许伟明,李学敏,张祎,Maulidi Barasa,张培泽,易佑中
XU Weimin,LI Xuemin,ZHANG Yi,Maulidi Barasa,ZHANG Peize,YI Youzhong

• 1:华中科技大学能源与动力工程学院

摘要(Abstract)：

在未标记且极不平衡的监测数据中进行异常检测是能源行业目前急需解决且最具挑战性的问题之一。由于自动编码器具有强大的高维数据分析能力，使用自动编码器进行异常检测变得越来越流行。基于O-DAE（优化的深度自编码器）和SVDD（支持向量数据描述），提出一种新的异常检测方法。首先，建立了一种样本筛选机制，用于去除未标记训练集中的异常样本，使得训练模型几乎不学习异常样本的特征。其次，以自编码器的隐藏特征和重构误差作为最终特征数据进行异常检测。最后，对不同结构的深度学习方法进行研究与比较，并对某汽轮机实际运行数据进行了实验，结合支持向量数据描述检测异常。与传统异常检测方法相比，该方法的异常检测精度提高了50%，能实现更灵敏鲁棒的汽轮机设备性能无监督异常检测。
Anomaly detection in unlabeled and highly imbalanced monitoring data is one of the most urgent to be solved and challenging industry problems. The use of autoencoders for anomaly detection is becoming more and more popular due to the powerful high-dimensional data analysis capabilities of autoencoders. A new anomaly detection method is developed base on O-DAE(optimized deep autoencoder) and SVDD(support vector data description).Firstly, to make the training model hardly learns the features of abnormal samples, a sample screening mechanism is established to remove abnormal samples in the unlabeled training set. Secondly, the hidden features and reconstruction errors of the autoencoder are used as the final feature data for anomaly detection. Finally, the deep learning methods with different architectures are studied and compared, the experiments on the actual operation data of a steam turbine are conducted, and the detection abnormity is described combining with the support vector data. Compared with the traditional anomaly detection method, the anomaly detection accuracy of this method is improved by 50%, which can realize more sensitive and robust unsupervised anomaly detection of equipment performance for steam turbines.

关键词(KeyWords)： 深度自动编码器;支持向量数据描述;汽轮机;异常检测
deep autoencoder;support vector data description;steam turbine;anomaly detection

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划资助项目（2018YFB606101）

作者(Author): 许伟明,李学敏,张祎,Maulidi Barasa,张培泽,易佑中
XU Weimin,LI Xuemin,ZHANG Yi,Maulidi Barasa,ZHANG Peize,YI Youzhong

DOI: 10.19585/j.zjdl.202307012

参考文献(References)：

• [1]CHANDOLA V,BANERJEE A,KUMAR V.Anomaly detection[J].ACM Computing Surveys,2009,41(3):1-58.
• [2]ZHAN J,WU C K,MA X D,et al.Abnormal vibration detection of wind turbine based on temporal convolution network and multivariate coefficient of variation[J].Mechanical Systems and Signal Processing,2022,174:109082.
• [3]JAW L C.Recent advancements in aircraft engine health management (EHM) technologies and recommendations for the next step[C]//Proceedings of ASME Turbo Expo2005:Power for Land,Sea,and Air,June 6-9,2005,Reno,Nevada,USA:683-695.
• [4]CHA J,KO S,PARK S Y,et al.Fault detection and diagnosis algorithms for transient state of an open-cycle liquid rocket engine using nonlinear Kalman filter methods[J].Acta Astronautica,2019,163:147-156.
• [5]FRANK P M.Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy[J].Automatica,1990,26(3):459-474.
• [6]LU F,ZHENG W H,HUANG J Q,et al.Life cycle performance estimation and In-flight health monitoring for gas turbine engine[J].Journal of Dynamic Systems,Measurement,and Control,2016,138(9):091009.
• [7]POURBABAEE B,MESKIN N,KHORASANI K.Sensor fault detection,isolation,and identification using multiple-model-based hybrid Kalman filter for gas turbine engines[J].IEEE Transactions on Control Systems Technology,2016,24(4):1184-1200.
• [8]ZHONG S S,FU S,LIN L.A novel gas turbine fault diagnosis method based on transfer learning with CNN[J].Measurement,2019,137:435-453.
• [9]FU X Y,LUO H,ZHONG S S,et al.Aircraft engine fault detection based on grouped convolutional denoising autoencoders[J].Chinese Journal of Aeronautics,2019,32(2):296-307.
• [10]SARKAR S,JIN X,RAY A.Data-driven fault detection in aircraft engines with noisy sensor measurements[J].Journal of Engineering for Gas Turbines and Power,2011,133(8):1.
• [11]YAN W Z,YU L J.On accurate and reliable anomaly detection for gas turbine combustors:a deep learning approach[EB/OL].[2019-08-25].https：//arxiv.org/abs/1908.09238.
• [12]LEE H,LI G Y,RAI A,et al.Real-time anomaly detection framework using a support vector regression for the safety monitoring of commercial aircraft[J].Advanced Engineering Informatics,2020,44:101071.
• [13]MOGHADDASS R,SHENG S W.An anomaly detection framework for dynamic systems using a bayesian hierarchical framework[J].Applied Energy,2019,240:561-582.
• [14]FAHIM M,SILLITTI A.Anomaly detection,analysis and prediction techniques in Io T environment:a systematic literature review[J].IEEE Access,2019,7:81664-81681.
• [15]DE CASTRO-CROS M,VELASCO M,ANGULO C.Machine-learning-based condition assessment of gas turbines-a review[J].Energies,2021,14(24):8468.
• [16]SHAH M P,MERCHANT S N,AWATE S P.Abnormality detection using deep neural networks with robust quasi-norm autoencoding and semi-supervised learning[C]//2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018),April 4-7,2018,Washington,USA:568-572.
• [17]AL BATAINEH A,MAIRAJ A,KAUR D.Autoencoder based semi-supervised anomaly detection in turbofan engines[J].International Journal of Advanced Computer Science and Applications,2020,11(11):41-47.
• [18]YAN W Z.Detecting gas turbine combustor anomalies using semi-supervised anomaly detection with deep representation learning[J].Cognitive Computation,2020,12(2):398-411.
• [19]VILLA-PéREZ M E，áLVAREZ-CARMONA Má，LOYOLA-GONZáLEZ O,et al.Semi-supervised anomaly detection algorithms:a comparative summary and future research directions[J].Knowledge-Based Systems,2021,218:106878.
• [20]WU D H,LIU C H,FAN H B,et al.Research on abnormal detection of one-class support vector machine based on ensemble cooperative semi-supervised learning[J].Journal of Physics:Conference Series,2019,1237(5):052007.
• [21]RAMASWAMY S,RASTOGI R,SHIM K.Efficient algorithms for mining outliers from large data sets[C]//Proceedings of the 2000 ACM SIGMOD international conference on Management of data,May 15-18,2000,Dallas,Texas,USA:427-438.
• [22]TANG J A,CHEN Z X,FU A W C,et al.Enhancing effectiveness of outlier detections for low density patterns[M]//CHEN M S,YU P S,LIU B.,Eds.Advances in Knowledge Discovery and Data Mining.Berlin,Heidelberg:Springer Berlin Heidelberg,2002:535-548.
• [23]BREUNIG M M,KRIEGEL H P,NG R T,et al.LOF:identifying density-based local outliers[C]//Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data,May 15-18,2000,Dallas,Texas,USA:93-104.
• [24]PU G,WANG L J,SHEN J,et al.A hybrid unsupervised clustering-based anomaly detection method[J].Tsinghua Science and Technology,2020,26(2):146-153.
• [25]HE Z Y,XU X F,DENG S C.Discovering cluster-based local outliers[J].Pattern Recognition Letters,2003,24(9/10):1641-1650.
• [26]KO J U,NA K,OH J S,et al.A new auto-encoder-based dynamic threshold to reduce false alarm rate for anomaly detection of steam turbines[J].Expert Systems With Applications,2022,189:116094.
• [27]FU S,ZHONG S S,LIN L,et al.A re-optimized deep auto-encoder for gas turbine unsupervised anomaly detection[J].Engineering Applications of Artificial Intelligence,2021,101:104199.
• [28]LEGRAND A,NIEPCERON B,COURNIER A,et al.Study of autoencoder neural networks for anomaly detection in connected buildings[C]//2018 IEEE Global Conference on Internet of Things (GCIo T),December 5-7,2018,Alexandria,Egypt:1-5.
• [29]THILL M,KONEN W,WANG H,et al.Temporal convolutional autoencoder for unsupervised anomaly detection in time series[J].Applied Soft Computing,2021,112:107751.
• [30]LEE G,JUNG M,SONG M,et al.Unsupervised anomaly detection of the gas turbine operation via convolutional auto-encoder[C]//2020 IEEE International Conference on Prognostics and Health Management (ICPHM),June8-10,2020,Detroit,USA:1-6.
• [31]CHOI H,KIM M,LEE G,et al.Unsupervised learning approach for network intrusion detection system using autoencoders[J].The Journal of Supercomputing,2019,75(9):5597-5621.
• [32]白明亮，张冬雪，刘金福，等.基于深度自编码器和支持向量数据描述的燃气轮机高温部件异常检测[J].发电技术，2021,42(4):422-430.BAI Mingliang,ZHANG Dongxue,LIU Jinfu,et al.Abnormal detection of gas turbine high temperature components based on depth self-encoder and support vector data description[J].Power Generation Technology,2021,42(4):422-430.
• [33]TAX D M J,DUIN R P W.Support vector data description[J].Machine Learning,2004,54(1):45-66.