scholarly journals Fault Diagnosis Approach of Main Drive Chain in Wind Turbine Based on Data Fusion

2021 ◽  
Vol 11 (13) ◽  
pp. 5804
Author(s):  
Zhen Xu ◽  
Ping Yang ◽  
Zhuoli Zhao ◽  
Chun Sing Lai ◽  
Loi Lei Lai ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Data Fusion ◽  
Wind Turbine ◽  
Wind Turbines ◽  
Smart Cities ◽  
Data Sources ◽  
Drive Chain ◽  
Data Source ◽  
Diagnosis Model ◽  
Diagnosis Approach

The construction and operation of wind turbines have become an important part of the development of smart cities. However, the fault of the main drive chain often causes the outage of wind turbines, which has a serious impact on the normal operation of wind turbines in smart cities. In order to overcome the shortcomings of the commonly used main drive chain fault diagnosis method that only uses a single data source, a fault feature extraction and fault diagnosis approach based on data source fusion is proposed. By fusing two data sources, the supervisory control and data acquisition (SCADA) real-time monitoring system data and the main drive chain vibration monitoring data, the fault features of the main drive chain are jointly extracted, and an intelligent fault diagnosis model for the main drive chain in wind turbine based on data fusion is established. The diagnosis results of actual cases certify that the fault diagnosis model based on the fusion of two data sources is able to locate faults of the main drive chain in the wind turbine accurately and provide solid technical support for the high-efficient operation and maintenance of wind turbines.

scholarly journals Low-Pass Filtering Empirical Wavelet Transform Machine Learning Based Fault Diagnosis for Combined Fault of Wind Turbines

Entropy ◽  
2021 ◽  
Vol 23 (8) ◽  
pp. 975
Author(s):  
Yancai Xiao ◽  
Jinyu Xue ◽  
Mengdi Li ◽  
Wei Yang
Keyword(s):  
Machine Learning ◽  
Wavelet Transform ◽  
Fault Diagnosis ◽  
Wind Turbine ◽  
Wind Turbines ◽  
Gear Tooth ◽  
Support Vector ◽  
Grey Wolf Optimizer ◽  
Empirical Wavelet Transform ◽  
Low Pass

Fault diagnosis of wind turbines is of great importance to reduce operating and maintenance costs of wind farms. At present, most wind turbine fault diagnosis methods are focused on single faults, and the methods for combined faults usually depend on inefficient manual analysis. Filling the gap, this paper proposes a low-pass filtering empirical wavelet transform (LPFEWT) machine learning based fault diagnosis method for combined fault of wind turbines, which can identify the fault type of wind turbines simply and efficiently without human experience and with low computation costs. In this method, low-pass filtering empirical wavelet transform is proposed to extract fault features from vibration signals, LPFEWT energies are selected to be the inputs of the fault diagnosis model, a grey wolf optimizer hyperparameter tuned support vector machine (SVM) is employed for fault diagnosis. The method is verified on a wind turbine test rig that can simulate shaft misalignment and broken gear tooth faulty conditions. Compared with other models, the proposed model has superiority for this classification problem.

scholarly journals Development of an SVR Model for the Fault Diagnosis of Large-Scale Doubly-Fed Wind Turbines Using SCADA Data

Energies ◽  
2019 ◽  
Vol 12 (17) ◽  
pp. 3396 ◽  
Author(s):  
Mingzhu Tang ◽  
Wei Chen ◽  
Qi Zhao ◽  
Huawei Wu ◽  
Wen Long ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Wind Turbine ◽  
Support Vector Regression ◽  
Confidence Intervals ◽  
Wind Turbines ◽  
Large Scale ◽  
Support Vector ◽  
Effective Response ◽  
Support Vector Regression Model ◽  
Doubly Fed

Fault diagnosis and forecasting contribute significantly to the reduction of operating and maintenance associated costs, as well as to improve the resilience of wind turbine systems. Different from the existing fault diagnosis approaches using monitored vibration and acoustic data from the auxiliary equipment, this research presents a novel fault diagnosis and forecasting approach underpinned by a support vector regression model using data obtained by the supervisory control and data acquisition system (SCADA) of wind turbines (WT). To operate, the extraction of fault diagnosis features is conducted by measuring SCADA parameters. After that, confidence intervals are set up to guide the fault diagnosis implemented by the support vector regression (SVR) model. With the employment of confidence intervals as the performance indicators, an SVR-based fault detecting approach is then developed. Based on the WT SCADA data and the SVR model, a fault diagnosis strategy for large-scale doubly-fed wind turbine systems is investigated. A case study including a one-year monitoring SCADA data collected from a wind farm in Southern China is employed to validate the proposed methodology and demonstrate how it works. Results indicate that the proposed strategy can support the troubleshooting of wind turbine systems with high precision and effective response.

scholarly journals On Variable-Universe Fuzzy Control for Drive Chain of Front-End Speed Regulated Wind Generator

2019 ◽  
Vol 2019 ◽  
pp. 1-10 ◽  
Author(s):  
Hongwei Li ◽  
Kaide Ren ◽  
Haiying Dong ◽  
Shuaibing Li
Keyword(s):  
Neural Network ◽  
Wind Turbine ◽  
Wind Turbines ◽  
Fuzzy Controller ◽  
Synchronous Generator ◽  
Variable Universe ◽  
Neural Network Controller ◽  
Front End ◽  
Network Controller ◽  
Drive Chain

The rapid development of wind generation technology has boosted types of the new topology wind turbines. Among the recently invented new wind turbines, the front-end speed regulated (FSR) wind turbine has attracted a lot of attention. Unlike conventional wind turbine, the speed regulation of the FSR machines is realized by adjusting the guide vane angle of a hydraulic torque converter, which is converterless and much more grid-friendly as the electrically excited synchronous generator (EESG) is also adopted. Therefore, the drive chain control of the wind turbine owns the top priority. To ensure that the FSR wind turbine performs as a general synchronous generator, this paper firstly modeled the drive chain and then proposed to use the variable-universe fuzzy approach for the drive chain control. It helps the wind generator operate in a synchronous speed and outperform other types of wind turbines. The multipopulation genetic algorithm (MPGA) is adopted to intelligently optimize the parameters of the expansion factor of the designed variable-universe fuzzy controller (VUFC). The optimized VUFC is applied to the speed control of the drive chain of the FSR wind turbine, which effectively solves the contradiction between the low precision of the fuzzy controller and the number of rules in the fuzzy control and the control accuracy. Finally, the main shaft speed of the FSR wind turbine can reach a steady-state value around 1500 rpm. The response time of the results derived using VUFC, compared with that derived from a neural network controller, is only less than 0.5 second and there is no overshoot. The case study with the real machine parameter verifies the effectiveness of the proposal and results compared with conventional neural network controller, proving its outperformance.

Fault Diagnosis of Wind Turbines Based on Improved Neural Network

2014 ◽  
Vol 978 ◽  
pp. 78-83
Author(s):  
Qiang Lan ◽  
Peng Da Zhao ◽  
Man Li Wang
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Wind Turbine ◽  
Wind Turbines ◽  
Feature Vector ◽  
Wind Turbine Gearbox ◽  
Vibration Sensors

The gearbox is an important module of wind turbine. In order to diagnosis the fault of wind turbine gearbox, a method based on the improved neural network is proposed. According to the characteristics of the wind turbine gearbox, several vibration sensors are set in the gearbox, so as to acquire the feature vector of gearbox. After training, the improved neural network is verified with some test samples. The result proved that the method is suitable for fault diagnosis in gearbox of wind turbine.. Keywords: wind turbine gearbox, fault diagnosis, particle swam, neural network.

Rolling Bearing Fault Diagnosis Based on Wavelet Packet and Improved BP Neural Network for Wind Turbines

2013 ◽  
Vol 347-350 ◽  
pp. 117-120
Author(s):  
Zhao Ran Hou
Keyword(s):  
Fault Diagnosis ◽  
Wind Turbine ◽  
Frequency Domain ◽  
Wind Turbines ◽  
Wavelet Packet ◽  
Roller Bearing ◽  
Rolling Bearing ◽  
Transmission System ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis

Vibration signal was a carrier of fault features of the wind turbine transmission system, it can reflect most of the fault information of the wind turbine transmission system. According to the frequency domain features of the roller bearing fault, wavelet packet transform for feature extraction was proposed as the characteristics of wind turbines in the presence of a large number of transient and non-stationary signals. The characteristics of wavelet packet was analyzed, combined with the wind turbines in the rolling bearing fault characteristic vibration extraction methods, the rolling bearing fault diagnosis was realized through the wavelet packet decomposition and reconstruction, the procedure was given. The simulation result shows that this application can reflect relationship of the failure characteristics and frequency domain feature vectors, also the nonlinear mapping ability of neural networks was played and the fault diagnosis capability enhanced.

scholarly journals Measuring conflation success

2017 ◽  
pp. 41-64
Author(s):  
Marta Padilla-Ruiz ◽  
Carlos López-Vázquez
Keyword(s):  
Big Data ◽  
Product Quality ◽  
Smart Cities ◽  
Spatial Scales ◽  
Evaluation Process ◽  
Heterogeneous Data ◽  
The Other ◽  
Data Sources ◽  
Data Source ◽  
Other Regarding

We are immersed in the Big Data era, where there is a large amount of heterogeneous data, both in time and spatial scales. This data starts to be streamed in real time from different devices and sensors, well illustrated by the new concept of Smart Cities. Conflation processes play an important role in this scenario, defined as the procedure for the combination and integration of different data sources, improving the level of information of the result. It also allows to update geographical databases (GDB), conflating different kind of sources where one of them is more accurate or updated than the other. Regarding geometric conflation, the procedure involves transforming features from one data source to another, minimizing the geometric discrepancies between them. Accuracy has to be taken into account in these processes, and the results need to be measured and evaluated in order to have a better understanding of product quality. In this paper, conflation evaluation process is described along with the different metrics and approaches to assess its accuracy.

scholarly journals Wind Turbine Anomaly Identification Based on Improved Deep Belief Network with SCADA Data

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Xiafei Long ◽  
Shengqing Li ◽  
Xiwen Wu ◽  
Zhao Jin
Keyword(s):  
Fault Diagnosis ◽  
Wind Turbine ◽  
Wind Power ◽  
Wind Turbines ◽  
Domain Knowledge ◽  
Wind Farm ◽  
Prediction Models ◽  
Moving Average ◽  
Pearson Correlation ◽  
Whale Optimization

This article presents a novel fault diagnosis algorithm based on the whale optimization algorithm (WOA)-deep belief networks (DBN) for wind turbines (WTs) using the data collected from the supervisory control and data acquisition (SCADA) system. Through the domain knowledge and Pearson correlation, the input parameters of the prediction models are selected. Three different types of prediction models, namely, the wind turbine, the wind power gearbox, and the wind power generator, are used to predict the health condition of the WT equipment. In this article, the prediction accuracy of the models built with these SCADA sample data is discussed. In order to implement fault monitoring and abnormal state determination of the wind power equipment, the exponential weighted moving average (EWMA) threshold is used to monitor the trend of reconstruction errors. The proposed method is used for 2 MW wind turbines with doubly fed induction generators in a real-world wind farm, and experimental results show that the proposed method is effective in the fault diagnosis of wind turbines.

Application of Dempster–Shafer Data Fusion Technique in Support of Decision Making with Big Data

2017 ◽  
Vol 2645 (1) ◽  
pp. 32-37 ◽  
Author(s):  
Ping Yi ◽  
Songling Zhang
Keyword(s):  
Decision Making ◽  
Big Data ◽  
Data Fusion ◽  
Incomplete Information ◽  
Data Sources ◽  
Fusion Technique ◽  
Crowd Management ◽  
Multiple Data ◽  
Data Source ◽  
Single Data

This paper introduces applications of the Dempster–Shafer (D-S) data fusion technique in transportation system decision making. D-S inference is a statistics-based data classification technique, and it can be used when data sources contribute discontinuous and incomplete information and no single data source can produce an overwhelmingly high probability of certainty for identifying the most probable event. The technique captures and combines the information contributed by the data sources by using Dempster’s rule to find the conjunction of the events and to determine the highest associated probability. The D-S theory is explained and its implementation described through numerical examples of a ride-hauling service and of crowd management at a subway station. Results from the applications have shown that the technique is very effective in dealing with incomplete information and multiple data sources in the era of big data.

Sign in / Sign up

Export Citation Format

Share Document