Dongxiang Jiang

Wind farm power prediction based on wavelet decomposition and chaotic time series

In this paper, a prediction model is proposed for wind farm power forecasting by combining the wavelet transform, chaotic time series and GM(1,1) method. The wavelet transform is used to decompose wind farm power into several detail parts associated with high frequencies and an approximate part associated with low frequencies. The characteristic of each high frequencies signal is identified, if it is chaotic time series then use weighted one-rank local-region method to predict it. If not, use GM(1,1) model to predict it. And the GM(1,1) model is also used to predict the approximate part of the low frequencies. In the end, the final forecasted result for wind farm power is obtained by summing the predicted results of all extracted high frequencies and the approximate part. According to the predicted results, the proposed method can improve the prediction accuracy of the wind farm power.

Application of the intrinsic time-scale decomposition method to fault diagnosis of wind turbine bearing

A fault diagnosis method of wind turbine bearing based on intrinsic time-scale decomposition (ITD) is put forward. In the proposed method, the vibration signal of the main bearing is decomposed into several proper rotation components by the ITD method. The frequency centers of the proper rotation components that contain predominant energy are computed and considered as fault feature vectors. The nearest neighbor algorithm is applied to identify the fault types of the wind turbine bearing. The experimental data of the wind turbine spherical roller bearing in four conditions (normal, outer race fault, inner race fault and roller fault) are applied to evaluate the performance of the proposed method. The results demonstrate the feasibility and accuracy of this approach for the diagnosis of the wind turbine bearing faults under uncertain conditions.

Application of Wavelet Neural Networks on Vibration Fault Diagnosis for Wind Turbine Gearbox

This paper applies an Artificial Neural Networks (ANN) method--- Wavelet Neural Networks (WNN) on fault diagnosis for a wind turbine gearbox. A gearbox is one of the most important units in a wind turbine drive train. It is significant to study fault diagnosis of gearbox conditions. First this paper presents the principles and advantages of Wavelet Neural Networks. Second this paper specifies the vibration mechanism of the gearbox and the feature parameter group reflecting fault feature, and then the standard fault samples (training samples) and simulation samples (testing samples) are obtained. Third this paper applies the WNN method to perform diagnosing. The accurate diagnostic results have proved the effectiveness of the method for vibration fault diagnosis of gearbox. Finally, the relative advantages of the WNN method are contrasted with those of BPNN method.

Global geometric similarity scheme for feature selection in fault diagnosis

This work presents a global geometric similarity scheme (GGSS) for feature selection in fault diagnosis, which is composed of global geometric model and similarity metric. The global geometric model is formed to construct connections between disjoint clusters in fault diagnosis. The similarity metric of the global geometric model is applied to filter feature subsets. To evaluate the performance of GGSS, fault data from wind turbine test rig is collected, and condition classification is carried out with classifiers established by Support Vector Machine (SVM) and General Regression Neural Network (GRNN). The classification results are compared with feature ranking methods and feature wrapper approaches. GGSS achieves higher classification accuracy than the feature ranking methods, and better time efficiency than the feature wrapper approaches. The hybrid scheme, GGSS with wrapper, obtains optimal classification accuracy and time efficiency. The proposed scheme can be applied in feature selection to get better accuracy and efficiency in condition classification of fault diagnosis.

Theoretical and experimental study on wind wheel unbalance for a wind turbine

In order to ensure safety of wind turbines using non-grid-connected wind power and to reduce the occurrence of faults, as well as to improve the reliability of wind turbines, three different wind wheel unbalance faults are researched through theoretical analysis and experimental simulation in laboratory conditions. A wind turbine test rig has been established and a wind turbine condition monitoring has been developed. Three wind wheel unbalance faults are simulated on the test rig, and by analyzing the experimental results of power output and vibration characteristics in different conditions, the influence of wind wheel unbalance on power output and vibration characteristics is presented.

Application of back propagation neural network to fault diagnosis of direct-drive wind turbine

The vibration signals of wind turbines are highly nonlinear and non-stationary due to wind turbine operation conditions that are very complicated. The signals will be more complex when a fault occurs. Aiming at these problems, a fault diagnosis method for direct-drive wind turbine is presented based on back propagation neural network (BPNN). The time-domain feature parameters of vibration signals in the horizontal and vertical direction are considered in the method. Five experiments of direct-drive wind turbine with normal, wind wheel mass imbalance, wind wheel aerodynamic imbalance, yaw and blade break are carried out in laboratory scale. Through analyzing the features of five conditions, the time-domain feature parameters in horizontal and vertical direction of the vibration signal are selected as the input samples of BPNN. By training, the BPNN model can be constructed between feature parameters and fault types. The validity of the BPNN model is verified using test samples. The results indicate that the proposed method has higher diagnostic accuracy. It can used in on-line fault diagnosis of direct-drive wind turbines.

Test system of a small wind turbine under laboratory conditions

As a clean, renewable, widely distributed, non-polluting energy, wind power plays an important role in the world’s renewable energy development. In order to ensure the stable operation of wind turbines using non-grid-connected wind power, as well as the efficient utilization of wind resources, a study of condition monitoring of wind turbines is necessary. A test system of wind turbines under laboratory conditions based on a LabView platform has been designed. and the system has been applied on small wind turbine test bed to test the performance of output power and vibration characteristics. The result of simulation testing has verified the effectiveness of the test system.

Application of RBF and Elman Neural Networks on Condition Prediction in CBM

The maintenance strategy develops quickly under the requirement of equipments’ near-zero-downtime running performance. Condition Based Maintenance (CBM) makes the maintenance strategy by detecting the equipment’s condition and corrects them before failure which attracts more attention. However, the equipments’ running process differs greatly. The parameters which can signify the faults onsets are also different. This paper attempts to find uniform rule for condition prediction. Artificial Neural Networks play more and more important roles in times series prediction which can achieve the desired output without exactly mathematical model. Application of Neural Networks to condition prediction is presented in this paper. For different concern of condition prediction, RBF Neural Network and Elman Neural Network are selected for the condition prediction which they both achieve good accuracy.

Modal analysis of wind turbine tower

As the support structure of wind turbine, the tower bears alternating loads of wind when the wind turbine runs. To ensure the reliability of the wind turbine, its necessary to carry out modal analysis on the tower, and this would prevent the natural frequency of the tower close to the rated speed of wind turbine. In this paper, finite element analysis of the tower is solved using ANSYS, and the natural frequencies and modes of the tower are presented. After comparing the results of three models, a simple model for modal analysis, which can be calculated in short time, is finally determined.

Experimental investigation and analysis for gearbox fault

As an important component of a wind turbine drive chain, the high failure rate of the gearbox can have a serious impact on the operation of wind turbine units. The fault diagnosis of the gearbox is therefore important for the safety of wind turbine units. In this paper, a gearbox experiment rig was built, experiments on the gear surface spalling fault were held on the rig under laboratory conditions, the shaft vibration displacement signals were collected, related vibration signals were analyzed by time domain, amplitude domain, frequency domain and wavelet analysis, and the results of different analysis methods were compared. The results show that the waveform of normal and fault signals are similar, the amplitude of the signals will change while the fault happens, and the wavelet analysis is more effective than frequency domain analysis on gearbox fault features extraction.