Aiming at the problems of low labor efficiency and inaccurate management in the maintenance process of expressway electromechanical equipment, an intelligent monitoring system of expressway electromechanical equipment based on FPGA is designed. At first, the system uses FPGA as the main control chip, and combines STM32 module to collect a variety of sensor data for equipment status information, in which the signal output by the sensor is conditioned by the amplification filter circuit. Secondly, hierarchical convolution deep learning is used to analyze the collected state data of electromechanical equipment. By replacing traditional feature extraction network with residual network and establishing loss function model of candidate region, intelligent fault detection of electromechanical equipment is realized. Experimental results show that, compared with other monitoring methods, the system's failure alarm rate under noise interference is greatly reduced to only 0.16%, which meets the requirements of automatic management.