TY - GEN
T1 - Coolant Pump Predictive Data Analytics from Signatures Generated by the Recursive Short Time Fast Fourier Transform
AU - Smith, James A.
AU - Agarwal, Vivek
N1 - Funding Information:
The major portion of this work was supported by the Laboratory Directed Research and Development for the Nuclear Science seU r Facility, under DEO -NE Idaho perO ations fO fice Contract DE -AC0 -I05 D14517. The authors are thankful to the ATR staffs (perO ations, Engineering and oW rking Group) for being so helpful and patient. A special acknowledgement goes to the INL technical editing group and Kelsey asG ton Judy Fairchild and Katie Stokes.
Funding Information:
The major portion of this work was supported by the Laboratory Directed Research and Development for the Nuclear Science User Facility, under DOE-NE Idaho Operations Office Contract DE-AC07-05ID14517. The authors are thankful to the ATR staffs (Operations, Engineering and Working Group) for being so helpful and patient. A special acknowledgement goes to the INL technical editing group and Kelsey Gaston, Judy Fairchild and Katie Stokes.
Publisher Copyright:
© 2023 American Nuclear Society, Incorporated.
PY - 2023
Y1 - 2023
N2 - Although a nuclear reactor is a hostile environment for sensors and signal transmissions, the reactor core is amenable to acoustic communication. An acoustic measurement infrastructure installed at the Advanced Test Reactor (ATR) nozzle trench area records acoustic signals that can capture reactor operating states. The distinct states produce unique signatures that can be identified and tracked using data processing and data analytics. The infrastructure relies on acoustic transmission through ATR in-pile structural components, piping, and coolant that transmit acoustically modified signals generated by the coolant pumps. This paper will discuss results from using the Recursive Short Time Fast Fourier Transform (RSTFFT) technique used to process acoustic signals and provide signatures that are identified and monitored by analytics. The RSTFFT is applied to ATR data to understand the vibration levels and signatures for different operating regimes as displayed by the spectrogram. The combination of coolant pumps for normal and high-power operation generate unique signatures. These acoustic signatures are used to develop machine learning approaches to automatically classify operating regimes. Two machine-learning models, Support Vector Machines and Linear Discriminant Analysis, were developed to classify two event classes. Class 1 is a normal steady-state operation, and Class 2 is any event that is due to start up, shut down, or other actions. Both types of machine learning models had over a 96% prediction accuracy for the two classes. These results lay the foundation for predictive analytic frameworks that can be leveraged by ATR to optimize operations and maintenance.
AB - Although a nuclear reactor is a hostile environment for sensors and signal transmissions, the reactor core is amenable to acoustic communication. An acoustic measurement infrastructure installed at the Advanced Test Reactor (ATR) nozzle trench area records acoustic signals that can capture reactor operating states. The distinct states produce unique signatures that can be identified and tracked using data processing and data analytics. The infrastructure relies on acoustic transmission through ATR in-pile structural components, piping, and coolant that transmit acoustically modified signals generated by the coolant pumps. This paper will discuss results from using the Recursive Short Time Fast Fourier Transform (RSTFFT) technique used to process acoustic signals and provide signatures that are identified and monitored by analytics. The RSTFFT is applied to ATR data to understand the vibration levels and signatures for different operating regimes as displayed by the spectrogram. The combination of coolant pumps for normal and high-power operation generate unique signatures. These acoustic signatures are used to develop machine learning approaches to automatically classify operating regimes. Two machine-learning models, Support Vector Machines and Linear Discriminant Analysis, were developed to classify two event classes. Class 1 is a normal steady-state operation, and Class 2 is any event that is due to start up, shut down, or other actions. Both types of machine learning models had over a 96% prediction accuracy for the two classes. These results lay the foundation for predictive analytic frameworks that can be leveraged by ATR to optimize operations and maintenance.
KW - Acoustics
KW - Data analytics
KW - Predictive maintenance
KW - Sensors
UR - https://www.scopus.com/pages/publications/85172427823
UR - https://www.mendeley.com/catalogue/29a9ba05-510c-33d2-ae58-6dace6733d0f/
U2 - 10.13182/NPICHMIT23-41335
DO - 10.13182/NPICHMIT23-41335
M3 - Conference contribution
AN - SCOPUS:85172427823
T3 - Proceedings of 13th Nuclear Plant Instrumentation, Control and Human-Machine Interface Technologies, NPIC and HMIT 2023
SP - 1306
EP - 1316
BT - Proceedings of 13th Nuclear Plant Instrumentation, Control and Human-Machine Interface Technologies, NPIC and HMIT 2023
PB - American Nuclear Society
T2 - 13th Nuclear Plant Instrumentation, Control and Human-Machine Interface Technologies, NPIC and HMIT 2023
Y2 - 15 July 2023 through 20 July 2023
ER -