Probabilistic anomaly detection approach for data-driven wind turbine condition monitoring

Yuchen Zhang; Meng Li; Zhao Yang Dong; Ke Meng

doi:10.17775/CSEEJPES.2019.00010

欢迎来到能源电力期刊网！

English Version 读者登录期刊登录

您当前的位置：

首页 >

文章列表页 >

Probabilistic anomaly detection approach for data-driven wind turbine condition monitoring

Regular Papers | 更新时间：2025-12-18

- Probabilistic anomaly detection approach for data-driven wind turbine condition monitoring
- Probabilistic anomaly detection approach for data-driven wind turbine condition monitoring
- 中国电机工程学会电力与能源系统学报(英文) 2019年5卷第2期页码：149-158
- 作者机构：
  
  1. University of New South Wales, Sydney, NSW, AU
  2. China University of Mining and Technology,,, CN,Jiangsu,Xuzhou
- 作者简介：
- 基金信息：
- DOI：10.17775/CSEEJPES.2019.00010
  中图分类号：
- 纸质出版：2019
- 稿件说明：
移动端阅览
Yuchen Zhang, Meng Li, Zhao Yang Dong, 等. Probabilistic anomaly detection approach for data-driven wind turbine condition monitoring[J]. 中国电机工程学会电力与能源系统学报(英文), 2019,5(2):149-158.

Yuchen Zhang, Meng Li, Zhao Yang Dong, et al. Probabilistic anomaly detection approach for data-driven wind turbine condition monitoring[J]. CSEE Journal of Power and Energy Systems, 2019, 5(2): 149-158.
Yuchen Zhang, Meng Li, Zhao Yang Dong, 等. Probabilistic anomaly detection approach for data-driven wind turbine condition monitoring[J]. 中国电机工程学会电力与能源系统学报(英文), 2019,5(2):149-158. DOI： 10.17775/CSEEJPES.2019.00010.

Yuchen Zhang, Meng Li, Zhao Yang Dong, et al. Probabilistic anomaly detection approach for data-driven wind turbine condition monitoring[J]. CSEE Journal of Power and Energy Systems, 2019, 5(2): 149-158. DOI： 10.17775/CSEEJPES.2019.00010.

摘要

Abstract

Continuous monitoring of wind turbine (WT) operation can improve the reliability of the wind turbine and lower the operation and maintenance costs. To improve the condition monitoring (CM) and fault detection performance on WTs

this paper proposes an artificial intelligence-based probabilistic anomaly detection approach that can not only provide a deterministic estimation of the WT condition but also evaluate the uncertainties associated with the estimation. An abnormal WT condition is detected based on the evaluated uncertainties

to provide a noise-free incipient fault indication. Compared to the conventional deterministic CM approaches with a residual-based anomaly detection criterion

the proposed probabilistic approach tends to accurately detect the faults earlier

which allows more time for maintenance scheduling to prevent WT component failure. The early fault detection ability of the proposed approach was verified on an operational WT in China.

关键词

Keywords

references

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

Failure Rate Prediction of a Power Transformer: A Decomposition-Based Bayesian Deep Learning Method

Learning to Optimize Joint Chance-Constrained Power Dispatch Problems

Restoration of High-Renewable-Penetrated Distribution Systems Considering Uncertain Repair Workloads

Multi-Time-Step Rolling Optimization Strategy for Post-Disaster Emergency Recovery in Distribution System Based on Model Predictive Control

Distributed and Risk-Averse ADP Algorithm for Stochastic Economic Dispatch of Power System with Multiple Offshore Wind Farms