Back Analysis of Surrounding Rock Mechanical Parameters of Underground Caverns Based on Genetic Algorithm北大核心CSCD

Surrounding rocks are the main bearing structure of underground caverns, and mechanical parameters used in design and analysis affect the result reliability directly. Based on the monitoring data of surrounding rocks of a water diversion tunnel and genetic algorithm, secondary development of software ABAQUS was conducted, related genetic algorithm was programmed to back analyze the mechanical parameters of surrounding rocks of underground caverns, then a comparison between the calculated parameters and the designed parameters was taken to discuss the rationality of the designed parameters. The results show that the inversion values are larger than the designed ones, and the displacements calculated by the inversion parameters are smaller than that of the original parameter values, showing that the parameters adopted in design are safe. The analysis results prove that the method proposed in this paper is available for parameter analysis in similar projects. © 2018, Editorial Office of "Modern Tunnelling Technology". All right reserved.     

Increasing the accuracy of loop detector counts using adaptive neural fuzzy inference system and genetic programming

Loop detectors are devices that are most commonly used for obtaining data at intersections. Multiple detectors are usually required to monitor a location, and this reduces the accuracy of detectors for collecting traffic volumes. The purpose of this paper is to increase the accuracy of loop detector counts using Adaptive Neural Fuzzy Inference System (ANFIS) and Genetic Programming (GP) based on detector volume and occupancy. These methods do not need microscopic analysis and are easy to employ. Four approaches for one intersection are used in a case study. Results show that the models can improve intersection detector counts significantly. Results also show that ANFIS produces more accurate counts compared to regression and GP.     

Road user charging design: dealing with multi-objectives and constraints

This paper proposes an innovative approach for designing a road user charging scheme to meet multiple policy objectives. Three practical features are integrated into the design methodology including (i) cordon formation, (ii) a set of design constraints, and (iii) multiple objectives of the scheme. The methods also consider possible responses of road travellers to the charging scheme. Two methods based on genetic algorithms (GA) are developed for optimising a charging cordon scheme with constraints and with multiple objectives. The dynamic self-adaptive penalty GA and Non-dominated Sorting GA II (NSGA-II) are applied to the constrained design and multi-objective design respectively. The objective functions or constraints considered include social welfare improvement, revenue generation, and distributional equity impact. A case study of the City of Edinburgh is presented and common characteristics of charging cordon designs which perform well against the three objectives are discussed.

A fuzzy-stochastic optimization model for the intermodal fleet management problem of an international transportation company

ABSTRACT

In this paper, a fuzzy-stochastic optimization model is developed for an intermodal fleet management system of a large international transportation company. The proposed model integrates various strategic, tactical and operational level decisions simultaneously. Since real-life fleet planning problems may involve different types of uncertainty jointly such as randomness and fuzziness, a hybrid chance-constrained programming and fuzzy interactive resolution-based approach is employed. Therefore, stochastic import/export freight demand and fuzzy transit times, truck/trailer availabilities, the transport capacity of Ro-Ro vessels, bounds on block train services, etc. can also be taken into account concurrently. In addition to minimize overall transportation costs, optimization of total transit times and CO₂ emission values are also incorporated in order to provide sustainable fleet plans by maximizing customer satisfaction and environmental considerations. Computational results show that effective and efficient fleet plans can be produced by making use of the proposed optimization model.     

复合功率分流系统发动机起动H∞鲁棒优化控制

为改善复合功率分流混合动力系统纯电动至混合动力模式切换过程的车辆驾驶平顺性,同时确保在模型不确定和外部干扰条件下切换控制的鲁棒性,本文中提出了一种发动机起动H∞鲁棒控制策略。首先,建立复合功率分流混合动力系统动力学模型,并对纯电动至混合动力模式切换过程进行分析。其次,以车辆驾驶平顺性和发动机起动时间为优化指标,通过动态规划求解发动机最优拖转转速曲线。然后,考虑到输入轴阻尼参数摄动、驾驶员输入、道路负载、输出端转速的不确定性变化和发动机转速量测噪声的干扰,设计了发动机起动H∞鲁棒控制器。最后,通过离线仿真和台架试验对所提出的控制策略进行验证。结果表明,该策略能有效将冲击度降低至11.52 m/s^3以内,同时对模型不确定性和外部干扰有较强的抑制能力。     

车用汽油机过渡工况进气流量预测研究

提出了一种基于混合遗传算法的径向基神经网络(HGARBF)的车用汽油机过渡工况进气流量预测模型。首先设计了一种新的混合遗传算法,利用梯度算法每次迭代得到的结果来改进遗传算法的群体,将遗传算法的最优个体与梯度算法的迭代解相比较,选择其中的最优点作为梯度算法下一步迭代的起始点,运用该混合遗传算法进行径向基神经网络参数的优化,改善径向基神经网络不同初始参数对其性能的影响;然后建立了基于HGARBF网络的过渡工况进气流量的预测模型。仿真结果表明,该预测模型优于经典的进气流量平均值模型,为精确及时测试汽油机进气流量提供了新的方法。     

并联混合动力汽车功率分配最优控制及其动态规划性能指标的研究

研究了并联混合动力汽车功率分配的最优控制方法,应用动态规划方法求解功率分配的最优解,并着重分析了其性能指标。该指标融入了电池(电机)功率和整车需求功率,同时建立了燃油消耗和荷电状态变化量之间的物理关系。仿真结果表明,动态规划方法可以大幅度提高混合动力汽车的燃油经济性,并且功率损失型性能指标的效果更加显著。     

基于遗传算法的车辆行驶速度的模糊控制研究

研究并建立车辆行驶速度控制系统的数学模型,对这一复杂的高阶、非线性、时变系统,提出一种基于遗传算法的车辆行驶速度模糊控制新方法,该方法较常规的模糊控制具有更优的控制性能。仿真实验结果表明该车辆行驶速度遗传算法的有效性。     

基于遗传算法的飞行器航迹规划研究

针对飞行器航迹规划问题展开研究,提出了一种基于遗传算法的飞行器航迹规划方法.该算法采用一种变长实值基因编码方式和一组重新设计的与之对应的进化算子.仿真实验结果表明,该算法能够快速有效地完成航迹规划任务,获得较为满意的航迹,同时也能满足在线实时规划的要求.     

Taxis in road pricing zone: should they pay the congestion charge?

This study aims at investigating the impact and feasibility of charging taxis with toll fee in the pricing zone when designing congestion pricing scheme. A bi‐level programming model is developed to compare the maximum social welfares before and after the congestion charge is imposed on taxis. The lower level is a combined network equilibrium model formulated as a variational inequality program, which considers the logit‐based mode split, route choice, elastic demand, and vacant taxi distributions. The upper level is to maximize the social welfare when toll rates vary. The bi‐level problem can be solved by the genetic algorithm, whereas the lower level is solved by the block Gauss–Seidel decomposition approach together with the method of successive averages and diagonalization algorithm. An application with numerical examples is conducted to demonstrate the effectiveness of the proposed model and algorithm and to reveal some interesting findings. Copyright © 2014 John Wiley & Sons, Ltd.