Rotary unmanned aerial vehicles path planning in rough terrain based on multi-objective particle swarm optimization

This paper presents a path planning approach for rotary unmanned aerial vehicles(R-UAVs)in a known static rough terrain environment.This approach aims to find collision-free and feasible paths with minimum altitude,length and angle variable rate.First,a three-dimensional(3D)modeling method is proposed to reduce the computation burden of the dynamic models of R-UAVs.Considering the length,height and tuning angle of a path,the path planning of R-UAVs is described as a tri-objective optimization problem.Then,an improved multi-objective particle swarm optimization algorithm is developed.To render the algorithm more effective in dealing with this problem,a vibration function is introduced into the collided solutions to improve the algorithm efficiency.Meanwhile,the selection of the global best position is taken into account by the reference point method.Finally,the experimental environment is built with the help of the Google map and the 3D terrain generator World Machine.Experimental results under two different rough terrains from Guilin and Lanzhou of China demonstrate the capabilities of the proposed algorithm in finding Pareto optimal paths.

Multi-objective Transmission Expansion Planning Considering Life Cycle Cost

为克服目前全寿命周期成本（life cycle cost,LCC）技术的应用局限于设备运行或维护阶段的不足,针对输电网整体建立一个3维LCC层级模型,包括时间维度、元件维度和费用维度。费用维度进一步分解为设备级、系统级、外部环境成本。研究了以可靠性为中心的维护手段的应用对维护成本的影响,利用电量不足期望值计算故障成本。在此基础上,对风电等4种不确定因素进行建模,建立以LCC成本最小和切负荷量最小为多目标的输电网机会约束规划模型。采用正态边界交点算法联合改进小生境遗传算法,对模型有效求解。最后,分别对18节点系统和77节点系统进行算例分析。研究结果给出了帕累托解集及推荐的最优规划方案;此外,LCC费用分解图表明了各费用的比重和影响,有利于指导未来资产管理。

Multi-objective evolutionary optimization for geostationary orbit satellite mission planning

In the past few decades, applications of geostationary orbit (GEO) satellites have attracted increasing attention, and with the development of optical technologies, GEO optical satellites have become popular worldwide. This paper proposes a general working pattern for a GEO optical satellite, as well as a target observation mission planning model. After analyzing the requirements of users and satellite control agencies, two objectives are simultaneously considered: maximization of total profit and minimization of satellite attitude maneuver angle. An NSGA-II based multi-objective optimization algorithm is proposed, which contains some heuristic principles in the initialization phase and mutation operator, and is embedded with a traveling salesman problem (TSP) optimization. The validity and performance of the proposed method are verified by extensive numerical simulations that include several types of point target distributions.

Two-Phase Multi Objective Fuzzy Linear Programming Approach for Sustainable Irrigation Planning

The objective of the present study is to develop the irrigation planning model and to apply the same in the form of Two-Phase Multi Objective Fuzzy Linear Programming (TPMOFLP) approach for crop planning in command area of Jayakwadi Project Stage I, Maharashtra State, India. The development of TPMOFLP model is on the basis of various Linear Programming (LP) models and Multi Objective Fuzzy Linear Programming (MOFLP) models, these models have been applied for maximization of the Net Benefits (NB), Crop production (CP), Employment Generation (EG) and Manure Utilization (MU) respectively. The significant increase in the value of level of satisfaction (λ) has been found from 0.58 to 0.65 by using the TPMOFLP approach as compare to that of MOFLP model based on maxmin approach. The two-phase approach solution provides NB = 1503.56 Million Rupees, CP = 335729.30 Tons, EG = 29.74 Million Man days and MU = 160233.70 Tons respectively. The proposed model will be helpful for the Decision Maker (DM) to take a decision under conflicting situation while planning for different conflicting objectives simultaneously and has potential to find out an integrated irrigation planning with prime consideration for economic, social and environmental issue.

Multi-Objective Production Planning Using Lexicographic Procedure

This paper presents a multi-objective production planning model for a factory operating under a multi-product, and multi-period environment using the lexicographic (pre-emptive) procedure. The model objectives are to maximize the profit, minimize the total cost, and maximize the Overall Service Level (OSL) of the customers. The system consists of three potential suppliers that serve the factory to serve three customers/distributors. The performance of the developed model is illustrated using a verification example. Discussion of the results proved the efficacy of the model. Also, the effect of the deviation percentages on the different objectives is discussed.

Optimal Irrigation Planning and Operation of Multi Objective Reservoir Using Fuzzy Logic

In the present study the MOFLP models have been developed for the optimal cropping pattern planning which maximizes the four objectives such as Net Benefits (NB), Crop Production (CP), Employment Generation (EG) and Manure Utilization (MU) under conflicting situation and also, for maximization of Releases for Irrigation (RI) and Releases for Power (RP) simultaneously under uncertainty by considering the fuzziness in the objective functions. The developed models have been applied using the LINGO 13 (Language for Interactive General Optimization) optimization software to the case study of the Jayakwadi Project Stage-II across Sindhphana River, in the State of Maharashtra India. The various constraints have been taken into consideration like sowing area, affinity to crop, labour availability, manure availability, water availability for optimal cropping pattern planning. Similarly constraints to find the optimal reservoir operating policy are releases for power and turbine capacity, irrigation demand, reservoir storage capacity, reservoir storage continuity. The level of satisfaction for a compromised solution of optimal cropping pattern planning for four conflicting objectives under fuzzy environment is worked out to be λ = 0.68. The MOFLP compromised solution provides NB = 1088.46 (Million Rupees), CP = 241003 (Tons), EG = 23.13 (Million Man days) and MU = 111454.70 (Tons) respectively. The compromised solution for optimal operation of multi objective reservoir yields the level of satisfaction (λ) = 0.533 for maximizing the releases for irrigation and power simultaneously by satisfying the constraint of the system under consideration. The compromised solution provides the optimal releases, i.e. RI = 348.670 Mm3 and RP = 234.285 Mm3 respectively.

基于改进NSGA-Ⅱ算法的船舶舾装作业计划优化研究

针对船舶舾装作业计划编制效率低、计划编制结果不符合作业预期要求等问题,建立多执行模式资源限制条件下的工期、成本和资源多目标优化模型.提出改进的非支配排序遗传算法(NSGA-Ⅱ),采用随机交叉算子、贪婪变异算子和自适应进化概率提升种群进化效率,同时融合模拟退火算法,增强算法的局部搜索能力,利用改进算法对实例进行仿真计算.结果表明:该方法可对船舶舾装作业计划进行多目标优化控制,实现舾装作业计划智能优化编制.通过算法对比分析,验证了改进NSGA-Ⅱ算法的可行性和有效性.

基于用户兴趣模型的个性化旅游线路生成建模研究

针对个性化旅游线路生成过程中用户个人喜好分析环节较为薄弱,依照用户兴趣分析结果生成路线景点过于分散,旅游线路景区覆盖率较低的问题,提出一种基于用户兴趣模型的个性化旅游线路生成建模方法。获取用户数据,并按照显性兴趣、隐性兴趣的分类方式设定数据标签,完成数据预处理。根据关联规则结合数据预处理结果,构建用户兴趣模型,分析用户对部分旅游目的地的兴趣值以及用户的旅游行为特征。基于用户兴趣模型的个性化旅游线路生成建模方法设计完成。实验结果证实,所提模型可有效克服用户个人喜好分析问题,提升旅游线路景区覆盖率。

陆地生态系统碳监测卫星自主任务规划研究

低轨遥感卫星往往以全球或全国范围内的特定地物为探测目标。为提高卫星在轨运行的自主性,文章提出了一种面向地物目标属性的遥感卫星自主任务规划方法。首先外推出预报点90 min后的星下点经纬度,并根据星载地图和太阳高度角,得到预报点的阳照/阴影、陆地/海洋、境内/境外属性。对地物目标属性信息进行平滑处理后,根据各载荷的地物目标属性,识别出各载荷的工作任务时间段,可实时实现提前约1个轨道圈的载荷自主任务规划。

基于区间理论的油田综合能源系统优化规划

针对油田的能源结构和用能负荷的特征,构建了油田综合能源系统架构;考虑可再生能源出力的不确定性和油田多元负荷用能的随机性,建立了光伏、光热出力的区间模型,热负荷区间模型和基于价格型响应的电负荷区间模型;通过分析设备投资成本的时间价值和区域碳中和途径,建立一种计及源荷不确定性的综合能源系统规划模型,并结合仿射算法和区间序关系,将不确定性优化问题转化为确定性的多目标优化问题进行求解。算例分析表明,油田综合能源系统架构符合油田能源禀赋和负荷实际耦合情况,设备配置方案投资回收年限短,不确定性权重系数越高,投资越大,年净收益区间越大,结果验证了规划方法的有效性。与传统鲁棒凸规划优化方法相比,所提方法为决策者提供了满足区间约束的解集,避免了规划方案的保守性。

Multi-objective route planning approach for timely searching tasks of a supervised robot

To performance efficient searching for an operator-supervised mobile robot, a multiple objectives route planning approach is proposed considering timeliness and path cost. An improved fitness function for route planning is proposed based on the multi-objective genetic algorithm （MOGA） for multiple objectives traveling salesman problem （MOTSP）. Then, the path between two route nodes is generated based on the heuristic path planning method A ＊. A simplified timeliness function for route nodes is proposed to represent the timeliness of each node. Based on the proposed timeliness function, experiments are conducted using the proposed two-stage planning method. The experimental results show that the proposed MOGA with improved fitness function can perform the searching function well when the timeliness of the searching task needs to be taken into consideration.

基于变时段设计改进多目标差分进化算法的风/光/火/储日前优化调度

在高比例新能源馈入的新型电力系统中,新能源出力的不确定性导致火电难以满足调度计划的精度需求,风/光/火/储系统的经济调度求解算法面临严峻挑战。为此,提出一种基于变时段设计的多目标差分进化算法。首先按各时段负荷特征构建风/光/火/储系统的变时段日前调度规则。进而以系统运行经济成本与污染排放量为目标,基于多目标差分进化算法求解变时段系统日前调度模型的Pareto解集。最后,用IEEE 39节点系统进行测试。结果表明在风、光、储与火电的约束条件均符合校验的情形下,相较于其他算法,该方法使计算结果更加优化,火电机组出力跟踪调度计划效果显著提高,验证了所提方法的有效性。

基于农机智能管理平台的田间燃油配给策略

在农业规模化生产中,为保证作业效率,农机燃油配给往往需要在田间完成。然而,现有的田间燃油配给方式存在不安全、不及时、缺乏科学系统的配给决策,导致燃油配给效率低、配送成本高等问题。针对上述问题,该研究结合农机燃油需求特点,提出基于农机智能管理平台的农机田间燃油配给策略。首先,以农机智能管理平台的实时数据为基础,基于可信性理论建立农机田间燃油配给的两阶段数学模型:第一阶段预优化,根据平台数据建立具有模糊需求和模糊时间窗的多目标车辆路径规划模型,第二阶段根据实际生产中发生的动态事件更新相关信息,重新规划未配送订单的配送路径;其次,以总配送成本最低及总满意度最高为目标,结合改进遗传算法求解农机田间燃油配给模型。最后,应用嫩江农场的数据进行实证分析,并与农场当前的配送成本等指标进行对比,验证可行性及实用性。结果表明:基于农机智能管理平台实时数据构建的农机田间燃油配给策略可以在降低配送成本的同时,保证较高的订单平均满意度,即时效性,与当前生产方案相比,配送路径减少了14条,虽然满意度较实际稍低,为72.85%,但总配送成本较当前方案降低了93.38%。研究结果可为农机田间燃油配给的智能化管理提供科学依据。

基于IMOGWO算法的机械臂多目标轨迹规划

为了在提高串联机械臂工作效率的同时保证运行轨迹良好的节能性、平稳性及灵活性,设计新的多目标轨迹优化方法。采用高次NURBS(non-uniform rational B-Spline,NURBS)曲线插值方法,构造机械臂高阶连续、首尾运动参数均可指定且具有局部修改特性的关节轨迹,保证了机械臂的运动性能。采用改进多目标灰狼算法(improved multi-objective grey wolf optimizer,IMOGWO)对机械臂轨迹进行优化,得到Pareto最优解集,该算法采用SIN混沌初始种群、非线性收敛因子、个体维度位置学习及领导者广义反向学习变异,并通过不可行度来处理多物理约束条件。在六自由度串联机械臂上的仿真实验结果表明,采用高次NURBS曲线规划方法可得到高阶连续的分段可调轨迹,采用IMOGWO算法可对NURBS曲线实现有效的多目标寻优,得到较为理想的Pareto分布,为用户提供多样化选择方案。

考虑节点重要度的城市轨道交通应急救援点选址研究

为实现对城市轨道交通中关键站点的识别和保护,提出1种考虑节点重要度的应急救援点选址方法,基于复杂网络理论构建城市轨道交通网络,从节点拓扑属性、车站属性、网络连通属性3方面出发建立节点重要度评价方法,构建节点重要度加权下的综合覆盖水平最大、最大救援响应时间最短和建设成本最低的多目标应急救援点选址模型,并以武汉地铁网络为例,基于熵权-TOPSIS法确定网络中共262个节点的重要度,设计变邻域遗传算法进行优化求解。研究结果表明:4种赋权方案下发现,相对不考虑节点重要度,本文方法所得目标在综合覆盖水平上分别提高1.44%,1.06%,2.51%和2.90%,同时可有效降低最大救援响应时间及建设成本,识别与保护关键站点。研究结果可为提升线网整体的应急能力提供指导。

基于改进A^(*)算法的西北航道多目标航路规划

全球气候变暖导致北极海冰消融,西北航道进行商业运输活动的船舶数量越来越多。针对北极西北航道复杂冰情下船舶航行安全及经济性的需求,充分考虑了海冰特性、船舶破冰能力以及实际航行风险,以船舶燃油消耗和航时为优化目标,构建了基于动态加权A^(*)算法的多目标冰区航路规划模型。提出了一种考虑安全距离的动态加权A^(*)算法,引入指数衰减因子调整A^(*)算法的搜索策略,减少不必要的搜索空间,并将其应用于冰区航路规划模型,进行西北航道航路规划仿真分析。仿真实验结果表明:该方法能够在确保船舶航行安全的基础上规划出燃油消耗及航时较优的航路,有效解决了船舶与海岸线、恶劣冰区边缘之间的安全距离问题,确保冰区航行的安全性。

基于改进多目标遗传算法的5G基站选址布局研究

5G基站的建设是5G产业链中十分重要的一环。对于运营商而言,基站的选址规划会直接影响5G网的信号质量和使用效率。针对基站选址规划不合理的问题,本文考虑了不同区域基站覆盖范围不同和网络业务量不同的特点,以基站建设成本最小、面积覆盖率和业务覆盖率最大为优化目标,建立了5G基站选址优化模型,使用改进的NSGA-Ⅱ算法对模型进行求解。仿真结果表明,该算法有效解决了基站选址问题,并且具有速度快、效率高、不易陷入局部最优解等优势。

基于MBO的急诊绿色通道策略优化方案在AIS患者抢救中的应用

目的探讨基于目标管理理论(MBO)的急诊绿色通道策略优化方案在脑卒中(AIS)患者抢救中的应用效果。方法选取桂林市某三级甲等医院2022年1月至12月收治的急诊绿色通道入院AIS患者139例为观察组,2021年1月至12月收治的同类患者151例为对照组。观察组采用基于MBO的AIS急诊绿色通道策略优化方案,对照组采用常规急诊绿色通道抢救方案,比较两组的再灌注率、神经功能缺损NIHSS评分、抢救时间、并发症(脑出血、消化道出血)发生率。结果救治后,观察组的血管再灌注率86.33%高于对照组的58.28%,差异有统计学意义(P<0.05);观察组的出院前NIHSS评分低于对照组(P<0.05);观察组自急诊科到CT室平均时间、自CTA+CTP结束到结果报告平均时间均短于对照组(P<0.05);治疗期间,观察组的消化道出血发生率2.16%低于对照组的5.30%(P<0.05);两组脑出血发生率无统计学差异(P>0.05)。结论基于MBO的AIS急诊绿色通道策略优化方案能提高患者再灌注率,缩短术前诊断时间,减少消化道出血并发症,提高治疗效果。

非结构化场景下的无人车轨迹规划研究

针对传统无人车轨迹规划算法在非结构化场景下存在实时性较低和轨迹平滑性较差等问题,提出了一种前后端分离的轨迹规划算法。该算法的前端路径搜索部分对Hybrid A*算法在控制空间进行搜索范围的剪枝且保留了车辆的运动学约束,并通过优化启发函数的计算方式,提高了图搜索的实时性。该算法的后端轨迹优化部分分为两个阶段:第一阶段设计了一个软约束非线性多目标优化器对路径进行局部优化,生成离散的轨迹位姿点和时间分配值;第二阶段基于五次样条曲线利用最小化Jerk的思想对离散位姿点进行平滑连接,提高了轨迹的平滑性。最后在室外停车场环境下对所提算法进行了实车测试,前端路径搜索和后端轨迹优化的实验结果表明该算法具有较高的实时性和轨迹平滑性。