https://orcid.org/0000-0002-8283-5903
![Sample our Built Environment journals, sign in here to start your access, Latest two full volumes FREE to you for 14 days]({"type":"image" , "src" : "/sda/5926/TOC-Subject-Sample-2021-Built-Environment.jpg"})
Abstract
The condition assessment of equipment in nuclear power plants (NPPs) could provide essential information for operation and maintenance decisions, which would have a significant impact on improving the safety and economy of NPPs. To date, substantial work has been conducted on the condition assessment based on machine learning for NPP equipment. To provide a comprehensive overview for researchers interested in developing machine learning methods for NPP equipment condition assessment, this critical review presents a detailed literature survey on state-of-the-art research and identifies challenges for future study. Valuable information is presented, including major failure modes, data sources, maintenance strategies, and the relationship between equipment lifetime, assessment technology, and maintenance strategy. Following the typical lifetime of NPP equipment for condition assessment, current works in this domain are categorized into anomaly detection, remaining useful life prediction, and fault detection and diagnosis. The techniques and methodologies adopted in the literature are summarized from each aspect. In particular, the in-depth NPP equipment condition assessment survey based on deep learning methods is presented. In addition, we elaborate on current issues, challenges, and future research directions for the condition assessment of equipment in NPPs. These directions we believe will pave the way for equipment condition assessment.
Acronyms
| 1-D: | = | one-dimensional |
| 1DCNN: | = | one-dimensional CNN |
| AANN: | = | auto-associative neural network |
| ac: | = | alternating current |
| AD: | = | anomaly detection |
| AE: | = | autoencoder |
| AGR: | = | advanced gas-cooled reactor |
| ANN: | = | artificial neural network |
| AR: | = | autoregressive |
| ARIMA: | = | autoregressive integrated moving average |
| BWR: | = | boiling water reactor |
| CBM: | = | condition-based maintenance |
| CM: | = | corrective maintenance |
| CNN: | = | convolutional neural network |
| CRPL: | = | change of reactor power level |
| DBN: | = | deep belief network |
| DCS: | = | distributed control system |
| DCNN: | = | deep convolutional neural network |
| DI&C: | = | digital instrument and control |
| DL: | = | deep learning |
| DNN: | = | deep neural network |
| ESDE: | = | excess steam demand event |
| ESVD: | = | enhanced singular value decomposition |
| EVS: | = | explained variance score |
| FBTR: | = | fast breeder test reactor |
| FCN: | = | full convolutional network |
| FDA: | = | Fisher discriminant analysis |
| FDD: | = | fault detection and diagnosis |
| FFANN: | = | feedforward artificial neural network |
| FFNN: | = | feedforward neural network |
| FMEA: | = | failure modes and effects analysis |
| FOUHSM: | = | first-order uncertain hidden semi-Markov |
| GAN: | = | generative adversarial network |
| GLRT: | = | generalized likelihood ratio test |
| GRU: | = | gated recurrent unit |
| HMM: | = | hidden Markov model |
| I&C: | = | instrument control |
| IAEA: | = | International Atomic Energy Agency |
| KFDA: | = | kernel Fisher discriminant analysis |
| KPCA: | = | kernel principal component analysis |
| KSVM: | = | kernel support vector machine |
| KNN: | = | K-nearest neighbors |
| LOAF: | = | loss of all feedwater |
| LOCA: | = | loss-of-coolant accident |
| LOEP: | = | loss of electrical power |
| LOFW: | = | loss of feedwater |
| LSTM: | = | long short-term memory |
| MAE: | = | mean absolute error |
| MCSVM: | = | multiclass support vector machine |
| MNN: | = | multiple neural networks |
| MNSR: | = | miniature neutron source reactor |
| MLP: | = | multilayer perceptron |
| MSLB: | = | main steam line break |
| NPP: | = | nuclear power plant |
| OC-LSTM: | = | one-class long short-term memory |
| OCSVM: | = | one-class support vector machine |
| OPRV: | = | opening of pressurizer relief valve |
| PCA: | = | principal component analysis |
| PCB: | = | printed circuit board |
| PDF: | = | probability distribution function |
| PdM: | = | predictive maintenance |
| PF: | = | particle filtering |
| PM: | = | preventive maintenance |
| PWR: | = | pressurized water reactor |
| RCM: | = | reliability-centered maintenance |
| RCP: | = | reactor coolant pump |
| RCPF: | = | reactor coolant pump failure |
| RERF: | = | reactivity-related faults |
| RF: | = | random forest |
| RMSE: | = | root-mean-squared error |
| RNN: | = | recurrent neural network |
| RUL: | = | remaining useful life |
| SDF: | = | symbolic dynamic filtering |
| SGTR: | = | steam generator tube rupture |
| SSC: | = | structures, systems, and components |
| SVD: | = | singular value decomposition |
| SVM: | = | support vector machine |
| SVR: | = | support vector regression |
| TCA: | = | traditional contribution analysis |
| TCN: | = | temporal convolution network |
| XGB: | = | extreme gradient boost regression |
Acknowledgments
This work was supported in part by Major Scientific Instrument Research of the National Natural Science Foundation of China (no. 61627810) and the National Science and Technology Major Program of China (no. 2018YFB1305003).
Disclosure Statement
No potential conflict of interest was reported by the authors.