Remaining Useful Life Prediction Techniques of Electric Valves for Nuclear Power Plants with Convolution Kernel and LSTM

Wang, Hang; Peng, Minjun; Liu, Yong-kuo; Liu, Shiwen; Xu, Renyi; Saeed, Hanan A.

doi:10.1155/2020/8349349

Cited by 7 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 7 shows the illustration of the RUL prediction . The DL technologies with strong feature extraction capability are more and more widely used in RUL prediction of key components in the nuclear industry [96,111,112] . Key Subject Laboratory of Nuclear Safety and Simulation Technology, Harbin Engineering University, Harbin, China studied the RUL prediction of electric valves in NPPs based on DL models [96,111,112] .…”

Section: Computer Vision In Nuclear Industrymentioning

confidence: 99%

“…The DL technologies with strong feature extraction capability are more and more widely used in RUL prediction of key components in the nuclear industry [96,111,112] . Key Subject Laboratory of Nuclear Safety and Simulation Technology, Harbin Engineering University, Harbin, China studied the RUL prediction of electric valves in NPPs based on DL models [96,111,112] . The aging and degradation of electric valves are mostly caused by the uneven lattice of valve body, uneven fluid impact, fluid corrosion effect, and radioactive material irradiation [97] .…”

Section: Computer Vision In Nuclear Industrymentioning

confidence: 99%

“…The aging and degradation of electric valves are mostly caused by the uneven lattice of valve body, uneven fluid impact, fluid corrosion effect, and radioactive material irradiation [97] . Wang et al [96,111,112] made some reasonable assumptions and approximate design for the aging parts of electric valves by adjusting the tightness of screws, referring to the experimental process and data collection method of simulating valve aging proposed in Ref. [113].…”

Section: Computer Vision In Nuclear Industrymentioning

confidence: 99%

“…[96] also introduced signal acquisition devices, e.g., acoustic emission sensor, pressure sensor, temperature sensor, and flow sensor, to obtain rich relevant features. Based on the previous pre-processing works, Wang et al [111] proposed DL methods based on LSTM with convolution kernel, improved temporal convolutional network [96] and Convolutional Auto-Encoder (CAE) [112] , to extract the sequential visual features of electric valves, so as to realize the prediction of RUL. Experiments demonstrate that these DL-based methods can predict RUL more accurately and quickly than other typical machine learning methods.…”

Section: Computer Vision In Nuclear Industrymentioning

confidence: 99%

See 3 more Smart Citations

Deep learning in nuclear industry: A survey

Tang

Gao

et al. 2022

Big Data Min. Anal.

View full text Add to dashboard Cite

As a high-tech strategic emerging comprehensive industry, the nuclear industry is committed to the research, production, and processing of nuclear fuel, as well as the development and utilization of nuclear energy.Nowadays, the nuclear industry has made remarkable progress in the application fields of nuclear weapons, nuclear power, nuclear medical treatment, radiation processing, and so on. With the development of artificial intelligence and the proposal of "Industry 4.0", more and more artificial intelligence technologies are introduced into the nuclear industry chain to improve production efficiency, reduce operation cost, improve operation safety, and realize risk avoidance. Meanwhile, deep learning, as an important technology of artificial intelligence, has made amazing progress in theoretical and applied research in the nuclear industry, which vigorously promotes the development of informatization, digitization, and intelligence of the nuclear industry. In this paper, we first simply comb and analyze the intelligent demand scenarios in the whole industrial chain of the nuclear industry. Then, we discuss the data types involved in the nuclear industry chain. After that, we investigate the research status of deep learning in the application fields corresponding to different data types in the nuclear industry. Finally, we discuss the limitation and unique challenges of deep learning in the nuclear industry and the future direction of the intelligent nuclear industry.

show abstract

Section: Computer Vision In Nuclear Industrymentioning

confidence: 99%

Section: Computer Vision In Nuclear Industrymentioning

confidence: 99%

Section: Computer Vision In Nuclear Industrymentioning

confidence: 99%

Section: Computer Vision In Nuclear Industrymentioning

confidence: 99%

See 2 more Smart Citations

Deep learning in nuclear industry: A survey

Tang

Gao

et al. 2022

Big Data Min. Anal.

View full text Add to dashboard Cite

show abstract

“…ey also verified that the high-pressure region on the surface of the valve plug was the main reason for the lateral oscillating fluid force, which was a negative damping force. Many other studies of control valves have also conducted [9][10][11][12][13][14].…”

Section: Introductionmentioning

confidence: 99%

Dynamic Simulation of a Warship Control Valve Based on a Mechanical-Electric-Fluid Cosimulation Model

Han

Xie

Wang

et al. 2021

Science and Technology of Nuclear Installations

View full text Add to dashboard Cite

Control valves have an important function in the warship power system. In engineering practice, the fluid oscillation inside the control valve causes the additional load to the valve actuator. When the additional load is added to the original load of the valve, it is possible that the required driving force (or driving moment) of the valve is greater than the maximum force (or moment) output by the actuator, which may cause the abnormal stop of the actuator. Conventionally, the interaction effect of the valve mechanical and electric components on the valve chamber’s flow field cannot be considered in computational fluid dynamics (CFD) simulations, so the oscillating fluid loads cannot be accurately obtained. In order to solve this problem, the mechanical-electric-fluid integrated valve model, using the FLUENT and AMESim cosimulation method, was developed to embody the interaction effect between the components of each part of the control valve and exhibit the fluid oscillation during the operating process of the control valve. Compared with the pure software simulations, the unsteady flow characteristics and dynamic response of the actuator were synchronously obtained in this study, which accurately captured the sudden fluid loads required for further compensation. At the same time, the differences in performance of different valve plugs were compared. The stability time of the valve plug and oscillation amplitude of the unstable fluid loads were distinct for control valves with different flow characteristics. The results can aid in understanding the instability mechanism of the fluid load in the control valve better, which provides the calculation basis for compensating the additional load on the valve plug and improve the reliability of the control valve.

show abstract

Deep learning the Hurst parameter of linear fractional processes and assessing its reliability

Boros,

Csanády,

Ivkovic

et al. 2024

Quality & Reliability Eng

View full text Add to dashboard Cite

This research explores the reliability of deep learning, specifically Long Short‐Term Memory (LSTM) networks, for estimating the Hurst parameter in fractional stochastic processes. The study focuses on three types of processes: fractional Brownian motion (fBm), fractional Ornstein–Uhlenbeck (fOU) process, and linear fractional stable motions (lfsm). The work involves a fast generation of extensive datasets for fBm and fOU to train the LSTM network on a large volume of data in a feasible time. The study analyses the accuracy of the LSTM network's Hurst parameter estimation regarding various performance measures like root mean squared error (RMSE), mean absolute error (MAE), mean relative error (MRE), and quantiles of the absolute and relative errors. It finds that LSTM outperforms the traditional statistical methods in the case of fBm and fOU processes; however, it has limited accuracy on lfsm processes. The research also delves into the implications of training length and valuation sequence length on the LSTM's performance. The methodology is applied to estimating the Hurst parameter in li‐ion battery degradation data and obtaining confidence bounds for the estimation. The study concludes that while deep learning methods show promise in parameter estimation of fractional processes, their effectiveness is contingent on the process type and the quality of training data.

show abstract

Remaining Useful Life Prediction Techniques of Electric Valves for Nuclear Power Plants with Convolution Kernel and LSTM

Cited by 7 publications

References 21 publications

Deep learning in nuclear industry: A survey

Deep learning in nuclear industry: A survey

Dynamic Simulation of a Warship Control Valve Based on a Mechanical-Electric-Fluid Cosimulation Model

Deep learning the Hurst parameter of linear fractional processes and assessing its reliability

Contact Info

Product

Resources

About