Intelligent PM2.5 prediction method based on second-order self-organizing fuzzy neural network

Abstract

The invention discloses an intelligent PM2.5 prediction method based on a second-order self-organizing fuzzy neural network and belongs to the field of environment engineering and also detection technology. PM2.5 prediction is challenging, while a neural network can better process systems that are characterized by high non-linearity and serious uncertainty. According to the invention, in order to over the difficulty of PM2.5 prediction, the method uses an intelligent air pollutant prediction method that is based on second-order self-organizing fuzzy neural network. The method includes the following steps: firstly using a main component analyzing method to extract characteristic variant of PM2.5, then using the second-order self-organizing fuzzy neural network to establish a soft measurement model between the characteristic variant and PM2.5, and predicting PM2.5 concentration in 24 hours. The method herein obtains better prediction effects, provide timely and accurate information about the quality of the atmosphere and environment for environment management authorities and the general public, can help prevention and treatment of air pollution, and increases living quality for the public.

Description

technical field [0001] The present invention relates to PM 2.5 The intelligent prediction method is an important branch in the field of advanced manufacturing technology, which belongs to both the field of environmental engineering and the field of detection technology. The intelligent prediction method is to predict the future trend of the system by extracting the characteristics of the complex system and establishing the soft sensor model of the system. PM 2.5 The prediction is of great significance to the prevention and control of air pollution. Applying intelligent predictive methods to PM 2.5 In the forecast of , PM can be obtained in time 2.5 Concentration information is beneficial to strengthen the control of air pollution and save the cost of air pollution monitoring. Therefore, PM 2.5 The application of intelligent forecasting method has far-reaching practical significance. Background technique [0002] At present, the situation of air pollution in my country...

AI Technical Summary

Problems solved by technology

The linear regression model is not suitable for modeling the atmospheric environment system which is inherently nonlinear; the interpretability of the artificial neural network is poor; compared with the neural network, the fuzzy neural network combined with the neural network and the fuzzy system has stronger expressive ability, but there is a certain structure The problem

Images