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

A practical scheme for selecting characterization parameters of boron-based fuel-rich propellant formulation was put forward; a calculation model for primary combustion characteristics of boron-based fuel-rich propellant based on backpropagation neural network was established, validated, and then was used to predict primary combustion characteristics of boron-based fuel-rich propellant. The results show that the calculation error of burning rate is less than ± 7 . 3 %; in the formulation range (hydroxyl-terminated polybutadiene 28%–32%, ammonium perchlorate 30%–35%, magnalium alloy 4%–8%, catocene 0%–5%, and boron 30%), the variation of the calculation data is consistent with the experimental results. 1. Introduction Boron-based fuel-rich propellant belongs to composite solid propellants and is used for solid rocket ramjet engine. The basic requirements of the propellant for the engine are high burning rate and appropriate pressure index at low pressure. In its combustion, there are multiphase physical and chemical reactions. The former low-pressure combustion model can only be used for qualitative analysis but not for simulation because many of the parameters cannot be measured by experiments, and thus primary combustion property research and formulation design are excessively dependent on experimental study [1–3]. Therefore, applying neural network to simulation of propellant combustion characteristics has become an important research direction, and, in recent years, the neural network method has been applied to HTPB composite solid propellant, NEPE propellant, and so forth [4–9]. But no public reports on the application of the method to calculation for primary combustion characteristics (burning rate and pressure index) of boron-based fuel-rich propellant can be found at home and abroad. BP neural network model can achieve a very close approximation to a complex nonlinear function and is suitable to deal with those problems in which causal relationship is not clear, therefore, in this paper, the concrete combustion process is not taken into account, and calculation for primary combustion characteristics is realized by training BP neural network with formulations and corresponding burning rate data directly. 2. Preferences of Propellant Formulation BP neural network is applied to calculation for primary combustion characteristics with inputs of pressure and characterization parameters of boron-based fuel-rich propellant formulation and output of corresponding burning rate; through training BP neural network, the complex function between input and