High-speed train noise prediction method based on interval neural network

Abstract

The invention discloses a high-speed train noise prediction method based on the interval neural network. The problem of uncertainty of acquired parameters affecting high-speed train noise is solved by means of the general interval theory, and high-speed train operation noise is accurately predicted with an interval neural network model. The method comprises the steps of 1, selecting parameters affecting high-speed train noise; 2, acquiring the historical data of the parameters affecting noise; 3, conducting data preprocessing; 4, conducting interval treatment of preprocessed data; 5, establishing an initial interval neural network model; 6, training the initial interval neural network model; 7, predicting high-speed train noise. The problem of uncertainty of parameters affecting high-speed train noise is solved by means of the general interval method, high-speed train operation noise is predicted by means of the interval neural network model predicting method, and the reliability of a noise prediction result is improved.

Description

technical field [0001] The invention relates to a high-speed train noise prediction method based on an interval neural network, and belongs to the technical field of high-speed train noise prediction. Background technique [0002] High-speed railway is the common development trend of the world's railways, and has become an important symbol of railway modernization. With the increase of the speed of the train, the noise pollution of the train has also increased sharply, which inevitably has a serious impact on the living environment along the train. The experience of foreign high-speed railway operation shows that the noise caused by high-speed railway is one of the most difficult problems of high-speed railway to solve, and it is also a problem that needs to be considered and solved urgently in the design and construction of high-speed railway. How to establish a reliable high-speed train operation noise prediction model, accurately predict the noise, and then propose corre...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is, aiming at the uncertainty problem of noise generated by high-speed train operation, the present invention proposes a high-speed train noise prediction method of interval neural network

Images