进化规划在电网规划中的应用

本文将进化规划引用到电网规划中来,克服了应用常规数学方法带来的弊端,进化规划跟遗传算法从两个不同的角度去解决同一问题。本文的结果表明应用进化规划来求解电网规划问题为电网规划工辟一条新途径。     

配网规划智能决策支持系统的研究——基于地理信息系统及人工智能方法

配电系统的最优规划（新域区的垦荒计划及旧城区的增容计划）是一个非常复杂的非线性组合优化问题。本文结合地理信息系统（ＧＩＳ）的空间特性与人工智能（ＡＩ）方法的鲁棒性两者的优点,进行配电网络规划设计,较详细地论述了用于配网规划的智能决策支持系统（ＩＤＳＳ）的结构和组合;并以遗传算法在初级布线中的应用为实例来说明ＩＤＳＳ的具体实现。     

基于代数连通度的域内节能路由算法

通过节能路由算法减少网络能耗是网络中需要解决的一个关键性的科学问题。如今已有的节能方案都是在已知流量矩阵的前提下研究网络节能,由于实时流量难以获取,使得这些方案都难以在实际中部署。因此,文中提出一种基于代数连通度的域内节能方案(Intra-domain Energy Efficient Routing Scheme Based on Algebraic Connectivity,EERSBAC)。EERSBAC不需要网络中的实时流量矩阵,仅依靠网络中的拓扑结构就可以实现节能。首先,提出链路关键度模型,利用链路关键度模型计算出网络中所有链路的重要程度;然后,提出代数连通度模型,利用代数连通度模型可以定量的衡量网络的连通性能。实验结果表明,EERSBAC不仅能够降低网络能耗,而且具有较小的路径拉伸度。     

一种移动机器人路径规划新算法

快速搜索随机树（Rapidly-exploring random Tree Star,RRT*）算法在移动机器人实际应用中规划路径在转向部分存在较多的冗余转折点,导致移动机器人在移动转向过程中出现多次停顿与转向,为剔除规划路径中的冗余路径点,提高机器人移动流畅性,提出一种改进的 RRT*算法。算法将局部逆序试连法引入移动机器人路径规划,在确保RRT*算法概率完备性和渐进最优性的前提下,剔除规划路径中的冗余路径节点,使最终路径更加接近最短路径。通过MATLAB仿真实验证明,规划路径平均长度缩短4%,算法耗时缩短35%,改进后的RRT*算法能缩短规划路径且转向部分路径更加平滑。最后,使用改进后的RRT*算法在室内环境下进行移动机器人路径规划实验。实验结果表明：规划路径上无冗余路径点,且移动机器人沿路径移动流畅。     

复杂装配体多层次装配路径规划研究

针对传统装配路径规划方法应用于复杂装配体时出现的组合爆炸问题,提出了一种基于人机交互的改进A-Star(A*)算法多层次装配路径规划方法。算法在传统启发式路径规划算法的基础上引入了干涉威胁概率、平滑度代价、权重系数参数,实现了算法不同侧重方向的最优路径寻找。算法首先根据基于人机交互的路径规划方法结合操作者的装配经验将复杂装配体划分为多个装配层次段,其次对各层次段中的装配零部件运用改进A*算法求解最优拆卸路径,并最终根据路径反演原则生成整个复杂装配体最优装配路径。结合算法仿真对比与KUKA工业机器人路径规划实例验证,得出上述方法较传统启发式路径规划方法提升了路径规划效率,满足了工业生产中复杂装配体自动路径规划需求。     

基于改进A^*算法的机场场面滑行路径优化

为了缓解机场场面交通拥挤状况,提高空侧交通运行效率和安全性,以优化进离场航班的滑行路径为目标,通过分析机场场面滑行路径优化问题,构建了机场场面滑行路径优化模型,并提出基于变步长的滑动时间窗方法和A*算法相结合的模型求解算法。以北京首都国际机场为例进行算例分析,与未考虑冲突的路径优化方案相比较,上述方法得到的总滑行时间节省121秒,通过算法实现对滑行冲突的智能识别与解脱,可为繁忙机场的调度工作提供了决策支持。     

高速高精度运动控制算法的研究与应用

为解决裁床运动控制系统在加工不规则轨迹曲线中存在的插补精度低,效率不高的问题,提出了基于改进BP神经网络B样条曲线插补算法的研究与设计。该算法通过加入动量因子改进BP神经网络离线训练B样条曲线,利用负反馈校正输出预测插补点,避免了BP神经网络插补器自身带来的偏差。同时根据加工曲线曲率半径的变化完成对速度的前瞻规划,实现了加工在拐角处的高速过渡。最后在Matlab上进行了算法仿真并在实验平台上进行了测试,实验结果表明本文提出的裁床运动控制算法能够高效高精度的完成材料切割。     

Decomposition-based bi-objective optimization for sustainable robotic assembly line balancing problems

Due to the increasing greenhouse gas emissions and the energy crisis, the manufacturing industry which is one of the most energy intensive sector is paying close attention to the improvement of environmental performance efficiency. Therefore, in this paper the automated assembly line is balanced in a sustainable way which aims to optimize a green manufacturing objective (the total energy consumption) and a productivity-related objective (similar working load) simultaneously. A comprehensive total energy consumption of each processing stage was analyzed and modeled. To make the model more practical, a sequence-based changeover time and robots with different efficiencies and energy consuming rates are considered and optimized. To properly solve the problem, the proposed novel optimal solution takes the well-known MOEA/D as a base and incorporates a well-designed coding scheme and a problem-specific local search mechanism. Computational experiments are conducted to evaluated each improving strategies of the algorithm and its superiority over two other high-performing multi-objective optimization methods. The model allows decision makers to select more sustainable assembly operations based on their decision impacts in both productivity and energy-saving.     

Using requirement-functional-logical-physical models to support early assembly process planning for complex aircraft systems integration

The assembly line process planning connects product design and manufacturing through translating design information to assembly integration sequence. The assembly integration sequence defines the aircraft system components installation and test precedence of an assembly process. This activity is part of the complex systems integration and verification process from a systems engineering view. In this paper, the complexity of modern aircraft is defined by classifying aircraft system interactions in terms of energy flow, information data, control signals and physical connections. At the early conceptual design phase of assembly line planning, the priority task is to understand these product complexities, and generate the installation and test sequence that satisfies the designed system function and meet design requirements. This research proposes a novel method for initial assembly process planning that accounts for both physical and functional integrations. The method defines aircraft system interactions by using systems engineering concepts based on traceable RFLP (Requirement, Functional, Logical and Physical) models and generate the assembly integration sequence through a structured approach. The proposed method is implemented in an industrial software environment, and tested in a case study. The result shows the feasibility and potential benefits of the proposed method.     

基于视觉分析的智能拾网球机器人研究

针对目前智能拾网球效率低的问题,本文给出一种基于图像处理算法和蚁群算法的智能拾取网球机器人,该机器人结构为笼式结构,系统通过摄像头实时采集图像信息,使用WIFI传送到PC机,PC机利用图像处理算法从场景中提取所有网球及每个网球的坐标点,使用蚁群算法对提取的网球坐标点进行路径规划得到拾球最短路径;通过摄像头实时采集的图片数据提取拾球机器人的实时位置及方位,控制机器人按规划好的路径对网球进行顺序拾取。