Application of radar sensors based on low-consumption industrial design in road detection

Abstract

In order to improve the sustainability of road engineering detection, this paper optimizes the radar sensors commonly used in road detection, reasonably adjusts the ratio of conventional detection and active detection, and improves the accuracy and feedback. In this paper, the deep learning method is fused with the traditional particle swarm optimization to form an improved particle swarm algorithm. First of all, according to the WIFI and cellular communication network, the road data of any radar sensor is obtained, including road conditions, traffic and environment. Then, through the deep learning method, the eigen values, the amount is simplified, the data processing ability is improved, and the impact on the calculation process and results is reduced. Finally, the particle swarm optimization is used to traverse the search, and the calculation results are obtained by combining the local adjustment parameters. The MATLAB simulation results show that the improved particle swarm optimization can reduce the energy consumption of the sensor by 20%, and improve the road detection accuracy to more than 90%. It can shorten the detection and feedback time, and the shortening amount is 10~20s. Therefore, the improved particle swarm optimization can reduce the energy consumption and improve the road detection effect, which has certain practical feasibility and provides support for related research.