scholarly journals Review and Perspectives of Machine Learning Methods for Wind Turbine Fault Diagnosis

2021 ◽  
Vol 9 ◽  
Author(s):  
Mingzhu Tang ◽  
Qi Zhao ◽  
Huawei Wu ◽  
Ziming Wang ◽  
Caihua Meng ◽  
...  
Keyword(s):  
Machine Learning ◽  
Control System ◽  
Fault Diagnosis ◽  
System Integration ◽  
Fault Detection And Diagnosis ◽  
System Control ◽  
Learning Methods ◽  
Pitch System ◽  
Detection And Diagnosis ◽  
Financial Losses

Wind turbines (WTs) generally comprise several complex and interconnected systems, such as hub, converter, gearbox, generator, yaw system, pitch system, hydraulic system control system,integration control system, and auxiliary system. Moreover, fault diagnosis plays an important role in ensuring WT safety. In the past decades, machine learning (ML) has showed a powerful capability in fault detection and diagnosis of WTs, thereby remarkably reducing equipment downtime and minimizing financial losses. This study provides a comprehensive review of recent studies on ML methods and techniques for WT fault diagnosis. These studies are classified as supervised, unsupervised, and semi-supervised learning methods. Existing state-of-the-art methods are analyzed and characteristics are discussed. Perspectives on challenges and further directions are also provided.

scholarly journals Data-Driven Machine Learning for Fault Detection and Diagnosis in Nuclear Power Plants: A Review

2021 ◽  
Vol 9 ◽  
Author(s):  
Guang Hu ◽  
Taotao Zhou ◽  
Qianfeng Liu
Keyword(s):  
Machine Learning ◽  
Fault Diagnosis ◽  
Power Plant ◽  
Nuclear Power Plant ◽  
Nuclear Power ◽  
Power Plants ◽  
State Of The Art ◽  
Fault Detection And Diagnosis ◽  
Data Driven ◽  
Detection And Diagnosis

Data-driven machine learning (DDML) methods for the fault diagnosis and detection (FDD) in the nuclear power plant (NPP) are of emerging interest in the recent years. However, there still lacks research on comprehensive reviewing the state-of-the-art progress on the DDML for the FDD in the NPP. In this review, the classifications, principles, and characteristics of the DDML are firstly introduced, which include the supervised learning type, unsupervised learning type, and so on. Then, the latest applications of the DDML for the FDD, which consist of the reactor system, reactor component, and reactor condition monitoring are illustrated, which can better predict the NPP behaviors. Lastly, the future development of the DDML for the FDD in the NPP is concluded.

Supervised process monitoring and fault diagnosis based on machine learning methods

2019 ◽  
Vol 102 (5-8) ◽  
pp. 2321-2337 ◽  
Author(s):  
Hajer Lahdhiri ◽  
Maroua Said ◽  
Khaoula Ben Abdellafou ◽  
Okba Taouali ◽  
Mohamed Faouzi Harkat
Keyword(s):  
Machine Learning ◽  
Fault Diagnosis ◽  
Process Monitoring ◽  
Learning Methods ◽  
Machine Learning Methods

Investigating Fault Detection and Diagnosis in a Hydraulic Pitch System Using a State Augmented EKF-Approach

2019 ◽  
Author(s):  
Magnus F. Asmussen ◽  
Henrik C. Pedersen ◽  
Lina Lilleengen ◽  
Andreas Larsen ◽  
Thomas Farsakoglou
Keyword(s):  
Kalman Filter ◽  
Fault Detection ◽  
Extended Kalman Filter ◽  
Fault Detection And Diagnosis ◽  
Sensor Faults ◽  
System Parameters ◽  
Power Regulation ◽  
Pitch System ◽  
Detection And Diagnosis ◽  
Drop Outs

Abstract Pitch systems impose an important part of today’s wind turbines, where they are both used for power regulation and serve as part of a turbines safety system. Any failure on a pitch system is therefore equal to an increase in downtime of the turbine and should hence be avoided. By implementing a Fault Detection and Diagnosis (FDD) scheme faults may be detected and estimated before resulting in a failure, thus increasing the availability and aiding in the maintenance of the wind turbine. The focus of this paper is therefore on the development of a FDD algorithm to detect leakage and sensor faults in a fluid power pitch system. The FDD algorithm is based on a State Augmented Extended Kalman Filter (SAEKF) and a bank of observers, which is designed utilizing an experimentally validated model of a pitch system. The SAEKF is designed to detect and estimate both internal and external leakage faults, while also estimating the unknown external load on the system, and the bank of observers to detect sensor drop-outs. From simulation it is found that the SAEKF may detect both abrupt and evolving internal and external leakages, while being robust towards noise and variation in system parameters. Similar it is found that the scheme is able to detect sensor drop-outs, but is less robust towards this.

Method on the Fault Detection and Diagnosis for the Railway Turnout Based on the Current Curve of Switch Machine

2013 ◽  
Vol 427-429 ◽  
pp. 1022-1027 ◽  
Author(s):  
Xue Mei Mo ◽  
Yu Fang ◽  
Yun Guo Yang
Keyword(s):  
Fault Diagnosis ◽  
Fault Detection ◽  
Fault Location ◽  
Fault Detection And Diagnosis ◽  
Curve Matching ◽  
Reference Curve ◽  
Current Curve ◽  
Diagnosis Method ◽  
Detection And Diagnosis ◽  
Railway Turnout

This paper proposes a method of the fault detection and diagnosis for the railway turnout based on the current curve of switch machine. Exact curve matching fault detection method and SVM-based fault diagnosis method are adopted in the paper. Based on envelope and morpheme match algorithm, exact curve matching method is used to match the detected current curve with the reference curve so as to predict whether the curve would have fault or not. Moreover, the SVM-based fault diagnosis method is used to make sure that the fault conditions could be diagnosed intelligently. Finally, the experimental results show that the proposed method can accurately identify the turnout fault status in the conversion process, and the accuracy rate in the diagnosis of the fault location is above 98%, which verify the effectiveness of the method in the fault detection and diagnosis.

Fault Detection and Diagnosis for Sensor in Complex Control System Based on KPCA

2014 ◽  
Vol 623 ◽  
pp. 202-210
Author(s):  
Ping Xu ◽  
You Cai Wang ◽  
Kai Wang ◽  
Qiu Yan Wang
Keyword(s):  
Control System ◽  
Fault Detection ◽  
Principal Component ◽  
Kernel Functions ◽  
Fault Detection And Diagnosis ◽  
Kernel Principal Component Analysis ◽  
Practical Result ◽  
Complex Control ◽  
Complex Control System ◽  
Detection And Diagnosis

The Fault detection and diagnosis for sensors are important for the performance of the complex control system seriously. The kernel principal component analysis (KPCA) effectively captures the nonlinear relationship of the process variables, which computes principal component in high-dimensional feature space by means of integral operators and nonlinear kernel functions. The KPCA method is used in diagnosing for four common sensor faults. At first its fault is detected by Q statistic; secondly its fault is identified by T2 contribution percent change. The simulation and the practical result show the KPCA method has good performance on complex control system in sensor fault detection and diagnosis.

Sign in / Sign up

Export Citation Format

Share Document