Optimum design of tilting bogie frame in consideration of fatigue strength and weight

This paper addresses the use of finite-element (FE) analysis to calculate the fatigue strength of a bogie frame, for the development of tilting trains in Korea. A multi-body dynamic analysis was performed to extract the load condition by tilting on curves. Using the results of the multi-body dynamic analysis and the load scenario setout in the UIC standard, FE analysis was performed to obtain the stress distribution and to calculate the fatigue strength. An attempt was made to minimize the weight of the bogie frame using a back-propagation artificial neural network (ANN). The results of this study reveal that the stresses at some nodes are near the fatigue limit in the Goodman diagram and by using back-propagation ANN, the weight of the bogie frame could be reduced by 4.7%.     

基于神经网络的无人无缆水下机器人运动建模与控制技术研究

对自主型水下机器人（ＡＵＶ）神经网络运动模型的结构进行了理论分析和探讨,提出了非完全回归型神经网络、增加积分层的输出层结构及相应的分步式学习方法。对ＡＵＶ运动过程中目标运动路径和目标运动速度的同时跟踪控制进行了系统研究。提出了由主控网络和伴随网络构成的神经网络控制器结构,给出了通过计算机模拟来生成教师样本的方法,提出了预测控制的思想。计算机仿真及水下机器人“Ｔｗｉｎ－Ｂｕｒｇｅｒ”的水池实验结果验证了本文所提出的建模方法和跟踪控制方法的有效性和可行性。     

变步长BP网络优化导航雷达跟踪滤波系统的研究

本文提出了采用变步长ＢＰ网络实时处理导航雷达目标跟踪滤波数据。其原理是在ＢＰ算法中加入变动量因子,用Ｎ层变步长寻优进行前馈神经网络的学习。该算法能够根据输入时间序列的特点自适应调整网络优化步长,对匀速和变加速运动目标的稳定跟踪精度分别在７．５ ｍ 和１１ ｍ 以内,而对急转弯的目标抖动２～４ 次就能及时跟踪上     

神经网络在船舶操纵中的应用研究

该文对人工神经网络用于船舶操纵动态特性的在线学习进行了研究,并提出了基于神经网络预报的操舵控制算法。仿真试验的结果表明了该控制算法的有效性。     

Optimization models for differentiating quality of service levels in probabilistic network capacity design problems

This paper develops various chance-constrained models for optimizing the probabilistic network design problem (PNDP), where we differentiate the quality of service (QoS) and measure the related network performance under uncertain demand. The upper level problem of PNDP designs continuous/discrete link capacities shared by multi-commodity flows, and the lower level problem differentiates the corresponding QoS for demand satisfaction, to prioritize customers and/or commodities. We consider PNDP variants that have either fixed flows (formulated at the upper level) or recourse flows (at the lower level) according to different applications. We transform each probabilistic model into a mixed-integer program, and derive polynomial-time algorithms for special cases with single-row chance constraints. The paper formulates benchmark stochastic programming models by either enforcing to meet all demand or penalizing unmet demand via a linear penalty function. We compare different models and approaches by testing randomly generated network instances and an instance built on the Sioux–Falls network. Numerical results demonstrate the computational efficacy of the solution approaches and derive managerial insights.     

Airline network competition: Full-service airlines, low-cost airlines and long-haul markets

The paper discusses airline network competition. Low-cost airlines and conventional airlines have distinctly different strategies and network types. This determines their ability to compete with other airlines in specific markets. The paper discusses the lack of competition between conventional airlines in local markets, and sees why low-cost airlines are the primary source of competition in such markets. Conventional airlines are relatively strong on long-haul markets, using their networks to keep costs per seat relatively low. Charter airlines show that a long-haul low-cost strategy is feasible For scheduled low-cost airlines, this may be more difficult, but this does not automatically mean that low-cost airlines cannot enter thick long-haul markets.     

Application of genetic algorithms for joint optimization of signal setting parameters and dynamic traffic assignment for the real network data

This paper presents the joint optimization of signal setting parameters and dynamic user equilibrium (DUE) traffic assignment for the congested urban road network. The simulation-based approach is employed to obtain the DUE condition for the case of multiple-origin multiple-destination traffic flows. The dynamic traffic assignment simulation program (DTASP), developed in C language is used to assign the traffic dynamically on the road network, whereas method of successive averages (MSA) is modified and used to arrive at the DUE condition. The artificial intelligence technique of genetic algorithms (GAs) is applied to obtain the optimal signal setting parameters and path flow distribution factor for DUE condition. The methodology developed in such a way that joint optimization of signal setting parameters with DUE is obtained. The proposed method is applied to the real network data of Fort Area of Mumbai city comprising of 17 nodes and 56 unidirectional links with 72 Origin–Destination pairs, where all the 17 nodes are signalized intersections. The traffic flow condition for the optimized signal setting parameters is considerably improved compared to the existing signal settings. The results prove that the GA is an effective technique to solve the joint optimization problem for the real network data.     

基于BP神经网络的隧道围岩分类

应用BP神经网络建立了隧道围岩分类模型,对其影响因素进行分析,并对模型进行优化,将训练好的分类模型运用到贵安隧道,为隧道围岩分类提供了一种简便可行的方法。     

Full vehicle simulation using thermomechanically coupled hybrid neural network shock absorber model

In the case of full vehicle models, the technique of multi-body simulation (MBS) is frequently used to study their highly non-linear dynamic behaviour. Many non-linearities in vehicle models are induced by force elements like springs, shock absorbers, bushings and tires. Commonly, spline functions are used to represent the force responses of these components. If the non-linear relationships are more complicated, the spline approximations are no more accurate. An alternative approach is based on empirical neural networks which are based on the mathematical approximation of measured data. It is well known that neural networks are able to represent and predict complex component responses accurately. The aim of this paper is to perform a dynamic full vehicle simulation using a thermomechanically coupled hybrid neural network shock absorber model. In this shock absorber model, the spline approach is combined with a temperature-dependent neural network. Based on a displacement-controlled excitation on a four post test rig in the ADAMS/Car MBS software, a rugged test track is simulated. In this way, the front and rear shock absorbers are dynamically loaded with comfort-relevant frequencies in the range of 0.75-30 Hz and velocity amplitudes up to 2 m/s. By the simulation, stability of the hybrid neural network model is demonstrated. Furthermore, the damping force, the vertical acceleration of the chassis and the required simulation times are compared. The standard spline approach is used as a reference.     

铁路通信信号标准及基础资料在线查询系统简介

利用现有成熟的信息技术,实现对标准文件的统一集中、规范化、安全化管理,为所属技术、科研人员提供简便有效的标准、规范的获取途径。