基于皮尔-遗传神经网络的高路堤沉降预测研究

为确保高速公路的建设质量，许多高速公路进行了路基沉降观测工作，以便对路堤填筑完成以后的沉降发展做出准确的预测，高路堤沉降预测模型较多，但均较难达到理想的精度。文章则依据高路堤填土施工期路基沉降实测资料，考虑到沉降单调增长的特殊性，根据位移分解原理，采用皮尔曲线提取沉降趋势，用基于免疫进化的新型遗传神经网络模型外推偏差，从而提出了一种高路堤沉降预测的新型智能方法。实际工程证明了所提智能预测方法的有效性和可行性。     

遗传算法在有竞争的物流配送中心选址中的应用

在分析有竞争的物流配送中心选址特点的基础上,引入了一种有竞争的物流配送中心选址模型。由于该模型是一个组合优化问题,具有NP难的性质,用常规算法对其进行求解时,经常会陷入局部优化解。针对这一情况,提出一种求解该模型的混合遗传算法,该算法主要利用Drezner算法的局部搜索性能来提高遗传算法的寻优能力。研究结果表明该算法能很好地处理有竞争的物流配送中心选址问题。     

时效物流运输网路规划研究

随着我国物流业的快速发展,能够承担大规模、跨区域运输任务物流公司已经开始出现。但针对于这类物流企业需要的时效物流运输网路规划的研究较少。本文在总结国内外有关运输服务网络规划理论的基础上,从物流运输服务企业(第三方物流企业)的角度,对区域时效性物流运输网路结构的设计规划以及在相应网络下的运输组织形式进行研究,并建立对应于物流运输企业行之有效的数学规划模型,从而为企业的相关决策提供帮助。     

改进的关联规则挖掘算法及其在教育信息挖掘中的应用

利用数据挖掘的关联规则技术，可以从大量数据中发现有价值的规则。文章利用改进的Apriori算法对上海海事大学的教育信息数据库进行了挖掘，从中发现了一些有价值的规则，为学校的教育决策和教学管理提供了有指导意义的信息。文章还实现了大量规则的文本和图形可视化。     

Designing H∞/GH 2 static-output feedback controller for vehicle suspensions using linear matrix inequalities and genetic algorithms

This paper presents an approach to design the H_∞/GH ₂ static-output feedback controller for vehicle suspensions by using linear matrix inequalities (LMIs) and genetic algorithms (GAs). Three main performance requirements for an advanced vehicle suspension are considered in this paper. Among these requirements, the ride-comfort performance is optimized by minimizing the H_∞ norm of the transfer function from the road disturbance to the sprung mass acceleration, while the road-holding performance and the suspension deflection limitation are guaranteed by constraining the generalized H₂ (GH ₂) norms of the transfer functions from the road disturbance to the dynamic tyre load and the suspension deflection to be less than their hard limits, respectively. At the same time, the controller saturation problem is considered by constraining its peak response output to be less than a given limit using the GH ₂ norm as well. A four-degree-of-freedom half-car model with active suspension system is applied in this paper. Several kinds of H_∞/GH ₂ static-output feedback controllers, which use the available sprung mass velocities or the suspension deflections as feedback signals, are obtained by using the GAs to search for the possible control gain matrices and then resolving the LMIs together with the minimization optimization problem. These designed H_∞/GH ₂ static-output feedback controllers are validated by numerical simulations on both the bump and the random road responses which show that the designed H_∞/GH ₂ static-output feedback controllers can achieve similar or even better active suspension performances compared with the state-feedback control case in spite of their simplicities.     

Transport Demand Management in Turkey: A Genetic Algorithm Approach

Abstract

This article proposes new models for estimating transport demand using a genetic algorithm (GA) approach. Based on population, gross national product and number of vehicles, four forms of the genetic algorithm transport planning (GATP) model are developed – one exponential and the others taking quadratic forms – and applied to Turkey. The best fit models in terms of minimum total average relative errors in the test period are selected for future estimation. Demand management strategies are proposed based on three scenarios: restricting private car use, restricting truck use and the simultaneous management of private car use and goods movement. Results show that the GATP model may be used to estimate transport demand in terms of passenger-kilometers traveled (pass-km), vehicle-kilometers traveled (veh-km) and ton-kilometers completed (ton-km). Results also show that the third scenario – simultaneous restrictions on private car use and goods movement – could reduce total veh-km by about 35% by 2025 in this study of Turkish rural roads.     

基于混合遗传算法的船台装配优化研究

为了在船台装配作业中最小化船台周期、降低作业成本、均衡资源负荷,分析了船台装配作业的特点并对其进行了建模,设计了一种适于解决本优化问题的混合遗传算法,开发了对应的软件。将最小化船台周期的优化目标体现在解码的过程中,保证了解码的唯一性;同时将降低成本的优化目标体现在评价和选择的过程中。经本方法得出的船台装配日程计划为实际生产提供了很好的指导。最后,通过一个算例,验证了本方法的可行性和有效性。     

基于候选集的轨道交通网络优化研究

给出基于候选集的轨道交通网络的规划流程和多目标规划的整数模型。模型综合考虑乘客与规划者,以最小化乘客出行时间、最小化轨道网络总长度、最小化轨道总发车次数为优化目标,并选用遗传算法作为模型的求解算法,给出模型解的编码与求解过程。     

A genetic algorithm-based method for improving quality of travel time prediction intervals

The transportation literature is rich in the application of neural networks for travel time prediction. The uncertainty prevailing in operation of transportation systems, however, highly degrades prediction performance of neural networks. Prediction intervals for neural network outcomes can properly represent the uncertainty associated with the predictions. This paper studies an application of the delta technique for the construction of prediction intervals for bus and freeway travel times. The quality of these intervals strongly depends on the neural network structure and a training hyperparameter. A genetic algorithm–based method is developed that automates the neural network model selection and adjustment of the hyperparameter. Model selection and parameter adjustment is carried out through minimization of a prediction interval-based cost function, which depends on the width and coverage probability of constructed prediction intervals. Experiments conducted using the bus and freeway travel time datasets demonstrate the suitability of the proposed method for improving the quality of constructed prediction intervals in terms of their length and coverage probability.     

Comparison of vibration response prediction on the main deck of a catamaran using experimental,numerical and correlated mode shapes

This work analyses the influence of three types of modal matrices on the prediction of vibration response (virtual sensing), at unmeasured degree of freedoms (DOFs), on a catamaran’s main deck: (1) uncorrelated finite element (FE), (2) correlated FE and (3) experimental modal matrices.A multi-objective genetic algorithm (MOGA) framework was developed to handle the optimization and prediction processes. This framework introduces a new metric called Time–Frequency-Error Response Assurance Criteria (TFERAC) to assess the prediction quality. This metric also allows estimating the best set of modal acceleration vectors, which is a critical step in the virtual sensing process.As a case study, only 06 accelerometers and 13 vibration modes (within each modal matrix) were used in the virtual sensing. The MOGA framework’s performance was evaluated using a variance analysis test (ANOVA) between measured and predicted response signals.Results showed that: (1) any one of the modal matrices could be used successfully for virtual sensing on the main deck, that is, there is no need to use correlated FE or experimental modal matrices; (2) the newly proposed metric TFERAC leads to smaller errors in the prediction of both vibration time series and vibration spectra;(3) it is possible to perform a virtual sensing on a ship’s main deck using a limited number of sensors and a numerical modal matrix without being correlated with experimental data.