Research on the health evaluation and prediction system for mine hoists
-
摘要: 针对目前对矿井提升机整个系统进行健康状态评估与预测的相关研究相对较少的问题,建立了矿井提升机健康状态评估指标体系和评语集,设计了矿井提升机健康状态评估与预测系统。针对矿井提升机各组成系统的监测数据无法充分利用、健康状态评估结果不能满足实际生产需求的问题,提出了一种提升机健康状态模糊综合评估方法:引入相对劣化度表征提升机不同类型指标的健康度,并利用健康度对矿井提升机的健康状态进行量化;采用模糊综合评估法计算矿井提升机的健康状态,使用指数标度代替1—9标度对层次分析法(AHP)进行改进,以降低计算复杂度;采用CRITIC客观赋权法,结合主客观权重计算各子系统和指标的综合权重;根据模糊综合评估计算过程和最大隶属原则,得到矿井提升机的健康状态评估结果和故障原因。在提升机健康状态评估结果基础上,利用哈里斯鹰优化(HHO)算法优化支持向量回归(SVR)模型的重要参数,构建HHO−SVR模型对矿井提升机的健康状态进行预测,提高健康预测结果的准确性。实验结果表明:模糊综合评估方法能够准确实现提升机健康状态评估;与粒子群优化支持向量回归(PSO−SVR)、遗传算法优化支持向量回归(GA−SVR)、灰狼算法优化支持向量回归(GWO−SVR)模型相比,HHO−SVR模型的预测结果更接近实际值,具有更好的预测效果。Abstract: In response to the relatively limited research on health evaluation and prediction of the entire system of mine hoists, a health evaluation index system and comment set for mine hoists have been established. The health evaluation and prediction system for mine hoists has been designed. A fuzzy comprehensive evaluation method for the health of mine hoists is proposed to address the issues of insufficient utilization of monitoring data from various components of mine hoists, and the inability of health evaluation results to meet actual production needs. The method introduces relative degradation degree to characterize the health of different types of indicators of the hoist. The method uses health degree to quantify the health of mine hoists. The fuzzy comprehensive evaluation method is used to calculate the health of mine hoists. The analytic hierarchy process (AHP) is improved by replacing the 1-9 scale with an exponential scale to reduce computational complexity. The method uses CRITIC objective weighting method and combines subjective and objective weights to calculate the comprehensive weights of each subsystem and indicator. Based on the fuzzy comprehensive evaluation calculation process and the maximum membership principle, the health evaluation results and fault causes of the mine hoist are obtained. On the basis of the health evaluation results of the mine hoist, the Harris hawks (HHO) algorithm is used to optimize the important parameters of the support vector regression (SVR) model. The HHO-SVR model is constructed to predict the health of the mine hoist, improving the accuracy of the health prediction results. The experimental results show that the fuzzy comprehensive evaluation method can accurately evaluate the health of the hoist. Compared with particle swarm optimization support vector regression (PSO-SVR), genetic algorithm optimization support vector regression (GA-SVR), and grey wolf algorithm optimization support vector regression (GWO-SVR) models, the prediction results of the HHO-SVR model are closer to the actual values and have better prediction performance.
-
表 1 提升机主要故障位置及其原因
Table 1. Main fault positions and causes of hoists
故障位置 主要原因 拖动部分 电动机超速;电动机电流过大;电动机温度过高;电动机轴承过热;电动机停转;变速器轴承变形;齿轮磨损严重;减速器轴承磨损 制动部分 制动转矩过大;制动转矩过小;制动失效;制动油温过高;制动油压过小;制动闸片温度过高;制动闸片间隙过大等 滑动控制部分 油温过高;油压过高;油压过低;油量过少;油中杂质太多 钢丝绳部分 钢丝绳磨损;钢丝绳腐蚀;钢丝绳变形 表 2 矿井提升机健康状态描述和检修决策
Table 2. Health status description and maintenance decision of mine hoists
健康等级 描述 维修决策 健康 所有子系统和指标值都很健康,指标值接近预期 矿井提升机处于健康状态,不需要维修 亚健康 子系统处于健康和警告的状态之间,指标值接近阈值 不影响正常运行,但要注意定期检测 警告 一些子系统处于亚健康状态,一些指标值在故障阈值附近波动 短时间内仍能正常运行,但要提高监测频率 故障 至少有1个子系统处于故障状态,传感器值大幅超过故障阈值 建议立即停车进行维修 表 3 矿井提升机健康等级与健康度之间的关系
Table 3. The relationship between the health level and health degree of mine hoists
健康状态 健康等级 健康度 健康(HS) V1 0.75≤d≤1.0 亚健康(SH) V2 0.4≤d<0.75 警告(CS) V3 0.15≤d<0.4 故障(FS) V4 0≤d<0.15 表 4 1—9标度与指数标度的关系
Table 4. The relationship between 1-9 scale and exponential scale
1—9 标度 相对重要性 指数标度 1 同等重要 q0 3 前者比后者稍微重要一些 q2 5 前者明显比后者更重要 q4 7 前者比后者非常重要 q6 9 前者绝对比后者更重要 q8 2,4,6,8 2个指标的中间值之间的逆向比较 q1,q3,q5,q7 表 5 实验平台主要参数
Table 5. Main parameters of the experimental platform
参数 值 提升高度/m 750 电动机功率/kW 5300 转速/(r·min−1) 49.7 钢丝绳直径/cm 10 提升速度/(m·s−1) 11 载质量/t 15 刹车数 5 表 6 不同指标在不同运行阶段的数值
Table 6. Values of different indicators at different operating stages
指标 类型 加速 匀速 减速 X11 成本型 2.7 2.38 2.57 X12 成本型 187.16 114.16 113.28 X13 成本型 38 36 37 X14 区间型 4.28 3.23 3.75 X21 区间型 0.73 0.63 0.66 X22 区间型 4.07 3.18 3.66 X23 成本型 36 35 35 X31 区间型 28 27 27 X32 区间型 30 28 28 X33 成本型 1.1 1.1 1.1 X34 成本型 2.0 1.8 1.9 X41 区间型 0.4 0.4 0.4 X42 成本型 4 2 3 X51 区间型 0.56 0.56 0.56 X52 区间型 20 20 23 X53 成本型 0.2 0.2 0.2 表 7 指标层和子系统层的综合权重
Table 7. Comprehensive weights of indicator layer and subsystem layer
子系统层 子系统层
综合权重指标层 指标层
综合权重X1 0.2572 X11 0.2982 X12 0.3055 X13 0.1702 X14 0.2261 X2 0.2334 X21 0.3573 X22 0.3605 X23 0.2822 X3 0.1853 X31 0.3276 X32 0.3021 X33 0.1780 X34 0.1923 X4 0.1570 X41 0.6873 X42 0.3127 X5 0.1671 X51 0.3534 X52 0.3150 X53 0.3316 -
[1] WANG Feng,HE Fengyou. Study of hoist perception system based on IOT technology[C]. International Conference on Web Information Systems and Mining,Sanya,2010:357-360. [2] ZHAO Huadong,WANG Hezheng,LIU Guoning,et al. The application of Internet of things (IOT) technology in the safety monitoring system for hoisting machines[J].Applied Mechanics and Materials,2012, 1976(209/210/211):2142-2145. [3] LI Juanli,XIE Jiacheng,YANG Zhaojian,et al. Fault diagnosis method for a mine hoist in the Internet of things environment[J]. Sensors,2018,18(6). DOI: 10.3390/s18061920. [4] LEI Yaguo,LI Naipeng,GUO Liang,et al. Machinery health prognostics:a systematic review from data acquisition to RUL prediction[J]. Mechanical Systems and Signal Processing,2018,104(1):799-834. [5] PENG Ying,DONG Ming. A prognosis method using age-dependent hidden semi-Markov model for equipment health prediction[J]. Signal Process,2011,25(1):237-252. [6] LI Hong,PAN Donghui,CHEN C L P. Intelligent prognostics for battery health monitoring using the mean entropy and relevance vector machine[J]. IEEE Transactions on Systems,Man,and Cybernetics:Systems,2014,44(7):851-862. [7] MA Meng,CHEN Xuefeng,WANG Shibin,et al. Bearing degradation assessment based on weibull distribution and deep belief network[C]. International Symposium on Flexible Automation,Cleveland,2016:382-385. [8] FUSTER-PARRA P,TAULER P,BENNASAR-VENY M,et al. Bayesian network modeling:a case study of an epidemiologic system analysis of cardiovascular risk[J]. Computer Methods & Programs in Biomedicine,2016,126(12):128-142. [9] WANG Lanjing,ALI Y,NAZIR S,et al. ISA evaluation framework for security of Internet of health things system using AHP-TOPSIS methods[J]. IEEE Access,2020,8:152316-152332. doi: 10.1109/ACCESS.2020.3017221 [10] MU Tongna,YU Hongmin,ZHANG Xueyan. Research on equipment health assessment based on grey system theory[C]. IEEE Prognostics and System Health Management Conference,Beijing,2012:1-4. [11] WEI Xiao,LUO Xiangfeng,LI Qing,et al. Online comment-based hotel quality automatic assessment using improved fuzzy comprehensive evaluation and fuzzy cognitive map[J]. IEEE Transactions on Fuzzy Systems,2015,23(1):72-84. doi: 10.1109/TFUZZ.2015.2390226 [12] LI Juanjuan,MENG Guoying,XIE Guangming,et al. Study on health assessment method of a braking system of a mine hoist[J]. Sensors,2019,19(4). DOI: 10.3390/s19040769. [13] DE SANTO A,GALLI A,GRAVINA M,et al. Deep learning for HDD health assessment:an application based on LSTM[J]. IEEE Transactions on Computers,2022,71(1):69-80. doi: 10.1109/TC.2020.3042053 [14] VATANI M,SZEREPKO M,PREBEN VIE J S. State of health prediction of li-ion batteries using incremental capacity analysis and support vector regression[C]. IEEE Milan PowerTech,Milan,2019:1-6. DOI: 10.1109/PTC.2019.8810665. [15] DEY P,CHAULYA S K,KUMAR S. Hybrid CNN-LSTM and IoT-based coal mine hazards monitoring and prediction system[J]. Process Safety and Environmental Protection,2021,152:249-263. doi: 10.1016/j.psep.2021.06.005 [16] CHENG Hongju,XIE Zhe,SHI Yushi,et al. Multi-step data prediction in wireless sensor networks based on one-dimensional CNN and bidirectional LSTM[J]. IEEE Access,2019,7:117883-117896. doi: 10.1109/ACCESS.2019.2937098 [17] REN Lei,DONG Jiabao,WANG Xiaokang,et al. A data-driven Auto-CNN-LSTM prediction model for lithium-ion battery remaining useful life[J]. IEEE Transactions on Industrial Informatics,2021,17(5):3478-3487. doi: 10.1109/TII.2020.3008223 [18] QIN Taichun,ZENG Shengkui,GUO Jianbin. Robust prognostics for state of health estimation of lithium-ion batteries based on an improved PSO-SVR model[J]. Microelectronics Reliability,2015,55(9/10):1280-1284. [19] MA Jun,TENG Zhaosheng,TANG Qiu,et al. Measurement error prediction of power metering equipment using improved local outlier factor and kernel support vector regression[J]. IEEE Transactions on Industrial Electronics,2022,69(9):9575-9585. doi: 10.1109/TIE.2021.3114740 [20] SAIDI L,ALI J B,BECHHOEFER E,et al. Wind turbine high-speed shaft bearings health prognosis through a spectral Kurtosis-derived indices and SVR[J]. Applied Acoustics,2017,120:1-8. doi: 10.1016/j.apacoust.2017.01.005 [21] FU Wenlong,SHAO Kaixuan,TAN Jiawen,et al. Fault diagnosis for rolling bearings based on composite multiscale fine-sorted dispersion entropy and SVM with hybrid mutation SCA-HHO algorithm optimization[J]. IEEE Access,2020,8:13086-13104. doi: 10.1109/ACCESS.2020.2966582 [22] AHMED R,ZAYED T,NASIRI F. A hybrid genetic algorithm-based fuzzy Markovian model for the deterioration modeling of healthcare facilities[J]. Algorithms,2020,13(9):210-230. doi: 10.3390/a13090210 [23] HUANG Zhi'an,LE Tian,GAO Yukun,et al. Safety assessment of emergency training for industrial accident scenarios based on analytic hierarchy process and gray-fuzzy comprehensive assessment[J]. IEEE Access,2020,8:144767-144777. doi: 10.1109/ACCESS.2020.3013671 [24] YU Xueyi,MU Chi,ZHANG Dongdong. Assessment of land reclamation benefits in mining areas using fuzzy comprehensive evaluation[J]. Sustainability,2020,12(5):1-20. [25] VAN HOUDT B. Randomized work stealing versus sharing in large-scale systems with nonexponential job sizes[J]. IEEE/ACM Transactions on Networking,2019,27(5):2137-2149. doi: 10.1109/TNET.2019.2939040 [26] CHITSAZAN M A,FADALI M S,TRZYNADLOWSKI A M. State estimation for large-scale power systems and FACTS devices based on spanning tree maximum exponential absolute value[J]. IEEE Transactions on Power Systems,2020,35(1):238-248. doi: 10.1109/TPWRS.2019.2934705 [27] LIN Zhenzhi,WEN Fushuan,WANG Huifang,et al. CRITIC-based node importance evaluation in skeleton-network reconfiguration of power grids[J]. IEEE Transactions on Circuits and Systems II:Express Briefs,2018,65(2):206-210. [28] YANG Tingfang,LIU Haifeng,ZENG Xiangjun,et al. Application of a combined decision model based on optimal weights in incipient faults diagnosis for power transformer[J]. IEEJ Transactions on Electrical and Electronic Engineering,2017,12(2):169-175. doi: 10.1002/tee.22363 [29] GUO Yanhui,HAN Siming,SHEN Chuanhe,et al. An adaptive SVR for high-frequency stock price forecasting[J]. IEEE Access,2018,6:11397-11404. doi: 10.1109/ACCESS.2018.2806180 [30] ZHANG Pengcheng,ZHOU Xuewu,PELLICCIONE P,et al. RBF-MLMR:a multi-label metamorphic relation prediction approach using RBF neural network[J]. IEEE Access,2017,5:21791-21805. doi: 10.1109/ACCESS.2017.2758790 -