An optimization model of UAV route planning for road segment surveillance

Unmanned aerial vehicle （UAV） was introduced to take road segment traffic surveillance. Considering the limited UAV maximum flight distance, UAV route planning problem was studied. First, a multi-objective optimization model of planning UAV route for road segment surveillance was proposed, which aimed to minimize UAV cruise distance and minimize the number of UAVs used. Then, an evolutionary algorithm based on Pareto optimality technique was proposed to solve multi-objective UAV route planning problem. At last, a UAV flight experiment was conducted to test UAV route planning effect, and a case with three scenarios was studied to analyze the impact of different road segment lengths on UAV route planning. The case results show that the optimized cruise distance and the number of UAVs used decrease by an average of 38.43% and 33.33%, respectively. Additionally, shortening or extending the length of road segments has different impacts on UAV route planning.     

基于DNA计算的焊接机器人路径规划算法

为寻求焊接机器人作业过程路径优化问题,运用DNA算法,提出焊接机器人路径规划的有效算法,通过算例证明了方法的有效性。     

预防性维修计划和生产调度的多目标优化

为了降低设备故障对生产成本和生产时间的影响,建立了单台设备预防性维修计划和生产调度的多目标联合优化模型.将维修成本、生产任务的最大完成时间、加权总完工时间及加权总延迟时间作为优化目标.采用了多目标遗传算法,同时对预防性维修计划和生产调度进行优化.通过实例,将预防性维修计划、生产调度的多目标联合优化方法分别与单目标联合优...     

Novel constrained multi-objective biogeography-based optimization algorithm for robot path planning

A constrained multi-objective biogeography-based optimization algorithm （CMBOA） was proposed to solve robot path planning （RPP）. For RPP, the length and smoothness of path were taken as the optimization objectives, and the distance from the obstacles was constraint. In CMBOA, a new migration operator with disturbance factor was designed and applied to the feasible population to generate many more non-dominated feasible individuals; meanwhile, some infeasible individuals nearby feasible region were recombined with the nearest feasible ones to approach the feasibility. Compared with classical multi-objective evolutionary algorithms, the current study indicates that CM- BOA has better performance for RPP.     

Multi-objective optimization design for leg mechanism of hydraulic-actuated quadruped robot

In order to improve the robot’s abilities of bearing heavy burdens and transporting in complex terrains,the multi-objective optimization design for leg mechanism of the quadruped robot with hydraulic actuated is studied in this paper. The kinematics and dynamics of the robot are analyzed and the two-dimensional linear inverted pendulum model is adopted in planning the trajectories of joints. Then the mathematical model of valve-controlled asymmetric cylinder and control model of single leg are proposed respectively. In the end,NSGA-II algorithm is used to achieve the multi-objective optimization design of parameters concerning single leg mechanism and PD torque control. The results prove that the optimized leg mechanism can significantly reduce the required maximum power of hydraulic system,thus decrease its own weight and lead to the obtaining of good dynamic performance.     

基于改进蚁群算法的移动机器人路径规划

针对大多数路径规划方法所忽视的路径尖峰,以及传统蚁群算法(ACA)易出现的早熟、陷入局部最优等问题,提出一种改进ACA以用于路径规划.首先,在ACA中融入遗传算子,利用交叉与变异操作来扩大解的搜索空间,提升解的全局性.然后,引入简化与平滑操作优化算子,对所寻路径做进一步处理,消除路径中不必要的尖峰,提高其平滑性.栅格环境下的机器人路径规划仿真结果表明,与A*以及传统ACA相比,所提算法能够得到更为平滑的最短路径.     

车用空调冷凝器性能多目标优化方法

针对车用空调平行流冷凝器的性能优化问题,将冷凝器划分为3个相区,分别为过热区、两相区和过冷区.通过划分微元并通过比焓或干度逐一判断所属相区并进行计算的方式,基于ε-NTU法建立结构参数与性能参数之间的数学关系,通过运行实验验证了该换热计算模型.利用多目标遗传算法(MOGA)分别获得双目标优化与多目标优化的Pareto最优解集,比较了两者的优劣.结果表明,采用MOGA能够解决车用空调平行流冷凝器性能优化问题,相对双目标优化具有更好的优化效果.通过对优化点进行分析,分别获得最佳综合性能、最佳运行性能、小型轻量化3种优化方案,其中综合性能优化方案提升换热效率4.7%、降低压降4.5%,体积和质量分别减小10.5%和6.4%.     

飞机路线多目标决策研究

针对多目标飞机路线规划难的问题,建立了多目标规划模型,提出了一种基于ELECTRE-IV的遗传算法。先是周期为一日的航班串的编制;而后是周期为三日的航班环的编制;最后是航班环的多目标筛选,将一个航班环作为一个遗传因子,由这些经过筛选的满足条件的遗传因子构成的染色体就是一个飞机路线方案。通过理论分析及实际案例证明了该算法的可行性。     

一种基于APGA的移动机器人路径规划算法

提出了基于自适应并行遗传算法的移动机器人路径规划算法,其基本思想是结合多种群并行进化及自适应调整控制参数,提高了搜索的范围和效率,缓解了传统遗传算法早熟收敛问题,从而克服了使用单种群遗传算法进行路径规划的不足．实验结果表明了该算法在移动机器人路径规划中的可行性和有效性．     

水下机器人运动规划中多目标遗传算法的选择方法

为探讨多目标遗传算法的选择方法对优化结果的影响,本文以水下机器人为对象,对多目标遗传算法的选择方法进行了分析和研究,提出了变权重系数法并对选择公式进行了修正,以水下机器人“Twin-Buger”为对象,进行运动规划的算例验证了本文所提出方法的有效性和可行性。     

基于混沌遗传算法的移动机器人路径规划方法

结合遗传算法优化的反演性和混沌优化方法的遍历性,基于混沌遗传算法的移动机器人路径规划方法能够有效改善遗传算法的局部搜索能力和搜索精度,避免单纯使用遗传算法规划机器人路径时容易出现的早熟收敛现象．仿真试验表明,提出的路径规划方法在稀疏环境和密集环境下均能收敛到全局最优路径,具有更强的鲁棒性．     

Multi-objective optimization of membrane structures based on Pareto Genetic Algorithm

A multi-objective optimization method based on Pareto Genetic Algorithm is presented for shape design of membrane structures from a structural view point.Several non-dimensional variables are defined as optimization variables,which are decision factors of shapes of membrane structures.Three objectives are proposed including maximization of stiffness,maximum uniformity of stress and minimum reaction under external loads.Pareto Multi-objective Genetic Algorithm is introduced to solve the Pareto solutions.Consequently,the dependence of the optimality upon the optimization variables is derived to provide guidelines on how to determine design parameters.Moreover,several examples illustrate the proposed methods and applications.The study shows that the multi-objective optimization method in this paper is feasible and efficient for membrane structures;the research on Pareto solutions can provide explicit and useful guidelines for shape design of membrane structures.     

一种移动机器人的全局动态运动规划方法

将遗传算法用于移动机器人的动态避障运动规划,使机器人在满足速度及加速度约束的前提下,按规划的运动规律运动,在实现动态避障的同时,从起始点到目标点耗时最少．为利用遗传算法实时、稳定地进行动态运动规划,将复杂的二维编码问题简化为一维编码问题,把边界约束、速度和加速度约束、动态避障、耗时最少要求融合为一个简洁的适应度函数．仿真实验表明了该方法的有效性．     

PORP：面向无人驾驶的路径规划并行优化策略

为了实现路径规划并行优化,解决基于位置的服务（LBS）在高峰时段遭遇大量路径规划的并发查询所导致的较高响应时间的问题,提出双层网格（DLG-index）索引,并基于此提出路径规划的并行算法（PORP）. 双层索引的顶层由完整路网的边界节点组成,底层由网格组成,网格由完整路网分割而来. 对于一个给定的查询,基于骨架图计算一条全局路径,然后将规划任务划分成多个局部优化任务. 每个局部优化任务对应此查询的全局路径通过的网格,同时,每个局部优化任务由不同的处理器独立维护. 算法能够基于复杂变化的路况,及时调整导航路线,整个调整过程分段实施,可以由多处理器依次协同完成,实现对海量并发查询做出快速响应. 与CANDS算法相比,PORP的响应时间平均减少了49.6%,处理时间平均减少了28.5%.     

产供销一体化的供应链生产多目标规划模型

从供应链管理的两个基本战略目标出发,以最小化供应链总成本和反应时间为目标函数,将这完整供应链中包含的几个企业类型加以充分考虑,提出符合实际的假设和约束条件,建立了产供销一体化的供应链多期生产多目标规划模型。利用加权和法求解模型得到了其相应的非劣解和生产计划调度方案。实例计算结果表明了模型的有效性和可行性。     

基于粗糙集移动机器人微种群路径规划算法

针对机器人的路径规划,提出了一种将粗糙集和微种群遗传算法相结合的路径规划算法.该算法采用栅格法划分机器人的工作空间,十进制路径编码方式.在粗糙集生成初始路径的基础上,通过运用微种群遗传算法对这些初始路径进行优化后,得到了一条最优或近似最优路径.在Matlab环境进行的机器人路径规划仿真实验中,笔者用到的微种群遗传算法与一般遗传算法相比,具有优化效果明显,环境适应性强等优点,能够有效地提高机器人路径规划速度,结果表明作者提出的方法是正确和有效的.     

求解服务等级感知服务组合问题的多目标遗传算法

针对已有求解多等级服务部署问题的算法存在的不足,提出了一种求解该问题的多目标遗传算法(SMOGA),建立了求解该问题的多目标优化模型。通过将个体的支配强度和被支配强度结合到一起建立对个体的评价策略,并根据评价结果进行环境选择及生成个体的交叉概率。此外还设计了一种局部搜索策略并将其融入到变异策略中,以提高变异操作的有效性。最后对SMOGA算法进行了分析,并将该算法与最近提出的求解该问题的E3-MOGA算法及NSGA-II算法在不同规模的测试用例上进行了实验对比,结果表明算法SMOGA能够更加有效地解决该问题。     

基于遗传算法热电冷联产系统多目标方案优化

根据用户全年冷、热、电负荷设计冷热电三联产系统方案并实现优化运行是决定联产系统经济性的关键．建立了以一次能源节约率、净现值和CO：排放量为优化目标,以冷热电三联产系统中主要设备容量为决策变量的多目标优化模型,同时运用实数编码遗传算法进行优化计算,得到了“以电定热”和“以热定电”2种不同运行模式下的冷热电三联产系统优化设计方案．     

Genetic algorithm-fuzzy based dynamic motion planning approach for a mobile robot

0　ＩＮＴＲＯＤＵＣＴＩＯＮＭｏｔｉｏｎｐｌａｎｎｉｎｇｏｆａｕｔｏｎｏｍｏｕｓｍｏｂｉｌｅｒｏｂｏｔｈａｓｂｅｅｎａｎｅｘｔｅｎｓｉｖｅｌｙｒｅｓｅａｒｃｈｅｄｉｓｓｕｅｉｎｔｈｅｉｎｔｅｌｌｉｇｅｎｔｍｏｂｉｌｅｒｏｂｏｔｆｉｅｌｄ .Ｍｏｓｔｒｅｓｅａｒｃｈｅｓｆｏｃｕｓｏｎａｖｏｉｄｉｎｇｓｔａｔｉｃｏｂｓｔａｃｌｅｓｉｎａｔｗｏ ｄｉｍｅｎｓｉｏｎａｌｅｎｖｉｒｏｎｍｅｎｔ.Ａｔｔｈｅｓａｍｅｔｉｍｅ ,ｍｏｒｅｒｅｓｅａｒｃｈａｂｏｕｔｄｙｎａｍｉｃｍｏｔｉｏｎｐｌａｎｎｉｎｇｉｎｗｈｉｃ…     

Three-dimensional multi-constraint route planning of unmanned aerial vehicle low-altitude penetration based on coevolutionary multi-agent genetic algorithm

To address the issue of premature convergence and slow convergence rate in three-dimensional (3D) route planning of unmanned aerial vehicle (UAV) low-altitude penetration, a novel route planning method was proposed. First and foremost, a coevolutionary multi-agent genetic algorithm (CE-MAGA) was formed by introducing coevolutionary mechanism to multi-agent genetic algorithm (MAGA), an efficient global optimization algorithm. A dynamic route representation form was also adopted to improve the flight route accuracy. Moreover, an efficient constraint handling method was used to simplify the treatment of multi-constraint and reduce the time-cost of planning computation. Simulation and corresponding analysis show that the planning results of CE-MAGA have better performance on terrain following, terrain avoidance, threat avoidance (TF/TA²) and lower route costs than other existing algorithms. In addition, feasible flight routes can be acquired within 2 s, and the convergence rate of the whole evolutionary process is very fast.