基于音频特征的工程车辆工况识别研究

高效率地使用工程车辆是工程项目管理中节约成本的有效方法，无人监管环境下工程车辆的工况识别，是实现工程车辆高效率使用的有效手段。目前以GPS等技术为核心的车辆智能管理系统未对工程车辆进行工况识别，提出一种基于GRU循环神经网络的工程车辆工况识别方法，通过对工程车辆在不同工况下产生的音频信号进行分析，从中提取Mel倒谱系数作为主要特征，构建GRU循环神经网络模型进行训练和识别。实验结果表明，该方法可以实现对工程车辆工况的有效识别。     

基于词性特征的明喻识别及要素抽取方法

比喻是一种利用事物之间的相似点建立关系的修辞方式。明喻是比喻中最常见的形式,具有明显的喻词,例如"像",用于关联本体和喻体。近年来高考语文散文类鉴赏题中多有考查明喻句的试题,为了解答此类鉴赏题,需要识别比喻句中的本体和喻体要素。该文提出了基于词性特征的明喻识别及要素抽取方法。首先将句子中词向量化表示与词性特征向量化表示进行融合,将融合后的向量输入到BiLSTM中进行训练,然后利用CRF解码出全局最优标注序列;最后得到明喻识别和要素抽取的结果。公开数据集上的实验结果表明,该方法优于已有的单任务方法;同时也将该文方法应用于北京高考语文鉴赏题中比喻句的识别与要素抽取,验证了方法的可行性。     

直流配网型混合动力系统在车客渡船上的应用

针对车客渡船动力负荷切换频繁,传统柴油机推进油耗高、排放和噪声大的问题,提出一种基于变速发电机组和超级电容储能装置的直流配网型混合动力系统。目前系统已成功应用于“江苏路渡3011”轮,实船运行数据显示:该混合动力系统不仅能达到较好的节油效果、降低排放,更在操控性、舒适性上优于传统的柴油机推进模式。     

基于混合蚁群算法的异质车队低碳VRP研究

针对货运车辆在配送调度过程中产生大量碳排放的问题，建立模型将多种影响碳排放量的因素协同优化。模型中考虑了不同载重量的异质车队，两个节点之间有多条道路的柔性路径，以及车辆重量随卸货而减少的动态负载等因素，以碳排放量、行驶时间和行驶路程为优化目标，并加入了节点需求时间窗、根据速度变化划分路段、交接和卸货时间的约束。提出了一种混合蚁群算法，利用蚁群算法信息素强度更新方式保持群体记忆性，利用粒子群算法的快速收敛特性增加计算效率。通过随机数值算例的仿真优化与对比分析，验证了算法和模型的有效性。     

Delay compensated control of the Stefan problem and robustness to delay mismatch

This paper presents a control design for the one‐phase Stefan problem under actuator delay via a backstepping method. The Stefan problem represents a liquid‐solid phase change phenomenon which describes the time evolution of a material's temperature profile and the interface position. The actuator delay is modeled by a first‐order hyperbolic partial differential equation (PDE), resulting in a cascaded transport‐diffusion PDE system defined on a time‐varying spatial domain described by an ordinary differential equation (ODE). Two nonlinear backstepping transformations are utilized for the control design. The setpoint restriction is given to guarantee a physical constraint on the proposed controller for the melting process. This constraint ensures the exponential convergence of the moving interface to a setpoint and the exponential stability of the temperature equilibrium profile and the delayed controller in the norm. Furthermore, robustness analysis with respect to the delay mismatch between the plant and the controller is studied, which provides analogous results to the exact compensation by restricting the control gain.     

Mathematical formulation and heuristic algorithms for optimisation of auto-part milk-run logistics network considering forward and reverse flow of pallets

The operational planning of distribution network for automotive industry is complex with many conditions to consider, including heterogeneous fleet, enforcing the feasibility of 3D-packing of pallets into vehicles to address the vehicle's capacity in terms of weight and volume, compatibility of orders in a vehicle, returning empty pallets from assembly-plants backwards to suppliers, and delivery time windows. A mathematical model (MILP) is proposed that takes account of these conditions to minimise total transportation costs. The network structure can be a combination of direct shipment and milk-run for both forward and reverse flow of pallets. The model is solved optimally for small-size problems. For solving larger problems, a heuristic algorithm (in two versions) is proposed that uses a similarity measure to generate a reasonable list of orders. Best/first-fit strategies are employed to generate a feasible solution with the aid of a relaxed version of the proposed MILP. Improvement heuristics are also designed. Unlike most of existing constructive heuristics, our aim for developing the heuristic approach is to force routing decision, with all of its considerations, being made optimal. We also use the proposed best-fit strategy in the body of grouping evolution strategy (GES) algorithm to attain an effective meta-heuristic approach. The effectiveness of heuristics is tested on generated instances which demonstrates they are optimal for small-size problems. They are also tested on the data of daily auto-parts shipments gathered from the largest Iranian automobile company. Results demonstrate there exists a significant potential for cost saving through milk-run strategy compared with the direct shipping strategy.     

Airline planning and scheduling: Models and solution methodologies

The airline industry is a representative industry with high cost and low profitability. Therefore, airlines should carefully plan their schedules to ensure that overall profit is maximized. We review the literature on airline planning and scheduling and focus on mathematical formulations and solution methodologies. Our research framework is anchored on three major problems in the airline scheduling, namely, fleet assignment, aircraft routing, and crew scheduling. General formulation, widely used solution approaches, and important extensions are presented for each problem and integrated problems. We conclude the review by identifying promising areas for further research.     

移相全桥变换器在电动汽车充电单元中的应用

分析了峰值电流控制模式下移相全桥变换器的工作原理,设计了电动汽车充电单元的串联双闭环控制器。该控制器外环主回路实时获取负载电压与输入参考电压之间的偏差,通过输入PID电压环对输出电压进行调节,其内环副回路实时计算原边控制电流与PID电压环控制输出的偏差,通过输入PID电流环对控制电流进行调节。针对当控制输入信号占空比大于50%后峰值电流变换器系统出现不稳定的问题,设计了一种斜坡补偿方法,并以PIC16F887单片机为核心,开发了一套电动汽车充电控制单元。实验结果表明,所设计的充电控制单元可以满足电动汽车的充电要求,并具有可靠性高、动态响应快、补偿网络易实现以及带宽增益较高等优点。     

一维—二维耦合的水库下游地区洪水演进数学模型及应用

针对水库下游地区河道洪水与漫堤洪水模拟需求,建立了一维—二维耦合的洪水演进数学模型。一维模型采用Pressimann格式离散求解,二维模型采用能够适应复杂几何形状和多种流态的Osher格式求解,一维—二维连接处采用堰流公式实现水流交互。应用该模型模拟白溪流域2015年"苏迪罗"台风实际洪水,可得到洪水在计算区域的演进过程和淹没情况。对比模拟结果与实际情况可知,该模型计算合理、准确,计算结果可为防汛部门防洪预案制定、防汛调度决策提供技术支撑。     

机动车尾气污染分析与防治策略

针对我国机动车保有量不断增加带来的空气污染严重问题，综合国内外相关文献成果，研究了我国机动车尾气污染特点，分析了机动车尾气的成分及其危害性。机动车尾气成分主要包括一氧化碳（CO），碳氢化合物（HC）、氮氧化物（NO_x）、铅（Pb）等，对生态环境和人体健康具有较大的危害。总结了我国机动车尾气排放特点，主要是局部污染排放量不清、污染移动性强和治理难度大。提出了机动车尾气污染的防治策略:车油路全覆盖整治，提高整合治理成效；政社企全方位监管，促进污染防治升级和推广新能源汽车；改善交通出行结构3个方面。