RBF神经网络在单轴旋转惯导系统轴向陀螺漂移辨识中的应用

在激光陀螺单轴旋转惯性导航系统中,单轴旋转可以自动补偿垂直于旋转轴上的惯性器件误差,却不能消除旋转轴方向上惯性器件的误差,因此单轴旋转惯性导航系统的导航精度主要由轴向陀螺漂移决定.提出了一种基于径向基函数神经网络的轴向陀螺漂移辨识方法,利用系统纬度误差和温度变化量作为训练集,针对系统热态、冷态两种情况对RBF神经网络进行训练,对轴向陀螺漂移的辨识精度达到0.0003°/h.试验结果表明:该方法能够有效地辨识轴向陀螺漂移,使系统达到较高的导航精度,满足实际应用的需要.     

神经网络的坦克目标威胁评估

在未来高技术局部战争条件下,坦克不得不面临一个动态复杂的战场环境,这就要求坦克能根据战场环境实时地进行目标威胁评估及自主射击。以坦克的自主作战为背景,提出了一种基于神经网络的目标威胁评估方法。首先提出了包含来袭目标性质、指战员指令、保卫目标的重要度、我方武器性能值等一套威胁评估指标体系;然后采用神经网络方法进行威胁评估。神经网络方法的优势主要体现在:①考虑了诸因素的相互关联;②充分考虑了战术信息;③权系数对具体环境的适应性;④方法的通用性。实例结果表明,神经网络方法科学合理,为坦克目标威胁的评估提供了新思路。神经网络方法具有普遍意义,能推广应用于其它武器平台的目标威胁评估。     

基于无标度网络的防空反导系统构建

构建高效的防空反导系统是防空反导作战的基础。运用复杂网络理论,建立基于无标度网络防空反导系统模型,并将其统计特征同基于WS小世界网络的模型进行了比较,得出基于无标度网络的防空反导系统有更好鲁棒性和抗毁性,对网络化防空反导系统的构建有一定参考价值。     

基于复杂网络的装备保障力量体系构建研究

论文首先阐述了复杂网络的内涵及其特征参量,以此为基础,对装备保障力量体系进行规范化描述,提出了装备保障力量体系的构建算法,并进行了实例验证及灵敏度分析,对于信息化条件下装备保障力量体系转型建设具有一定的参考价值和指导意义．     

基于神经网络集成方法预测膜蛋白类型

由Chou等人提出的预测膜蛋白分类的机器学习算法在近年来不断改进,使得预测膜蛋白类型的准确率越来越高。但是由于膜蛋白类分布不均衡而导致少数类的预测准确率非常低,使用神经网络集成方法能解决此问题。该方法中Bagging算法通过对多数类欠采样和少数类过采样来解决膜蛋白训练数据集不均衡问题。此外,用神经网络集成方法对已训练数据集和独立数据集进行分类测试,得出神经网络集成方法预测效果优于单个最好神经网络。该方法为解决蛋白质分类预测问题提供了一种新的策略,特别是训练数据集不均衡时,该方法的优势更加明显。     

军事指挥控制中的贝叶斯决策支持

军事指挥控制是一个复杂的决策过程,该过程中信息是结合定性的专家知识和定量的融合数据而得到的.贝叶斯网为指挥控制系统提供了一个框架来处理这种专家知识和具体数据相结合的问题,并且影响图作为贝叶斯网的延伸可被用于分析指挥控制系统中某个决策的可行性.进一步地,为了减少所需指定的条件概率的数量并引入时变的概念,提出动态影响网作为一种新的决策支持方法.     

A robust queueing network analyzer based on indices of dispersion

We develop a robust queueing network analyzer algorithm to approximate the steady-state performance of a single-class open queueing network of single-server queues with Markovian routing. The algorithm allows nonrenewal external arrival processes, general service-time distributions and customer feedback. The algorithm is based on a decomposition approximation, where each flow is partially characterized by its rate and a continuous function that measures the stochastic variability over time. This function is a scaled version of the variance-time curve, called the index of dispersion for counts (IDC). The required IDC functions for the external arrival processes can be calculated from the model primitives or estimated from data. Approximations for the IDC functions of the internal flows are calculated by solving a set of linear equations. The theoretical basis is provided by heavy-traffic limits for the flows established in our previous papers. A robust queueing technique is used to generate approximations of the mean steady-state performance at each queue from the IDC of the total arrival flow and the service specification at that queue. The algorithm's effectiveness is supported by extensive simulation studies.     

3D laser scanning strategy based on cascaded deep neural network

A 3D laser scanning strategy based on cascaded deep neural network is proposed for the scanning system converted from 2D Lidar with a pitching motion device. The strategy is aimed at moving target detection and monitoring. Combining the device characteristics, the strategy first proposes a cascaded deep neural network, which inputs 2D point cloud, color image and pitching angle. The outputs are target distance and speed classification. And the cross-entropy loss function of network is modified by using focal loss and uniform distribution to improve the recognition accuracy. Then a pitching range and speed model are proposed to determine pitching motion parameters. Finally, the adaptive scanning is realized by integral separate speed PID. The experimental results show that the accuracies of the improved network target detection box, distance and speed classification are 90.17%, 96.87% and 96.97%, respectively. The average speed error of the improved PID is 0.4239°/s, and the average strategy execution time is 0.1521 s. The range and speed model can effectively reduce the collection of useless information and the deformation of the target point cloud. Conclusively, the experimental of overall scanning strategy show that it can improve target point cloud integrity and density while ensuring the capture of target.     

二进制无线传感器网络目标定位解析算法初步研究

针对二进制传感器网络目标定位跟踪问题,提出一种利用传感器位置信息和目标穿过传感器探测区域的时间信息进行解算的解析算法,并对该算法进行了仿真验证。仿真结果表明,相对于目前最常用的线性拟和算法,该算法具有对目标经过的传感器数量要求低、解算精度高等优点。     

基于粗糙集-神经网络编队协同空战决策系统

为了提高空战决策的实时性和准确度,将粗糙集理论和神经网络引入到编队协同空战战术决策研究中,提出了应用SOM网络-粗糙集-BP网络集成进行编队协同空战战术决策的方案:应用SOM网络离散化决策系统输入数据的连续属性值;利用粗糙集数据分析方法,从数据中提取出规则将输入映射到输出的子空间上;在这个子空间上用BP网络进行逼近.2:4编队空战实例仿真结果验证该方案的可行性,在数据充分的条件下,该方案可以推广应用于其它空战决策系统.