Open AccessThe Research on Improving the Precision of The Polymer IFHI By BP Neural Network of The Method Data Normalization
Author(s) -
Dingran Zhang,
Lei Chen,
Yiqi Wang,
Huiya Wang
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/692/3/032067
Subject(s) - artificial neural network , normalization (sociology) , computer science , matlab , database normalization , standardization , backpropagation , artificial intelligence , data mining , time delay neural network , machine learning , pattern recognition (psychology) , sociology , anthropology , operating system
BP neural network has a good effect on data prediction. Using BP neural network to predict polymer fire risk index (IFHI) is a cross research method based on computer intelligent learning model and traditional fire risk assessment. In order to solve the defect of low precision of BP neural network in IFHI prediction, a solution to standardize the initial data processing is proposed to optimize the BP neural network simulation model. In the construction of BP neural network model, the range, threshold, and weight of the initial data need to be processed globally, and then the BP neural network is simulated and trained. Finally, the data is simulated and predicted by using MATLAB. The output results of the neural network with different data standardization processing methods are compared to verify the simulation accuracy. The results show that the input node parameters of BP neural network are processed by Z-score normalization method, which improves the learning ability of the model, improves the accuracy of the prediction effect, and reduces the IFHI error of prediction.