哈大高铁影响下东北城市群交通网络空间结构特征研究

哈大高铁的运行缩短了东北城市群之间的相对距离,优化了东北城市群城市交通网络空间结构.通过建立向心性分形模型以及相关性分形模型,以交通距离代替空间的实际距离来研究城市群之间分形特征,通过城市间高速铁路时间距离和高速公路时间距离进行对比,计算高铁开通前后东北城市群交通空间聚集维数和空间关联维数,分析东北城市群交通网络空间结...     

ISS-based robust adaptive fuzzy algorithm for maintaining a ship's track

This paper focuses on the problem of linear track keeping for marine surface vessels. The influence exerted by sea currents on the kinematic equation of ships is considered first. The input-to-state stability(ISS) theory used to verify the system is input-to-state stable. Combining the Nussbaum gain with backstepping techniques,a robust adaptive fuzzy algorithm is presented by employing fuzzy systems as an approximator for unknown nonlinearities in the system. It is proved that the proposed algorithm that guarantees all signals in the closed-loop system are ultimately bounded. Consequently,a ship's linear track-keeping control can be implemented. Simulation results using Dalian Maritime University's ocean-going training ship 'YULONG' are presented to validate the effectiveness of the proposed algorithm.     

基于线谱特征提取的被动声纳目标识技术研究

该文针对被动声纳目标识别,着重研究了线谱特征提取方法,提出了一种自适应遗传BP算法,并用该算法训练神经网络目标分类器。经对上海上实录三类目标噪声分类识别实验结果表明,所设计的被动声纳目标识别系统具有很好的分类效果。     

神经网络在船舶主柴油机建模中的应用

该文研究用BP神经网络建立船舶主柴油机模型的方法,并对BP算法进行了改进,提出了一种动态优化学习率的方法,对6L80MC柴油机实际数据用BP网络进行计算的结果表明,该算法能有效地建立船舶主柴油机模型。该模型已成功用于船舶主机遥控仿真系统中。     

对ANN技术表达船体曲线算法的改进

应用人工神经元网络（ANN）技术表达船体曲线。根据问题性质,选用小波基作为前向单层神经网络的神经元激励函数,结合逐层学习（OHLO）算法对一艘3．6万吨散货船的后半体进行了表达。编程运算结果表明,该方法速度较传统的BP算法有较大提高。     

基于神经网络预报的实时专家控制器设计

该文提出一种在保证控制系统稳定的前提下,能实时跟踪船舶航行环境变化和船舶操纵动态特性变化,以逐步提高自动操纵系统控制性能的实时专家控制器。仿真结果表明了此实时专家控制器的有效性,且算法简单,易在线实现。     

带阈值的广义双向细胞联想神经网络GCBAM及其稳定性质研究

在提出双向细胞联想神经网络CBAM的基础上,通过引入阈值概念,进而提出了广义双向细胞 联想神经网络GCBAM,研究了其平衡态,存在性质及其Lyapunov意义下的网络稳定性质。     

A new approach for improving the performance of freight train timetabling of a single-track railway system

A new approach for improving the performance of freight train timetabling for single-track railways is proposed. Using the idea of a fixed-block signaling system, we develop a matrix representation to express the occupation of inter- and intra-station tracks by trains illustrating the train blocking time diagram in its entirety. Train departure times, dwell times, and unnecessary stopping are adjusted to reduce average train travel time and single train travel time. Conflicts between successive stations and within stations are identified and solved. A fuzzy logic system is further used to adjust the range of train departure times and checks are made to determine whether dwell times and time intervals can be adjusted for passenger and freight trains at congested stations to minimize train waiting times. By combining manual scheduling expertise with the fuzzy inference method, timetable efficiency is significantly improved and becomes more flexible.     

Large-scale evacuation network optimization: a bi-level control method with uncertain arterial demand

To improve the efficiency of large-scale evacuations, a network aggregation method and a bi-level optimization control method are proposed in this paper. The network aggregation method indicates the uncertain evacuation demand on the arterial sub-network and balances accuracy and efficiency by refining local road sub-networks. The bi-level optimization control method is developed to reconfigure the aggregated network from both supply and demand sides with contraflow and conflict elimination. The main purpose of this control method is to make the arterial sub-network to be served without congestion and interruption. Then, a corresponding bi-objective network flow model is presented in a static manner for an oversaturated network, and a Genetic Algorithm-based solution method is used to solve the evacuation problem. The numerical results from optimizing a city-scale evacuation network for a super typhoon justify the validity and usefulness of the network aggregation and optimization control methods.     

多传感器融合车载电池舱灭火方法研究

电动汽车属于汽车行业的支柱产业,越来越受到社会的重视,但随之产生的汽车安全问题也逐渐增多。电池舱属于复杂环境,易出现着火事件,本文开展多传感器融合车载电池舱灭火方法研究,运用温度、烟雾浓度传感器实现对火灾的实时监测。设计贝叶斯网络模型,并考虑到了传感器失效及误报,实验结果表明本系统具有良好的响应速度及稳定性,为相关领域研究提供了一种解决方法。