考虑运行特性的风电齿轮箱轴承劣化态势感知

赵洪山; 张一波; 林诗雨; 张绣梅; 张扬帆; 杨伟新

doi:10.19805/j.cnki.jcspe.2026.240756

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

考虑运行特性的风电齿轮箱轴承劣化态势感知

数字化与智能化 | 更新时间：2026-10-10

- 考虑运行特性的风电齿轮箱轴承劣化态势感知
- Deterioration Trend Perception of Wind Turbine Gearbox BearingsConsidering Operational Characteristics
- 动力工程学报 2026年46卷第2期页码：157-163
- 作者机构：
  
  1. 华北电力大学电力工程系,河北,保定,071003
  2. 国网冀北电力有限公司科学研究院,北京,100045
- 作者简介：
  
  赵洪山(1965—),男,北京人,教授,博士生导师,研究方向为电力系统动态分析与控制、主动配网以及故障预测等,E-mail:zhaohshcn@126.com
- 基金信息：
  
  国网冀北电力有限公司电力科学研究院科学技术资助项目(52018K22001P)
- DOI：10.19805/j.cnki.jcspe.2026.240756
  中图分类号：
- 网络首发：2026-02-10，
  
  纸质出版：2026-02-10
- 稿件说明：
移动端阅览
赵洪山,张一波,林诗雨,张绣梅,张扬帆,杨伟新. 考虑运行特性的风电齿轮箱轴承劣化态势感知动力工程学报, 2026, 46(2): 157-163 https://doi.

org/10.19805/j.cnki.jcspe.2026.240756
赵洪山,张一波,林诗雨,张绣梅,张扬帆,杨伟新. 考虑运行特性的风电齿轮箱轴承劣化态势感知动力工程学报, 2026, 46(2): 157-163 https://doi. DOI： 10.19805/j.cnki.jcspe.2026.240756.

org/10.19805/j.cnki.jcspe.2026.240756 DOI：

摘要

提出了一种考虑风机运行特性的劣化态势感知算法。首先

提出了一种基于损伤累积理论的动力学劣化态势指标

通过Hertz理论计算轴承劣化度(DL);其次

提出了一种结合混合长短期记忆(LSTM)-CatBoost预测器(HLCP)的劣化预测方法

通过引入轴承转速作为时间序列输入的方法

考虑风机运行特性的影响

预测劣化度增长值;基于仿真模型计算轴承损伤临界值

从而预测轴承剩余寿命;最后

使用我国北方某风电场的振动和数据采集与监视控制系统(SCADA)数据进行验证。结果表明:所提出的劣化态势指标在预测趋势与历史趋势上的相似度约为74.42%

具有明显的趋势性和单调性;基于HLCP模型得到的剩余寿命预测结果与实际失效时间的误差仅为640 h

相较于未考虑风机运行特性的预测方法

误差减少了16 461 h。

Abstract

A deterioration trend perception algorithm considering the operating characteristics of wind turbines was proposed. Firstly

a kinetic deterioration state indicator based on damage accumulation theory was proposed

and the bearing deterioration level (DL) was calculated by Hertz theory. Secondly

a hybrid long short-term memory (LSTM)-CatBoost predictor (HLCP) deterioration prediction method was proposed. The deterioration growth value was predicted by considering the influence of wind turbine operating characteristics and introducing the bearing speed as a time series input. Then

the critical value of bearing damage was calculated based on the simulation model

so as to predict the remaining bearing life. Finally

it was validated using the vibration and supervisory control and data acquisition (SCADA) data from a wind farm in the north of China. Results show that the proposed deterioration state indicator has a similarity of about 74.42% in predicting trend and historical trend

with obvious trend and monotonicity. The error between the remaining life prediction results obtained based on the HLCP model and the actual failure time is only 640 h

which is 16 461 h less compared to the prediction method that does not take into account the turbine's operating characteristics.

关键词

Keywords

references

BHARDWAJ U, TEIXEIRA A P, SOARES C G. Reliability prediction of an offshore wind turbine gearbox[J]. Renewable Energy, 2019, 141:693-706.

NEJAD A R, GUO Yi, GAO Zhen, et al. Development of a 5 MW reference gearbox for offshore wind turbines[J]. Wind Energy, 2016, 19(6):1089-1106.

张书瑶, 刘长良, 王梓齐, 等. 基于改进实例学习算法的风电机组齿轮箱状态监测[J] .动力工程学报, 2024, 44(10):1620-1631.ZHANG Shuyao, LIU Changliang, WANG Ziqi, et al. Wind turbine gearbox condition monitoring based on improved instance learning algorithm[J]. Journal of Chinese Society of Power Engineering, 2024, 44(10):1620-1631.

范永胜, 丁雪, 邓艾东. 基于深度条件子域自适应网络的轴承跨域故障诊断研究[J] .动力工程学报, 2024, 44(1):62-67, 83.FAN Yongsheng, DING Xue, DENG Aidong. Research on cross-domain fault diagnosis of bearings based on deep conditional subdomain adaptive network[J]. Journal of Chinese Society of Power Engineering, 2024, 44(1):62-67, 83.

HU Chao, YOUN B D, WANG Pingfeng, et al. Ensemble of data-driven prognostic algorithms for robust prediction of remaining useful life[J]. Reliability Engineering & System Safety, 2012, 103:120-135.

李俊卿, 耿继亚, 国晓宇, 等. 一种POA-VMD和自编码器结合的风电机组轴承劣化指标构建及故障诊断方法[J]. 机床与液压, 2024, 52(13):219-226.LI Junqing, GENG Jiya, GUO Xiaoyu, et al. A method for wind turbine bearing deterioration index construction and fault diagnosis by combining POA-VMD and autoencoder[J]. Machine Tool & Hydraulics, 2024, 52(13):219-226.

LI Lin, MING Tingfeng, LIU Shuyong, et al. An effective health indicator based on two dimensional hidden Markov model[J]. Journal of Mechanical Science and Technology, 2017, 31(4):1543-1550.

LIU Zhiqi, GUO Yu. A neural network approach for prediction of bearing performance degradation tendency[C] //Proceedings of 20179th International Conference on Modelling, Identification and Control. Kunming:IEEE, 2017:204-208.

ZHANG Shuai, ZHANG Yongxiang, LI Lin, et al. An effective health indicator for rolling elements bearing based on data space occupancy[J]. Structural Health Monitoring, 2018, 17(1):3-14.

王海鑫, 刘铭崎, 董鹤楠, 等. 含高比例新能源的电力系统低频振荡分析与抑制综述[J]. 电力自动化设备, 2023, 43(9):152-163.WANG Haixin, LIU Mingqi, DONG Henan, et al. Review on analysis and suppression of low-frequency oscillation in power system with high penetration of renewable energy sources[J]. Electric Power Automation Equipment, 2023, 43(9):152-163.

KUMAR P S, KUMARASWAMIDHAS L A, LAHA S K. Bearing degradation assessment and remaining useful life estimation based on Kullback-Leibler divergence and Gaussian processes regression[J]. Measurement, 2021, 174:108948.

ALI J B, CHEBEL-MORELLO B, SAIDI L, et al. Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network[J]. Mechanical Systems and Signal Processing, 2015, 56-57:150-172.

WANG Han, TANG Gang, ZHOU Youguang, et al. A novel multiscale deep health indicator with bidirectional LSTM network for bearing performance degradation trend prognosis[J]. Shock and Vibration, 2020, 2020:8871981.

王延忠, 贾彦蓉, 鄂世元. 基于劣化机理的轴承剩余使用寿命预测[J]. 新技术新工艺, 2023(5):77-80.WANG Yanzhong, JIA Yanrong, E Shiyuan. Prediction of remaining service life of bearing based on deterioration mechanism[J]. New Technology & New Process, 2023(5):77-80.

董兴辉, 张光, 程友星, 等. 一种风电机组轴承健康劣化趋势预测方法[J]. 动力工程学报, 2018, 38(5):374-379, 393.DONG Xinghui, ZHANG Guang, CHENG Youxing, et al. A method for predicting bearing health degradation trend of wind turbines[J]. Journal of Chinese Society of Power Engineering, 2018, 38(5):374-379, 393.

GEBRAEEL N, LAWLEY M, LIU R, et al. Residual life predictions from vibration-based degradation signals:a neural network approach[J]. IEEE Transactions on Industrial Electronics, 2004, 51(3):694-700.

曲岳晗, 赵洪山, 程晶煜, 等. 基于物联感知数据和张量融合的电力变压器绕组绝缘劣化评估方法[J]. 电工技术学报, 2024, 39(4):1208-1220.QU Yuehan, ZHAO Hongshan, CHENG Jingyu, et al. Evaluation method for power transformer winding insulation degradation based on IoT sensing data and tensor fusion[J]. Transactions of China Electrotechnical Society, 2024, 39(4):1208-1220.

JIANG Zhiyuan, HUANG Xianzhen, LIU Huizhen, et al. Dynamic reliability analysis of main shaft bearings in wind turbines[J]. International Journal of Mechanical Sciences, 2022, 235:107721.

KONG Xiannian, TANG Jinyuan, HU Zehua, et al. A new approach for analyzing internal load and fatigue life of deep groove ball bearing in high-speed gearbox system[J]. Journal of Vibration and Control, 2023, 29(21/22):4972-4986.

YUAN X, ZHU Y S, ZHANG Y Y. Multi-body vibration modelling of ball bearing-rotor system considering single and compound multi-defects[J]. Proceedings of the Institution of Mechanical Engineers, Part K:Journal of Multi-body Dynamics, 2014, 228(2):199-212.

BELMILOUD D, LACHI M, PRON H, et al. Thermo-dynamical modelisation of the degradation of a ball bearing in variables use conditions[J]. Mechanics & Industry, 2020, 21(6):608.

田亮, 袁存波. 基于LSTM和证据理论的引风机轴承故障诊断[J] .动力工程学报, 2023, 43(5):614-621.TIAN Liang, YUAN Cunbo. Fault diagnosis of induced draft fan bearing based on LSTM and evidence theory[J]. Journal of Chinese Society of Power Engineering, 2023, 43(5):614-621.

ZHANG Bin, ZHANG Lijun, XU Jinwu. Degradation feature selection for remaining useful life prediction of rolling element bearings[J]. Quality and Reliability Engineering International, 2016, 32(2):547-554.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于TDLAS的二维温度场与H2O浓度场重建研究

基于T-S模糊模型的风力机系统事件触发控制

热电厂耦合蒸汽储能电热特性研究与优化

基于多通道特征提取与深度交互融合网络的IES多元负荷短期预测

奇异值分解用于早期摩擦故障诊断的研究