Generic scalable fault diagnosis system for multimachine power grids

•Capable of accurate fault detection, classification and location identification.•This approach is scalable to multi-machine systems of any size and description.•Considers complete dynamics of power system.

A new approach for fault diagnosis in power grids is presented in this paper. The approach is capable of detecting, classifying and locating, with high speed and accuracy, any type of faults anywhere in the grid using bus voltage or line current measurements only. Fault detection and classification is accomplished by applying logic on measured data while fault location is determined by fault location identification functions generated off-line by using a least-square support vector machine. The high speed and accuracy aspects of the proposed approach are verified through case studies in three test power systems.