Autonomous maneuver decision-making for a UCAV in short-range aerial combat based on an MS-DDQN algorithm

To solve the problem of realizing autonomous aerial combat decision-making for unmanned combat aerial vehicles (UCAVs) rapidly and accurately in an uncertain environment, this paper proposes a decision-making method based on an improved deep reinforcement learning (DRL) algorithm: the multi-step double deep Q-network (MS-DDQN) algorithm. First, a six-degree-of-freedom UCAV model based on an aircraft control system is established on a simulation platform, and the situation assessment functions of the UCAV and its target are established by considering their angles, altitudes, environments, missile attack performances, and UCAV performance. By controlling the flight path angle, roll angle, and flight velocity, 27 common basic actions are designed. On this basis, aiming to overcome the defects of traditional DRL in terms of training speed and convergence speed, the improved MS-DDQN method is introduced to incorporate the final return value into the previous steps. Finally, the pre-training learning model is used as the starting point for the second learning model to simulate the UCAV aerial combat decision-making process based on the basic training method, which helps to shorten the training time and improve the learning efficiency. The improved DRL algorithm significantly accelerates the training speed and estimates the target value more accurately during training, and it can be applied to aerial combat decision-making.     

长杆射弹侵彻三种混凝土靶的实验研究

为了研究钻地武器的侵彻性能,在57mm口径的气炮上发射长杆射弹对三种靶体进行模拟侵彻实验。靶体为水泥砂浆石靶、钢纤维混凝土靶和含单层密排刚玉球的钢纤维混凝土靶。实验结果表明,弹头形状对侵彻深度有明显影响;当长杆射弹和撞击速度都相同时,与侵彻钢纤维混凝土靶相比,含单层密排刚玉球的钢纤维混凝土靶中的侵彻深度大约降低了11%,而水泥砂浆石靶中的侵彻深度增加了12%。     

面向突防效能的超声速巡航导弹总体设计技术初步研究

防御系统技术的不断发展,对超声速巡航导弹设计提出了新的需求.针对以“性能”为核心的设计不能满足超声速巡航导弹设计新需求的问题,初步探讨了面向突防效能的超声速巡航导弹总体设计技术.分析了国内外导弹武器设计技术的发展,指出设计技术向着以“效能为核心”的设计方向发展;提出了面向效能的设计理念,分析指出面向效能的设计是以追求满意设计为目标的优化设计;在新的设计理念指导下提出了面向突防效能设计的技术框架,主要说明了面向突防效能的超声速巡航导弹设计框架、效能基础、技术基础、基本模式以及几项关键技术等.     

坦克实体智能机动路径模型

根据坦克机动作战的一般原则,首先对影响坦克实体机动的因素进行了分析和合理的假设;充分考虑战术模拟中的实际情况,将数字地图中各点间的空间距离转化为以各点间机动时间为权边的网图,通过求任意两点间的最短距离的方法,建立坦克实体机动最短时间路径的数学模型。并给出了人工智能算法,把问题求解过程简化,从而解决战术模拟系统中智能机动中的路径选择问题。     

一种适用于拦截高速目标的末段导引律

基于在视线坐标系中的导弹-目标相对运动模型,以控制导弹-目标视线角速度趋于零为基本思想,设计了一种末制导律,用于拦截高超声速目标。以脱靶量和能量消耗为约束条件,以目标无机动时有很好的性能为目的,首先设计了最优制导律;然后,基于滑模控制理论,选择合适的滑模趋近律,对所设计的最优制导律进行改进得到最优滑模制导律;用李雅普诺夫理论证明了该制导律的稳定性,分析了该制导律参数选择条件。仿真结果表明,与最优制导律相比,所设计的制导律对目标机动有较强的鲁棒性,能以直接碰撞的方式拦截高超声速目标。     

Partial penetration of annular grooved projectiles impacting ductile metal targets

Changing and optimizing the projectile nose shape is an important way to achieve specific ballistic performance. One special ballistic performance is the embedding effect, which can achieve a delayed high-explosive reaction on the target surface. This embedding effect includes a rebound phase that is significantly different from the traditional penetration process. To better study embedment behavior, this study proposed a novel nose shape called an annular grooved projectile and defined its interaction process with the ductile metal plate as partial penetration. Specifically, we conducted a series of low-velocity-ballistic tests in which these steel projectiles were used to strike 16-mm-thick target plates made with 2024-O aluminum alloy. We observed the dynamic evolution characteristics of this aluminum alloy near the impact craters and analyzed these characteristics by corresponding cross-sectional views and numerical simulations. The results indicated that the penetration resistance had a brief decrease that was influenced by its groove structure, but then it increased significantly-that is, the fluctuation of penetration resistance was affected by the irregular nose shape. Moreover, we visualized the distribution of the material in the groove and its inflow process through the rheology lines in microscopic tests and the highlighted mesh lines in simulations. The combination of these phenomena revealed the embed-ment mechanism of the annular grooved projectile and optimized the design of the groove shape to achieve a more firm embedment performance. The embedment was achieved primarily by the target material filled in the groove structure. Therefore, preventing the shear failure that occurred on the filling material was key to achieving this embedding effect.     

对机动突防反舰导弹的防御

建立了舰空导弹反导拦截模型和反舰导弹“蛇行机动”突防弹道模型,通过攻防对抗仿真的方法研究了舰空导弹对末端机动突防反舰导弹的防御问题,提出了对舰空导弹未来发展的建议.     

不同截面形状复合长杆弹对陶瓷复合靶板侵彻研究

采用数值模拟技术研究了由3种不同截面形状的钨芯外包覆一层钢,形成的钢包覆层复合长杆弹在入射速度为1200m/s～1700m/s时对陶瓷/金属复合靶板的侵彻过程。结果表明:对于同一入射速度、相同弹体长度、同种材料的弹芯和包覆层以及靶板材料而言,等面积的六边形截面钨芯复合长杆弹的侵彻深度明显大于圆形及方形截面,方形及六边形截面与和它们等外接圆形成的圆形截面复合长杆弹侵彻深度没有明显差别,本研究认为这是与不同截面钨芯的外接圆直径直接相关。六边形截面长杆弹侵彻过程中的自锐化现象是其侵彻深度明显大于其它两种弹体的主要原因。     

目标摆式机动对反导舰炮射击精度的影响

为了探讨目标机动对舰炮武器系统射击精度的影响,采用仿真方法计算了目标末端摆式机动时近程反导舰炮武器系统的命中概率,以图示方式给出多种机动周期、多种摆幅、2种射速条件下的计算结果.结果表明,较小周期的摆式机动可显著降低舰炮武器系统命中概率,提高舰炮射速是增大对机动目标命中概率的有效途径.     

不同初速弹丸对靶板的损伤仿真与评估

为了研究弹丸对武器装备的损伤,建立弹丸侵彻多层靶板的有限元模型,对不同初速弹丸侵彻多层靶板进行仿真试验,引入等效应变及等效应力参量以精确描述靶板损伤,提出一种基于多元统计分析对靶板损伤进行评估的方法。结果表明：利用该方法所得到的计算结果与理论分析结果完全一致。这说明基于多元统计分析的靶板损伤评估方法能够正确地评价仿真实验中目标靶板的战损程度,因而可以进一步应用于装备侵彻损伤评估与易损性研究中。