基于模糊逻辑和支持向量机的高压输电线路故障分类器

High voltage transmission line fault classification based on fuzzy logic and Support Vector Machines

高压输电线路故障类型的正确识别是输电线路故障定位和事故分析的前提保证,探求有效、实用的识别方法是有意义的。在对高压输电线路故障类型识别原理及实现方法进行总结分析的基础上,提出采用小样本高泛化能力的支持向量机(Support VectorM achines,即SVM)算法,并结合适于处理具有不确定线性划分关系问题的模糊集理论,来完成高压输电线路的故障分类器,实现了使期望风险最小化的最优分类。仿真结果表明:所提方法判别过程简单、清晰,能正确识别高压输电线路的故障类型,而且还不受输电线路系统模型结构的限制,具有较强的通用性和实用性。提出的基于模糊逻辑和SVM的高压输电线路故障类型识别新方法,克服了常规线性分类方法的局限性,实现了输电线路故障模式空间的非线性可分,解决了高压输电线路故障模式识别的根本性问题。

Accurate fault types recognition for high voltage transmission line is the basis of fault location and accident analysis, it is significant to explore efficient and practical fault recognition techniques. On the basis of analyzing the principles and methods of accomplishing high voltage transmission line fault types classification, this paper presented to combine Support Vector Machines (SVM) with strong generalization ability for small samples and fuzzy set theory of being suitable for solving uncertainty linear division relations to perform the recognition task for high voltage transmission line fault types, so as to obtain the effect of optimum classification with expected risk minimization. The simulation results show that the proposed method has the characteristic of simple and clear recognition process, is able to identify fault types correctly and is fit for any model structures of high voltage transmission line, and therefore the generality and practicability can be ensured. Consequently the recognition method for high voltage transmission line fault types based on fuzzy logic and SVM technique completely overcomes the limitations by using conventional linear classification methods, achieves nonlinear partition for transmission line fault mode space, solves the essential problem for high voltage transmission line fault types recognition.