混合动力汽车能量管理控制器参数优化

设计了一种新的基于人工免疫网络优化的模糊神经混合动力汽车能量管理控制器．该控制器结合模糊控制和神经网络的优点,利用神经网络的自学习能力,自动生成模糊规则和隶属函数,并不断优化隶属函数的参数,直到达到设计要求．为了避免神经网络的学习过程陷入局部极值点,采用人工免疫网络优化神经网络的参数．仿真结果显示,经过参数优化的模糊神经能量管理控制器的性能比普通能量管理控制器好,能进一步降低HEV的油耗．     

基于WebGIS 的汉江水环境管理信息系统

依据互联网地理信息系统（WebGIS）的实现技术及特点,分析了ArcIMS的体系结构及其运行机制,通过基于ArcIMS9平台并结合JS,JSP等技术,提出一种新的具有多层结构的WebGIS解决方案,并结合具体实例阐述了其在水环境管理信息系统的实现．结合水环境管理信息系统的需求,给出了基于WebGIS的水环境管理信息系统的功能体系结构．采用Apache＋Tomcat作为网络服务器、ArcIMS作为地图服务器完成了系统功能设计,实现了网上数字地图的处理、传送,以及基于地图的水环境信息查询、评估、统计、分析,和排放污染总量与污染源的控制决策．     

基于WRT方法的港口危化品物流风险评估研究

针对港口危化品物流风险管理中风险因素众多和交互影响的复杂性,构建港口危化品物流的WRT风险评估模型.首先基于物理-事理-人理WSR理论构建港口危化品物流风险评估指标框架,其次通过风险过滤和排序RFRM理论对风险因素进行双重过滤,保留关键风险因素.然后基于TSS情景构建理论从物理、事理和人理三个层面构建港口危化品物流的多维风险情景,通过深入剖析各风险情景下风险因素之间的耦合关系,刻画港口危化品物流中的不同风险状态与风险源最后,基于熵权法和贝叶斯理论对我国7个重要港口进行多维情景风险评估,结果表明天津港和南京港整体风险较大,多数情况下二维情景风险大于三维情景风险,同时从多维风险情景下对物理、事理、人理的耦合风险进行分析,展示了各港口的薄弱环节,最后为港口危化品物流风险管理提出建议.     

基于模型预测控制的轮式移动机器人轨迹规划

针对轮式移动机器人(Wheeled Mobile Robot-WMR)自身欠驱动的特点,并考虑到实际工作时的各种约束和限制,提出了一种基于模型预测控制(Model Predictive Control -MPC)的多约束轨迹规划方法。可以对车体自身的运动学约束、物理约束以及避障等约束进行集中有效的处理,可以生成符合车体自身模型特点并满足各种约束的可行轨迹,充分保证了轮式移动机器人自主行驶的可行性,安全性,高效性。仿真结果充分验证了该方法的有效性。     

基于改进神经网络的多AUV全覆盖路径规划

针对三维环境下的多自主水下机器人(Autonomous Underwater Vehicle,AUV)全覆盖路径规划问题,提出一种基于改进神经网络—Glasius生物启发神经网络（Glasius Bio-inspired Neural Network,GBNN）的全覆盖路径规划算法。对AUV的水下工作环境构建离散的三维栅格地图;根据栅格地图,建立相对应的三维GBNN模型;根据GBNN活性值的动态变化,AUV规划各自的搜索路径,对水下任务区域进行全覆盖搜索。仿真结果表示,多AUV可以协同完成覆盖搜索任务,能够自动避开各类静态和动态的障碍物,自动逃离路径的死锁区。     

Incorporating textual and management factors into financial distress prediction: A comparative study of machine learning methods

Financial distress prediction (FDP) has been widely considered as a promising approach to reducing financial losses. While financial information comprises the traditional factors involved in FDP, nonfinancial factors have also been examined in recent studies. In light of this, the purpose of this study is to explore the integrated factors and multiple models that can improve the predictive performance of FDP models. This study proposes an FDP framework to reveal the financial distress features of listed Chinese companies, incorporating financial, management, and textual factors, and evaluating the prediction performance of multiple models in different time spans. To develop this framework, this study employs the wrapper-based feature selection method to extract valuable features, and then constructs multiple single classifiers, ensemble classifiers, and deep learning models in order to predict financial distress. The experiment results indicate that management and textual factors can supplement traditional financial factors in FDP, especially textual ones. This study also discovers that integrated factors collected 4 years prior to the predicted benchmark year enable a more accurate prediction, and the ensemble classifiers and deep learning models developed can achieve satisfactory FDP performance. This study makes a novel contribution as it expands the predictive factors of financial distress and provides new findings that can have important implications for providing early warning signals of financial risk.     

Fault tolerant motion planning based on joint torque limit for redundant manipulators

0 IntroductionWith the development of science and technology,manipulators have been widely utilized in some specialfields of space , deeper ocean, and nuclear materialcleanup.Becausethese workingenvironments are distant ,harsh and dangerous ,itis difficultfor peopletorepairthefailed manipulators onthe spot .Therefore ,the manipula-tors should operate normally for a long time . To meetthese requirements ,the manipulators must have not onlyhigher reliability but also fault tolerance capabilities…     

The start-up of biohydrogen-producing process by bioaugmentation in the EGSB reactor

Expanded granular sludge bed (EGSB) reactor and bioaugmentation were employed to investigate biohydrogen production with molasses wastewater. The start-up experiments consisted of two stages. In the first stage (0～24d) seeded with activated sludge, the butyric acid type-fermentation formed when the initial expanding rate, organic loading rate (OLR), the initial redox potential (ORP) and hydraulic retention time (HRT) were 10%, 10.0 kg COD/(m3·d), - 215 mV and 6.7 h, respectively. At the beginning of the second stage on day 25, the novel hydrogen-producing fermentative bacterial strain B49 (AF481148 in EMBL) were inoculated into the reactor under the condition of OLR 16. 0 kg COD/(m3·d), ORP and HRT about - 139 mV and 6.7 h, respectively, and then the reaction system transformed to ethanol-type fermentation gradually with the increase in OLR. When OLR, ORP and HRT were about 94.3 kg COD/(m3·d), -250 mV and 1.7 h, respectively, the system achieved the maximum hydrogen-producing rate of 282.6 mL H2/L reactor· h and hydrogen percentage of 51%～53% in the biogas.     

Wheeled foot quadruped robot HITAN-I

0IntroductionInthe past,much work has been done toinvestigatefour-legged walking.Two of the earliest works are the G.E.Quadruped and Phoney[1].With the introduction ofmore powerful computers,more and more bionic robotshave beeninvented in recent years.WARP1[2]in2002,TITAN[3-5]from1989,BISAM[6]in1998and SCOUTII[7]in1999are examples for these developments.Asground vehicle,the advantages of mobile robot have beenrecognized by peopleinengineeringfields.Ground mobilerobots are usually cl…     

The research of controller area network on hybrid electrical vehicle

It is of increasing importance to design and implement vehicle networks for transferring information between electrical control units on Hybrid Electrical Vehicle （HEV）. This paper presents a scheme of using Controller Area Network （CAN） technology to realize communication and datasharing between the electrical units on the HEV. The principle and communication protocol of Electrical Control Units （ECU） CAN node are introduced. By considering different sensitivity of the devices to the latency of data transportation, a new design procedure is proposed for the purpose of simplifying network codes and wiring harness, reducing assembly space and weight, improving assembly efficiency, and enhancing fault-diagnose in auto networks.