A digital twin approach to system-level fault detection and diagnosis for improved equipment health monitoring

Nguyen, Tat Nghia; Ponciroli, Roberto; Bruck, Paul; Esselman, Thomas C.; Rigatti, Joseph A.; Vilim, Richard B.

doi:10.1016/j.anucene.2022.109002

A digital twin approach to system-level fault detection and diagnosis for improved equipment health monitoring

Journal Article · Sat Feb 19 00:00:00 EST 2022 · Annals of Nuclear Energy

DOI:https://doi.org/10.1016/j.anucene.2022.109002· OSTI ID:1957418

Nguyen, Tat Nghia ^[1]; Ponciroli, Roberto ^[1]; Bruck, Paul ^[2]; Esselman, Thomas C. ^[2]; Rigatti, Joseph A. ^[3]; Vilim, Richard B. ^[1]

Argonne National Lab. (ANL), Lemont, IL (United States)
LPI, Inc., Amsebury, MA (United States)
Dominion Energy, Richmond, VA (United States)

Automating the task of fault detection and diagnosis is crucial in the effort to reduce the operation and maintenance cost in the nuclear industry. This paper describes a physics-based approach for system-level diagnosis in thermal-hydraulic systems in nuclear power plants. The inclusion of physics information allows for the creation of virtual sensors, which provide improved fault diagnosis capability. The physics information also serves to better constrain diagnostic solutions to the physical domain. As a demonstration, various test cases for fault diagnosis in a high-pressure feedwater system were considered. The use of virtual sensors allows constructing performance models for two first-point feedwater heaters which would not have been possible otherwise due to the limited sensor set. Real-time plant data provided by a utility partner were used to assess the diagnostic approach. The detection of an abnormal event immediate after a plant startup pointed to faulty behaviors in the two first-point feedwater heaters. Further, this double-blind fault diagnosis was subsequently confirmed by the plant operator. In addition, several simulated sensor fault events demonstrated the capability of our algorithms in detecting and discriminating sensor faults.

View Accepted Manuscript (DOE)

Research Organization:: Argonne National Laboratory (ANL), Argonne, IL (United States)

Sponsoring Organization:: USDOE Office of Nuclear Energy; USDOE Office of Nuclear Energy (NE)

Grant/Contract Number:: AC02-06CH11357

OSTI ID:: 1957418

Alternate ID(s):: OSTI ID: 1962909

Journal Information:: Annals of Nuclear Energy, Journal Name: Annals of Nuclear Energy Vol. 170; ISSN 0306-4549

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (19)

The Unbearable Shallow Understanding of Deep Learning Plebe, Alessio; Grasso, Giorgio Minds and Machines, Vol. 29, Issue 4 https://doi.org/10.1007/s11023-019-09512-8	journal	December 2019
A review of process fault detection and diagnosis Venkatasubramanian, Venkat; Rengaswamy, Raghunathan; Yin, Kewen Computers & Chemical Engineering, Vol. 27, Issue 3 https://doi.org/10.1016/S0098-1354(02)00160-6	journal	March 2003
Fundamentals of model-based diagnosis de Kleer, Johan; Kurien, James IFAC Proceedings Volumes, Vol. 36, Issue 5 https://doi.org/10.1016/S1474-6670(17)36467-4	journal	June 2003
Secure embedded intelligence in nuclear systems: Framework and methods Garcia, Humberto E.; Aumeier, Steven E.; Al-Rashdan, Ahmad Y. Annals of Nuclear Energy, Vol. 140 https://doi.org/10.1016/j.anucene.2019.107261	journal	June 2020
A probabilistic model-based diagnostic framework for nuclear engineering systems Nguyen, Tat Nghia; Downar, Thomas; Vilim, Richard Annals of Nuclear Energy, Vol. 149 https://doi.org/10.1016/j.anucene.2020.107767	journal	December 2020
A multi-stage hybrid fault diagnosis approach for operating conditions of nuclear power plant Wang, Zhichao; Xia, Hong; Peng, Binsen Annals of Nuclear Energy, Vol. 153 https://doi.org/10.1016/j.anucene.2020.108015	journal	April 2021
Ensemble learning with diversified base models for fault diagnosis in nuclear power plants Li, Jiangkuan; Lin, Meng Annals of Nuclear Energy, Vol. 158 https://doi.org/10.1016/j.anucene.2021.108265	journal	August 2021
A data-driven adaptive fault diagnosis methodology for nuclear power systems based on NSGAII-CNN He, Chen; Ge, Daochuan; Yang, Minghan Annals of Nuclear Energy, Vol. 159 https://doi.org/10.1016/j.anucene.2021.108326	journal	September 2021
Research on robustness of five typical data-driven fault diagnosis models for nuclear power plants Li, Jiangkuan; Lin, Meng Annals of Nuclear Energy, Vol. 165 https://doi.org/10.1016/j.anucene.2021.108639	journal	January 2022
A physics-based parametric regression approach for feedwater pump system diagnosis Nguyen, Tat Nghia; Ponciroli, Roberto; Kibler, Timothy Annals of Nuclear Energy, Vol. 166 https://doi.org/10.1016/j.anucene.2021.108692	journal	February 2022
A deep transfer learning method for system-level fault diagnosis of nuclear power plants under different power levels Wang, Zhichao; Xia, Hong; Zhang, Jiyu Annals of Nuclear Energy, Vol. 166 https://doi.org/10.1016/j.anucene.2021.108771	journal	February 2022
A physics-informed deep learning approach for bearing fault detection Shen, Sheng; Lu, Hao; Sadoughi, Mohammadkazem Engineering Applications of Artificial Intelligence, Vol. 103 https://doi.org/10.1016/j.engappai.2021.104295	journal	August 2021
Physics-informed deep learning for signal compression and reconstruction of big data in industrial condition monitoring Russell, Matthew; Wang, Peng Mechanical Systems and Signal Processing, Vol. 168 https://doi.org/10.1016/j.ymssp.2021.108709	journal	April 2022
Driven by Data or Derived Through Physics? A Review of Hybrid Physics Guided Machine Learning Techniques With Cyber-Physical System (CPS) Focus Rai, Rahul; Sahu, Chandan K. IEEE Access, Vol. 8 https://doi.org/10.1109/ACCESS.2020.2987324	journal	January 2020
A Survey of Fault Diagnosis and Fault-Tolerant Techniques—Part I: Fault Diagnosis With Model-Based and Signal-Based Approaches Gao, Zhiwei; Cecati, Carlo; Ding, Steven X. IEEE Transactions on Industrial Electronics, Vol. 62, Issue 6 https://doi.org/10.1109/TIE.2015.2417501	journal	June 2015
Explainable and Trustworthy Diagnostics Achievable Through Process-Based Automated Reasoning Vilim, R.; Nguyen, T.; Ponciroli, R. 12th Nuclear Plant Instrumentation, Control and Human-Machine Interface Technologies (NPIC&HMIT 2021) https://doi.org/10.13182/T124-34543	conference	January 2021
Physics-Based Automated Reasoning for Health Monitoring: Sensor Set Selection Vilim, R.; Nguyen, T.; Ponciroli, R. 12th Nuclear Plant Instrumentation, Control and Human-Machine Interface Technologies (NPIC&HMIT 2021) https://doi.org/10.13182/T124-34545	conference	January 2021
Explainable Agency for Intelligent Autonomous Systems Langley, Pat; Meadows, Ben; Sridharan, Mohan Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 31, Issue 2 https://doi.org/10.1609/aaai.v31i2.19108	journal	February 2017
Digital Twin Concepts with Uncertainty for Nuclear Power Applications Kochunas, Brendan; Huan, Xun Energies, Vol. 14, Issue 14 https://doi.org/10.3390/en14144235	journal	July 2021

Similar Records

A physics-based parametric regression approach for feedwater pump system diagnosis

Journal Article · Tue Sep 28 20:00:00 EDT 2021 · Annals of Nuclear Energy · OSTI ID:1962058

Combined expert system/neural networks method for process fault diagnosis

Patent · Tue Aug 15 00:00:00 EDT 1995 · OSTI ID:100994

Combined expert system/neural networks method for process fault diagnosis

Patent · Sat Dec 31 23:00:00 EST 1994 · OSTI ID:870030

Related Subjects

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS
Fault detection
Feedwater system
Model-based diagnosis
Real-time data

A digital twin approach to system-level fault detection and diagnosis for improved equipment health monitoring

Citation Formats

References (19)

Similar Records

Related Subjects