Wind turbine failure prediction and health assessment based on adaptive maximum mean discrepancy

2022 ◽  
Vol 134 ◽  
pp. 107391
Author(s):  
Jieyang Peng ◽  
Andreas Kimmig ◽  
Zhibin Niu ◽  
Jiahai Wang ◽  
Xiufeng Liu ◽  
...  
Keyword(s):  
Wind Turbine ◽  
Health Assessment ◽  
Failure Prediction ◽  
Maximum Mean Discrepancy

scholarly journals Three-Stage Wind Turbine Assessment Method: Condition Monitoring, Failure Prediction, And Health Assessment

2021 ◽  
Author(s):  
Yongsheng Qi ◽  
Tongmei Jing ◽  
Chao Ren ◽  
Xuejin Gao
Keyword(s):  
Wind Turbine ◽  
Condition Monitoring ◽  
Wind Farm ◽  
Health Management ◽  
Health Assessment ◽  
Failure Prediction ◽  
Fuzzy Comprehensive Evaluation ◽  
Assessment Method ◽  
Generalized Regression Neural Network ◽  
Monitoring Method

Abstract To improve the wind turbine shutdown early warning ability, we present a generalized model for wind turbine (WT) prognosis and health management (PHM) based on the data collected from the SCADA system. First, a new condition monitoring method based on kernel entropy component analysis (KECA) was developed for nonlinear data. Then, an aggregate statistic T was designed to express the state change of the monitoring parameters. As the features were submerged because of the diversity and nonlinearity of SCADA data, an enhanced generalized regression neural network (GRNN) method—KECA-GRNN—for failure prediction was developed by adding KECA for feature extraction to improve the predictive performance. Finally, the results of the KECA-GRNN model were visualized by a bubble chart, which made the health assessment results of the WT more intuitive. Similarly, the fusion residual was defined to analyze the health trend of the WT, and the health status of the WT was represented by two visualization methods—bubble chart and fuzzy comprehensive evaluation. Furthermore, they were evaluated using SCADA data that were collected from a wind farm. Observations from the results of the model indicated the ability of the approach to trend and assess turbine degradation before known downtime occurrences.

Wind Turbine Failure Prediction Model using SCADA-based Condition Monitoring System

2021 ◽  
Author(s):  
Bara Alzawaideh ◽  
Payam Teimourzadeh Baboli ◽  
Davood Babazadeh ◽  
Susanne Horodyvskyy ◽  
Isabel Koprek ◽  
...  
Keyword(s):  
Prediction Model ◽  
Wind Turbine ◽  
Monitoring System ◽  
Condition Monitoring ◽  
Failure Prediction ◽  
Condition Monitoring System

scholarly journals Vestas V90-3MW Wind Turbine Gearbox Health Assessment Using a Vibration-Based Condition Monitoring System

2016 ◽  
Vol 2016 ◽  
pp. 1-18 ◽  
Author(s):  
A. Romero ◽  
Y. Lage ◽  
S. Soua ◽  
B. Wang ◽  
T.-H. Gan
Keyword(s):  
Fault Diagnosis ◽  
Wind Turbine ◽  
Condition Monitoring ◽  
Learning Algorithm ◽  
Health Assessment ◽  
Field Trials ◽  
Health Condition ◽  
Normal Operation ◽  
Wind Turbine Gearbox ◽  
Operation Conditions

Reliable monitoring for the early fault diagnosis of gearbox faults is of great concern for the wind industry. This paper presents a novel approach for health condition monitoring (CM) and fault diagnosis in wind turbine gearboxes using vibration analysis. This methodology is based on a machine learning algorithm that generates a baseline for the identification of deviations from the normal operation conditions of the turbine and the intrinsic characteristic-scale decomposition (ICD) method for fault type recognition. Outliers picked up during the baseline stage are decomposed by the ICD method to obtain the product components which reveal the fault information. The new methodology proposed for gear and bearing defect identification was validated by laboratory and field trials, comparing well with the methods reviewed in the literature.

Strength Evaluation and Failure Prediction of a Composite Wind Turbine Blade Using Finite Element Analysis

2010 ◽  
Author(s):  
Prenil Poulose ◽  
Zhong Hu
Keyword(s):  
Finite Element Analysis ◽  
Finite Element ◽  
Wind Turbine ◽  
Turbine Blade ◽  
Turbine Blades ◽  
Failure Prediction ◽  
Element Model ◽  
Wind Turbine Blade ◽  
Element Analysis ◽  
Strength Evaluation

Strength evaluation and failure prediction on a modern composite wind turbine blade have been conducted using finite element analysis. A 3-dimensional finite element model has been developed. Stresses and deflections in the blade under extreme storm conditions have been investigated for different materials. The conventional wood design turbine blade has been compared with the advanced E-glass fiber and Carbon epoxy composite blades. Strength has been analyzed and compared for blades with different laminated layer stacking sequences and fiber orientations for a composite material. Safety design and failure prediction have been conducted based on the different failure criteria. The simulation error estimation has been evaluated. Simulation results have shown that finite element analysis is crucial for designing and optimizing composite wind turbine blades.

scholarly journals Feature Selection Algorithms for Wind Turbine Failure Prediction

Energies ◽  
2019 ◽  
Vol 12 (3) ◽  
pp. 453 ◽  
Author(s):  
Pere Marti-Puig ◽  
Alejandro Blanco-M ◽  
Juan Cárdenas ◽  
Jordi Cusidó ◽  
Jordi Solé-Casals
Keyword(s):  
Feature Selection ◽  
Mutual Information ◽  
Wind Turbine ◽  
Wind Farm ◽  
Feature Selection Method ◽  
Failure Prediction ◽  
Exhaustive Search ◽  
Input Selection ◽  
Selection Algorithms ◽  
Optimal Set

It is well known that each year the wind sector has profit losses due to wind turbine failures and operation and maintenance costs. Therefore, operations related to these actions are crucial for wind farm operators and linked companies. One of the key points for failure prediction on wind turbine using SCADA data is to select the optimal or near optimal set of inputs that can feed the failure prediction (prognosis) algorithm. Due to a high number of possible predictors (from tens to hundreds), the optimal set of inputs obtained by exhaustive-search algorithms is not viable in the majority of cases. In order to tackle this issue, show the viability of prognosis and select the best set of variables from more than 200 analogous variables recorded at intervals of 5 or 10 min by the wind farm’s SCADA, in this paper a thorough study of automatic input selection algorithms for wind turbine failure prediction is presented and an exhaustive-search-based quasi-optimal (QO) algorithm, which has been used as a reference, is proposed. In order to evaluate the performance, a k-NN classification algorithm is used. Results showed that the best automatic feature selection method in our case-study is the conditional mutual information (CMI), while the worst one is the mutual information feature selection (MIFS). Furthermore, the effect of the number of neighbours (k) is tested. Experiments demonstrate that k = 1 is the best option if the number of features is higher than 3. The experiments carried out in this work have been extracted from measures taken along an entire year and corresponding to gearbox and transmission systems of Fuhrländer wind turbines.

scholarly journals GA-BP Neural Network-Based Strain Prediction in Full-Scale Static Testing of Wind Turbine Blades

Energies ◽  
2019 ◽  
Vol 12 (6) ◽  
pp. 1026 ◽  
Author(s):  
Zheng Liu ◽  
Xin Liu ◽  
Kan Wang ◽  
Zhongwei Liang ◽  
José A.F.O. Correia ◽  
...  
Keyword(s):  
Wind Turbine ◽  
Turbine Blades ◽  
Back Propagation ◽  
Health Assessment ◽  
Prediction Method ◽  
Full Scale ◽  
Wind Turbine Blades ◽  
Static Test ◽  
Static Testing ◽  
Input Variables

This paper proposes a strain prediction method for wind turbine blades using genetic algorithm back propagation neural networks (GA-BPNNs) with applied loads, loading positions, and displacement as inputs, and the study can be used to provide more data for the wind turbine blades’ health assessment and life prediction. Among all parameters to be tested in full-scale static testing of wind turbine blades, strain is very important. The correlation between the blade strain and the applied loads, loading position, displacement, etc., is non-linear, and the number of input variables is too much, thus the calculation and prediction of the blade strain are very complex and difficult. Moreover, the number of measuring points on the blade is limited, so the full-scale blade static test cannot usually provide enough data and information for the improvement of the blade design. As a result of these concerns, this paper studies strain prediction methods for full-scale blade static testing by introducing GA-BPNN. The accuracy and usability of the GA-BPNN prediction model was verified by the comparison with BPNN model and the FEA results. The results show that BPNN can be effectively used to predict the strain of unmeasured points of wind turbine blades.

Health assessment and management of wind turbine blade based on the fatigue test data

2017 ◽  
Vol 75 ◽  
pp. 205-214 ◽  
Author(s):  
Xuezong Bai ◽  
Zongwen An ◽  
Yunfeng Hou ◽  
Qiang Ma
Keyword(s):  
Wind Turbine ◽  
Fatigue Test ◽  
Turbine Blade ◽  
Test Data ◽  
Health Assessment ◽  
Wind Turbine Blade

Wind Turbine Gearbox Failure Prediction Based on Time Series Analysis and Statistical Process Control

2011 ◽  
Vol 347-353 ◽  
pp. 2236-2240 ◽  
Author(s):  
Fei Fei Wang ◽  
Xiao Qing Xiao ◽  
Hong Shan Zhao
Keyword(s):  
Time Series ◽  
Process Control ◽  
Wind Turbine ◽  
Statistical Process Control ◽  
Arima Model ◽  
Failure Prediction ◽  
Temperature Data ◽  
Operating Conditions ◽  
Statistical Process ◽  
Normal Operating

The Time Series method and Statistical Process Control strategy is applied to predict failures of wind turbine gearboxes. First, based on the real-time temperature data of gearboxes measured by temperature sensors, the temperature prediction model under normal operating conditions is established by ARIMA model. The analysis of the predicted values and the actual values of gearbox temperature is done, and proves that its residuals are normally distributed; then combined with statistical process control (SPC) methods, the big number of temperature data is used to calculate the standard deviation(σ) of residuals, and the gearbox failure threshold will be identified; Finally, the temperature data are analyzed both in normal operating condition and the failure condition to determine the operation status of the gearbox, statistical analysis and residual charts are carried out for gearbox failure prediction, verifying the feasibility and effectiveness of the proposed method.

Sign in / Sign up

Export Citation Format

Share Document