Zhigang Liu

A new detection approach of transient disturbances combining wavelet packet and Tsallis entropy

Tsallis entropy owns additivity property for different independent subsystems, which will not produce the frequency aliasing and energy leakage in comparison with Shannon entropy and wavelet transform. Singular value decomposition can simply obtain the hidden information of data. In this paper, we propose a new detection approach of transient disturbances, which combines wavelet packet, Tsallis entropy and singular value decomposition. Through the introduction of Tsallis entropy and wavelet packet, the definition of wavelet packet Tsallis entropy (WPTSE) and calculation method are given. The key parameters during the course of detection, including wavelet decomposition levels, window width, and nonextensive parameter of Tsallis entropy, are respectively discussed in detail. The detection plan of transient disturbances with WPTSE is proposed. The experimental results show that the precision of proposed detection approach is high. It owns the anti-noise ability, and the influences of the disturbance parameters are very small. In the end, the comparisons show that the detection performance of WPTSE is better than that of wavelet transform and EEMD (ensemble empirical mode decomposition). The PSCAD/EMTDC and real-life signals also demonstrate its feasibility and validity.

A new classification method for transient power quality combining spectral kurtosis with neural network

This paper aims to develop a new idea for the classification of transient disturbances on power quality. The method is based on the combination of spectral kurtosis (SK) and artificial neural network (ANN). The SK is a high-order statistical moment which can detect the non-Gaussian components in a signal. Through the introduction of SK and its properties, we propose a classification plan for five transient disturbances combining SK and ANN. Firstly, the high frequency parts of five disturbance signals are extracted with DB4 wavelet transform (WT). Secondly, their SK values are respectively computed based on short time Fourier transform (STFT) and WT. Because the features of SK based on WT for five disturbance signals are not clearly distinguished, we propose a new computation method of SK based on Butterworth Distribution (BUD). Lastly, we choose the maximum, minimum and average values of SK based on STFT and BUD as the eigenvectors for the transient disturbance classification, which are input into RBF neural network. The simulation results show that the recognition rate of five transient disturbances is high, and the classification method proposed in the paper for transient power quality combining SK with ANN is efficient and feasible.

A new short-term load forecasting method of power system based on EEMD and SS-PSO

Aiming to the disadvantages of short-term load forecasting with empirical mode decomposition (EMD) such as mode mixing and many high-frequency random components, a new short-term load forecasting model based on ensemble empirical mode decomposition (EEMD) and sub-section particle swarm optimization (SS-PSO) is proposed in this paper. Firstly, the load sequence is decomposed into a limited number of intrinsic mode function (IMF) components and one remainder by EEMD, which can avoid the mode mixing problem of traditional EMD. Then, through calculating and observing the spectrum of decomposed series, some low-frequency IMFs are extracted and reconstructed. Other IMFs can be forecasted with appropriate forecasting models. Since IMF1 is main random component of the load sequence, the linear combination model is adopted to forecast IMF1. Because the weights of the linear combination model are very important to obtain high forecasting accuracy, SS-PSO is proposed and used to optimize the linear combination weights. In addition, the factors such as temperature and weekday are taken into consideration for short-term load forecasting. Simulation results show that accuracy of the load forecasting model proposed in the paper is higher than that of BP neural network, RBF neural network, support vector machine, EMD and their combinations.

A novel method of short-term load forecasting based on multiwavelet transform and multiple neural networks

This paper aims to develop a load forecasting method for short-term load forecasting based on multiwavelet transform and multiple neural networks. Firstly, a variable weight combination load forecasting model for power load is proposed and discussed. Secondly, the training data are extracted from power load data through multiwavelet transform. Lastly, the obtained data are trained through a variable weight combination model. BP network, RBF network and wavelet neural network are adopted as the training network, and the trained data from three neural networks are input to a three-layer feedforward neural network for the load forecasting. Simulation results show that accuracy of the combination load forecasting model proposed in the paper is higher than any one single network model and the combination forecast model of three neural networks without preprocessing method of multiwavelet transform.

A new short-term load forecasting model of power system based on HHT and ANN

Aiming to the disadvantages of short-term load forecasting with HHT such as mode mixing and random component, a new short-term load forecasting model based on HHT and ANN is proposed The first order difference algorithm is adopted to eliminate mode mixing The random component is forecast with different methods including BP, RBF, SVM, linear and ANN combination Other components can be forecast with proper method The simulation results show that the higher accuracy of short-term load forecasting can be obtained.

The transformer fault diagnosis combing KPCA with PNN

The probabilistic neural network (PNN) can detect the complex relationships and be used to develop its basis for the interpretation of dissolved gas-in-oil data that can identify the fault types. An efficient algorithm known as the kernel principle component analysis (KPCA) is applied to increase features in order to get higher detection accuracy. KPCA reflects the nonlinear or high order features that permit to represent and classify the varying states. More features can be obtained by the nonlinear transformation of KPCA, which can realize the biggest between-class margin of the classifiers. In this paper, we apply the method of combining KPCA with PNN in transformer fault diagnosis. The method has more superior performance than traditional PNN alone method. The property of the nonlinear extension of original data of KPCA can obtain the higher diagnosis accuracy, which can achieve better classification and diagnosis.

Combining Multi Wavelet and Multi NN for Power Systems Load Forecasting

In the paper, two pre-processing methods for load forecast sampling data including multiwavelet transformation and chaotic time series are introduced. In addition, multi neural network for load forecast including BP artificial neural network, RBF neural network and wavelet neural network are introduced, too. Then, a combination load forecasting model for power load based on chaotic time series, multiwavelet transformation and multi-neural networks is proposed and discussed in the paper. Firstly, the training sample is extracted from power load data through chaotic time series and multiwavelet decomposition. Then the obtained data is trained through BP network, RBF network and wavelet neural network. Lastly, the trained data from three neural networks are input a three-layer feedforward neural network based the variable weight combination load forecasting model. Simulation results show that accuracy of the combination load forecasting model proposed in the paper is higher than any one sole network model and the combination forecast model of three neural networks.

Power system load forecasting based on EEMD and ANN

In order to fully mine the characteristics of load data and improve the accuracy of power system load forecasting, a load forecasting model based on Ensemble Empirical Mode Decomposition (EEMD) and Artificial Neural Networks (ANN) is proposed in this paper. Firstly, the load data can be resolved into a limited number of Intrinsic Mode Function (IMF) components and one remainder by EEMD which avoids the mode mixing problem of Empirical Mode Decomposition (EMD). Then, through the observation of the spectrum by Hilbert transform, its obvious that the regularity and periodicity of low frequency components are stronger than high frequency components. So one sole appropriate ANN forecasting model is chosen for each low frequency component, and the linear combination of ANN model is applied to forecasting each high frequency component. Simulation results show that the new model proposed in paper is better than anyone ANN forecasting model.

An approach of power quality disturbances recognition based on EEMD and probabilistic neural network

Based on intrinsic mode functions (IMFs), standard energy difference of each IMF obtained by EEMD and probabilistic neural network (PNN), a new method is proposed to the recognition of power quality transient disturbances. In this method, ensemble empirical mode decomposition (EEMD) is used to decompose the non-stationary power quality disturbances into a number of IMFs. Then the standard energy differences of each IMF are used as feature vectors. At last, power quality disturbances are identified and classified with PNN. The experimental results show that the proposed method can effectively realize feature extraction and classification of single and mixed power quality disturbances.

The recognition study of impulse and oscillation transient based on spectral kurtosis and neural network

To improve the precision of classification and recognition of transient power quality disturbances, a new algorithm based on spectral kurtosis (SK) and neural network is proposed. In the proposed algorithm, Morlet complex wavelet is used to obtain the WT-based SK of two kinds of disturbances, such as the impulse transient and oscillation transient. Two characteristic quantities, i.e., the maximum value of SK and the frequencies of the signals, are chosen as the input of neural network for the classification and recognition of transient power quality disturbances. Simulation results show that the transient disturbance characteristics can be effectively extracted by WT-based SK. With RBF neural network, the two kinds of transient disturbances can be effectively classified and recognized with the method in the paper.