A multi-stage hybrid fault diagnosis approach for operating conditions of nuclear power plant

Prognostics and Health Management in Nuclear Power Plants: An Updated Method-Centric Review With Special Focus on Data-Driven Methods

“…In the nuclear field, Wang et al (2019b) developed an improved particle swarm optimization, and Zhang et al (2015b) used a hybrid of the bare bones particle swarm optimization and differential evolution. Beyond simply developing a better means of parameter optimization, Wang et al (2021) introduced a hybrid least squares SVM method for fault diagnosis in NPPs. Another approach beyond optimization was to separately train an ensemble of SVMs and combine them after training .…”

Data‐driven fault diagnosis approaches for industrial equipment: A review

“…Turbine of thermal power plant (Ali & Mahdi, 2014;Ricks & Mengshoel, 2014), steam turbine (Ajami & Daneshvar, 2012;Karlsson et al, 2008;Rodriguez et al, 2013;Salahshoor et al, 2011), nuclear power plant (Ayodeji et al, 2018;Jianping & Jiang, 2015;Jin et al, 2023;Lu & Upadhyaya, 2005;Sihombing & Torbol, 2018;Wang et al, 2022;Wang, Xia, et al, 2021;Wu et al, 2018;You et al, 2021), gas turbine of generator (Wong et al, 2014), hydroelectric system (Xu et al, 2019), wind turbine (Biswal & Sabareesh, 2015;Asgarpour & Sorensen, 2018;Bakdi et al, 2019;Durbhaka & Selvaraj, 2016;Pashazadeh et al, 2018;Schlechtingen & Ferreira, 2011;Wang, Liang, et al, 2020;Yu et al, 2018), inverter (Cai et al, 2017), Power transmission (Yongli et al, 2006), transformer (Chen, 2016, and electrical energy consumption in supermarket (Mavromatidis et al, 2013).…”

“…The data‐driven approach establishes the causal relationships between cause, symptom, and fault to predict the fault (Jun & Kim, 2017; Sahu & Palei, 2020b). Looking at the importance of fault diagnosis, its applications have been extended from medical sciences to engineering by researchers for wide variety of industrial machines/systems: air‐conditioning equipment (Mirnaghi & Haghighat, 2020), rotating machine (Brito et al, 2022; Liu, Yang, et al, 2018; Nath et al, 2021), bearing fault diagnosis (Cerrada et al, 2018; Zhang, Zhang, et al, 2019), induction motor (Kumar & Hati, 2020), dragline (Sahu & Palei, 2020a; Sahu & Palei, 2020b; Sahu & Palei, 2022), thermal power plant (Ali & Mahdi, 2014; Ricks & Mengshoel, 2014), steam turbine (Ajami & Daneshvar, 2012; Karlsson et al, 2008; Salahshoor et al, 2011), and nuclear power plant (Ayodeji et al, 2018; Jianping & Jiang, 2015; Lu & Upadhyaya, 2005; Sihombing & Torbol, 2018; Wang, Xia, et al, 2021; Wu et al, 2018; You et al, 2021). The fault diagnosis of heavy industrial machinery through DDFD approaches are demonstrated in past studies using Bayesian network (BN) (Sahu & Palei, 2020b), artificial neural network (ANN) (Karlsson et al, 2008; Sahu & Palei, 2020a), fault tree (Gupta et al, 2006; Sihombing & Torbol, 2018), fuzzy inference (Salahshoor et al, 2011), principal component analysis (PCA) (Bakdi et al, 2019; Lu & Upadhyaya, 2005), independent component analysis (Ajami & Daneshvar, 2012), support vector machine (SVM) (Dindarloo & Siami‐Irdemoosa, 2017; Jung, 2019), hidden Markov model (HMM) (Fan et al, 2019), and deep learning (Li, Yao, et al, 2021; Mushtaq et al, 2021; Zhu et al, 2023).…”

“…The data-driven approach establishes the causal relationships between cause, symptom, and fault to predict the fault (Jun & Kim, 2017;Sahu & Palei, 2020b). Looking at the importance of fault diagnosis, its applications have been extended from medical sciences to engineering by researchers for wide variety of industrial machines/systems: air-conditioning equipment (Mirnaghi & Haghighat, 2020), rotating machine (Brito et al, 2022;Liu, Yang, et al, 2018;Nath et al, 2021), bearing fault diagnosis (Cerrada et al, 2018;, induction motor (Kumar & Hati, 2020), dragline (Sahu & Palei, 2020a;Sahu & Palei, 2020b;Sahu & Palei, 2022), thermal power plant (Ali & Mahdi, 2014;Ricks & Mengshoel, 2014), steam turbine (Ajami & Daneshvar, 2012;Karlsson et al, 2008;Salahshoor et al, 2011), and nuclear power plant (Ayodeji et al, 2018;Jianping & Jiang, 2015;Lu & Upadhyaya, 2005;Sihombing & Torbol, 2018;Wang, Xia, et al, 2021;Wu et al, 2018;You et al, 2021).…”

Metamodeling and On-Line Clustering for Loss-of-Flow Accident Precursors Identification in a Superconducting Magnet Cryogenic Cooling Circuit

“…In the nuclear field (which is of particular interest to the present paper), several techniques have been employed for the early identification and diagnosis of accidents in fission systems, including: classical neural network architectures and Bayesian statistics for identifying LOCA events in a pressurized heavy water reactor [58]; deep neural networks for the fault detection and remaining useful life prediction of solenoid operated valves [59] and for online monitoring of the (modular) Integrated Pressurized Water Reactor IP-200 [60]; (Kernel) Principal Component Analysis combined with clustering for anomaly detection and isolation in an advanced heavy water reactor [61] and for spotting pipe ruptures in the cooling system of a pressurized light-water reactor [62]; particle filters embedded with neural networks to detect very small-break LOCAs in pressurized water reactors [63]; Auto-Associative Kernel Regression for early warnings about the water level of a pressurizer, on the moisture separator and reheater temperature transmitters and on environmental influences in real nuclear power plants of the Korea Hydro & Nuclear Power Co., Ltd. (KHNP) (Central Research Institute, KHNP, 70, 1312-gil, Yuseong-daero, Yuseong-gu, Daejeon 34101, Republic of Korea) [64]; Bayesian Networks for the modelbased diagnosis in a single-phase heat exchanger [65]; Support Vector Machines combined with Gaussian Process Regression for the transient analysis of seven different (normal and accidental) conditions (LOCAs, load rejection, steam generator rupture, etc.) in a simulated nuclear plant [66]; incremental learning and reconciliation of different clustering approaches by unsupervised schemes applied to a fleet of nuclear power plant turbines during shut-down transients [67]. While acknowledging this wide and diversified framework of algorithms and applications, it is important to notice that to the best of the authors' knowledge: (i) the structured, integrated combination of advanced methods proposed in this work is new and original; (ii) no intelligent techniques for prompt anomaly detection, fault diagnosis and precursor identification have yet been developed for, and applied to, nuclear fusion systems.…”