Deep Domain-Adversarial Anomaly Detection With One-Class Transfer Learning  

作　　者：Wentao Mao Gangsheng Wang Linlin Kou Xihui Liang 

机构地区：[1]IEEE [2]the School of Computer and Information Engineering,Henan Normal University,Xinxiang 453007,China [3]the Technology Department,Beijing Mass Transit Railway Operation Corp.Ltd.,Beijing 100044,China [4]the Department of Mechanical Engineering,University of Manitoba,Winnipeg R3T 5V6,Canada

出　　处：《IEEE/CAA Journal of Automatica Sinica》2023年第2期524-546,共23页自动化学报（英文版）

基　　金：supported by the National Natural Science Foundation of China(NSFC)(U1704158);Henan Province Technologies Research and Development Project of China(212102210103);the NSFC Development Funding of Henan Normal University(2020PL09);the University of Manitoba Research Grants Program(URGP)。

摘　　要：Despite the big success of transfer learning techniques in anomaly detection,it is still challenging to achieve good transition of detection rules merely based on the preferred data in the anomaly detection with one-class classification,especially for the data with a large distribution difference.To address this challenge,a novel deep one-class transfer learning algorithm with domain-adversarial training is proposed in this paper.First,by integrating a hypersphere adaptation constraint into domainadversarial neural network,a new hypersphere adversarial training mechanism is designed.Second,an alternative optimization method is derived to seek the optimal network parameters while pushing the hyperspheres built in the source domain and target domain to be as identical as possible.Through transferring oneclass detection rule in the adaptive extraction of domain-invariant feature representation,the end-to-end anomaly detection with one-class classification is then enhanced.Furthermore,a theoretical analysis about the model reliability,as well as the strategy of avoiding invalid and negative transfer,is provided.Experiments are conducted on two typical anomaly detection problems,i.e.,image recognition detection and online early fault detection of rolling bearings.The results demonstrate that the proposed algorithm outperforms the state-of-the-art methods in terms of detection accuracy and robustness.

关 键 词：Anomaly detection domain adaptation domainadversarial training one-class classification transfer learning 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]