An Image Processing Based Method For Transient Power Quality Classification

While the rapid development of the power electronic system bringing more convenience to people, at the same time, the attendant issues can’t be ignored. In power system, power quality problems may cause damage to some electric power equipment, or make sensitive load not work properly. It will cause a major accident of power system when there is no effectively monitor on it. Therefore, the key to improve the quality of the grid is how to quickly and effectively classify the power quality disturbance, and improve the accurate of detecting various disturbance types, then, we can prevent and control the effective of the power quality problem.Firstly, the basic concept of power quality problems and the main analysis methods were briefly introduced, then, elaborated some traditional classification method of power quality disturbance, such as FFT, wavelet transform(WT), S transform, etc. And we make detail introduction and simulation of the analysis method--the 2-D static wavelet transform.In this paper, A new method is proposed to improve the accuracy of method for classifying transient power quality disturbance by extracting morphological characteristics of disturbance signal. First, the grayscale images are created by normalizing the data of disturbance voltage waveforms. Then image enhancement techniques, such as gamma correction and edge detection as well as peak detection methods, are employed to produce new grayscale images and binary images so as to make characteristics of the disturbance striking. The morphologic feature values are extracted from the binary images. The probability neural network(PNN) is trained by the morphologic feature values and then used to classify transient power quality disturbance. The proposed new method for classifying transient power quality disturbance is simulated and compared with the method of 2-D static wavelet transform. The results show that the accuracy of the new method is better than theexisting methods, it is effective and practical.Finally, we designed a hardware simulation platform with software system which based on DSP of TMS320VC5509. With a detailed description of the principle of the hardware circuit, and the design of software system, the proposed method for classifying the transient power quality disturbance which based on digital image processing can be validated.