Research On Faults Diagnosis Of Power Network And Wide Area Backup Protection Algorithm

With the increasing scale and more complex structure of power system, further requests have been advanced in power network fault diagnosis, The developments in Artificial Intelligent technology provide plentiful theories and methods for this research field. Bayesian Network is one of the most effective theoretical models for uncertainty knowledge expression and reasoning, It's character is in accord with the require of fault diagnosis in power network, many experts have researched it and yielded substantial results, but there are some problems and flaws in it's application. Fault diagnosis is applied after the blackout in power network, the cascading fault or power system collapse might have happened. Studies of the significant power system blackouts indicate that, in certain abnormal operation situations aroused by bigger disturbances, conventional protection relays based on the locally measured inputs is of easy misoperation, and resulted in accidental expansion. With the recent advances of computer and communication technology, the wide area protection has been proposed as an approach to solve the problems of the kinds.Dissolved gas analysis (DGA) is the most effective and convenient method in transformer fault diagnosis. Due to the randomness and uncertainty of power transformer fault diagnosis data, a novel specific transformer fault diagnosis method based on Fuzzy Bayesian network is proposed in this paper. It used in the method that the Bayesian network satisfactory capacity of knowledge representation and strong solving ability to deal with uncertain facts, the Fuzzy set can represent fuzzy knowledge and fuzzy event. First, the segmentation spaces of three ratio methods were processed fuzzily using a membership function, then, the fault type was diagnosised by theory of fuzzy Bayesian networks. Finally, the correctness and effectiveness of this method are validated, and a novel method is provided for the diagnosis of the fault transformer.According to the fault conditions of complicated topology and large-scale power networks, in this paper, an efficient method is proposed to partition the large-scale power networks. A hierarchical recursive fault diagnosis model is proposed basing on Rough set and Bayesian network, using the ability of knowledge reduction and processing indeterminate information of rough set theory, the hierarchical mining of substation's fault diagnosis knowledge is carried out and optimal seeking of attributes is performed, then applying Bayesian networks to identify fault areas and fault components. And it can adopt parallel diagnosis to every area. Results of calculation examples show that the proposed method is correct and effective, and can improve the fault tolerance capability and speed of the fault diagnosis system while the kernel attribute is lost, so this method is available.A wide area backup protection algorithm with high fault-tolerance performance is proposed to implement the distributed wide area backup protection system. The distributed wide area backup protection system can locate the fault element with fault-tolerance judgment according to fault direction and the zone 1 and 2 of fault distance protection information within the protection coverage. The proposed algorithm is simple and with good fault-tolerance capability, the results of a case study show that it has good adaptability in case any one or two of protection elements mal-operates, fails to operate or loss of fault information since communication outage, it can increase performance of backup protection system greatly.