Approximation of multiclass queueing networks with highly variable arrivals under deterministic routing

In this paper, we present the heavy‐traffic bottleneck phenomenon under multiclass deterministic routing and discuss how it can be addressed by decomposition approximation. Examples show that Bitran and Tirupati's method and Whitt's enhancements for deterministic routing may not properly account for this phenomenon. We propose refinements to these methods based on Whitt's variability functions. Results of numerical experiments on simple networks and semiconductor manufacturing process show significant improvement in the approximation of expected waiting time at bottleneck stations. © 2005 Wiley Periodicals, Inc. Naval Research Logistics, 2005.     

A model to predict the residual life of aircraft engines based upon oil analysis data

This paper reports on a study using the available oil monitoring information, such as the data obtained using the Spectrometric Oil Analysis Programme (SOAP), to predict the residual life of a set of aircraft engines. The relationship between oil monitoring information and the residual life is established using the concept of the proportional residual, which states that the predicted residual life may be proportional to the wear increment measured by the oil analysis programmes. Assuming such a relationship between wear and the residual life exists, we formulated a recursive prediction model for the item's residual life given measured oil monitoring information to date. A set of censored life data of 30 aircraft engines (right censored due to preventive overhaul) along with the history of their monitored metal concentration information are available to us. The metal concentration information includes many variables, such as Fe, Cu, Al, etc.; not all of them are useful, and some of them may be correlated. The principal component analysis (PCA) has been adopted to reduce the dimension of the original data set and to produce a new set of uncorrelated variables, which we shall use in the prediction model. The procedure associated with estimating model parameters is discussed. The model is fitted to the actual SOAP data from the aircraft engines, and the goodness‐of‐fit test has been carried out. © 2005 Wiley Periodicals, Inc. Naval Research Logistics, 2005.     

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。     

基于复杂网络理论的指挥信息网络拓扑模型研究

从网络科学的观点出发对作战指挥机构进行研究,建立了指挥关系网络和通信网络,以及在两者基础上的指挥信息网络拓扑模型,分析了指挥信息网络的度分布特性,提出了描述指挥信息网络的特征参量,进行了针对指挥信息网络的体系破击仿真实验,得出了与战争实际相符的结论,为利用复杂网络知识研究信息化条件下的体系对抗进行了积极地尝试和探索。     

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...     

采用弹道修正技术的红外干扰弹性能优化

针对弹道修正弹的高维非线性特性导致的性能优化难题,改变概念设计阶段传统的串行设计方式,提出了一种基于实验设计(Design Of Experiments,DOE)和响应面(Response Surface Methodology,RSM)的智能优化算法,定义基本的弹丸结构模型以及相关的设计参数.在DOE的基础上,将设计...     

多目标环境下基于分布式融合思想的误差估计方法

针对多雷达多目标跟踪过程中分布未知的系统误差估计问题,提出了基于"分布式融合思想"的误差估计方法。给出相应误差估计方法的计算公式,利用改进截断奇异值方法来减轻矩阵病态性的影响,提高误差估计的稳健性。设置了两种不同的系统误差仿真场景,对"分布式"误差估计方法在两种情形下的估计性能进行了仔细对比分析。结合"分布式"误差估计方法与"集中式估计"方法所体现出的优缺点,提出了一种将两种方法结合起来的系统误差估计算法,算法通过合理选择阈值门限η,能够在多雷达多目标且系统误差分布未知的复杂环境下对两种误差估计算法自适应地进行切换,从而充分发挥两种误差估计算法各自的优点,给出更好的误差估计结果。     

Using stochastic programming to solve an outpatient appointment scheduling problem with random service and arrival times

We study a stochastic outpatient appointment scheduling problem (SOASP) in which we need to design a schedule and an adaptive rescheduling (i.e., resequencing or declining) policy for a set of patients. Each patient has a known type and associated probability distributions of random service duration and random arrival time. Finding a provably optimal solution to this problem requires solving a multistage stochastic mixed‐integer program (MSMIP) with a schedule optimization problem solved at each stage, determining the optimal rescheduling policy over the various random service durations and arrival times. In recognition that this MSMIP is intractable, we first consider a two‐stage model (TSM) that relaxes the nonanticipativity constraints of MSMIP and so yields a lower bound. Second, we derive a set of valid inequalities to strengthen and improve the solvability of the TSM formulation. Third, we obtain an upper bound for the MSMIP by solving the TSM under the feasible (and easily implementable) appointment order (AO) policy, which requires that patients are served in the order of their scheduled appointments, independent of their actual arrival times. Fourth, we propose a Monte Carlo approach to evaluate the relative gap between the MSMIP upper and lower bounds. Finally, in a series of numerical experiments, we show that these two bounds are very close in a wide range of SOASP instances, demonstrating the near‐optimality of the AO policy. We also identify parameter settings that result in a large gap in between these two bounds. Accordingly, we propose an alternative policy based on neighbor‐swapping. We demonstrate that this alternative policy leads to a much tighter upper bound and significantly shrinks the gap.     

融合神经网络与超像素的候选区域优化算法

为解决目标检测中候选区域召回率低的问题,提出融合神经网络与超像素的目标候选区域算法。该算法利用神经网络提取更能清楚表达目标边界的特征,并使用聚类、相似性等策略,计算每个滑动窗口所含有的边缘信息量;将待测图像使用简单线性迭代聚类算法分割成若干个超像素,并利用超像素的空间位置、完整性、相邻超像素间的对比度信息,计算各个超像素的显著性得分及每个滑动窗口的显著性得分;根据每个滑动窗口的边缘信息及显著性得分筛选滑动窗口。在PASCAL VOC 2007测试集上进行对比实验,其实验结果表明:所述算法能够快速产生定位质量高的候选区域。     

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.