该文针对风电机组轴承剩余寿命预测误差较大的问题,建立一种新型的寿命预测模型,考虑了寿命预测失效阈值的随机性,采用极大似然法估计模型中的参数,并依据贝叶斯理论对模型参数进行更新,同时,针对预测模型本身的误差会随时间累积,进而影响寿命预测的精确度问题,建立误差修正模型,并求解剩余使用寿命的概率分布,进而得到其剩余使用寿命。采用该文所建立的预测模型对风电机组轴承的剩余寿命进行预测,验证了所提策略的有效性。
Abstract
This article establishes a new type of life prediction model to address the issue of large prediction errors in the remaining life of wind turbine bearings. This model considers the randomness of the failure threshold for life prediction, uses the maximum likelihood method to estimate the parameters in the model, and updates the parameters based on Bayesian theory. At the same time, considering that the errors of the prediction model itself will accumulate over time, which will affect the accuracy of life prediction, an error correction model is established, and the distribution of its remaining service life was solved. The prediction model established in this article was used to predict the remaining life of wind turbine bearings, verifying the effectiveness of the proposed strategy.
关键词
风电机组 /
轴承健康状态 /
监测数据 /
寿命预测 /
贝叶斯理论
Key words
wind turbines /
bearing /
health status /
monitoring data /
life prediction /
Bayesian theory
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 胡姚刚, 李辉, 廖兴林, 等. 风电轴承性能退化建模及其实时剩余寿命预测[J]. 中国电机工程学报, 2016, 36(6): 1643-1649.
HU Y G, LI H, LIAO X L, et al.Performance degradation model and prediction method of real-time remaining life for wind turbine bearings[J]. Proceedings of the CSEE, 2016, 36(6): 1643-1649.
[2] 刘军, 安柏任, 张维博, 等. 大型风力发电机组健康状态评价综述[J]. 电力系统保护与控制, 2023, 51(1): 176-187.
LIU J, AN B R, ZHANG W B, et al.Review of health status evaluation of large wind turbines[J]. Power system protection and control, 2023, 51(1): 176-187.
[3] RUIZ M, MUJICA L E, ALFÉREZ S, et al. Wind turbine fault detection and classification by means of image texture analysis[J]. Mechanical systems and signal processing, 2018, 107: 149-167.
[4] 李帅永, 张超, 梅琳, 等. 基于改进Holt双指数模型的轴承剩余寿命预测方法[J]. 自动化与仪器仪表, 2023(2): 87-93.
LI S Y, ZHANG C, MEI L, et al.Prediction method of bearing residual life based on improved Holt double exponential model[J]. Automation & instrumentation, 2023(2): 87-93.
[5] LI X L, TENG W, PENG D K, et al.Feature fusion model based health indicator construction and self-constraint state-space estimator for remaining useful life prediction of bearings in wind turbines[J]. Reliability engineering & system safety, 2023, 233: 109124.
[6] XU Z F, BASHIR M, LIU Q S, et al.A novel health indicator for intelligent prediction of rolling bearing remaining useful life based on unsupervised learning model[J]. Computers & industrial engineering, 2023, 176: 108999.
[7] CAO Y D, JIA M P, DING Y F, et al.Complex domain extension network with multi-channels information fusion for remaining useful life prediction of rotating machinery[J]. Mechanical systems and signal processing, 2023, 192: 110190.
[8] 徐洲常, 王林军, 刘洋, 等. 采用改进回归型支持向量机的滚动轴承剩余寿命预测方法[J]. 西安交通大学学报, 2022, 56(3): 197-205.
XU Z C, WANG L J, LIU Y, et al.A prediction method for remaining life of rolling bearing using improved regression support vector machine[J]. Journal of Xi’an Jiaotong University, 2022, 56(3): 197-205.
[9] PENG W W, YE Z S, CHEN N.Bayesian deep-learning-based health prognostics toward prognostics uncertainty[J]. IEEE transactions on industrial electronics, 2020, 67(3): 2283-2293.
[10] CHANG Z H, YUAN W, HUANG K.Remaining useful life prediction for rolling bearings using multi-layer grid search and LSTM[J]. Computers and electrical engineering, 2022, 101: 108083.
[11] 刘学娟. 基于随机系数回归模型的退化过程及维修策略[J]. 控制与决策, 2021, 36(3): 754-760.
LIU X J.Degradation process and maintenance planning based on random coefficient regression model[J]. Control and decision, 2021, 36(3): 754-760.
[12] 杨志凌, 刘俊华. 基于数据融合和Wiener过程的风电轴承剩余寿命预测[J]. 太阳能学报, 2021, 42(10): 189-194.
YANG Z L, LIU J H.Remaining life prediction of wind turbine bearings based on data fusion and Wiener processes[J]. Acta energiae solaris sinica, 2021, 42(10): 189-194.
[13] FENG H K, PEI H J, YANG F Q, et al.Estimation of leaf nitrogen content of maize based on Akaike’s information criterion in Beijing[C]//2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). Fort Worth, TX, USA, 2017: 5057-5060.
PDF(1568 KB)
