APPLICATION OF RADAR SENSORS BASED ON LOW-CONSUMPTION INDUSTRIAL DESIGN IN ROAD DETECTION

Abstract

In order to reduce the energy consumption of radar sensing, improve the accuracy of road detection, and play its practical function, this paper proposes an improved particle swarm algorithm. Firstly, the mapping method is used to collect road data and simplify the complexity of the data. Secondly, according to the logical relationship between the data, the correlation of the detection data was calculated to reduce the influence of randomness on the road detection results. In addition, the rate of change of the objective function is calculated with equality and inequality constraints to improve the characteristics of the results. Finally, through the iterative method of deep learning, the road control results of the sensor are calculated, and the stability and accuracy of the overall operation of the sensor are calculated. The MATLAB simulation results show that the deep learning algorithm in this paper can reduce the energy consumption of the sensor by 20%, improve the accuracy of road detection by 90%, shorten the detection time, and shorten the detection time by 10~20s. Therefore, the use of improved particle swarm optimization can reduce the energy consumption of radar sensors and improve the road detection effect, which has certain feasibility and effectiveness.