Prediction method and system for error back propagation neural network and server

Abstract

The invention provides a prediction method and system for an error back propagation neural network. The method comprises: constructing an initial neural network; training the initial neural network by utilizing pre-acquired N training data samples to obtain a first convergent neural network; performing correlation analysis on output data of neuron nodes of a hidden layer in the first convergent neural network, and combining neuron nodes, greater than a preset correlation threshold, of the hidden layer to generate a second convergent neural network reserving m neuron nodes of the hidden layer; performing correlation analysis on the output data of the neuron nodes of the hidden layer in the second convergent neural network and output data of neuron nodes of an output layer in the first convergent neural network to obtain an optimized neural network; and training the optimized neural network by utilizing the N training data samples again to obtain a predicted neural network. According to the prediction method and system, the number of the nodes of the hidden layer of the single-hidden-layer neural network is determined, so that the deficiencies of single principal component analysis and correlation coefficient method are made up for.

Description

technical field [0001] The invention belongs to the technical field of safety and emergency response, and relates to a prediction method and system, in particular to a prediction method, system and server of an error backpropagation neural network. Background technique [0002] With the rapid development of the economy, the development of the chemical industry is becoming more and more prosperous. At the same time, accidents of leakage and diffusion of hazardous chemicals in chemical parks occur frequently, posing a serious threat to personal safety and the natural environment around the accident site. At the same time, when a hazardous chemical leakage accident occurs, especially a toxic gas leakage accident, the influence of meteorological factors on the diffusion rate and diffusion range cannot be ignored, especially the wind speed. The collection of wind speed often has high requirements on equipment. At the same time, the data from the collection site can not be importe...

AI Technical Summary

Problems solved by technology

[0006] First, only the correlation between nodes in the hidden layer is considered, and the correlation with the nodes in the output layer is not considered. It is possible that the hidden layer nodes that are retained may also contain nodes that have little correlation with the output layer nodes the node;

[0007] Second, although the number of hidden layer nodes and output layer nodes is reduced, the correlation between hidden layer nodes is not considered, and the remaining hidden layer nodes may still have a large correlation the node

[0008] Therefore, how to provide a prediction method, system and server of an error backpropagation neural network, so as to solve the problems in the existing hidden layer nodes that do not consider the correlation between the hidden layer nodes and the output layer nodes. Contains nodes with little correlation with the output layer nodes, and does not consider the correlation between hidden layer nodes, resulting in the retention of hidden layer nodes with relatively high correlation nodes and other defects. It has become a practitioner in this field. technical issues to be resolved

Images