1.Key Laboratory of Modern Measurement and Control Technology of the Ministry of Education,Beijing Information Science;and Technology University,Beijing 100192,China
To address the challenges in the integrated transmission devices of special vehicle working process, including complex data, the imbalance between normal and abnormal data and the high false alarm and underreporting rates of traditional statistical methods in detecting sensor anomalies, a new method, called ACA-SVM anomaly detection method, combining an attention mechanism convolutional autoencoder (ACA) with a support vector machine (SVM) is proposed. Using operation data from armored tracked vehicles, the monitoring data from integrated transmission sensors is preprocessed. Key features in the transmission data are identified and focused by the attention mechanism. The convolutional autoencoder (CAE) then reduces the dimensionality of the original data and extracts features to facilitate data detection, resulting in the calculation of reconstruction errors and eigenvalues. The support vector machine classifies and calculates the abnormal scores of the training set data samples, and the detection performance is compared with the traditional anomaly detection models. Experimental results show that the proposed ACA-SVM method outperforms CAE, gated recurrent unit (GRU), and other models in detecting anomalies in the integrated transmission data of special vehicles, achieving a detection accuracy of 97.2% and an F1 of 0.976.
XUB R, ZHANGJ L, WANL,et al. A service status identification method of comprehensive transmission based on multi-sensor data association[J]. Acta Armamentarii,2024,45(2): 574-583.(in Chinese)
YANS F, MAB, ZHENGC S. Condition-based maintenance for power-shift steering transmission based on oil spectral analysis[J]. Spectroscopy and Spectral Analysis, 2019, 39(11): 3470.(in Chinese)
ZHOUR, JIANGJ Y, QIAOL .Research on integrated model evaluation and verification of integrated transmission[J]. Computer Measurement & Control,2020,28(4):246-250.(in Chinese)
YANS F, MAB, ZHENGC S,et al .Wear localization and identification under nonlinear condition monitoring data[J].Journal of Jilin University (Engineering and Technology Edition),2019, 49(2): 359-365.(in Chinese)
YUX S, XUM, WANGY,et al. Anomaly detection method based on convolutional variational auto-encoder[J]. Chinese Journal of Scientific Instrument,2021,42(5): 151-158.(in Chinese)
XUF, ZHANGQ Q, JIW L, et al. Study on abnormal wear location of integrated transmission components based on oil spectral data[J]. Spectroscopy and Spectral Analysis, 2024, 44(5): 1398-1404.(in Chinese)
ZHANGL X, FENGF Z, LIUX B,et al. Research on fault detection and isolation method for typical hydraulic system[J]. Journal of System Simulation,2018,30(5):1818-1825.(in Chinese)
LIUQ, JIG Z, CAOP L,et al .Reliability design and analysis methodfor complex mechanical system based on physics of failure[J]. Acta Armamentarii,2022,43(Sup.1):189-195.(in Chinese)
MAB, ZHAOY, QIL C. Application of variational auto-encoder in mechanical fault early warning[J]. Computer Engineering and Applications, 2019, 55(12): 245-249.(in Chinese)
LIB B, PENGL. Bearing vibration abnormal detection based on improved autoencoder network[J]. Journal of Frontiers of Computer Science and Technology,2022,16(1):163-175.(in Chinese)
LIH Q, YINGN, GUOC S,et al. High-dimensional outlier detection based on deep belief network and linear one-class SVM[J]. Telecommunications Science,2018,34(1):34-42.(in Chinese)
QIY S, GONGY R, GAOS L,et al. Semi-supervised fault diagnosis of rolling bearing based on CL-ICAE[J]. Journal of Vibration and Shock,2023,42(7): 301-311.(in Chinese)
NINGZ J, CHENT, XUF,et al. Abnormal detection method of integrated transmission device condition monitoring data under complex working conditions[J]. Journal of Mechanical & Electrical Engineering, 2023, 40(9): 1387-1394.(in Chinese)
[31]
HOOSHMANDM K, HOSAHALLID. Network anomaly detection using deep learning techniques[J]. CAAI Transactions on Intelligence Technology, 2022, 7(2): 228-243.
[32]
LIUY Z, ZOUY S, WUY,et al. A novel abnormal detection method for bearing temperature based on spatiotemporal fusion[J]. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 2022, 236(3): 317-333.
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)