Real-time prediction of projectile penetration to laminates by training machine learning models withfinite element solver as the trainer

Studies on ballistic penetration to laminates is complicated, but important for design effective protection of structures. Experimental means of study is expensive and can often be dangerous. Numerical simu-lation has been an excellent supplement, but the computation is time-consuming. Main aim of this thesis was to develop and test an effective tool for real-time prediction of projectile penetrations to laminates by training a neural network and a decision tree regression model. A large number of finite element models were developed;the residual velocities of projectiles fromfinite element simulations were used as the target data and processed to produce sufficient number of training samples. Study focused on steel 4340tpolyurea laminates with various configurations. Four different 3D shapes of the projectiles were modeled and used in the training. The trained neural network and decision tree model was tested using independently generated test samples using finite element models. The predicted projectile velocity values using the trained machine learning models are then compared with thefinite element simulation to verify the effectiveness of the models. Additionally, both models were trained using a published experimental data of projectile impacts to predict residual velocity of projectiles for the unseen samples. Performance of both the models was evaluated and compared. Models trained with Finite element simulation data samples were found capable to give more accurate predication, compared to the models trained with experimental data, becausefinite element modeling can generate much larger training set, and thus finite element solvers can serve as an excellent teacher. This study also showed that neural network model performs better with small experimental dataset compared to decision tree regression model.     

An interface shear damage model of chromium coating/steel substrate under thermal erosion load

The Cr-plated coating inside a gun barrel can effectively improve the barrel's erosion resistance and thus increase the service life.However,due to the cyclic thermal load caused by high-temperature gun-powder,micro-element damage tends to occur within the Cr coating/steel substrate interface,leading to a gradual deterioration in macro-mechanical properties for the material in the related region.In order to mimic this cyclic thermal load and,thereby,study the thermal erosion behavior of the Cr coating on the barrel's inner wall,a laser emitter is utilized in the current study.With the help of in-situ tensile test and finite element simulation results,a shear stress distribution law of the Cr coating/steel substrate and a change law of the interface ultimate shear strength are identified.Studies have shown that the Cr coating/steel substrate interface's ultimate shear strength has a significant weakening effect due to increasing temperature.In this study,the interfacial ultimate shear strength decreases from 2.57 GPa(no erosion)to 1.02 GPa(laser power is 160 W).The data from this experiment is employed to establish a Cr coating/steel substrate interface shear damage model.And this model is used to predict the flaking process of Cr coating by finite element method.The simulation results show that the increase of coating crack spacing and coating thickness will increase the service life of gun barrel.     

装备表面现代维修保养技术研究

结合装备表面智能维修保养技术方面的研究成果,介绍了装甲装备故障智能检测技术、自适应、自修复功能材料,装甲装备器材全自动保养设备等先进技术,侧重装备维修保养阐述了如何提高信息化程度,推进军队武器装备维修保养技术的现代化建设。     

基于有限元模型的机枪结构动态特性仿真

在对机枪进行结构设计时,了解机枪的固有频率和射击载荷作用下的动态响应特性对整个武器射击精度的影响十分必要。利用有限元分析软件对某机枪模型进行模态仿真分析,进而得出该武器对射击精度影响较大的部件。同时对机枪在射击载荷作用下的动力响应特性进行仿真计算,阐述了在机枪结构设计时频率匹配、射向一致的必要性,为机枪结构动力修改提供了理论依据。     

边界扫描测试在显示技术中的应用

为有效检测电路板焊接质量与器件质量,实现高精度的故障定位,提出了基于边界扫描技术与功能测试技术的解决方案。在显示产品设计中,开展可测试性设计,形成完整的边界扫描测试链;针对VRAM器件特点,提出了基于DRAM的测试方法,并设计相应的测试模型。最终,实现了对电路板的边界扫描测试,快速完成了对显示器件质量与焊接质量的有效检测。边界扫描技术与功能测试的结合,可以扩展边界扫描技术的应用范围,实现了更高的测试覆盖率。     

基于小波网络的非线性系统辨识研究

小波网络为非线性系统辨识研究提供了一种有效的方法,但目前用于小波网络学习的进化算法易陷入局部极小等缺陷.结合生物免疫系统的概念和理论,在非线性系统辨识中引入基于免疫算法的小波网络.该算法中抗体通过浓度相互作用的机制来促进或抑制抗体的生成,借此保持抗体的多样性,并产生了高亲和力的抗体对种群进行不断的更新,提高了算法的全局搜索能力和收敛速度.最后,把基于免疫算法的小波网络用于一个非线性系统辨识的标准实例中,仿真结果验证了该算法的有效性.     

整环上不定方程组的通解公式及其应用

借助Z上矩阵A∈Mm×n(Z)的标准形式D=VAU=diag(d1,d2,…,dq,0,…,0),得到了整环上不定方程组AX=B的通解公式以及矩阵初等变换法.     

基于接触的捞雷具夹紧爪接触面形状优化

介绍了在捞雷具夹紧爪设计过程中引入的基于接触的有限元形状优化设计方法.传统的机械设计方法仅考虑了零件的几何尺寸,而对其形状的设计却考虑不够,导致设计结果不理想.文中将基于接触的有限元形状优化方法应用于传统的机械设计过程.对捞雷具夹紧爪建立基于有限元分析的优化设计模型,使夹紧爪既能满足打捞鱼雷的要求,又得到了优化的形状.结构的特性与受力状况均得到改善.     

破片模拟弹侵彻钢板的有限元分析

根据破片模拟弹侵彻钢板的实验研究,采用MSC.Dytran对破片模拟弹侵彻钢板的侵彻过程、侵彻特性、钢板的破坏模式以及弹体的侵彻速度、靶板的侵彻阻力进行了有限元分析,并将分析结果与实验结果进行了比较.分析结果表明,破片模拟弹冲击钢装甲的侵彻过程可大致分为初始接触、弹体侵入、剪切冲塞和穿甲破坏4个阶段.有限元分析的破片模拟弹侵彻特性及靶板破坏模式与实验观测结果有较好的一致性,在靶板破口的正面,与弹体平面凸缘两端接触的部分,变形以剪切为主,而与切削面接触的部分,以挤压变形为主;靶板破口背面为剪切冲塞破坏;有限元模拟的弹体剩余速度与实验结果吻合较好,弹体侵彻过程中弹靶作用界面的速度和侵彻速度近似呈线性变化.有限元分析结果还表明,采用适当的模型,有限元法能较好地模拟破片模拟弹侵彻钢板的侵彻过程、侵彻特性以及钢板的破坏模式.     

一类非线性时滞双曲型偏微分方程的振动性

研究一类非线性时滞双曲型偏泛函微分方程解的振动性,利用微分不等式方法和广义Riccati变换,获得了该类方程在第一类边值条件下振动的新的充分条件,所得结果通过实例加以阐明.