基于IACrossformer-ESPOT的风电机组齿轮箱状态监测

张健; 刘帅; 刘卫亮; 张启亮; 刘长良; 王昕; 徐家豪; 张照彦

doi:10.19805/j.cnki.jcspe.2026.250001

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 >

基于IACrossformer-ESPOT的风电机组齿轮箱状态监测

数字化与智能化 | 更新时间：2026-10-10

- 基于IACrossformer-ESPOT的风电机组齿轮箱状态监测
- Condition Monitoring of Wind Turbine Gearbox Based on IACrossformer-ESPOT
- 动力工程学报 2026年46卷第4期页码：127-137
- 作者机构：
  
  1. 华北电力大学控制与计算机工程学院,北京,102206
  2. 保定市综合能源系统状态检测与优化调控重点实验室,河北,保定,071003
  3. 华北电力大学河北省发电过程仿真与优化控制技术创新中心,河北,保定,071003
  4. 国家能源集团新能源技术研究院有限公司,北京,102209
  5. 河北大学电子信息工程学院,河北,保定,071002
- 作者简介：
  
  张健(2000—),男,江西吉安人,硕士研究生,研究方向为风电机组故障预警,E-mail:15949662064@163.com。
- 基金信息：
  
  中央高校基本科研业务费资助项目(2023JG005,2023JC010);河北省高等学校科学技术研究资助项目(CXY2023001);河北省省级科技计划资助项目(22567643H)
- DOI：10.19805/j.cnki.jcspe.2026.250001
  中图分类号： TK83
- 纸质出版：2026
- 稿件说明：
移动端阅览
张健, 刘帅, 刘卫亮, 张启亮, 刘长良, 王昕, 徐家豪, 张照彦. 基于IACrossformer-ESPOT的风电机组齿轮箱状态监测[J]. 动力工程学报, 2026, 46(4): 127-137.
张健, 刘帅, 刘卫亮, 张启亮, 刘长良, 王昕, 徐家豪, 张照彦. 基于IACrossformer-ESPOT的风电机组齿轮箱状态监测[J]. 动力工程学报, 2026, 46(4): 127-137. DOI： 10.19805/j.cnki.jcspe.2026.250001.

DOI： 10.19805/j.cnki.jcspe.2026.250001

摘要

为实现风电机组齿轮箱故障的早期预警

针对现有模型在时域和频域特征提取方面的不足

以及传统阈值设置方法适应性差的问题

提出一种基于时频特征提取网络(IACrossformer)-流式自适应阈值法(ESPOT)的风电机组齿轮箱状态监测方法。首先

对风电机组数据采集与监控系统(SCADA)数据进行预处理

并通过最大信息系数(MIC)筛选出与齿轮箱油温相关的变量

将其作为模型输入;然后

借助交互式卷积(ICB)和自适应频谱(ASB)的特征提取能力

基于IACrossformer算法有效捕捉齿轮箱油温数据时频域中的复杂模式变化

从而建立齿轮箱正常油温模型;最后

采用ESPOT算法自适应地设置预测残差的阈值。结果表明:所提出的方法可精确建立齿轮箱正常油温模型

且阈值设置算法具有良好的参数适应性

能够实现齿轮箱故障的早期预警。

Abstract

In order to realize early warning of wind turbine gearbox faults

aiming at problems of insufficient feature extraction of existing models in time domain and frequency domain and poor adaptability of traditional threshold setting methods

a condition monitoring method of the wind turbine gearbox based on IACrossformer-ESPOT was proposed. Firstly

the SCADA data of wind turbine were preprocessed

and variables related to the oil temperature of the gearbox were selected as the model input through the maximum information coefficient (MIC). Then

with the feature extraction ability of interactive convolution (ICB) and adaptive spectrum (ASB)

the complex pattern changes in the time-frequency domain of the gearbox oil temperature data were effectively captured based on the IACrossformer algorithm

and the normal oil temperature model of the gearbox was established. Finally

the ESPOT algorithm was used to adaptively set the threshold of the prediction residual to achieve efficient residual analysis and condition monitoring. Results show that the proposed method can accurately establish the normal oil temperature model of gearbox

and the threshold setting algorithm has good parameter adaptability

which can realize the early warning of gearbox fault.

关键词

Keywords

references

高明非, 张策, 解彤, 等. 考虑风光消纳的综合能源系统多元储能优化配置方法[J]. 动力工程学报, 2023, 43(6): 796-804.GAO Mingfei, ZHANG Ce, XIE Tong, et al. Multiple energy storage optimal configuration method for comprehensive energy system considering wind/photovoltaic power accommodation[J]. Journal of Chinese Society of Power Engineering, 2023, 43(6): 796-804.

许勤华, 李文琪. 全球碳中和背景下的中国能源安全方略[J]. 南通大学学报社会科学版, 2023, 39(1): 117-129.XU Qinhua, LI Wenqi. China's energy security strategy in the context of global carbon neutrality[J]. Journal of Nantong University (Social Sciences Edition), 2023, 39(1): 117-129.

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.

张书瑶, 王梓齐, 刘长良. 基于改进集成KNN回归算法的风电机组齿轮箱状态监测[J]. 动力工程学报, 2023, 43(6): 759-767.ZHANG Shuyao, WANG Ziqi, LIU Changliang. Wind turbine gearbox condition monitoring based on improved ensemble KNN regression algorithm[J]. Journal of Chinese Society of Power Engineering, 2023, 43(6): 759-767.

龙寰, 杨婷, 徐劭辉, 等. 基于数据驱动的风电机组状态监测与故障诊断技术综述[J]. 电力系统自动化, 2023, 47(23): 55-69.LONG Huan, YANG Ting, XU Shaohui, et al. Review of data-driven condition monitoring and fault diagnosis technologies for wind turbines[J]. Automation of Electric Power Systems, 2023, 47(23): 55-69.

GUO Peng, INFIELD D. Wind turbine power curve modeling and monitoring with Gaussian process and SPRT[J]. IEEE Transactions on Sustainable Energy, 2020, 11(1): 107-115.

DHIMAN H S, DEB D, MUYEEN S M, et al. Wind turbine gearbox anomaly detection based on adaptive threshold and twin support vector machines[J]. IEEE Transactions on Energy Conversion, 2021, 36(4): 3462-3469.

ZHANG Chen, HU Di, YANG Tao. Anomaly detection and diagnosis for wind turbines using long short-term memory-based stacked denoising autoencoders and XGBoost[J]. Reliability Engineering & System Safety, 2022, 222: 108445.

ZHAN Jun, WU Chengkun, YANG Canqun, et al. Condition monitoring of wind turbines based on spatial-temporal feature aggregation networks[J]. Renewable Energy, 2022, 200: 751-766.

XIANG Ling, YANG Xin, HU Aijun, et al. Condition monitoring and anomaly detection of wind turbine based on cascaded and bidirectional deep learning networks[J]. Applied Energy, 2022, 305: 117925.

VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach: Curran Associates Inc., 2017.

ACHEAMPONG F A, NUNOO-MENSAH H, CHEN Wenyu. Transformer models for text-based emotion detection: a review of BERT-based approaches[J]. Artificial Intelligence Review, 2021, 54(8): 5789-5829.

PARVAIZ A, KHALID M A, ZAFAR R, et al. Vision Transformers in medical computer vision—a contemplative retrospection[J]. Engineering Applications of Artificial Intelligence, 2023, 122: 106126.

LI Yasong, ZHOU Zheng, SUN Chuang, et al. Variational attention-based interpretable transformer network for rotary machine fault diagnosis[J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(5): 6180-6193.

CHEN Wenhe, ZHOU Hanting, CHENG Longsheng, et al. Condition monitoring and anomaly detection of wind turbines using temporal convolutional informer and robust dynamic mahalanobis distance[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 3536914.

ZHANG Yunhao, YAN Junchi. Crossformer: transformer utilizing cross-dimension dependency for multivariate time series forecasting[C]//Proceedings of the 11th International Conference on Learning Representations. Kigali: OpenReview.net, 2023.

胡阳, 胡耀宗, 程逸, 等. 基于FD-AT-LSTM的大型风电机组变频器温度状态监测[J]. 动力工程学报, 2023, 43(9): 1207-1215.HU Yang, HU Yaozong, CHENG Yi, et al. Temperature monitoring of heavy wind power unit inverters based on FD-AT-LSTM[J]. Journal of Chinese Society of Power Engineering, 2023, 43(9): 1207-1215.

向玲, 朱浩伟, 丁显, 等. 基于CAE与BiLSTM结合的风电机组齿轮箱故障预警方法研究[J]. 动力工程学报, 2022, 42(6): 514-521.XIANG Ling, ZHU Haowei, DING Xian, et al. Research on fault warning method of wind turbine gearbox based on CAE and BiLSTM[J]. Journal of Chinese Society of Power Engineering, 2022, 42(6): 514-521.

田雯雯, 吕丽霞, 刘长良, 等. 基于动态矩阵与特征相似度的AAKR风电机组状态监测[J]. 太阳能学报, 2024, 45(10): 536-543.TIAN Wenwen, LV Lixia, LIU Changliang, et al. Dynamic matrix and feature similarity-based auto associative kernel regression for condition monitoring of wind turbine[J]. Acta Energiae Solaris Sinica, 2024, 45(10): 536-543.

SIFFER A, FOUQUE P A, TERMIER A, et al. Anomaly detection in streams with extreme value theory[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Halifax: ACM, 2017: 1067-1075.

ELDELE E, RAGAB M, CHEN Zhenghua, et al. TSLANet: rethinking transformers for time series representation learning[C]//Proceedings of the 41st International Conference on Machine Learning. Vienna: JMLR.org, 2024: 494.

LIN Chunming, DU Bowen, SUN Leilei, et al. Hierarchical context representation and self-adaptive thresholding for multivariate anomaly detection[J]. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(7): 3139-3150.

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

基于神经基拓展分析的风电机组齿轮箱故障预警

多分支时间序列预测与迁移学习相结合的齿轮箱状态监测

燃煤机组燃烧器火焰动态特性建模与量化评估方法研究

基于半马尔可夫的风电机组自触发变桨控制

基于WOA的循环流化床锅炉SO2排放浓度VMD-Transformer预测模型