Lifespan Prediction of Electronic Card in Nuclear Power Plant Based on Few Samples

doi:10.1007/s12204-023-2669-9

Abstract

Abstract: A lifespan prediction model was developed based on a few samples to provide decision-making information for operation and maintenance, as well as improve the economy and safety of nuclear power plant (NPP) operations. This paper applies a Weibull model to forecast the lifespan of electronic cards with a few samples in NPPs. Relationship between the lifespan prediction of electronic cards and the ambient temperature is revealed using the Arrhenius equation. Censored samples are used to compensate for the lack of fault electronic card data. Scale parameter and shape parameter of the Weibull model are optimized by adjusting the weight ratio between the censored data and the fault data. Characteristic life is then obtained using the rank regression fitting equation. Parameters of the Arrhenius equation can be calculated by dividing the samples into groups according to the ambient temperature. A case study of the intermediate range high-voltage electric card of ex-core neutron detectors demonstrates that the lifespan prediction of electronic cards in NPPs can be successfully predicted with a few samples by combining the Weibull model and the Arrhenius model. This can help provide preventive maintenance recommendations for electronic cards. Finally, operation suggestions for the electronic card’s ambient temperature can be made by utilizing the temperature-life model.

Key words: lifespan, few samples, Weibull model, Arrhenius equation, nuclear power plant (NPP)

摘要： 在小样本故障数据情形下，对核电厂电子板卡剩余寿命进行预测研究，可以为核电厂运维提供必要的决策依据，提升核电厂机组运行的经济性和安全性。为了解决小样本故障问题，本文采用威布尔模型来预测在核电厂电子卡件寿命，并利用阿伦尼斯方程揭示了电子卡寿命预测与环境温度之间的关系。首先采用截尾数据来扩充故障样本，通过删失数据与故障数据之间的权重比来进一步优化威布尔模型的尺度参数和形状参数；并利用秩回归拟合方程的方法获得卡件的特征寿命；采用小样本分组实验的方法来获取阿伦尼斯模型参数。通过对堆外中程高压电子卡的案例研究表明，在小样本故障场景下，结合威布尔模型和阿伦尼斯模型，可以对核电厂电子卡的寿命进行成功预测。该方法可以为核电厂电子卡件的预防性维修周期制定提供决策依据。最后利用温度-寿命模型可以为卡件的运维提供参考建议。

关键词: 寿命，少样本，威布尔模型，阿伦尼乌斯公式，核电厂

CLC Number:

TM623.7

XU Yong, CAI Yunze, SONG Lin. Lifespan Prediction of Electronic Card in Nuclear Power Plant Based on Few Samples[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(6): 1188-1194.

References

[1] XU Y, CAI Y Z, SONG L. Review of research on condition assessment of nuclear power plant equipment based on data-driven [J]. Journal of Shanghai Jiao Tong University, 2022, 56(3): 267-278 (in Chinese).

[2] YU W K, HARRIS T A. A new stress-based fatigue life model for ball bearings [J]. Tribology Transactions, 2001, 44(1): 11-18.

[3] MADAR E, KLEIN R, BORTMAN J. Contribution of dynamic modeling to prognostics of rotating machinery [J]. Mechanical Systems and Signal Processing, 2019, 123: 496-512.

[4] REN S H, XUE F, YU W W, et al. Reliability residual-life prediction method for thermal aging based on performance degradation [J]. Nuclear Power Engineering, 2013, 34(5): 96-99 (in Chinese).

[5] UTAH M N, JUNG J C. Fault state detection and remaining useful life prediction in AC powered solenoid operated valves based on traditional machine learning and deep neural networks [J]. Nuclear Engineering and Technology, 2020, 52(9): 1998-2008.

[6] LEE B S, CHUNG H S, KIM K T, et al. Remaining life prediction methods using operating data and knowledge on mechanisms [J]. Nuclear Engineering and Design, 1999, 191(2): 157-165.

[7] NGUYEN H P, FAURIAT W, ZIO E, et al. A data-driven approach for predicting the remaining useful life of steam generators [C]//2018 3rd International Conference on System Reliability and Safety. Barcelona: IEEE, 2018: 255-260.

[8] AIZPURUA J I, MCARTHUR S D J, STEWART B G, et al. Adaptive power transformer lifetime predictions through machine learning and uncertainty modeling in nuclear power plants [J]. IEEE Transactions on Industrial Electronics, 2019, 66(6): 4726-4737.

[9] WANG H, PENG M J, XU R Y, et al. Remaining useful life prediction based on improved temporal convolutional network for nuclear power plant valves [J]. Frontiers in Energy Research, 2020, 8: 584463.

[10] WANG H, PENG M J, LIU Y K, et al. Remaining useful life prediction techniques of electric valves for nuclear power plants with convolution kernel and LSTM [J]. Science and Technology of Nuclear Installations, 2020, 2020: 1-13.

[11] SAARELA O, HULSUND J E, TAIPALE A, et al. Remaining Useful Life Estimation for Air Filters at a Nuclear Power Plant[C]//2nd European Conference of the Prognostics and Health Management Society 2014. Nantes: PHM Society, 2014: 75-81.

[12] YOU D Z, LIU H, ZHANG Y P. Optimization design and reliability statistical analysis of mechanical accelerated life test based on Weibull distribution [J]. Journal of Mechanical & Electrical Engineering, 2023, 40(5): 664-672 (in Chinese).

[13] LU J, GONG P H, YE J P, et al. Learning from very few samples: A survey [DB/OL]. (2020-09-06). https://arxiv.org/abs/2009.02653

[14] HALLINAN A J Jr. A review of the weibull distribution [J]. Journal of Quality Technology, 1993, 25(2): 85-93.

[15] SHI J, SHEN D H, SHI H N, et al. Reliability data process and analysis of instrument and control switch in nuclear power plants [J]. Nuclear Power Engineering, 2010, 31(2): 54-57 (in Chinese).

[16] KANG M, LEE S, PARK H, et al. Lifetime estimation for optocouplers using accelerated degradation test [J]. Quality and Reliability Engineering International, 2022, 38(1): 560-573.