Urban road traffic noise measurement method based on gradient descent

Abstract

The invention discloses an urban road traffic noise measurement method based on gradient descent. The urban road traffic noise measurement method based on gradient descent is characterized by comprising the following steps that firstly, original data of traffic noise of a certain urban road are collected and normalized; secondly, the data of all monitoring points of the original data of the traffic noise of the urban road are extracted to built a training sample set D; thirdly, the training sample set D is trained, and an urban road traffic noise predication model meeting the accuracy requirement is obtained; fourthly, the urban road traffic noise predication model is used for carrying out multiple times of predication, the predicated values are compared with the actually measured values and then corrected, and an actual predicating model meeting the accuracy requirement is obtained; fifthly, a predicating sample set D* is input to the actual predicating model obtained in the fourth step, and the noise values of all positions in the area covered by corresponding monitoring points are obtained; sixthly, by integrating the measured noise values of all the monitoring points and the noise values of all positions in the range covered by the monitoring points, the complete noise value data of the urban road are obtained.

Description

technical field [0001] The invention relates to the technical field of noise monitoring, in particular to a method for measuring urban road traffic noise based on gradient descent. Background technique [0002] In recent years, with the rapid development of the economy, the number of automobiles in my country has increased sharply, and the urban traffic volume has increased rapidly. The degree and scope of traffic noise pollution to the normal life, work, study, and rest environment of residents along the road have also intensified and expanded. Traffic noise pollution has gradually become the most concerned environmental pollution problem for residents along roads, especially along main traffic roads. According to the survey: Noise can have adverse effects on people's psychology and body at the same time, especially on the nervous system and cardiovascular system. Therefore, in order to adapt to the rapid development of traffic, controlling and reducing traffic noise is r...

AI Technical Summary

Problems solved by technology

[0006] (1) In the case of limited monitoring points, the measurement coverage is low

[0007] (2) The empirical parameters are not suitable for the specific environment, resulting in low measurement accuracy

[0008] (3) Most of the existing prediction models lack learning ability, which makes it difficult to correct and optimize the prediction results, and it is difficult to improve the prediction accuracy

Images