In order to solve the distribution network in three dimensional space fault detection of optimal allocation problem of sensor nodes, the improved artificial fish algorithm is proposed based on the iot sensor effectively which realizes effective optimal allocation of space detection sensor nodes. Firstly, the MSP 430F 149 microprocessor chip is utilized to construct the space sensor node together with the monitoring computer to form the distribution station temperature monitoring system which realizes the effective collection, transmission and processing of the distribution station temperature detection data. Secondly, the traditional artificial fish swarm algorithm is improved through the initialization of artificial fish swarm and the improved gradient descent method. The field of view and the convergence accuracy of the algorithm is improved. Finally, an improved artificial fish swarm algorithm is applied to optimize the placement of sensor nodes. It is shown that the improved artificial fish swarm algorithm based on IoT sensors can effectively optimize the monitoring of substation space.