scholarly journals An Improved LightGBM Algorithm for Online Fault Detection of Wind Turbine Gearboxes

Energies ◽  
2020 ◽  
Vol 13 (4) ◽  
pp. 807 ◽  
Author(s):  
Mingzhu Tang ◽  
Qi Zhao ◽  
Steven X. Ding ◽  
Huawei Wu ◽  
Linlin Li ◽  
...  
Keyword(s):  
Fault Detection ◽  
Wind Turbine ◽  
Wind Farm ◽  
Performance Indicator ◽  
Southern China ◽  
Confusion Matrix ◽  
Maximum Information ◽  
Detection Model ◽  
Low Efficiency ◽  
A Performance

It is widely accepted that conventional boost algorithms are of low efficiency and accuracy in dealing with big data collected from wind turbine operations. To address this issue, this paper is devoted to the application of an adaptive LightGBM method for wind turbine fault detections. To this end, the realization of feature selection for fault detection is firstly achieved by utilizing the maximum information coefficient to analyze the correlation among features in supervisory control and data acquisition (SCADA) of wind turbines. After that, a performance evaluation criterion is proposed for the improved LightGBM model to support fault detections. In this scheme, by embedding the confusion matrix as a performance indicator, an improved LightGBM fault detection approach is then developed. Based on the adaptive LightGBM fault detection model, a fault detection strategy for wind turbine gearboxes is investigated. To demonstrate the applications of the proposed algorithms and methods, a case study with a three-year SCADA dataset obtained from a wind farm sited in Southern China is conducted. Results indicate that the proposed approaches established a fault detection framework of wind turbine systems with either lower false alarm rate or lower missing detection rate.

Research on the Met Mast Siting Used in Post Assessment of Mountain Wind Farm

2014 ◽  
Vol 953-954 ◽  
pp. 443-447
Author(s):  
Jia Yuan Yang ◽  
Yu Mo Woo ◽  
Ke Sheng ◽  
Yu Hui Tang
Keyword(s):  
Wind Turbine ◽  
Turbulence Intensity ◽  
Wind Farm ◽  
Southern China ◽  
Average Level ◽  
Speed Up ◽  
Relationship Of ◽  
Post Assessment

Abstract. For a mountain wind farm in southern China, the paper used CFD software, METEODYN WT, to simulate the wind in all directions to assess their speed-up factor, turbulence intensity, inflow angle and horizontal deviation caused by the terrain. The turbulence intensity, the horizontal deviation and the inflow angle in the met-mast position should be low or small, and the speed-up factor should be able to represent the average level of all the wind turbine sites. The positional relationship of the wind turbine and met-mast is reference to IEC61400-12-1. The paper provided two optional areas.

scholarly journals Fault Detection for Pitch System of Wind Turbine-Driven Doubly Fed Based on IHHO-LightGBM

2021 ◽  
Vol 11 (17) ◽  
pp. 8030
Author(s):  
Mingzhu Tang ◽  
Zhonghui Peng ◽  
Huawei Wu
Keyword(s):  
Experimental Data ◽  
Control System ◽  
Fault Detection ◽  
False Alarm ◽  
Wind Turbine ◽  
False Alarm Rate ◽  
Optimization Algorithm ◽  
Pitch Control ◽  
Detection Model ◽  
Light Gradient

To address the issue of a large calculation and difficult optimization for the traditional fault detection of a wind turbine-based pitch control system, a fault detection model, based on LightGBM by the improved Harris Hawks optimization algorithm (light gradient boosting machine by the improved Harris Hawks optimization,IHHO-LightGBM) for the wind turbine-based pitch control system, is proposed in this article. Firstly, a trigonometric function model is introduced by IHHO to update the prey escape energy, to balance the global exploration ability and local development ability of the algorithm. In this model, the fault detection false alarm rate is used as the fitness function, and the two parameters are used as the optimization objects of the improved Harris Hawks optimization algorithm, to optimize the parameters, so as to achieve the global optimal parameters to improve the performance of the fault detection model. Three different fault data of the pitch control system in actual operations of domestic wind farms are used as the experimental data, the Pearson correlation analysis method is introduced, and the wind turbine power output is taken as the main state parameter, to analyze the correlation degree of all the characteristic variables of the data and screen the important characteristic variables out, so as to achieve the effective dimensionality reduction process of the data, by using the feature selection method. Three established fault detection models are selected and compared with the proposed method, to verify its feasibility. The experimental data indicate that compared with other algorithms, the fault detecting ability of the proposed model is improved in all aspects, and the false alarm rate and false negative rate are lower.

scholarly journals Wind Farm Fault Detection by Monitoring Wind Speed in the Wake Region

Energies ◽  
2020 ◽  
Vol 13 (24) ◽  
pp. 6559
Author(s):  
Minh-Quang Tran ◽  
Yi-Chen Li ◽  
Chen-Yang Lan ◽  
Meng-Kun Liu
Keyword(s):  
Energy Dissipation ◽  
Wind Speed ◽  
Fault Detection ◽  
Wind Turbine ◽  
Wind Farm ◽  
Stokes Equations ◽  
Navier Stokes ◽  
Wake Region ◽  
Navier Stokes Equations ◽  
Dissipation Model

A novel concept of wind farm fault detection by monitoring the wind speed in the wake region is proposed in this study. A wind energy dissipation model was coupled with a computational fluid dynamics solver to simulate the fluid field of a wind turbine array, and the wind velocity and direction in the simulation were exported for identifying wind turbine faults. The 3D steady Navier–Stokes equations were solved by using the cell center finite volume method with a second order upwind scheme and a k−ε turbulence model. In addition, the wind energy dissipation model, derived from energy balance and Betz’s law, was added to the Navier–Stokes equations’ source term. The simulation results indicate that the wind speed distribution in the wake region contains significant information regarding multiple wind turbine faults. A feature selection algorithm specifically designed for the analysis of wind flow was proposed to reduce the number of features. This algorithm proved to have better performance than fuzzy entropy measures and recursive feature elimination methods under a limited number of features. As a result, faults in the wind turbine array could be detected and identified by machine learning algorithms.

scholarly journals Fault Detection of the Wind Turbine Variable Pitch System Based on Large Margin Distribution Machine Optimized by the State Transition Algorithm

2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Mingzhu Tang ◽  
Jiahao Hu ◽  
Zijie Kuang ◽  
Huawei Wu ◽  
Qi Zhao ◽  
...  
Keyword(s):  
Fault Detection ◽  
Wind Turbine ◽  
State Transition ◽  
The State ◽  
Variable Pitch ◽  
Large Margin ◽  
Detection Model ◽  
Margin Distribution ◽  
State Transition Algorithm ◽  
Pitch System

Aiming at solving the problem that the parameters of a fault detection model are difficult to be optimized, the paper proposes the fault detection of the wind turbine variable pitch system based on large margin distribution machine (LDM) which is optimized by the state transition algorithm (STA). By setting the three parameters of the LDM model as a three-dimensional vector which was searched by STA, by using the accuracy of fault detection model as the fitness function of STA, and by adopting the four state transformation operators of STA to carry out global search in the form of point, line, surface, and sphere in the search space, the global optimal parameters of LDM fault detection model are obtained and used to train the model. Compared with the grid search (GS) method, particle swarm optimization (PSO) algorithm, and genetic algorithm (GA), the proposed model method has lower false positive rate (FPR) and false negative rate (FNR) in the fault detection of wind turbine variable pitch system in a real wind farm.

An Investigation of the Low Performance of the First Wind Farm in Thailand: A Case of Poor Wind Turbine-Site Matching

2013 ◽  
Vol 724-725 ◽  
pp. 469-475
Author(s):  
Akraphon Janon ◽  
Tanakorn Wongwuttanasatian ◽  
Gumphol Faikaow ◽  
Panumas Srinor
Keyword(s):  
Wind Turbine ◽  
Wind Farm ◽  
Performance Indicator ◽  
Wind Farms ◽  
Measured Data ◽  
Capacity Factor ◽  
Contributing Factors ◽  
Short Period ◽  
Low Performance ◽  
Turbine Capacity

This research investigates causes of the low performance of the first commercial wind farm in Thailand. The measured data suggests that this wind farm is uncompetitive. We found that this is due to poor turbine-site matching. In contrary to a traditionally held belief, the hub-height and turbine capacity are not the contributing factors. Key performance indicators are obtained for use as benchmarks in future wind farm appraisal. Then a turbine selection method is proposed to increase the capacity factor (CF) of the wind farm. CF is used as the main performance indicator, which can be compared to other wind farms. The real capacity factor (CFR) determined using measured data is 14.90%. This CFR is considerably lower than the estimated capacity factor (CFE) of 21.53%. The low CFR is due to grid instability. In addition, the CFR is lower than the CFE by a factor of 0.69. This information is valuable to investors and wind farm developers in a wind farm feasibility study. A graphical wind turbine-site matching is proposed. Wind turbine-site matching is achieved by using normalised power output plots and power density plots on a probability density graph of the wind site. This process consumes a short period of time. An improved turbine-site matching is achieved.

scholarly journals Fault Detection of Wind Turbine Induction Generators through Current Signals and Various Signal Processing Techniques

2020 ◽  
Vol 10 (21) ◽  
pp. 7389
Author(s):  
Yuri Merizalde ◽  
Luis Hernández-Callejo ◽  
Oscar Duque-Perez ◽  
Raúl Alberto López-Meraz
Keyword(s):  
Fault Detection ◽  
Wind Turbine ◽  
Wind Farm ◽  
Electrical Signal ◽  
Fault Detection And Diagnosis ◽  
Maintenance Cost ◽  
Research Report ◽  
Electric Generator ◽  
Detection And Diagnosis ◽  
Processing Techniques

In the wind industry (WI), a robust and effective maintenance system is essential. To minimize the maintenance cost, a large number of methodologies and mathematical models for predictive maintenance have been developed. Fault detection and diagnosis are carried out by processing and analyzing various types of signals, with the vibration signal predominating. In addition, most of the published proposals for wind turbine (WT) fault detection and diagnosis have used simulations and test benches. Based on previous work, this research report focuses on fault diagnosis, in this case using the electrical signal from an operating WT electric generator and applying various signal analysis and processing techniques to compare the effectiveness of each. The WT used for this research is 20 years old and works with a squirrel-cage induction generator (SCIG) which, according to the wind farm control systems, was fault-free. As a result, it has been possible to verify the feasibility of using the current signal to detect and diagnose faults through spectral analysis (SA) using a fast Fourier transform (FFT), periodogram, spectrogram, and scalogram.

Overview of Subsynchronous Oscillation in Grid-connected Wind Farm

2020 ◽  
Vol 13 (7) ◽  
pp. 969-979
Author(s):  
Xu Pei-Zhen ◽  
Lu Yong-Geng ◽  
Cao Xi-Min
Keyword(s):  
Power Systems ◽  
Wind Turbine ◽  
Large Scale ◽  
Wind Farm ◽  
Wind Farms ◽  
Induction Generator ◽  
Future Research ◽  
Stable Operation ◽  
Subsynchronous Oscillation ◽  
Different Types

Background: Over the past few years, the subsynchronous oscillation (SSO) caused by the grid-connected wind farm had a bad influence on the stable operation of the system and has now become a bottleneck factor restricting the efficient utilization of wind power. How to mitigate and suppress the phenomenon of SSO of wind farms has become the focus of power system research. Methods: This paper first analyzes the SSO of different types of wind turbines, including squirrelcage induction generator based wind turbine (SCIG-WT), permanent magnet synchronous generator- based wind turbine (PMSG-WT), and doubly-fed induction generator based wind turbine (DFIG-WT). Then, the mechanisms of different types of SSO are proposed with the aim to better understand SSO in large-scale wind integrated power systems, and the main analytical methods suitable for studying the SSO of wind farms are summarized. Results: On the basis of results, using additional damping control suppression methods to solve SSO caused by the flexible power transmission devices and the wind turbine converter is recommended. Conclusion: The current development direction of the SSO of large-scale wind farm grid-connected systems is summarized and the current challenges and recommendations for future research and development are discussed.

Experimental Study for SPAR Type Floating Offshore Wind Turbine With Blade-Pitch Control

2013 ◽  
Author(s):  
Toshiki Chujo ◽  
Yoshimasa Minami ◽  
Tadashi Nimura ◽  
Shigesuke Ishida
Keyword(s):  
Wind Turbine ◽  
Wind Farm ◽  
Offshore Wind ◽  
Scale Model ◽  
Offshore Wind Turbine ◽  
Experimental Proof ◽  
Pitch Control ◽  
Model Experiments ◽  
North Eastern ◽  
North Eastern Part

The experimental proof of the floating wind turbine has been started off Goto Islands in Japan. Furthermore, the project of floating wind farm is afoot off Fukushima Prof. in north eastern part of Japan. It is essential for realization of the floating wind farm to comprehend its safety, electric generating property and motion in waves and wind. The scale model experiments are effective to catch the characteristic of floating wind turbines. Authors have mainly carried out scale model experiments with wind turbine models on SPAR buoy type floaters. The wind turbine models have blade-pitch control mechanism and authors focused attention on the effect of blade-pitch control on both the motion of floater and fluctuation of rotor speed. In this paper, the results of scale model experiments are discussed from the aspect of motion of floater and the effect of blade-pitch control.

Sign in / Sign up

Export Citation Format

Share Document