Airport noise monitoring data restoration method based on deep noise-reduction self-encoding

Abstract

The invention discloses an airport noise monitoring data restoration method based on deep noise-reduction self-encoding and belongs to the technical field of airport noise monitoring abnormity restoration. The method comprises the following steps: to begin with, obtaining noise data by utilizing a noise monitoring device in an airport; then, carrying out pretreatment on the noise data to obtain a sample set; next, setting a candidate deep noise-reduction self-encoding model for extracting sample set features, and carrying out network weight initialization on each model; training parameters of each model layer by layer through a greedy algorithm, and adjusting the parameters through a back propagation algorithm to obtain a parameter value of each model; then, calculating data reconstruction errors of each model, selecting the model having the smallest error and extracting implied depth features of the sample set in the model to train a support vector regression model; and at last, carrying out predication on noise monitoring data to be restored by utilizing the trained model. The method is high in intelligence, can accurately and efficiently restore abnormal data and improves airport noise monitoring data restoration timeliness and effectiveness.

Description

technical field [0001] The invention discloses an airport noise monitoring data restoration method based on deep noise reduction self-encoding, and belongs to the technical field of airport noise monitoring abnormal restoration. Background technique [0002] With the development of society and economy, my country's investment in aviation, aerospace and other fields has increased year by year, and the number of airports has also increased. However, while airports provide fast and convenient transportation for passengers and goods, various problems related to airport noise also follow. The airport noise problem has become one of the obstacles affecting the sustainable development of the civil aviation industry. [0003] In terms of the layout of noise monitoring points, the grid-like layout of monitoring points can collect the noise conditions of the entire airport and its surroundings in a real, timely and detailed manner. This layout method needs to arrange a lot of monitor...

AI Technical Summary

Problems solved by technology

[0005] However, hardware equipment will inevitably have problems such as damage or aging. In view of the wide geographical distribution of monitoring points and the complexity of equipment, airport staff often cannot rush to the monitoring site to maintain abnormal equipment in time, resulting in inaccurate monitoring points. Collect noise data in your area

Images