基于深度神经网络的高位滑坡范围预测

以贵州尖山营滑坡为工程背景,通过对深度学习的总结与分析,建立多层感知器模型以对该滑坡危险区范围进行非线性预测研究。通过对深度神经网络算法的优化,构建64-128-32-1四层多层感知器模型,并以滑坡最大高差、滑坡体积、滑源区坡度、坡脚坡度、地层倾角作为输入量,以滑坡最大水平运动距离作为输出量对该模型进行训练,实现影响因素与运动距离的非线性映射。根据对贵州省尖山营滑坡调查和研究,尖山营滑坡区域面积约648 700 m2,体积约1 200万 m3,属于特大型滑坡。依据最优模型对该滑坡进行滑距预测,滑坡平面直线距离1 769 m区域内为危险区域。     

基于PXI总线的导弹角速度编码器组合测试系统设计

针对某型导弹角速度编码器组合测试快速化、模块化、自动化的要求,通过对角速度编码器组合进行分析,结合角速度编码器组合输入信号的模拟、输出信号的采集、测试系统功能和性能要求,设计了基于PXI总线的导弹角速度编码器组合测试系统;介绍了测试系统的测试原理、硬件结构和软件组成、主要设计思想;实验表明,该测试系统工作性能稳定,能有效地进行组合测试和分组件测试并运用层次故障树分析法定位故障,提高了武器系统检测维修保障能力.     

移动位置的信息服务系统研究

随着移动通信技术的发展,无线网的覆盖面越来越广,移动电话发起的紧急呼叫数量在全部紧急呼叫中所占的比例也随之上升。现有的无线网能为移动电话紧急呼叫提供的辅助决策信息非常少。研究的目标是设计一种精确安全的报警系统,使得市民可以便捷并安全地将案情报告给指挥中心,而且指挥中心能够根据案发地点找出最近的警力及时赶往现场,第一时间处理案情。研究表明,系统能够实现报警电话快速定位的功能,并通过地图或文字描述等方式展示位置信息,达到接警、处警对位置信息的要求。     

Existence and Exponential Stability of Multiple Periodic Solutions for a Multidirectional Associative Memory Neural Network

The paper proposes several mathematical models of the multidirectional associative memory (MAM) neural network by analyzing its structure. A model of MAM with distributed delays is studied. Under some new assumptions on activation functions, 2^n₀[m/2]{2^{n_0[m/2]}} invariant subsets of MAM are constructed. Then the existence and the exponential stability of 2^n₀[m/2]{2^{n_0[m/2]}} periodic solutions located on invariant subsets are obtained by constructing a suitable Liapunov function and a Poincaré mapping. An estimating method of the exponential convergence rate is given. The obtained results are new to MAM neural networks. An example is given to illustrate the effectiveness of the results.     

Long-term information collection with energy harvesting wireless sensors: a multi-armed bandit based approach

This paper reports on the development of a multi-agent approach to long-term information collection in networks of energy harvesting wireless sensors. In particular, we focus on developing energy management and data routing policies that adapt their behaviour according to the energy that is harvested, in order to maximise the amount of information collected given the available energy budget. In so doing, we introduce a new energy management technique, based on multi-armed bandit learning, that allows each agent to adaptively allocate its energy budget across the tasks of data sampling, receiving and transmitting. By using this approach, each agent can learn the optimal energy budget settings that give it efficient information collection in the long run. Then, we propose two novel decentralised multi-hop algorithms for data routing. The first proveably maximises the information throughput in the network, but can sometimes involve high communication cost. The second algorithm provides near-optimal performance, but with reduced computational and communication costs. Finally, we demonstrate that, by using our approaches for energy management and routing, we can achieve a 120% improvement in long-term information collection against state-of-the-art benchmarks.     

Topology optimization of free vibrating continuum structures based on the element free Galerkin method

In this paper, the topology optimization design of the free vibrating continuum structures is formulated based on the element free Galerkin (EFG) method. Considering the relative density of nodes as design variable, and the maximization of the fundamental eigenvalue as an objective function, the mathematical formulation of the topology optimization model is developed using the solid isotropic microstructures with penalization (SIMP) interpolation scheme. The topology optimization problem is solved by the optimality criteria method. Finally, the feasibility and efficiency of the proposed method are illustrated with several 2D examples that are widely used in the topology optimization design.     

自行火炮扭力轴强化疲劳寿命计算及分析

开展自行火炮强化试验研究,关键问题是如何计算强化路面下自行火炮扭力轴疲劳寿命.首先,基于虚拟样机技术,建立了某型自行火炮的虚拟样机,结合强化路面数字化模型,开展自行火炮行驶强化试验仿真,获得自行火炮悬挂装置关键件扭力轴的载荷时间历程.然后,利用有限元分析软件MSC.Nastran与疲劳分析软件MSC.Fatigue计算其疲劳寿命.最后,针对自行火炮在部分强化路面上行驶时,随着车速的提高,出现了扭力轴疲劳寿命不降反升的现象,利用振动学的相关理论,从路面、车速对载荷的影响规律入手,对这种现象的原因进行了分析,为自行火炮实车强化行驶试验方案的制订提供了数据参考.     

传感器网络启动式自组织方法

无线传感器网络如何形成一个有序的自组织网络结构是一项重要研究内容,针对按地理区域交替性工作的动态监测网络,提出了相应的网络自组织方法,该方法以启动式方式运行网络,通过单播信令的方式分配MAC地址,标记相邻节点。在数据转发过程中以局部最小代价函数为准则转发数据。仿真实验表明,该自组织方法具有较短的MAC地址,适宜相应的网络环境。     

基于9种无约束优化算法的岩爆预测BP模型优选

为研究不同训练样本数量和无约束优化算法对岩爆BP(Back Propagation)神经网络模型预测准确率的影响,选取围岩最大切向应力与岩石单轴抗压强度比σθ/σc、岩石单轴抗压强度与单轴抗拉强度比σc/σt和弹性能量指数Wet作为预测指标,广泛搜集整理100组典型岩爆实例建立了训练样本数据库.在样本数量分别为40、70和100时,基于标准算法和9种无约束优化算法建立了10个岩爆BP神经网络预测模型,并提出了考虑不同样本规模影响的岩爆烈度等级预测指数——综合准确值N.比较研究结果表明:BP模型的预测准确率随样本数量增加而提高,3种样本数量下的模型平均预测准确率分别为62.5％、76.4％和87.5％;基于9种优化算法建立的BP网络模型的N值均高于标准BP模型;基于Ploak-Ribiere共轭梯度法优化的BP模型的N值(195)和预测准确率(99.0％)均最高,且在5个工程实例中的预测结果完全符合现场实际,优于标准BP模型、支持向量机模型和其他优化模型,为岩爆烈度等级预测的最佳模型.