Construction of health index and condition assessment of coal mine rotating machinery
-
摘要: 煤矿设备监测参数为时间序列数据,其时序特征对健康评估的影响较大。针对传统机械设备健康评估中存在的信号时空特性提取不完备、人为经验依赖程度高、设备早期状态变化评估难等问题,建立了基于二维数组的长短期记忆降噪卷积自编码器(2D−LSTMDCAE)模型,并提出了基于2D−LSTMDCAE的煤矿旋转机械健康指标(HI)构建及状态评估方法。将一维振动数据转换为二维数组,通过二维卷积网络模型充分学习原始数据中所包含的信息,增强模型对数据特征的学习能力;将样本并行输入卷积和长短期记忆(LSTM)单元,以获取完备的信号时空特征;构建无监督学习的降噪卷积自编码器(DCAE)模型并进行样本重构,采用Bray−Curtis距离计算原始样本与重构样本间相似度,得到HI,解决设备运行过程中状态标签难以获取的问题,提升模型在强背景噪声中的适应能力。使用XJTU−SY轴承数据集验证2D−LSTMDCAE模型的特征学习能力,并采用相关性和单调性2个指标评价基于HI的状态评估方法,测试结果表明:二维输入样本构建方法及学习数据时序特征的HI构建方法对轴承的性能退化更敏感,2D−LSTMDCAE模型能够更早地检测到设备的早期故障,在测试轴承上相比于LSTMDCAE和DCAE模型构建的HI及均方根平均提前了约7 min;与LSTMDCAE和DCAE模型构建的HI、均方根相比,2D−LSTMDCAE模型构建的HI的相关性和单调性均较高,能更好地反映轴承的退化情况。采用减速器加速退化实验数据进行健康评估实验,在测试减速器上,相比于均方根指标,通过2D−LSTMDCAE模型构建的HI能够提前8 min发现早期故障,且HI相关性提高了0.007,单调性提高了0.211,能够更好地反映减速器的退化情况。Abstract: The monitoring parameters of coal mine equipment are time-series data, and the time-series characteristics have great influence on health assessment. The traditional mechanical equipment health assessment has the problems of incomplete extraction of signal spatiotemporal characteristics, high dependence on human experience, and difficult assessment of early condition change of equipment. In order to solve these problems. A two-dimensional array long short-term memory denoising convolutional autoencoder (2D-LSTMDCAE) model is constructed, and a health index (HI) construction and condition assessment method of coal mine rotating machinery based on 2D-LSTMDCAE is proposed. The one-dimensional vibration data is converted into a two-dimensional array. The two-dimensional convolution network model is used to fully learn the information contained in the original data, so the learning capability of the model on data characteristics is enhanced. The samples are input into convolution and long short-term memory (LSTM) units in parallel to obtain complete signal spatiotemporal characteristics. The unsupervised learning denoising convolutional autoencoder (DCAE) model is constructed for sample reconstruction. The similarity between the original sample and the reconstructed sample is calculated by Bray-Curtis distance to obtain the HI. It solves the problem that it is difficult to obtain the condition tag during the operation of the equipment, and improves the adaptability of the model in strong background noise. The characteristic learning capability of the 2D-LSTMDCAE model is verified by using XJTU-SY bearing data set. The two indexes of correlation and monotonicity are adopted to evaluate the condition assessment method based on HI. The test results show the following points. The two-dimensional input sample construction method and the HI construction method of learning the time series characteristics of data are more sensitive to the performance degradation of bearings. The 2D-LSTMDCAE model can detect the early failure of the equipment earlier. On the test bearing, the HI and RMS constructed by the 2D-LSTMDCAE model are about 7 min earlier than that of the LSTMDCAE and DCAE models. Compared with the HI and RMS constructed by the LSTMDCAE and DCAE models, the HI constructed by the 2D-LSTMDCAE model has higher correlation and monotonicity, and it can better reflect the degradation of bearings. The health assessment experiment is carried out by using the accelerated degradation experimental data of the reducer. On the test reducer, compared with RMS, it can detect early failure 8 min in advance by using the HI constructed by the 2D-LSTMDCAE model. The correlation is improved by 0.007, and the monotonicity is improved by 0.211, which can better reflect the degradation situation of the reducer.
-
表 1 各工况下轴承参数
Table 1. Bearing parameters under various working conditions
工况 轴承 样本总数 失效位置 1 轴承1_1 123 外圈 轴承1_2 161 外圈 轴承1_3 158 外圈 2 轴承2_1 491 内圈 轴承2_2 161 外圈 轴承2_3 533 保持架 3 轴承3_1 2 538 外圈 轴承3_2 2 496 内圈、滚动体、保持架、外圈 轴承3_3 371 内圈 轴承3_4 1515 内圈 轴承3_5 114 外圈 表 2 HI的评价指标
Table 2. The evaluation index of HI
HI 相关性 单调性 2D−LSTMDCAE模型构建的HI 0.8205 0.5790 LSTMDCAE模型构建的HI 0.8055 0.5068 DCAE模型构建的HI 0.7896 0.4948 均方根 0.7731 0.3067 表 3 3种深度学习模型构建的HI的评价指标
Table 3. Evaluation index of HI constructed by three deep learning models
HI 相关性 单调性 2D−LSTMDCAE模型构建的HI 0.820 5 0.579 0 1D−ADSCAE模型构建的HI 0.709 2 0.256 0 DRAE模型构建的HI 0.795 2 0.490 3 表 4 减速器HI的评价指标
Table 4. HI evaluation index of the reducer
HI 相关性 单调性 2D−LSTMDCAE模型构建的HI 0.821 2 0.346 4 均方根 0.814 6 0.135 1 -
[1] 王国法,刘峰,庞义辉,等. 煤矿智能化−煤炭工业高质量发展的核心技术支撑[J]. 煤炭学报,2019,44(2):349-357. doi: 10.13225/j.cnki.jccs.2018.2041WANG Guofa,LIU Feng,PANG Yihui,et al. Coal mine intellectualization:the core technology of high quality development[J]. Journal of China Coal Society,2019,44(2):349-357. doi: 10.13225/j.cnki.jccs.2018.2041 [2] 王国法,刘峰,孟祥军,等. 煤矿智能化(初级阶段)研究与实践[J]. 煤炭科学技术,2019,47(8):1-36. doi: 10.13199/j.cnki.cst.2019.08.001WANG Guofa,LIU Feng,MENG Xiangjun,et al. Research and practice on intelligent coal mine construction (primary stage)[J]. Coal Science and Technology,2019,47(8):1-36. doi: 10.13199/j.cnki.cst.2019.08.001 [3] 李国发,王彦博,何佳龙,等. 机电装备健康状态评估研究进展及发展趋势[J]. 吉林大学学报(工学版),2022,52(2):267-279.LI Guofa,WANG Yanbo,HE Jialong,et al. Research progress and development trend of health assessment of electromechanical equipment[J]. Journal of Jilin University(Engineering and Technology Edition),2022,52(2):267-279. [4] 潘红光,裴嘉宝,侯媛彬. 智慧煤矿数据驱动检测技术研究[J]. 工矿自动化,2020,46(10):49-54. doi: 10.13272/j.issn.1671-251x.17606PAN Hongguang,PEI Jiabao,HOU Yuanbin. Research on data-driven detection technology of smart coal mine[J]. Industry and Mine Automation,2020,46(10):49-54. doi: 10.13272/j.issn.1671-251x.17606 [5] 李杰其,胡良兵. 基于机器学习的设备预测性维护方法综述[J]. 计算机工程与应用,2020,56(21):11-19. doi: 10.3778/j.issn.1002-8331.2006-0016LI Jieqi,HU Liangbing. Review of machine learning for predictive maintenance[J]. Computer Engineering and Applications,2020,56(21):11-19. doi: 10.3778/j.issn.1002-8331.2006-0016 [6] 来杰,王晓丹,向前,等. 自编码器及其应用综述[J]. 通信学报,2021,42(9):218-230. doi: 10.11959/j.issn.1000-436x.2021160LAI Jie,WANG Xiaodan,XIANG Qian,et al. Review on autoencoder and its application[J]. Journal on Communications,2021,42(9):218-230. doi: 10.11959/j.issn.1000-436x.2021160 [7] HUANG Feng,LI Zhixiong,XIANG Shuchen,et al. A new wind power forecasting algorithm based on long short-term memory neural network[J]. International Transactions on Electrical Energy Systems,2021,31(12). DOI: 10.1002/2050-7038.13233. [8] JANA D,PATIL J,HERKAL S,et al. CNN and convolutional autoencoder (CAE) based real-time sensor fault detection,localization,and correction[J]. Mechanical Systems and Signal Processing,2022,169. DOI: 10.1016/j.ymssp.2021.108723. [9] 石延新,何进荣,李照奎,等. 3D卷积自编码器高光谱图像分类模型[J]. 中国图象图形学报,2021,26(8):2021-2036. doi: 10.11834/jig.210146SHI Yanxin,HE Jinrong,LI Zhaokui,et al. Hyperspectral image classification model based on 3D convolutional auto-encoder[J]. Journal of Image and Graphics,2021,26(8):2021-2036. doi: 10.11834/jig.210146 [10] RICOTTA C,PAVOINE S. A new parametric measure of functional dissimilarity:bridging the gap between the Bray-Curtis dissimilarity and the Euclidean distance[J]. Ecological Modelling,2022,466. DOI: 10.1016/j.ecolmodel.2022.109880. [11] 赵志宏,李乐豪,杨绍普,等. 一种无监督的轴承健康指标及早期故障检测方法[J]. 中国机械工程,2022,33(10):1234-1243. doi: 10.3969/j.issn.1004-132X.2022.10.013ZHAO Zhihong,LI Lehao,YANG Shaopu,et al. An unsupervised bearing health indicator and early fault detection method[J]. China Mechanical Engineering,2022,33(10):1234-1243. doi: 10.3969/j.issn.1004-132X.2022.10.013 [12] WANG Biao,LEI Yaguo,LI Naipeng,et al. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings[J]. IEEE Transactions on Reliability,2020,69(1):401-412. doi: 10.1109/TR.2018.2882682 [13] 雷亚国,韩天宇,王彪,等. XJTU−SY滚动轴承加速寿命试验数据集解读[J]. 机械工程学报,2019,55(16):1-6. doi: 10.3901/JME.2019.16.001LEI Yaguo,HAN Tianyu,WANG Biao,et al. XJTU-SY rolling element bearing accelerated life test datasets:a tutorial[J]. Journal of Mechanical Engineering,2019,55(16):1-6. doi: 10.3901/JME.2019.16.001 [14] 张永峰,陆志强. 基于集成神经网络的剩余寿命预测[J]. 工程科学学报,2020,42(10):1372-1380.ZHANG Yongfeng,LU Zhiqiang. Remaining useful life prediction based on an integrated neural network[J]. Chinese Journal of Engineering,2020,42(10):1372-1380. [15] KHELIF R,CHEBEL-MORELLO B,MALINOWSKI S,et al. Direct remaining useful life estimation based on support vector regression[J]. IEEE Transactions on Industrial Electronics,2017,64(3):2276-2285. doi: 10.1109/TIE.2016.2623260 [16] 徐海铭,夏乔阳,李勇,等. 基于深度可分离卷积神经网络轴承剩余寿命预测[J]. 机械强度,2022,44(4):763-771. doi: 10.16579/j.issn.1001.9669.2022.04.001XU Haiming,XIA Qiaoyang,LI Yong,et al. Bearing remaining life prediction based on deep separable convolutional neural network[J]. Journal of Mechanical Strength,2022,44(4):763-771. doi: 10.16579/j.issn.1001.9669.2022.04.001 [17] 张小刚,丁华,王晓波,等. 深度残差网络在滚动轴承故障诊断中的研究[J]. 机械设计与制造,2022,371(1):77-80. doi: 10.3969/j.issn.1001-3997.2022.01.017ZHANG Xiaogang,DING Hua,WANG Xiaobo,et al. Study on fault diagnosis of rolling bearing by deep residual network[J]. Machinery Design & Manufacture,2022,371(1):77-80. doi: 10.3969/j.issn.1001-3997.2022.01.017 -