Journal of Combustion / 2012 / Article / Tab 2

Research Article

Calculation for Primary Combustion Characteristics of Boron-Based Fuel-Rich Propellant Based on BP Neural Network

Table 2

The setting of the basic parameters of BP neural network model.

Basic parameters of BP neural networkParameter setting

StructureThree-layer, 6-10-1
Transfer functiontansig, purelin
Performance functionMean square error of training samples
AlgorithmGradient descent with momentum and adaptive learning rate backpropagation
Momentum coefficient0.9
Initial value of learning rate0.05
Ratio to increase learning rate1.05
Ratio to decrease learning rate0.7
Maximum performance increase1.04
Performance goal0.001
Maximum number of epochs to train5000

Article of the Year Award: Outstanding research contributions of 2020, as selected by our Chief Editors. Read the winning articles.