为了提高冷水机组传感器的故障诊断性能,提出了一种基于软阈值时序卷积网络的编码-解码器重构模型(ST-TCN)
并建立基于该模型的传感器故障诊断方法。采用时序卷积网络(TCN)充分挖掘冷水机组传感器的时间相关性、热力学物理量间的数据相关性以及动态响应差异性特征。在TCN的残差块中引入软阈值自适应模块剔除冗余信息,降低噪声干扰。依托ST-TCN模型“端到端”的网络结构优势,将绝对重构残差向量与故障阈值向量进行比较,直接定位故障传感器。在实际压缩式冷水机组平台上采集传感器数据进行实验,结果表明,软阈值自适应模块能有效地增强网络模型的重构能力,从而提高故障传感器的诊断性能。以压缩机吸气温度传感器T1为例,ST-TCN的平均偏差故障识别率比改进前提升了45.9%;与其他故障诊断方法相比,所提的最新框架获得了较高的偏差故障识别率。
石大亮,刘江岩,李夔宁,刘彬.基于关联规则分类的冷水机组故障诊断[J].制冷学报,2020(05).
王秋杰,金涛,梅李鹏,刘军.基于模型分层的配电网故障诊断方法[J].电力自动化设备,2020(01).
陈乐瑞,曹建福,王晓琪.结合非线性频谱和核主元分析的机器人用RV减速器故障诊断[J].西安交通大学学报,2020(01).
李冬辉,尹海燕,郑博文,刘玲玲.改进的LSTM方法在冷水机组传感器故障检测中的应用[J].电工技术学报,2019(11).
王卉,李英顺.改进型证据更新规则的动态故障诊断算法[J].计算机工程与应用,2020(02).
翟坤,杜文霞,吕锋,辛涛,句希源.一种改进的动态核主元分析故障检测方法[J].化工学报,2019(02).
赵广社,吴思思,荣海军.多源统计数据驱动的航空发动机剩余寿命预测方法[J].西安交通大学学报,2017(11).
Yao Wanli,Li Donghui,Gao Long.Fault detection and diagnosis using tree-based ensemble learning methods and multivariate control charts for centrifugal chillers[J].Journal of Building Engineering,2022.
Yan Xiuying,Guan Ting,Fan Kaixing,Sun Qing.Novel double layer BiLSTM minor soft fault detection for sensors in air-conditioning system with KPCA reducing dimensions[J].Journal of Building Engineering,2021.
Wu Ping,Lou Siwei,Zhang Xujie,He Jiajun,Liu Yichao,Gao Jinfeng.Data-Driven Fault Diagnosis Using Deep Canonical Variate Analysis and Fisher Discriminant Analysis[J].IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,2021.
Liu Chongdang,Zhang Linxuan,Yao Rong,Wu Cheng.Dual Attention-Based Temporal Convolutional Network for Fault Prognosis Under Time-Varying Operating Conditions[J].IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,2021.
Zhenxin Zhou,Guannan Li,Jiangyu Wang,Huanxin Chen,Hanlu Zhong,Zihan Cao.A comparison study of basic data-driven fault diagnosis methods for variable refrigerant flow system[J].Energy & Buildings,2020.
Zhao Minghang,Zhong Shisheng,Fu Xuyun,Tang Baoping,Pecht Michael.Deep Residual Shrinkage Networks for Fault Diagnosis[J].IEEE Transactions on Industrial Informatics,2020.
Chao Meng,Xue Song Jiang,Xiu Mei Wei,Tao Wei.A Time Convolutional Network Based Outlier Detection for Multidimensional Time Series in Cyber-Physical-Social Systems[J].IEEE Access,2020.
Big Data Enterprise and Artificial Intelligence Laboratory, University of the West of England, United Kingdom,Division of Building Science and Technology, College of Engineering, City University of Hong Kong, Hong Kong.Novel pattern recognition-enhanced sensor fault detection and diagnosis for chiller plant[J].Energy & Buildings,2020.
Ding Li,Donghui Li,Chengdong Li,Lin Li,Long Gao.A novel data-temporal attention network based strategy for fault diagnosis of chiller sensors[J].Energy & Buildings,2019.
School of Urban Construction, Wuhan University of Science and Technology, Wuhan, PR China,School of Urban Construction, Wuhan University of Science and Technology, Wuhan, PR China,Department of Building Environment and Energy Engineering, Wuhan Business University, Wuhan, PR China,Center for the Built Environment, University of California, Berkeley, USA,School of Urban Construction, Wuhan University of Science and Technology, Wuhan, PR China.Chiller sensor fault detection based on empirical mode decomposition threshold denoising and principal component analysis[J].Applied Thermal Engineering,2018.
Pankaj Malhotra,Anusha Ramakrishnan,Gaurangi Anand,Lovekesh Vig,Puneet Agarwal,Gautam Shroff.LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection.[J].CoRR,2016.
Shengwei Wang,Jingtan Cui.Sensor-fault detection, diagnosis and estimation for centrifugal chiller systems using principal-component analysis method[J].Applied Energy,2004.
Bernhard Sch&ouml,lkopf,Alexander Smola,Klaus-Robert M&uuml,ller.Nonlinear Component Analysis as a Kernel Eigenvalue Problem[J].Neural Computation,1998(5).
0
浏览量
13
下载量
1
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621