Information Technology,2020,42(1):234-248.
[8]	任建亭,汤宝平,雍彬,等. 基于深度变分自编码网络融合SCADA数据的风电齿轮箱故障预警[J]. 太阳能学报,2021,42(4):403-408. REN Jianting,TANG Baoping,YONG Bin,et al. Wind turbine gearbox fault warning based on depth variational autoencoders network fusion SCADA data[J]. Acta Energiae Solaris Sinica,2021,42(4):403-408.
[9]	万安平,杨洁,王景霖,等. 基于深度学习的航空发动机齿轮故障诊断[J]. 振动. 测试与诊断,2022,42(6):1062-1067,1239. WAN Anping,YANG Jie,WANG Jinglin,et al. Fault diagnosis of aeroengine gear based on deep learning[J]. Journal of Vibration,Measurement & Diagnosis,2022,42(6):1062-1067,1239.
[10]	王学文,李素华,谢嘉成,等. 机器人运动学与时序预测融合驱动的刮板输送机调直方法[J]. 煤炭学报,2021,46(2):652-666. WANG Xuewen,LI Suhua,XIE Jiacheng,et al. Straightening method of scraper conveyor driven by robot kinematics and time series prediction[J]. Journal of China Coal Society,2021,46(2):652-666.
[11]	刘家瑞,杨国田,杨锡运. 基于深度卷积自编码器的风电机组故障预警方法研究[J]. 太阳能学报,2022,43(11):215-223. LIU Jiarui,YANG Guotian,YANG Xiyun. Research on wind turbine fault warning method based on deep convolution auto-encoder[J]. Acta Energiae Solaris Sinica,2022,43(11):215-223.
[12]	MA Yanhua,DU Xian,SUN Ximing. Adaptive modification of turbofan engine nonlinear model based on LSTM neural networks and hybrid optimization method[J]. Chinese Journal of Aeronautics,2022,35(9):314-332. doi: 10.1016/j.cja.2021.11.005
[13]	LI Lei,HASSAN M A,YANG Shurong,et al. Development of image-based wheat spike counter through a faster R-CNN algorithm and application for genetic studies[J]. The Crop Journal,2022,10(5):1303-1311. doi: 10.1016/j.cj.2022.07.007
[14]	WU Yizhi,FAN Yiren. Fast hierarchical inversion for borehole resistivity measurements in high-angle and horizontal wells using ADNN-AMLM[J]. Journal of Petroleum Science and Engineering,2021,203. DOI: 10.1016/j.petrol.2021.108662.
[15]	LEE J H,HONG J K. Comparative performance analysis of vibration prediction using RNN techniques[J]. Electronics,2022,11(21). DOI: 10.3390/electronics11213619.
[16]	杨婷婷,高乾,李浩千,等. 基于卷积神经网络−长短时记忆神经网络的磨煤机故障预警[J]. 热力发电,2022,51(10):122-129. YANG Tingting,GAO Qian,LI Haoqian,et al. Coal mill fault early warning technology based on CNN-LSTM network[J]. Thermal Power Generation,2022,51(10):122-129.
[17]	王莹莹,安维峥,乔婷婷,等. 基于LSTM的水下电子模块温度预测及预警方法[J]. 中国海上油气,2022,34(1):161-167. WANG Yingying,AN Weizheng,QIAO Tingting,et al. LSTM-based temperature prediction and early warning method for subsea electronic module[J]. China Offshore Oil and Gas,2022,34(1):161-167.
[18]	HAN Fei,DU Wenhua,ZENG Zhiqiang,et al. A novel dense residual network based on Adam-S optimizer for fault diagnosis of bearings under different working conditions[J]. Measurement Science and Technology,2022,33(12). DOI: 10.1088/1361-6501/ac8dad.
[19]	BAFAKEEH O T,YASIR M,RAZA A,et al. The minimality of mean square error in chirp approximation using fractional fourier series and fractional fourier transform[J]. Scientific Reports,2022,12. DOI: 10.1038/s41598-022-23560-8.
[20]	LI Shichun,MO Bin,WANG Kunming,et al. Nonlinear prediction modeling of surface quality during laser powder bed fusion of mixed powder of diamond and Ni-Cr alloy based on residual analysis[J]. Optics & Laser Technology,2022,151. DOI: 10.1016/j.optlastec.2022.107980.
[21]	ZHEN Dong,GUO Junchao,XU Yuandong,et al. A novel fault detection method for rolling bearings based on non-stationary vibration signature analysis[J]. Sensors,2019,19(18). DOI: 10.3390/s19183994.