With the continuous optimization and development of intelligent substation, the path planning of substation inspection robot based on traditional ant colony algorithm has many problems, such as weak optimization ability, slow convergence speed and easy to fall into local optimum under complex working environment. In order to improve the work efficiency of substation inspection robot, an improved ACO-SA algorithm is proposed. This algorithm defines a new heuristic function to improve the global search ability. The uneven distribution mechanism of initial pheromone and the introduction of dynamic volatile factor of pheromone can avoid the blindness of the initial search and improve the search efficiency of the algorithm. The tempering mechanism of simulated annealing algorithm is introduced to eliminate local optimization. According to the working environment of the substation inspection robot, the environment model is established by grid method, and the simulation results prove the feasibility of the improved algorithm.