Calculation for high-pressure combustion properties of high-energy solid propellant based on GA-BP neural network

To read the full-text of this research, you can request a copy directly from the authors.


A genetic algorithm (GA)-back-propagation (BP) neural network was established. The high-pressure combustion properties of NEPE high-energy solid propellant were simulated and calculated by using the GA-BP neural network. Aiming at calculation requirement, NEPE high-energy solid propellant formulation was characterized, and 13 parameters were put forward. The burning-rate prediction results show that the calculation error of the method is less than 10%, and its accuracy is high; the method can be used for high-pressure combustion property research and formulation design of NEPE high-energy solid propellant. At the same time, the method can reflect essential characteristics of the formulation, and the investigation provides a kind of new method for burning-rate prediction of high-energy solid propellant.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... However, this model failed to consider the influence of the particle size on the propellant combustion process. Zhang and Dai (2007) established a combustion model of NEPE propellants using a genetic algorithm-back propagation (GA-BP) neural network, and then simulated its combustion performance under high pressure. Li et al. (2008aLi et al. ( , 2008bLi et al. ( , 2009) established the calculation formula of the burning rate and the pressure index of NEPE propellants based on the thermal decomposition characteristics and free radical cracking model of NEPE solid propellant. ...
Nitrate ester plasticized polyether (NEPE) is a kind of high-energy solid propellant that has both good mechanical properties and high specific impulse. However, its unique composition makes its combustion mechanism different from both double-base propellants and composite propellants. In order to study the combustion mechanism of NEPE propellants, we improved the free radical cracking model of previous research to make it capable of predicting the burning rate of NEPE propellants. To study the combustion characteristics and provide data support for the model, an experimental system was built and four kinds of NEPE propellants with different compositions and grain size distributions were tested. The results show that our modified model can reflect the combustion characteristics of NEPE propellants with an acceptable accuracy. The difference between the model and the experimental data is mainly caused by uncertain environmental factors and the ignorance of interactions between components. Both the experimental data and the results predicted by the model show that increasing the backpressure helps to increase the burning rate of NEPE propellants. Furthermore, the grain size of the oxidizer inside the NEPE propellant has a more severe impact on the burning rate but a lighter impact on the burning rate pressure exponent in comparison with the grain size of aluminum. For aluminum-free NEPE propellants, the reaction in the gas phase is dominant in the combustion process while adding aluminum into the propellant makes the solid phase dominant in the final stage. The combustion of fine aluminum particles near the burning surface generates heat feedback to the burning surface which evidently influences the surface temperature. However, the agglomeration of coarse aluminum particles has little effect on the burning surface temperature.
... The reference [2] introduced the neural network model, multi model composite flame combustion model and evaluation of the advantages and disadvantages. The reference [3] used genetic neural network NEPE high to simulate high pressure solid propellant combustion performance. The reference [4] used different neural network model in the burning temperature and burning rate prediction calculation analysis. ...
... 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][2][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][5][6][7][8][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 fuelrich propellant can be found at home and abroad. ...
Full-text available
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.
A PSO-BP neural network simulation model was established with particle swarm optimization (PSO) optimizing biases and weights of back-propagation (BP) neural network. By using the PSO-BP neural network, low-pressure burning rate was simulated and calculated. When the important factor changes in a range, for instance HTPB(hydroxyl terminated polybutadiene, 28%-32%), AP(ammonium perchlorate, 30%-35%, weight-mean diameter 0.06-0.140 mm), GFP(catocene, 0%-5%), the burning rate and pressure index of corresponding formulas were calculated and compared to corresponding experimental results. The results show that the calculation errors of the PSO-BP method are less than ±7%.
The effects of aluminum with different diameters (1, 3, 7, 13, 24μm) on the burning rate and the pressure index of CMDB propellant were studied at two different pressure ranges, 3 -10MPa and 10-18MPa. The results showed that the burning rate of the propellant increased with increasing of aluminum particle size, the pressure index decreased with increasing of aluminum particle size. The pressure index was brought down from 0.92 to 0. 51 and from 0. 74 to 0. 13 at the pressure range 3 -10MPa and 10-18MPa respectively when the particle size of the aluminum increased. When its diameter was 24 μm, the propellant showed the plateaucombustion characteristics in the pressure range of 10-18MPa.
A new model for the combustion of composite solid propellants is developed. The flame is represented as burning at the interfacial region between streams of fuel and oxidant which are generated by vaporization of each solid component. The interface between the two solid phases receives the greatest heat flux from the reaction zone and vaporization occurs most rapidly near the interface. The reaction zone is a ‘phalanx’ which spearheads the attack of hot reaction gases on the solid. The model provides a rational physical explanation for many qualitative observations of solid propellant combustion and successfully correlates the pressure dependence of burning rates.