Passenger station environment temperature prediction method and device

Abstract

The invention provides a passenger station environment temperature prediction method and device. The passenger station environment temperature prediction method comprises: receiving collected data corresponding to current time; by adopting a preset first LSTM model, carrying out prediction based on the collected data, and obtaining an environment characteristic variable prediction result; and based on the environment characteristic variable prediction result, adopting a preset LightGBM model to obtain a corresponding temperature prediction value. The LSTM model and the LightGBM model are used for predicting the temperature value in the future time, the error between the predicted temperature value and the real future temperature value can be reduced, the prediction accuracy of the future temperature value is improved, and then a passenger station worker is assisted to make a decision in advance, such as setting a proper air conditioner temperature value and ventilation quantity in advance, so that the purposes of energy conservation and emission reduction are achieved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a method and device for predicting the ambient temperature of a passenger station. Background technique [0002] Intelligent high-speed rail has become the development direction of the current railway transportation field, and promoting the construction of intelligent stations is an important part of building intelligent high-speed rail. As an important bridge between cities, the passenger station has become the goal pursued by people with intelligent experience and comfortable travel. Some large passenger stations have a large number of people entering and leaving, and are prone to dense and crowded situations, and the internal air environment directly affects the experience of passenger comfort, especially temperature has become an important physical quantity in the environmental index. The adjustment of the feng shui system in the station is directly affected ...

AI Technical Summary

Problems solved by technology

However, the existing technology lacks the overall prediction and perception ability of the ambient temperature of the station, and some existing algorithms are not suitable for predicting the ambient temperature value of the station, that is, they cannot effectively predict the characteristics of the ambient temperature value of the station, and the prediction results lack reference significance , which is not conducive to promoting the construction of intelligent stations

Images