Key Laboratory of Modern Measurement and Control Technology,Ministry of Education,Beijing Information Science andTechnology University,Beijing 100192,China
To address the issue of low accuracy in anomaly detection for integrated transmission devices caused by high data complexity during operation, this paper proposes an integrated GRU-CNN anomaly detection model based on dynamically gated regulation. The model dynamically generates regulation factors for the update gate and reset gate of the GRU through a gating mechanism, enabling flexible adjustments at each time step. This achieves the combined effect of the dynamically gated regulation mechanism and the GRU. By preprocessing sensor monitoring data and partitioning datasets to clean redundant data, the dynamically gated regulation mechanism selects critical features, assigns appropriate weights, and adjusts these weights in real-time according to operational states. Validation through two anomaly detection case studies on integrated transmissions shows that, compared to traditional methods, the proposed method significantly improves detection accuracy—achieving 99.40% and 98.36%—thus verifying its effectiveness. The dynamically gated GRU-CNN approach provides a novel solution for anomaly detection in integrated transmission devices.
DINGX O, YUS J, WANGM X, et al .Anomaly detection on industrial time series based on correlation analysis[J].Journal of Software, 2020, 31(3): 726-747.(in Chinese)
[3]
SUY, ZHAOY J, NIUC H,et al .Robust anomaly detection for multivariate time series through stochastic recurrent neural network[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.Anchorage AK USA. ACM, 2019: 2828-2837.
HUJ J, WANGX F, ZHANGM, et al .Time-series data anomaly detection method based on deep learning[J].Information and Control, 2019, 48(1):1-8.(in Chinese)
ZHANP, CHENL, CAOL H, et al .Time series anomaly detection based on kernel turning points clipped representation[J]. Computer Engineering and Applications, 2020, 56(23):130-138.(in Chinese)
ZHUOL, ZHAOH Y, ZHANS Y. Overview of anomaly detection methods and applications[J]. Application Research of Computers, 2020, 37(Sup.1): 9-15.(in Chinese)
[10]
BREUNIGM M, KRIEGELH P, NGR T,et al .LOF:identifying density-based local outliers[C]//Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data.Dallas Texas USA:ACM,2000: 93-104.
[11]
RAMASWAMYS, RASTOGIR, SHIMK .Efficient algorithms for mining outliers from large data sets[C]//Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data.Dallas Texas USA. ACM, 2000:427-239.
YAOH Y, CHENT, JIAR, et al .Detection method of integrated transmission system anomaly based on improved CNN-LSTM[J]. Journal of Mechanical & Electrical Engineering, 2024, 41(11):1986-1994.(in Chinese)
LIUB S, LIANGD .Evaluation index system construction of tracked armored combat vehicles’ transmission service properties[J].Science Technology and Engineering, 2024, 24(6):2355-2361.(in Chinese)
TIANQ W, FENGF Z, LIM, et al .Gear crack fault diagnosis of convergent planetary rowbased on 1-D depth residual shrinkage network[J].Journal of Vibration and Shock, 2022, 41(19):198-206.(in Chinese)
[18]
RODRIGUESJ, COSTAI, FARINHAJ, et al .Predicting motor oil condition using artificial neural networks and principal component analysis[J]. Eksploatacjai Niezawodność-Maintenance and Reliability, 2020, 22(3):440-448.
NINGZ J, CHENT, XUF, et al .Abnormal detection method of integrated transmission device condition monitoring data under complex working conditions[J]. Mechanical & Electrical Engineering Magazine, 2023, 40(9): 1387-1394.(in Chinese)
[21]
ZHAOH S, LIUH H, HUW J,et al. Anomaly detection and fault analysis of wind turbine components based on deep learning network[J].Renewable Energy,2018,127:825-834.
[22]
DUW L, GUOZ, LIC, et al. From anomaly detection to novel fault discrimination for wind turbine gearboxes with a sparse isolation encoding forest[J]. IEEE Transactions on Instrumen- tation and Measurement, 2022, 71:2512710.
[23]
LIT F, ZHAOZ B, SUNC, et al .Domain adversarial graph convolutional network for fault diagnosis under variable working conditions[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70:3515010.
[24]
LIZ, LIJ Y, WANGY, et al .A deep learning approach for anomaly detection based on SAE and LSTM in mechanical equipment[J].The International Journal of Advanced Manufacturing Technology, 2019, 103(1):499-510.
[25]
VOS K, PENGZ X, JENKINSC, et al .Vibration-based anomaly detection using LSTM/SVM approaches[J].Mechanical Systems and Signal Processing, 2022, 169:108752.
[26]
LEIW P, LIC Y, DONGX M, et al .Multiworking conditions anomaly detection of mechanical system based on conditional variational auto-encoder[J].Shock and Vibration, 2023, 2023:2332669.
基金资助
北京市教委科研计划科技一般项目(KM202311232006)
Beijing Municipal Commission of Education Science Research Program General Science and Technology Project(KM202311232006)