固体推进剂中AP颗粒的级配不同会导致力学性能相差巨大,为了探究AP颗粒的粒度值和质量分数对端羟基聚丁二烯(HTPB)推进剂力学性能的影响规律,采用机器学习的方法对推进剂的力学性能进行仿真预测,降低了实验成本并提高了预测效率。首先,...固体推进剂中AP颗粒的级配不同会导致力学性能相差巨大,为了探究AP颗粒的粒度值和质量分数对端羟基聚丁二烯(HTPB)推进剂力学性能的影响规律,采用机器学习的方法对推进剂的力学性能进行仿真预测,降低了实验成本并提高了预测效率。首先,对不同级配的HTPB推进剂进行拉伸试验,得到不同温度下抗拉强度和伸长率;其次,以拉伸试验结果为样本进行机器学习,分别构建了反向传播(Back Propagation,BP)神经网络、粒子群算法优化的反向传播(Particle Swarm Optimization Back Propagation,PSOBP)神经网络和遗传算法优化的反向传播(Genetic Algorithms Back Propagation,GABP)神经网络对推进剂的力学性能进行预测。结果表明,力学性能与颗粒级配的内在关系较为复杂,并非简单的线性关系。PSOBP和GABP可以用于预测不同级配下HTPB推进剂力学性能,并且GABP神经网络可以更好地预测推进剂的力学性能变化。展开更多
In this paper,to study the mechanical responses of a solid propellant subjected to ultrahigh acceleration overload during the gun-launch process,specifically designed projectile flight tests with an onboard measuremen...In this paper,to study the mechanical responses of a solid propellant subjected to ultrahigh acceleration overload during the gun-launch process,specifically designed projectile flight tests with an onboard measurement system were performed.Two projectiles containing dummy HTPB propellant grains were successfully recovered after the flight tests with an ultrahigh acceleration overload value of 8100 g.The onboard-measured time-resolved axial displacement,contact stress and overload values were successfully obtained and analysed.Uniaxial compression tests of the dummy HTPB propellant used in the gunlaunched tests were carried out at low and intermediate strain rates to characterize the propellant's dynamic properties.A linear viscoelastic constitutive model was employed and applied in finite-element simulations of the projectile-launching process.During the launch process,the dummy propellant grain exhibited large deformation due to the high acceleration overload,possibly leading to friction between the motor case and propellant grain.The calculated contact stress showed good agreement with the experimental results,though discrepancies in the overall displacement of the dummy propellant grain were observed.The dynamic mechanical response process of the dummy propellant grain was analysed in detail.The results can be used to estimate the structural integrity of the analysed dummy propellant grain during the gun-launch process.展开更多
The 2D sandwich model serves as a potent tool in exploring the influence of surface geometry on the combustion attributes of Ammonium perchlorate/Hydroxyl-terminated polybutadiene(AP/HTPB)propellant under rapid pressu...The 2D sandwich model serves as a potent tool in exploring the influence of surface geometry on the combustion attributes of Ammonium perchlorate/Hydroxyl-terminated polybutadiene(AP/HTPB)propellant under rapid pressure decay.The thickness of the sandwich propellant is derived from slicing the 3D random particle packing,an approach that enables a more effective examination of the micro-flame structure.Comparative analysis of the predicted burning characteristics has been performed with experimental studies.The findings demonstrate a reasonable agreement,thereby validating the precision and soundness of the model.Based on the typical rapid depressurization environment of solid rocket motor(initial combustion pressure is 3 MPa and the maximum depressurization rate is 1000 MPa/s).A-type(a flatter surface),B-type(AP recesses from the combustion surface),and C-type(AP protrudes from the combustion surface)propellant combustion processes are numerically simulated.Upon comparison of the evolution of gas-phase flame between 0.1 and 1 ms,it is discerned that the flame strength and form created by the three sandwich models differ significantly at the beginning stage of depressurization,with the flame structures gradually becoming harmonized over time.Conclusions are drawn by comparison extinction times:the surface geometry plays a pivotal role in the combustion process,with AP protrusion favoring combustion the most.展开更多
文摘固体推进剂中AP颗粒的级配不同会导致力学性能相差巨大,为了探究AP颗粒的粒度值和质量分数对端羟基聚丁二烯(HTPB)推进剂力学性能的影响规律,采用机器学习的方法对推进剂的力学性能进行仿真预测,降低了实验成本并提高了预测效率。首先,对不同级配的HTPB推进剂进行拉伸试验,得到不同温度下抗拉强度和伸长率;其次,以拉伸试验结果为样本进行机器学习,分别构建了反向传播(Back Propagation,BP)神经网络、粒子群算法优化的反向传播(Particle Swarm Optimization Back Propagation,PSOBP)神经网络和遗传算法优化的反向传播(Genetic Algorithms Back Propagation,GABP)神经网络对推进剂的力学性能进行预测。结果表明,力学性能与颗粒级配的内在关系较为复杂,并非简单的线性关系。PSOBP和GABP可以用于预测不同级配下HTPB推进剂力学性能,并且GABP神经网络可以更好地预测推进剂的力学性能变化。
文摘In this paper,to study the mechanical responses of a solid propellant subjected to ultrahigh acceleration overload during the gun-launch process,specifically designed projectile flight tests with an onboard measurement system were performed.Two projectiles containing dummy HTPB propellant grains were successfully recovered after the flight tests with an ultrahigh acceleration overload value of 8100 g.The onboard-measured time-resolved axial displacement,contact stress and overload values were successfully obtained and analysed.Uniaxial compression tests of the dummy HTPB propellant used in the gunlaunched tests were carried out at low and intermediate strain rates to characterize the propellant's dynamic properties.A linear viscoelastic constitutive model was employed and applied in finite-element simulations of the projectile-launching process.During the launch process,the dummy propellant grain exhibited large deformation due to the high acceleration overload,possibly leading to friction between the motor case and propellant grain.The calculated contact stress showed good agreement with the experimental results,though discrepancies in the overall displacement of the dummy propellant grain were observed.The dynamic mechanical response process of the dummy propellant grain was analysed in detail.The results can be used to estimate the structural integrity of the analysed dummy propellant grain during the gun-launch process.
基金supported by the National Natural Science Foundation of China(Grant No.51176076)。
文摘The 2D sandwich model serves as a potent tool in exploring the influence of surface geometry on the combustion attributes of Ammonium perchlorate/Hydroxyl-terminated polybutadiene(AP/HTPB)propellant under rapid pressure decay.The thickness of the sandwich propellant is derived from slicing the 3D random particle packing,an approach that enables a more effective examination of the micro-flame structure.Comparative analysis of the predicted burning characteristics has been performed with experimental studies.The findings demonstrate a reasonable agreement,thereby validating the precision and soundness of the model.Based on the typical rapid depressurization environment of solid rocket motor(initial combustion pressure is 3 MPa and the maximum depressurization rate is 1000 MPa/s).A-type(a flatter surface),B-type(AP recesses from the combustion surface),and C-type(AP protrudes from the combustion surface)propellant combustion processes are numerically simulated.Upon comparison of the evolution of gas-phase flame between 0.1 and 1 ms,it is discerned that the flame strength and form created by the three sandwich models differ significantly at the beginning stage of depressurization,with the flame structures gradually becoming harmonized over time.Conclusions are drawn by comparison extinction times:the surface geometry plays a pivotal role in the combustion process,with AP protrusion favoring combustion the most.
