典型文献
Anomaly detection of control rod drive mechanism using long short-term memory-based autoencoder and extreme gradient boosting
文献摘要：
Anomaly detection for the control rod drive mechanism(CRDM)is key to enhancing the security of nuclear power plant equipment.In CRDM real-time con-dition-based maintenance,most existing methods cannot deal with long sequences and periodic abnormal events and have poor feature extraction from these data.In this paper,a learning-based anomaly detection method employing a long short-term memory-based autoencoder(LSTM-AE)network and an extreme gradient boosting(XGBoost)algorithm is proposed for the CRDM.The nonlinear and sequential features of the CRDM coil currents can be automatically and efficiently extracted by the LSTM neural units and AE network.The normal behavior LSTM-AE model was established to reconstruct the errors when feeding abnormal coil current signals.The XGBoost algorithm was leveraged to monitor the residuals and identify outliers for the coil currents.The results demon-strate that the proposed anomaly detection method can effectively detect different timing sequence anomalies and provide a more accurate forecasting performance for CRDM coil current signals.
文献关键词：
中图分类号：
作者姓名：
Jing Chen;Ze-Shi Liu;Hao Jiang;Xi-Ren Miao;Yong Xu
作者机构：
College of Electrical Engineering and Automation,Fuzhou University,Fuzhou 350108,China;The Department of Automation,Shanghai Jiao Tong University,Shanghai 200240,China;Fujian Fuqing Nuclear Power Co.,Ltd.,Fujian 350318,China
文献出处：
引用格式：
[1]Jing Chen;Ze-Shi Liu;Hao Jiang;Xi-Ren Miao;Yong Xu-.Anomaly detection of control rod drive mechanism using long short-term memory-based autoencoder and extreme gradient boosting)[J].核技术（英文版）,2022(10):53-67
A类：
B类：
Anomaly,detection,control,rod,drive,mechanism,using,long,short,term,memory,autoencoder,extreme,gradient,boosting,CRDM,key,enhancing,security,nuclear,power,plant,equipment,In,real,dition,maintenance,most,existing,methods,cannot,deal,sequences,periodic,abnormal,events,have,poor,extraction,from,these,data,this,paper,learning,anomaly,employing,AE,network,XGBoost,algorithm,proposed,nonlinear,sequential,features,coil,currents,automatically,efficiently,extracted,by,neural,units,behavior,model,was,established,reconstruct,errors,when,feeding,signals,leveraged,monitor,residuals,identify,outliers,results,demon,strate,that,effectively,different,timing,anomalies,provide,more,accurate,forecasting,performance
AB值：
0.559593
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
