Neural network modeling to evaluate the dynamic flow stress of high strength armor steels under high strain rate compression

An artificial neural network (ANN) constitutive model is developed for high strength armor steel tempered at 500 °C, 600 °C and 650 °C based on high strain rate data generated from split Hopkinson pressure bar (SHPB) experiments. A new neural network configuration consisting of both training and validation is effectively employed to predict flow stress. Tempering temperature, strain rate and strain are considered as inputs, whereas flow stress is taken as output of the neural network. A comparative study on Johnson–Cook (J–C) model and neural network model is performed. It was observed that the developed neural network model could predict flow stress under various strain rates and tempering temperatures. The experimental stress–strain data obtained from high strain rate compression tests using SHPB, over a range of tempering temperatures (500–650 °C), strains (0.05–0.2) and strain rates (1000–5500/s) are employed to formulate J–C model to predict the high strain rate deformation behavior of high strength armor steels. The J-C model and the back-propagation ANN model were developed to predict the high strain rate deformation behavior of high strength armor steel and their predictability is evaluated in terms of correlation coefficient (R) and average absolute relative error (AARE). R and AARE for the J–C model are found to be 0.7461 and 27.624%, respectively, while R and AARE for the ANN model are 0.9995 and 2.58%, respectively. It was observed that the predictions by ANN model are in consistence with the experimental data for all tempering temperatures.     

Data-driven prediction of plate velocities and plate deformation of explosive reactive armor

Explosive reactive armor (ERA) is currently being actively developed as a protective system for mobile devices against ballistic threats such as kinetic energy penetrators and shaped-charge jets. Considering mobility, the aim is to design a protection system with a minimal amount of required mass. The efficiency of an ERA is sensitive to the impact position and the timing of the detonation. Therefore, different designs have to be tested for several impact scenarios to identify the best design. Since analytical models are not predicting the behavior of the ERA accurately enough and experiments, as well as numerical simulations, are too time-consuming, a data-driven model to estimate the displacements and deformation of plates of an ERA system is proposed here. The ground truth for the artificial neural network (ANN) is numerical simulation results that are validated with experiments. The ANN approximates the plate positions for different materials, plate sizes, and detonation point positions with sufficient accuracy in real-time. In a future investigation, the results from the model can be used to estimate the interaction of the ERA with a given threat. Then, a measure for the effectiveness of an ERA can be calculated. Finally, an optimal ERA can be designed and analyzed for any possible impact scenario in negligible time.     

碳化硼基3DMC材料抗弹性能的初步探讨

通过7.62穿甲燃烧弹的射击考核,分析了碳化硼基3DMC材料的抗弹性能,发现其综合抗弹性能优于等厚度的某型号装甲钢,并具有抗击连续打击的能力,认为该材料可以独立用于装甲防护。     

Statistical variability and fragility assessment of ballistic perforation of steel plates for 7.62 mm AP ammunition

The paper describes field test results of 7.62 × 51 mm M61 AP (armour piercing) ammunition fired into mild steel targets at an outdoor range. The targets varied from 10 mm to 32 mm in thickness. The tests recorded penetration depth, probability of perforation (i.e., complete penetration), muzzle and impact velocities, bullet mass, and plate yield strength and hardness. The measured penetration depth exhibited a variability of approximately ±12%. The paper then compared ballistic test results with predictive models of steel penetration depth and thickness to prevent perforation. Statistical parameters were derived for muzzle and impact velocity, bullet mass, plate thickness, plate hardness, and model error. A Monte-Carlo probabilistic analysis was then developed to estimate the probability of plate perforation of 7.62 mm M61 AP ammunition for a range of impact velocities, and for mild steels, and High Hardness Armour (HHA) plates. This perforation fragility analysis considered the random variability of impact velocity, bullet mass, plate thickness, plate hardness, and model error. Such a probabilistic analysis allows for reliability-based design, where, for example, the plate thickness with 95% reliability (i.e. only 1 in 20 shots will penetrate the wall) can be estimated knowing the probabilistic distribution of perforation. Hence, it was found that the plate thickness to ensure a low 5% probability of perforation needs to be 11–15% thicker than required to have a 50/50 chance of perforation for mild steel plates. Plates would need to be 20–30% thicker if probability of perforation is reduced to zero.     

Prediction of flow stress of 7017 aluminium alloy under high strain rate compression at elevated temperatures

An artificial neural network(ANN) constitutive model and JohnsoneC ook(Je C) model were developed for 7017 aluminium alloy based on high strain rate data generated from split Hopkinson pressure bar(SHPB) experiments at various temperatures. A neural network configuration consists of both training and validation, which is effectively employed to predict flow stress. Temperature, strain rate and strain are considered as inputs, whereas flow stress is taken as output of the neural network. A comparative study on Johnsone Cook(Je C) model and neural network model was performed. It was observed that the developed neural network model could predict flow stress under various strain rates and temperatures. The experimental stressestrain data obtained from high strain rate compression tests using SHPB over a range of temperatures(25 e300 C), strains(0.05e0.3) and strain rates(1500e4500 s 1) were employed to formulate JeC model to predict the flow stress behaviour of 7017 aluminium alloy under high strain rate loading. The JeC model and the back-propagation ANN model were developed to predict the flow stress of 7017 aluminium alloy under high strain rates, and their predictability was evaluated in terms of correlation coefficient(R) and average absolute relative error(AARE). R and AARE for the J-C model are found to be 0.8461 and 10.624%, respectively, while R and AARE for the ANN model are 0.9995 and 2.58%, respectively. The predictions of ANN model are observed to be in consistent with the experimental data for all strain rates and temperatures.     

陶瓷基复合装甲防12.7mm穿甲燃烧弹的靶试研究（Ⅰ）

基于对材料特性和防弹机理的认识,设计了由Al2O3陶瓷、616装甲钢和高强PE材料构成的陶瓷基复合装甲板,并用现役127.mm穿甲燃烧弹进行靶试考核,检验靶板设计思路,结果表明：防护面密度为128 kg/m2的靶板可防住该弹。     

A bayesian optimisation methodology for the inverse derivation of viscoplasticity model constants in high strain-rate simulations

We present an inverse methodology for deriving viscoplasticity constitutive model parameters for use in explicit finite element simulations of dynamic processes using functional experiments, i.e., those which provide value beyond that of constitutive model development. The developed methodology utilises Bayesian optimisation to minimise the error between experimental measurements and numerical simulations performed in LS-DYNA. We demonstrate the optimisation methodology using high hardness armour steels across three types of experiments that induce a wide range of loading conditions: ballistic penetration, rod-on-anvil, and near-field blast deformation. By utilising such a broad range of conditions for the optimisation, the resulting constitutive model parameters are generalised, i.e., applicable across the range of loading conditions encompassed the by those experiments (e.g., stress states, plastic strain magnitudes, strain rates, etc.). Model constants identified using this methodology are demonstrated to provide a generalisable model with superior predictive accuracy than those derived from conventional mechanical characterisation experiments or optimised from a single experimental condition.     

穿甲子弹垂直侵彻防弹钢试验与理论模型

试验研究了穿甲子弹垂直侵彻高强防弹钢的机理,提出了一个分析靶板极限速度和弹体剩余速度的理论模型,该模型综合考虑了材料的应变率与热软化效应,结果表明,理论值与试验值吻合很好.分析了失效准则的影响,研究了剪切带温度和靶板耗能随入射速度的变化规律.     

基于ANN模式识别的某型导弹测试车配电系统故障诊断

人工神经网络诊断特点与基于模式识别的诊断特点非常相似。将ANN模式识别技术应用于某型导弹测试车配电系统故障诊断。根据测试车配电系统的故障特点,设计ANN为4层BP网络,具有9个输入、10个输出,两个隐含层神经元数目分别为9和6。测试结果表明该方法能有效诊断测试车配电系统故障。     

基于遗传算法和神经网络的混合自学习策略

通过对神经网络自学习方法和基因遗传算法的研究 ,采用自适应基因遗传算法对神经网络进行训练 ,形成基于遗传算法和神经网络的混合自学习策略 ,克服了神经网络自学习方法的不足 ,提高了系统的自学习能力     

超声激励条件下微裂纹生热的有限元分析及试验研究

为解决现行装甲装备裂纹检测手段效率低、输出结果不直观等问题,将超声红外热波检测技术引入装甲装备零部件缺陷鉴定环节。针对装甲板等平板类结构的厚度特点,建立了厚度9～13121m的含微裂纹铝合金平板试件有限元分析模型,通过不同厚度试件微裂纹生热及裂纹面相对运动频谱的对比,揭示了微裂纹生热机理及其与试件厚度之间的关系。最后,通过试验验证了采用有限元分析的可行性。     

Application of ultrasonic waves in measurement of hardness of welded carbon steels

The ultrasonic contact impedance technique and ultrasonic wave velocities have been widely used for non-destructive hardness measurement.Ultrasonic wave velocity shift provides through the thickness average hardness, however, the correlations are performed according to surface hardness. In order to accept this technique as a particular non-destructive method for determination of hardness, it is necessary to test it with industrial applications. A widely used joining(welding) technique is selected for this purpose. Samples of carbon steels with three different carbon contents, but similar composition, are annealed in order to obtain the softened samples with different hardness values. Rockwell B scale hardness of heat treated samples, which are assumed to be isotropic, are determined and correlated with ultrasonic wave velocity shifts. Effect of welding process on hardness is investigated using ultrasonic wave velocity shifts, and the results are verified with destructive hardness measurements.     

Ballistic impact properties of woven bamboo- woven E-glass- unsaturated polyester hybrid composites

In this study, a laminated woven bamboo/woven E glass/unsaturated polyester composite is developed to combat a ballistic impact from bullet under shooting test. The aim of this study is to understand the fundamental effects of the woven bamboo arrangement towards increasing ballistic resistance properties. The work focusses on the ballistic limit test known as NIJ V50, which qualifies materials to be registered for use in combat armor panels. The results show that the composites withstood 482.5 m/s ± 5 limit of bullet velocity, satisfying the NIJ test at level II. The findings give a strong sound basis decision to engineers whether or not green composites are qualified to replace synthetic composites in certain engineering applications.     

基于体系对抗仿真的装甲装备体系效能评估

针对体系效能评估中仿真结果数据的转化和聚合问题,提出采用效用函数方法加以解决。首先构建了装甲装备体系作战效能的层次化指标体系,在此基础上,引入效用函数对仿真数据进行转化,然后通过加权求和得到体系的整体作战效能和作战能力。最后,通过装甲装备体系对抗仿真和效能评估实例,说明了该方法用于解决体系效能评估问题的可行性和有效性。     

Interface defeat studies of long-rod projectile impacting on ceramic targets

The interface defeat phenomenon always occurs when a long-rod projectile impacting on the ceramic target with certain velocity, i.e., the projectile is forced to flow radially on the surface of ceramic plates for a period of time without significant penetration. Interface defeat has a direct effect upon the ballistic performance of the armor piercing projectile, which is studied numerically and theoretically at present. Firstly, by modeling the projectiles and ceramic targets with the SPH (Smoothed Particle Hydrodynamics) particles and Lagrange finite elements, the systematic numerical simulations on interface defeat are performed with the commercial finite element program AUTODYN. Three different responses, i.e., complete interface defeat, dwell and direct penetration, are reproduced in different types of ceramic targets (bare, buffered, radially confined and oblique). Furthermore, by adopting the validated numerical algorithms, constitutive models and the corresponding material parameters, the influences of projectile (material, diameter, nose shape), constitutive models of ceramic (JH-1 and JH-2 models), buffer and cover plate (thickness, constraints, material), as well as the prestress acted on the target (radial and hydrostatic) on the interface defeat (transition velocity and dwell time) are systematically investigated. Finally, based on the energy conservation approach and taking the strain rate effect of ceramic material into account, a modified model for predicting the upper limit of transition velocity is proposed and validated. The present work and derived conclusions can provide helpful reference for the design and optimization of both the long-rod projectile and ceramic armor.     

A three-stage model for the perforation of finite metallic plates by long rods at high velocities

A three-stage theoretical model is presented herein to predict the perforation of a thick metallic plate struck normally by a long rod at high velocities. The model is suggested on the basis of the assumption that the perforation of a thick metallic plate by a long rod can be divided into three stages: (1) initial penetration; (2) plug formation and (3) plug slipping and separation. Various analytical equations are derived which can be employed to predict the ballistic limit, residual velocity and residual length of the long rod. It is demonstrated that the present model predictions are in good agreement with available experimental results for the perforation of finite steel targets struck normally by steel as well as tungsten alloy long rods at high velocities. It is also demonstrated that the dynamic maximum shear stress of a plate material has strong effect on plug formation and plug thickness which, in turn, exerts considerable influence on the residual velocities and lengths of a long rod at impact velocities just above the ballistic limit.     

军事电子信息处理中的人工神经网络技术

本文首先分析了现代战场环境对军事电子系统智能信息处理的应用需求，然后对人工神经网络理论与技术在军事电子信息处理中的现实应用与潜在前景给出了一个较为详细的介绍与分析。着重介绍了神经网络在雷达、红外及声纳目标的检测、识别、多机动目标跟踪及武器系统的智能控制等方面的应用情况，力图展示神经网络用于军事电子信息处理的特色与优势。最后分析了人工神经网络技术发展与应用中存在的一些问题。     

Experimental study on ceramic balls impact composite armor

Ceramic balls represent a new type of damaging element, and studies on their damaging power of composite armor are required for a comprehensive evaluation of the effectiveness of various types of weapons. The goal of this study was to determine the impact of ϕ7 mm toughened Al₂O₃ ceramic balls on a composite ceramic/metal armor. The influences of the ceramic panel and the thickness of the metal backing material on the destroying power of the ceramic balls were first determined. Based on the agreement between numerical simulation, experimental results, and calculation models of the target plate resistance, the response mechanism of the ceramic balls was further analyzed. The results indicate that for a back plate of Q235 steel, with an increasing thickness of the ceramic panel, the piercing speed limit of the ceramic balls gradually increases and the diameter of the out-going hole on the metal back decreases. Different conditions were tested to assess the effects on the piercing speed, the diameter of the out-going hole, the micro-element stress, and the integrity of the recovered ceramic bowl.     

神经网络的原理及应用

人工神经网络是在现代神经科学研究成果的基础上提出的,反映了人脑功能的基本特征。但它只是人脑功能的某种抽象、模拟和简化。研究这一技术的目的在于,探索人脑加工、储存和搜索信息的机制,并将其原理应用于人工智能的可能性。本文介绍了一些神经网络模型及应用。     

Experimental study of transient pressure wave in the behind armor blunt trauma induced by different rifle bullets

Pressure wave plays an important role in the occurrence of behind armor blunt trauma (BABT), and ballistic gelatin is widely used as a surrogate of biological tissue in the research of BABT. Comparison of pressure wave in the gelatin behind armor for different rifle bullets is lacking. The aim of this study was to observe dynamic changes in pressure wave induced by ballistic blunt impact on the armored gelatin block and to compare the effects of bullet type on the parameters of the transient pressure wave. The gelatin blocks protected with National Institute of Justice (NIJ) class III bulletproof armor were shot by three types of rifle bullet with the same level of impact energy. The transient pressure signals at five locations were recorded with pressure sensors and three parameters (maximum pressure, maximum pressure impulse, and the duration of the first positive phase) were determined and discussed. The results indicated that the waveform and the twin peak of transient pressure wave were not related to the bullet type. However, the values of pressure wave’s parameters were significantly affected by bullet type. Additionally, the attenuation of pressure amplitude followed the similar law for the three ammunitions. These findings may be helpful to get some insight in the BABT and improve the structure design of bullet.