| 22 | 0 | 9 |
| Downloads | Citas | Reads |
Aiming at the problem of difficulty in estimating reliability parameters in the case of small samples, a reliability parameter estimation method based on the combination of virtual augmentation theory and Bayes is proposed(BP-B-Bayes). First, the original small-sample data are learned by BP neural network, and the trained BP neural network is used to generate virtual data with the same distribution law as the real data; then the Bootstrap method is used to sample the virtual data to obtain the virtual sample set, and the parameter estimation set is obtained by the great likelihood method; then, the distribution fitting method is used to obtain the parameter a priori by combining the normal distribution with the kernel density estimation. Then, the prior distribution of parameters is obtained by combining normal distribution and kernel density estimation; finally, the parameter estimation is realized by using Bayesian on the basis of this prior distribution, and compared with other traditional parameter estimation methods. The results show that, based on the technique of virtual sample augmentation, the parameter estimation of small samples by Bayesian method has higher stability and accuracy, which provides a new solution idea for the reliability parameter estimation of small samples.
[1]王艺玮,邓蕾,郑联语,等.基于多通道融合及贝叶斯理论的刀具剩余寿命预测方法[J].机械工程学报,2021,57(13):214-224.WANG Y W,DENG L,ZHENG L Y,et al.A tool remaining life prediction method based on multi-channel fusion and Bayesian theory[J].Journal of Mechanical Engineering,2021,57(13):214-224.
[2]刘彪,赵宇飞,陈祖煜,等.小样本条件下砂砾石坝料级配特征参数的贝叶斯估计方法[J].水利学报,2022,53(5):608-620.LIU B,ZHAO Y F,CHEN Z Y,et al.Bayesian estimation method of gravel dam material gradation characteristic parameters under small sample condition[J].Journal of Water Resources,2022,53(5):608-620.
[3]GABBARD H,MESSENGER C,HENG I S,et al.Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy[J].Nature Physics,2022,18(1):112-117.
[4]曾强,黄政,魏曙寰.融合专家先验知识和单调性约束的贝叶斯网络参数学习方法[J].系统工程与电子技术,2020,42(3):646-652.ZENG Q,HUANG Z,WEI S H.Bayesian network parameter learning method integrating expert prior knowledge and monotonicity constraint[J].Systems Engineering and Electronics,2020,42(3):646-652.
[5]VAN D S R,DEPAOLI S,KING R,et al.Bayesian statistics and modelling[J].Nature Reviews Methods Primers,2021,1(1):1.
[6]BISSI A,SINHA A,ZHOU X.Selected topics in analytic conformal bootstrap:aguided journey[J].Physics Reports,2022,991:1-89.
[7]李铁成,刘清泉,任江波,等.基于动态优化马尔可夫链的线路继电保护装置状态预测方法[J].电力系统保护与控制,2022,50(13):97-106.LI T C,LIU Q Q,REN J B,et al.State prediction method of line relay protection dvice based on dnamic otimization Markov chain[J].Power System Protection and Control,2022,50(13):97-106.
[8]LI Y,GAN Z,SHEN Y,et al.Storygan:a sequential conditional gan for story visualization[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach:IEEE,2019:6329-6338.
[9]JIANG F,MA J,WEBSTER C J,et al.Building layout generation using site-embedded GAN model[J].Automation in Construction,2023,151:104888.
[10]戴志辉,李芷筠,焦彦军,等.基于BP神经网络的小样本失效数据下继电保护可靠性评估[J].电力自动化设备,2014,34(11):129-134.DAI Z H,LI Z J,JIAO Y J,et al.Reliability assessment of relay protection under small sample failure data based on BP neural network[J].Power Automation E-quipment,2014,34(11):129-134.
[11]SONG S,XIONG X,WU X,et al.Modeling the SOFCby BP neural network algorithm[J].International Journal of Hydrogen Energy,2021,46 (38):20065-20077.
[12]RUAN X,ZHU Y,LI J,et al.Predicting the citation counts of individual papers via a BP neural network[J].Journal of Informetrics,2020,14(3):101039.
[13]MANLY B F.Randomization,bootstrap and Montecarlo methods in biology[M].London:Chapman&Hall/CRC,2018.
[14]SMID S C,MCNEISH D,MIOCEVIC M,et al.Bayesian versus frequentist estimation for structural equation models in small sample contexts:a systematic review[J].Structural Equation Modeling:A Multidisciplinary Journal,2020,27(1):131-161.
[15]张震,刘俭辉,赵成,等.基于Bootstrap的小样本可靠性评估方法[J].兰州理工大学学报,2022,48(1):39-44.ZHANG Z,LIU J H,ZHAO C,et al.Small sample reliability evaluation method based on Bootstrap[J].Journal of Lanzhou University of Technology,2022,48(1):39-44.
Basic Information:
DOI：10.13291/j.cnki.djdxac.2026.03.015
China Classification Code:TB114.3;TP183
Citation Information:
[1]GONG Qi,REN Mingrui,ZOU Zhichao.A Small-Sample Reliability Parameter Estimation Method Based on Virtual Augmentation Theory[J].Journal of Dalian Jiaotong University().DOI:10.13291/j.cnki.djdxac.2026.03.015.
Fund Information:
辽宁省教育厅科学研究项目(LJKZ0503); 辽宁省自然科学基金计划项目(2022-BS-258)
2026-06-10
2026-06-10
2026-06-10