基于人工神经网络的柴油机故障诊断

故障诊断是计算机模式识别领域的一个活跃课题。文中提出了基于人工神经网络的柴油机故障诊断方法，设计了适合该诊断系统的BP网络结构，并给出了一种基于黄金分割法改进的BP算法，用来自适应调整网络学习速率。仿真结果表明：该算法具有很快的学习速度和较高的学习精度，完全适用于柴油机故障诊断系统。     

关于一、三级公路安全性认知因素的试验建模研究

在实测86处一级公路典型路段和188处三级公路典型路段道路结构基础上,确定驾驶员对国道一、三级公路的安全性认知因素集,进而针对一级公路的38处样本路段和三级公路的77处样本路段,组织47名驾驶人员进行现场认知评价试验,并应用模糊集合原理和模糊统计方法对评价试验得到的2829组(一级路673组、三级路2156组)有效认知试验评语数据进行分析处理,得到一、三级公路安全性认知因素的模糊评价隶属函数,从而给出驾驶人员对一、三级公路道路条件和交通环境的安全性模糊评价模型。     

关于集成化汽车故障诊断系统及其支持技术研究

集成化汽车故障诊断系统有两种不同的体系结构,可由状态检测、信息融合、故障诊断、网络信息获取以及网络通讯等模块构成。在系统分析各模块功能得基础上,论述了检测设备仪器通讯的标准化、故障诊断专家系统的通用化、故障诊断推理方法的多元化和故障诊断知识获取的网络化是实现集成化汽车故障诊断系统的关键性支持技术。     

基于FWD检测结果旧路地基脱空状况的模糊评定

总结了利用FWD检测旧路基层脱空的方法,分析其各自的优缺点。在此基础上优化评价方法,引入模糊思想,提出一种新的地基脱空评价方法—模糊评定法,详细介绍模糊评定模型的建立方法和过程,并结合G325国道粤境开平段路面大修改善工程,探讨利用FWD检测结果现场模糊评定旧混凝土路面地基的脱空状态。工程实践表明,该方法取得了很好的实用效果,有效地指导了路面大修施工。     

Fuzzy-logic applied to yaw moment control for vehicle stability

In this paper, we propose a new yaw moment control based on fuzzy logic to improve vehicle handling and stability. The advantages of fuzzy methods are their simplicity and their good performance in controlling non-linear systems. The developed controller generates the suitable yaw moment which is obtained from the difference of the brake forces between the front wheels so that the vehicle follows the target values of the yaw rate and the sideslip angle. The simulation results show the effectiveness of the proposed control method when the vehicle is subjected to different cornering steering manoeuvres such as change line and J-turn under different driving conditions (dry road and snow-covered).     

工程机械管理及维护系统的设计与开发

从预防性维护的角度出发,提出了工程机械管理及维护系统的设计与开发思路.介绍了系统的设计原理,主要功能模块,工作流程和技术特点.系统集机械台帐管理、状态检测、维护保养、故障诊断、维修等模块于一体,适用于多数公路企业的机械管理工作,对提高公路企业的管理水平和工作效率具有重要的意义.     

基于模糊层次的铁路混装货物装运安全评价研究

随着客户运输需求的多样化升级,采用铁路混装货物装运模式在提升铁路运输效率、吸引多样货源等方面相较于单一品名装运显示出一定的优越性,同时混装货物装运面临的安全压力相较于单一品名装运出现骤增。为保障铁路混装货物装运安全,在阐述混装货物装运特点及安全控制要点的基础上,从"人防""物防""技防"3方面构建混装货物装运安全评价指标体系,采用层次分析法确定各指标权重,并利用模糊综合评价法对铁路混装货物装运安全进行评价,通过实例验证该评价方法的实用性及有效性,为铁路混装货物装运安全评价提供依据。     

A carbon footprint-based closed-loop supply chain model under uncertainty with risk analysis: A case study

The management of products’ end-of-life and the recovery of used products has gained significant importance in recent years. In this paper, we address the carbon footprint-based problem that arises in a closed-loop supply chain where returned products are collected from customers. These returned products can either be disposed of or be remanufactured to be resold as new ones. Given this environment, an optimization model for a closed-loop supply chain (CLSC) in which carbon emission is expressed in terms of environmental constraints, i.e., carbon emission constraints, is developed. These constraints aim to limit the carbon emission per unit of product supplied with different transportation modes. Here, we design a closed-loop network where capacity limits, single-item management and uncertainty on product demands and returns are considered. First, fuzzy mathematical programming is introduced for uncertain modeling. Then, the statistical approach to the possibility to synthesize fuzzy information is utilized. Therefore, using a defined possibilistic mean and variance, we transform the proposed fuzzy mathematical model into a crisp form to facilitate efficient computation and analysis. Finally, the risk caused by violating the estimated resource constraints is analyzed so that decision makers (DMs) can trade off between the expected cost savings and the expected risk. We utilize data from a company located in Iran.     

Balancing energy consumption and risk of delay in high speed trains: A three-objective real-time eco-driving algorithm with fuzzy parameters

Eco-driving is an energy efficient traffic operation measure that may lead to important energy savings in high speed railway lines. When a delay arises in real time, it is necessary to recalculate an optimal driving that must be energy efficient and computationally efficient.In addition, it is important that the algorithm includes the existing uncertainty associated with the manual execution of the driving parameters and with the possible future traffic disturbances that could lead to new delays.This paper proposes a new algorithm to be executed in real time, which models the uncertainty in manual driving by means of fuzzy numbers. It is a multi-objective optimization algorithm that includes the classical objectives in literature, running time and energy consumption, and as well a newly defined objective, the risk of delay in arrival. The risk of delay in arrival measure is based on the evolution of the time margin of the train up to destination.The proposed approach is a dynamic algorithm designed to improve the computational time. The optimal Pareto front is continuously tracked during the train travel, and a new set of driving commands is selected and presented to the driver when a delay is detected.The algorithm evaluates the 3 objectives of each solution using a detailed simulator of high speed trains to ensure that solutions are realistic, accurate and applicable by the driver. The use of this algorithm provides energy savings and, in addition, it permits railway operators to balance energy consumption and risk of delays in arrival. This way, the energy performance of the system is improved without degrading the quality of the service.     

大城市中心区实施拥堵收费的影响评价研究

文章在分析大城市中心区拥堵收费实施条件与方式的基础上,定性分析实施拥堵收费对居民出行行为以及中心区动静态交通的影响,最后提出基于模糊评价理论的中心区拥堵收费影响评价模型.