This paper presents a genetic algorithm to optimize support vector machine parameters for grounding grid fault diagnosis method. Grounding grid is equivalent to a pure resistance model, extract characteristics of different kinds of corrision states, Using genetic algorithm optimize support vector machine kernel function parameters, achieve the identification of the type of failure mode, Grounding grid of 6 × 6 test can quickly detect the grounding grid corrosion, simulation results show that the method has higher accuracy than support vector machine.