The Application Of Artificial Intelligent Technique To Stability Control Of Power System

Asynchronism is a kind of abnormal state of generator. The asynchronizing operation of generator with excitation will make strong oscillation of voltage, current and power. While, the asynchronizing operation of generator out of excitation will absorb plenty of reactive power from system, which will bring ill effect to either system or the safety operation of generator itself. But it is indicated by theory study and operation experience that it is advantageous to improve the operation condition of system by adopting measure actively and carefully to make generator resume synchronism provided that the asynchronizing generator is permitted to operate in short time under certain situations.So in this paper, the control strategy which will be adopted when asynchronous generators with excitation enter synchronism梤esynchronization by supplementary discrete controller (which has been presented in paper[13-15]) is discussed and a kind of simple discrete controller is also brought forward in this paper. Both of them are appended to the control scheme in the aspect of exciter and prime mover (that is quick excitation and fast valving), and both have better controlling effect.Intelligent control is the advanced phase of the development of controlling theory-It is mainly used to solve those controlling questions of complex system which are difficult to settle by traditional methods. Besides, intelligent control has such controlling function characteristics as study function, adaptability function andorganizing function. So, in this paper, those theories presented above are realized separately by fuzzy controlling theory, and a fuzzy-neural network is used to complete the controlling mechanism of resynchronization of generator using simplifying supplementary discrete controller. The validity of the theory of resynchronization of generators using simplifying supplementary discrete control and these intelligent controllers are testified by simulation.At present, the computational methods of finding the optimal reclosing time for instantaneous faults mostly are off-line. For example, the usage of transient energy function is difficult in computation and needs long computational time, which is not conformed to the requirements of real operation under changing condition in power system. Wavelet transform is a kind of analysis method of time-scale (time-frequency), and it has the characteristic of multi-resolution analysis. It also has the ability of showing the local characteristics of signal in time and frequency. And artificial neural network has its special intelligent controlling function. Therefore, in this paper, an on-line method for obtaining the optimal reclosing time of transient fault is presented based on wavelet transform and artificial neural network, which costs less time to calculation the optimal reclosing time. At last, the validity and accuracy of this method is testified by test examples.