RBF神经网络的C4ISR系统效能评估

针对当前效能评估方法存在人为因素干扰的问题,并考虑到RBF网络具有收敛速度快,无局部极小优点等优点,建立了基于RBF网络的C4ISR系统效能评估模型.模型采用K-均值聚类算法确定隐层节点数据中心和扩展常数;用最小二乘法进行输出层权值的修正;为防止病态,用目标总函数动态地确定隐节点的个数.最后,将得到的结果和BP网络输出...     

反对称铺层碳纤维复合材料圆柱壳的双稳态应力特性

双稳态复合材料可广泛应用于各类可变结构的设计。针对反对称铺层的圆柱壳,利用有限元软件ABAQUS的Standard准静态分析,模拟其双稳态跳变过程和跳回过程,探讨在整个连续过程中圆柱壳上的应力分布情况,以及应力随时间和载荷变化的趋势,从而对该类可变结构的设计起到指导作用。结果表明:该类复合材料圆柱壳跳变过程中最大应力出现在载荷施加点与约束点附近,第二稳态下应力关于板中心呈中心对称分布,最大应力沿板壳对角线出现在四个角内侧附近,而跳回过程中应力由第二稳态下的分布慢慢变为集中在约束点附近。而且整个圆柱壳上的最大应力时刻与最大载荷施加的时刻不重叠,具有滞后性。     

Damage mechanics and energy absorption capabilities of naturalfiber reinforced elastomeric based bio composite for sacrificial structural applications

The present study deals with the experimental, finite element (FE) and analytical assessment of low ballistic impact response of proposedflexible'green' composite make use of naturally available jute and rubber as the constituents of the composite with stacking sequences namely jute/rubber/jute (JRJ), jute/rubber/rubber/jute (JRRJ) and jute/rubber/jute/rubber/jute (JRJRJ). Ballistic impact tests were carried out by firing a conical projectile using a gas gun apparatus at lower range of ballistic impact regime. The ballistic impact response of the proposed flexible composites are assesses based on energy absorption and damage mechanism. Results revealed that inclusion of natural rubber aids in better energy ab-sorption and mitigating the failure of the proposed composite. Among the three different stacking se-quences of flexible composites considered, JRJRJ provides better ballistic performance compared to its counterparts. The damage study reveals that the main mechanism of failure involved in flexible com-posites is matrix tearing as opposed to matrix cracking in stiff composites indicating that the proposedflexible composites are free from catastrophic failure. Results obtained from experimental, FE and analytical approach pertaining to energy absorption and damage mechanism agree well with each other. The proposed flexible composites due to their exhibited energy absorption capabilities and damage mechanism are best suited as claddings for structural application subjected to impact with an aim of protecting the main structural component from being failed catastrophically.     

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.     

改善Al对B4C润湿性的研究

依据金属Al的特性及其与B4C相互作用的关系,在理论上分析Al对B4C的润湿性,分析理论润湿性与实际润湿性差异的原因,在此基础上,通过实验寻求改善Al对B4C润湿性的方法和工艺,发现升高温度可以改善润湿性,温度由1 050℃升至1 100℃时,润湿角θ由52°降至23°;在Al中添加小量Mg后,真空1×10-3Pa,温度1 100℃×3 h时Al对B4C润湿角由原来的23°降至9°.     

光电干扰武器系统C^3I可执行建模研究

基于UML的C3I系统模型的设计结果是对系统的静态表述,而C3I系统的本质是动态的。着色Petri网(Colored Petri Net,CPN)具有强大的描述能力及严密的数学基础和多种分析手段,并且它是可以仿真运行的。提出了从UML产品映射到可用于逻辑、行为和性能方面体系结构评价的CPN可执行模型的方法,先对光电干扰武器系统C3I进行UML建模的一般描述,再详细地阐述了光电干扰武器系统C3I从UML产品映射到CPN建立可执行模型的过程。通过对可执行模型CPN的仿真可对光电干扰武器系统C3I进行完整准确地评价。     

基于SEA的舰载C3I系统防空作战效能评估模型

现代海战中,空中目标对舰艇的威胁越来越大,舰艇的防空作战能力已成为衡量其综合作战能力的主要指标。而C3I系统作为舰艇的指挥中枢,其性能直接决定着舰艇防空作战的成败。根据现代海战中空中目标的武器作战使用方式,并针对SEA方法的要求,提出了评估C3I系统在防空作战时系统效能的三个主要性能量度(MOP),通过分析C3I系统在防空作战时的特点,建立了评估C3I系统防空作战效能的SEA方法模型。并利用该模型比较了不同的C3I系统的作战效能,对结果进行了简要分析,证明了SEA方法模型对舰载防空C3I系统进行效能评估的可行性。     

From the International Conference on the Great Lakes Region-led negotiation to the Intervention Brigade

The eastern Democratic Republic of Congo (DRC) has been characterised by chaos and insecurity for a number of years, but the rise of the M23 rebellion in 2012 once again highlighted just how dire the humanitarian and security situation is. For most of 2012, the crisis was addressed through negotiations between M23 and Kinshasa, mediated by the International Conference on the Great Lakes Region (ICGLR). However, 2013 marked the signing of the Peace, Security and Cooperation Framework Agreement (PSC Framework), and the United Nations Security Council's adoption of Resolution 2098, which contains the mandate of the long-awaited Intervention Brigade (IB). The PSC Framework calls on Kinshasa to implement substantial political reforms while also urging the neighbours of the DRC to stop interfering in its internal affairs. The IB is mandated to carry out targeted operations against the so-called ‘negative forces’ that operate in the eastern DRC. For now, hope of resolving this ongoing crisis hinges on the continuing ICGLR negotiations, the implementation of the PSC Framework and the success of the IB. However, there are critical questions about all of these processes that need to be answered and understood, as the expectations for these processes – especially in the case of the IB – are extremely high. Will the ICGLR manage to negotiate a peace agreement and will the IB succeed, or will they go down in history as yet another failure to save the eastern DRC?     

基于改进半监督FCM聚类的复合材料超声检测脱粘缺陷识别

针对径向基（RBF）神经网络在进行超声检测脱粘缺陷识别时存在参数选择不确定、网络结构鲁棒性差等问题,提出一种改进的自适应半监督模糊C均值聚类（FCM）的RBF神经网络的方法,将kw近邻估计法和半监督模糊C均值聚类方法相结合,改进了隶属度函数,自适应确定聚类数目。将改进的RBF神经网络应用于超声检测脱粘缺陷识别,实验结果表明：与传统RBF神经网络相比,本方法减弱了孤立样本对网络结构的影响,增强了网络结构的鲁棒性,提高了脱粘缺陷识别的准确率,是一种较好的超声检测脱粘缺陷识别分类方法．     

The Armoury Gauging System and Interchangeable Manufacture

Abstract

Scientifically analysing important artefacts from the site of historic battles is vital if the best information is to be retrieved from the field. A detailed knowledge of the specific equipment that was available to the combatants from a known battle is also required at a high level so that artefacts and fragments resulting from an historic battlefield archaeological survey can be recognised when found. Access to specialists from all walks of life is required throughout each battlefield-related project, from the fieldwork stages to the dissemination of information. The following paper discusses the importance of working alongside museums and specialists and gives examples of how the Towton Battlefield Archaeology Project has successfully worked with the staff at the Royal Armouries Leeds.