期刊文献+
共找到1,161篇文章
< 1 2 59 >
每页显示 20 50 100
Variations of δ^(18)O in Precipitation along Vapor Transport Paths 被引量:10
1
作者 章新平 刘晶淼 +2 位作者 田立德 何元庆 姚檀栋 《Advances in Atmospheric Sciences》 SCIE CAS CSCD 2004年第4期562-572,共11页
Three sampling cross sections along the south path starting from the Tropics through the vapor passage in the Yunnan-Guizhou Plateau to the middle-low reaches of the Yangtze River, the north path from West China, via ... Three sampling cross sections along the south path starting from the Tropics through the vapor passage in the Yunnan-Guizhou Plateau to the middle-low reaches of the Yangtze River, the north path from West China, via North China, to Japan under the westerlies, and the plateau path from South Asia over the Himalayas to the northern Tibetan Plateau, are set up, based on the IAEA (International Atomic Energy Agency)/WMO global survey network and sampling sites on the Tibetan Plateau. The variations, and the relationship with precipitation and temperature, of the δ18 O in precipitation along the three cross sections are analyzed and compared. Along the south path, the seasonal differences of mean δ18O in precipitation are small at the stations located in the Tropics, but increase markedly from Bangkok towards the north, with the δ18O in the rainy season smaller than in,the dry season. The δ18O values in precipitation fluctuate on the whole, which shows that there are different vapor sources. Along the north path, the seasonal differences of the mean δ18O in precipitation for the stations in the west of Zhengzhou are all greater than in the east of Zhengzhou. During the cold half of the year, the mean δ18O in precipitation reaches its minimum at Urumqi with the lowest temperature due to the wide, cold high pressure over Mongolia, then increases gradually with longitude, and remains at roughly the same level at the stations eastward from Zhengzhou. During the warm half of the year, the δ18O values in precipitation are lower in the east than in the west, markedly influenced by the summer monsoon over East Asia. Along the plateau path, the mean δ18O values in precipitation in the rainy season are correspondingly high in the southern parts of the Indian subcontinent, and then decrease gradually with latitude. A sharp depletion of the stable isotopic compositions in precipitation takes place due to the very strong rainout of the stable isotopic compositions in vapor in the process of lifting over the southern slope of the Himalayas. The low level of the δ18O in precipitation is from Nyalam to the Tanggula Mountains during the rainy season, but δ18O increases persistently with increasing latitude from the Tanggula Mountains to the northern Tibetan Plateau because of the replenishment of vapor with relatively heavy stable isotopic compositions originating from the inner plateau. During the dry season, the mean δ18O values in precipitation basically decrease along the path from the south to the north. Generally, the mean δ18O in precipitation during the rainy season is lower than in the dry season for the regions controlled by the monsoons over South Asia or the plateau, and opposite for the regions without a monsoon or with a weak monsoon. 展开更多
关键词 stable isotope vapor transport path TEMPERATURE PRECIPITATION
在线阅读 下载PDF
Optimal paths planning in dynamic transportation networks with random link travel times 被引量:3
2
作者 孙世超 段征宇 杨东援 《Journal of Central South University》 SCIE EI CAS 2014年第4期1616-1623,共8页
A theoretical study was conducted on finding optimal paths in transportation networks where link travel times were stochastic and time-dependent(STD). The methodology of relative robust optimization was applied as mea... A theoretical study was conducted on finding optimal paths in transportation networks where link travel times were stochastic and time-dependent(STD). The methodology of relative robust optimization was applied as measures for comparing time-varying, random path travel times for a priori optimization. In accordance with the situation in real world, a stochastic consistent condition was provided for the STD networks and under this condition, a mathematical proof was given that the STD robust optimal path problem can be simplified into a minimum problem in specific time-dependent networks. A label setting algorithm was designed and tested to find travelers' robust optimal path in a sampled STD network with computation complexity of O(n2+n·m). The validity of the robust approach and the designed algorithm were confirmed in the computational tests. Compared with conventional probability approach, the proposed approach is simple and efficient, and also has a good application prospect in navigation system. 展开更多
关键词 min-max relative regret approach robust optimal path problem stochastic time-dependent transportation networks stochastic consistent condition
在线阅读 下载PDF
Risk-taking path choice behaviors under ATIS in transportation networks with demand uncertainty 被引量:2
3
作者 Shao, Hu Tian, Qiong +1 位作者 Yuan, Xiaoming Wang, Guodong 《Journal of Southeast University(English Edition)》 EI CAS 2008年第S1期43-48,共6页
A new travel time reliability-based traffic assignment model is proposed to investigate the effects of an advanced transportation information system (ATIS) on drivers' risk-taking path choice behaviours in transpo... A new travel time reliability-based traffic assignment model is proposed to investigate the effects of an advanced transportation information system (ATIS) on drivers' risk-taking path choice behaviours in transportation networks with demand uncertainty. In the model, drivers are divided into two classes. The first class is not equipped with ATIS, while the second class is equipped with ATIS. Different risk-taking path choice behaviours of the two classes are studied, respectively. A corresponding mixed equilibrium traffic assignment model is formulated as a variational inequality problem in terms of path flows, which is solved by a heuristic solution algorithm. Numerical results indicate that the ATIS can influence the drivers' risk-taking path choice behaviours and the total system travel time in transportation networks with demand uncertainty. It is also found that under higher demand levels, the benefits of ATIS for network performance enhancement may be more obvious. 展开更多
关键词 risk-taking path choice behaviours advanced transportation information system (ATIS) demand uncertainty traffic assignment problem variational inequality
在线阅读 下载PDF
Path Selection of Multimodal Transport Based on Multi-Objective Mixed Integer Programming
4
作者 Zhongxin Luo 《Journal of Transportation Technologies》 2019年第4期462-473,共12页
Based on “One Belt and One Road”, this paper studies the path selection of multimodal transport by using the method of multi-objective mixed integer programming. Therefore, this paper studies the factors of transpor... Based on “One Belt and One Road”, this paper studies the path selection of multimodal transport by using the method of multi-objective mixed integer programming. Therefore, this paper studies the factors of transportation time, transportation cost and transportation safety performance, and establishes a mathematical model. In addition, the method of multi-objective mixed integer programming is used to comprehensively consider the different emphasis and differences of customers on cargo transportation. Then we use planning tools of Microsoft Excel to solve path selection and to determine whether the chosen path is economical and reliable. Finally, a relatively complex road network is built as an example to verify the accuracy of this planning method. 展开更多
关键词 ONE BELT and ONE Road MULTI-OBJECTIVE MULTIMODAL transport Mixed INTEGER PROGRAMMING path Selection
在线阅读 下载PDF
Mass and Energy Transportation in Ore-Forming Processes of Sulfide Deposits in Tongling District 被引量:2
5
作者 Cen Kuang Yu Chongwen(Faculty of Earth Sciences, China University of Geosciences, Wuhan 430074) 《Journal of Earth Science》 SCIE CAS CSCD 1999年第4期299-304,共6页
Based on dynamics of heat conduction, fluid flow caused by heating and chemical material transport induced by fluid flow, temperature and stream fields of fluid flow in ore-forming processes of Cu-Au sulfide in the To... Based on dynamics of heat conduction, fluid flow caused by heating and chemical material transport induced by fluid flow, temperature and stream fields of fluid flow in ore-forming processes of Cu-Au sulfide in the Tongling district deposits was modeled and analyzed. It is shown that: (1) Mass and energy flow caused by fluid flow is key problem of kythrothermal ore-forming processes; the heating from magma intruded is basic power for driving fluid flow. (2) occurrence of pluton, different chemical property and porosity of wall rocks and infiltration restrict the specifically field of precipitation for ore-forming material.Therefore, the dissolution and precipitation field for ore-forming material in deposit can be forecasted. (3) Iron and sulfur material comes mostly from sandstone formation of Wutong Group, which contains pyrite and high porosity. The cataclastic dolomite interlayered in sandstone and limestone is a favorable place for ore accumulating. The difference of chemical property between sandstone and dolomite forms a favorable interface for ore-forming processes. 展开更多
关键词 heat conduction mass transportation fluid path-line STREAMLINE
在线阅读 下载PDF
A modification of local path marginal cost on the dynamic traffic network 被引量:1
6
作者 Zhengfeng Huang Gang Ren +1 位作者 Lili Lu Yang Cheng 《Journal of Modern Transportation》 2014年第1期12-19,共8页
Path marginal cost (PMC) is the change in totaltravel cost for flow on the network that arises when timedependentpath flow changes by 1 unit. Because it is hardto obtain the marginal cost on all the links, the local... Path marginal cost (PMC) is the change in totaltravel cost for flow on the network that arises when timedependentpath flow changes by 1 unit. Because it is hardto obtain the marginal cost on all the links, the local PMC,considering marginal cost of partial links, is normallycalculated to approximate the global PMC. When analyzingthe marginal cost at a congested diverge intersection, ajump-point phenomenon may occur. It manifests as alikelihood that a vehicle may unsteadily lift up (down) inthe cumulative flow curve of the downstream links. Previously,the jump-point caused delay was ignored whencalculating the local PMC. This article proposes an analyticalmethod to solve this delay which can contribute toobtaining a more accurate local PMC. Next to that, we usea simple case to calculate the previously local PMC and themodified one. The test shows a large gap between them,which means that this delay should not be omitted in thelocal PMC calculation. 展开更多
关键词 transportation network path marginal cost Cumulative flow curve Dynamic traffic Systemoptimization
在线阅读 下载PDF
基于仿生算法的多式联运路径规划方法综述 被引量:5
7
作者 孙哲 马胜男 +1 位作者 解相朋 孙知信 《控制与决策》 北大核心 2025年第2期375-386,共12页
多式联运可有效提高物流企业的运作效率并降低经营成本,是现代物流的未来发展趋势之一.然而,其路径规划问题常常存在许多非线性约束,传统的精确算法在求解时也面临着模糊性、特殊性、动态性、高维性等挑战.鉴于仿生算法模拟生物系统时... 多式联运可有效提高物流企业的运作效率并降低经营成本,是现代物流的未来发展趋势之一.然而,其路径规划问题常常存在许多非线性约束,传统的精确算法在求解时也面临着模糊性、特殊性、动态性、高维性等挑战.鉴于仿生算法模拟生物系统时的智能优势在解决这一类复杂组合优化问题时具备广泛性和高效性,研究近年来基于多式联运路径规划的仿生算法,并将其分为3类:群智能算法、进化算法和基于物理的仿生算法,分别罗列了多式联运路径规划问题涉及到的特殊背景、关键特征和未来研究方向,广泛对比、分析了该问题下各仿生算法的原理、改进、优点和局限性,并为不同问题下的特殊场景提供了合适的仿生算法.最后,讨论了多式联运路径规划问题目前面临的挑战和未来的研究方向. 展开更多
关键词 多式联运 路径规划 仿生算法 不确定性 绿色运输 可持续性
原文传递
Case study scenarios in site selection of hazardous material facilities based on transportation preferences 被引量:1
8
作者 Babak Mehran Musharraf Ahmad Khan +2 位作者 Mina Mehran Hyukjae Roh Satish Sharma 《Journal of Modern Transportation》 2019年第4期317-333,共17页
A methodology is proposed to evaluate and rank potential sites for facilities dealing with hazardous materials(HAZMAT).The proposed methodology incorporates HAZMAT route planning into facility siting while considering... A methodology is proposed to evaluate and rank potential sites for facilities dealing with hazardous materials(HAZMAT).The proposed methodology incorporates HAZMAT route planning into facility siting while considering transportation preferences and challenges.The area of interest is divided into smaller zones representing potential sites for a HAZMAT facility.A multimodal transportation network including railways and roads is considered for transportation of HAZMAT.Each zone is evaluated based on its accessibility from a set of selected points of interests(POIs),which are defined as potential origin/destination points for transportation of HAZMAT.The shortest routes between each POI and potential zones are evaluated based on a cost function which can accommodate multiple criteria to determine the associated disutility for each potential zone.Finally,zones are ranked based on their cumulative disutility scores.The proposed analysis method is quantitative,and at the same time it is adequately flexible to allow inclusion of subjective criteria.Application of the proposed methodology is demonstrated for identifying optimal locations for a HAZMAT facility(e.g.,a nuclear facility)using the Canadian province of Saskatchewan as an example.Three scenarios were evaluated including(1)all network segments and POIs were treated equally,(2)network segments were rank ordered based on their functional classification while POIs were treated equally and(3)network segments were rank ordered based on their functional classification with preferences given to specific POI(s). 展开更多
关键词 HAZMAT transportATION SITE selection ROUTE PLANNING Shortest path analysis
在线阅读 下载PDF
基于AFD融合算法的运输机器人路径规划方法 被引量:1
9
作者 袁杰 张迎港 +3 位作者 加尔肯别克 张宁宁 刘超 谢霖伟 《农业机械学报》 北大核心 2025年第6期594-607,共14页
为提高运输机器人在导航中的自主性和安全性,需要进行有效合理的路径规划。本研究提出了一种改进型AFD(A*Fuzzy-DWA)融合算法,以解决经典A*算法在运输机器人路径规划中存在的问题,如搜索时间长、路径冗余、拐点多且不平滑、动态避障能... 为提高运输机器人在导航中的自主性和安全性,需要进行有效合理的路径规划。本研究提出了一种改进型AFD(A*Fuzzy-DWA)融合算法,以解决经典A*算法在运输机器人路径规划中存在的问题,如搜索时间长、路径冗余、拐点多且不平滑、动态避障能力不足等。该算法通过设计障碍率评价指标优化评价函数以减少搜索时间和遍历节点,进而设计Smooth Floyd方法简化全局路径,并采用圆内切平滑策略进一步优化路径,最后设计评价函数权重模糊推理方法提高局部路径规划效率,从而实现全面的路径优化。仿真实验结果表明,与对比算法相比,AFD算法在静态和动态环境下的全局及局部路径长度和运行时间均显著减小。实际场景验证进一步证实了该算法在提升运输机器人自主导航能力和安全性方面的有效性。 展开更多
关键词 运输机器人 路径规划 Smooth Floyd方法 圆内切策略 模糊推理 融合算法
在线阅读 下载PDF
数字经济赋能智慧交通运输构建的路径探讨 被引量:3
10
作者 方照琪 《物流科技》 2025年第1期115-116,共2页
近些年来,随着我国整体科学技术水平的不断提升,数字经济已经成为当前社会的主流发展趋势。在这样的背景下,交通运输行业作为人民日常生活中必不可少的一部分内容,其与数字技术整合的产物——智慧交通运输也为当前社会的不断发展注入了... 近些年来,随着我国整体科学技术水平的不断提升,数字经济已经成为当前社会的主流发展趋势。在这样的背景下,交通运输行业作为人民日常生活中必不可少的一部分内容,其与数字技术整合的产物——智慧交通运输也为当前社会的不断发展注入了更强的动力。但在实际的智慧交通运输构建过程中,受到一些因素影响仍然存在部分不足未被解决,因此,对这些不足进行科学处理并加强数字经济赋能下的智慧交通运输构建,已经成为当前社会不断发展的重要基础。 展开更多
关键词 数字经济 智慧交通运输 构建路径
在线阅读 下载PDF
Radiation mean free path for non-LTE fully ionized medium
11
作者 Zhang Jun ( Institute of Applied Physics and Computational Mathematics, Beijing100088) 《Nuclear Science and Techniques》 SCIE CAS CSCD 1998年第3期129-133,共5页
1IntroductionTheradiationmeanfrepath(RMFP)[1,2]isaveryimportantphysicalparameterincalculationsofradiationhyd... 1IntroductionTheradiationmeanfrepath(RMFP)[1,2]isaveryimportantphysicalparameterincalculationsofradiationhydrodynamicsandtran... 展开更多
关键词 等离子体 流体力学 辐照平均自由路径 非定域热平衡
在线阅读 下载PDF
小麦高效吸收利用磷素机制研究进展
12
作者 康国章 王鹏飞 +2 位作者 李艳 王金凤 韩巧霞 《植物营养与肥料学报》 北大核心 2025年第4期800-809,共10页
小麦作为高需磷量的主要粮食作物,实现稳产高产高度依赖磷肥施用。然而,我国小麦当季磷肥利用率仅19%,提升磷素吸收利用效率已成为小麦养分研究领域的核心科学问题。本文基于作者团队前期关于小麦磷高效利用的研究基础,首先剖析了土壤... 小麦作为高需磷量的主要粮食作物,实现稳产高产高度依赖磷肥施用。然而,我国小麦当季磷肥利用率仅19%,提升磷素吸收利用效率已成为小麦养分研究领域的核心科学问题。本文基于作者团队前期关于小麦磷高效利用的研究基础,首先剖析了土壤磷素利用效率低下的原因,梳理了小麦及其他作物实现磷素高效吸收利用的5条关键途径:根系形态重塑、根际微生物互作、有机酸分泌、体内磷再分配以及基因表达调控,并深入阐述了小麦高亲和磷转运蛋白基因(TaPHT1s)的分类与功能特性。其次,详细介绍了磷素吸收效率与利用效率的计算方法,剖析了正向遗传学在定位与克隆小麦磷高效基因时进展缓慢的制约因素,同时阐述了利用反向遗传学手段挖掘出的磷高效候选基因。在分子调控机制层面,着重探讨了小麦磷信号转导通路中转录因子TaPHR1、TaMYB4等的功能。最后,从小麦磷高效精准表型组高通量的研发、花后体内磷再分配关键PHTs基因的精准鉴定,以及全基因组测序与高通量芯片技术的综合应用等方面,对小麦磷高效利用研究的未来发展方向进行展望。 展开更多
关键词 小麦 磷高效 高亲和磷转运蛋白 信号通路
在线阅读 下载PDF
A Transportation Network Equilibrium Reformulation of Eco-Industry Chain Network
13
作者 Yi-Wen Sun Guo-Shan Liu Shi-Qin Xu 《Journal of Harbin Institute of Technology(New Series)》 EI CAS 2013年第1期107-112,共6页
In this paper, we demonstrate that the eco-industrial network equilibrium model of link flow version previously introduced can be reformulated as a transportation network equilibrium problem of path flow version. Then... In this paper, we demonstrate that the eco-industrial network equilibrium model of link flow version previously introduced can be reformulated as a transportation network equilibrium problem of path flow version. Then, some methodological tools mainly applied in the field of transportation science can be used to discuss the eco-industrial chain network problem. What the highlighted contribution lies in is that the paper not only expands theory of supply chain model with reducing path flow but also generalizes the traditional transportation network equilibrium problem by new applications. 展开更多
关键词 eco-industry chain network transportation network system optimization network equilibrium path flow
在线阅读 下载PDF
大模型在交通运输行业的应用路径
14
作者 张丽 郑晓峰 +2 位作者 刘礼勇 孙逸帆 林垚 《交通运输研究》 2025年第4期67-78,共12页
为加快推动人工智能与交通运输的深度融合,通过人工智能技术赋能交通运输高质量发展,以交通运输典型场景带动人工智能技术迭代升级,研究提出大模型在交通运输行业的应用路径。首先,梳理大模型在交通运输行业应用研究进展,总结典型应用场... 为加快推动人工智能与交通运输的深度融合,通过人工智能技术赋能交通运输高质量发展,以交通运输典型场景带动人工智能技术迭代升级,研究提出大模型在交通运输行业的应用路径。首先,梳理大模型在交通运输行业应用研究进展,总结典型应用场景,分析应用研究特征和存在的主要问题。其次,开展大模型在交通运输行业的技术适配性研究,解构大模型的核心技术能力,分析交通建设、管理、养护、运营和服务五大领域的痛点和大模型支撑解决行业痛点问题的能力,对大模型在交通运输行业的应用进行SWOT分析。最后,研究提出包括总体架构、三类重点应用场景、三种技术路径和实施策略的大模型应用路径。研究结果可为大模型在交通运输行业的应用落地提供理论和方法参考。 展开更多
关键词 大模型 交通运输 人工智能 智慧交通 技术路径
在线阅读 下载PDF
城市街道空间对儿童活力通学的影响研究
15
作者 郭嵘 王珂馨 《规划师》 北大核心 2025年第7期54-61,共8页
随着儿童友好城市建设的不断深化、拓展,儿童通学逐渐成为社会多方关注的焦点。以哈尔滨松北区、道外区的6所小学为研究对象,通过问卷访谈、实地调研及采用大数据工具等方式,获取哈尔滨街道空间现状特征、儿童活力通学行为特征及通学感... 随着儿童友好城市建设的不断深化、拓展,儿童通学逐渐成为社会多方关注的焦点。以哈尔滨松北区、道外区的6所小学为研究对象,通过问卷访谈、实地调研及采用大数据工具等方式,获取哈尔滨街道空间现状特征、儿童活力通学行为特征及通学感知特征,并对其影响作用展开分析。结果表明:街道空间在交通结构维度对儿童活力通学的直接影响路径效应占比相对最高,通过影响便捷可达性和安全防护性而产生的间接影响路径效应占比次之,通过影响舒适愉悦性而产生的影响路径效应占比相对最低;在功能设施维度对儿童活力通学的直接影响路径效应占比相对最高,通过影响安全防护性而产生的间接影响路径效应占比次之,通过影响便捷可达性而产生的影响路径效应占比相对最低;在景观环境维度仅通过儿童通学感知中的舒适愉悦性对儿童活力通学产生间接影响。据此,提出儿童通学街道空间优化策略,以期为今后哈尔滨儿童活力通学街道空间的优化提升提供借鉴。 展开更多
关键词 街道空间 儿童 活力通学 影响路径效应 哈尔滨
在线阅读 下载PDF
A DYNAMIC MODEL OF MULTIPLE PATH TRAFFIC ASSIGNMENT
16
作者 王炜 《Journal of Southeast University(English Edition)》 EI CAS 1991年第1期64-69,共6页
A “Random Shortest Path”traffic assignment model and its algorithm arepresented by simulating the trip-makers’route-choice characters,and the dynamic meth-od is introduced in the assignment model.It is a ideal mult... A “Random Shortest Path”traffic assignment model and its algorithm arepresented by simulating the trip-makers’route-choice characters,and the dynamic meth-od is introduced in the assignment model.It is a ideal multiple path assignment modelwhich can be carried out by the dynamic method and static method,can better reflect boththe shortest path factor and the random factor in the route-choice,and is of reasonableassignment volumes.Besides,both dynamic and static softwares particularly suited to thetraffic assignment of large and medium-sized transportation networks arc developed. 展开更多
关键词 shortest path TRAFFIC DISTRIBUTION TRAFFIC and transport networks/dynamic route-choice TRAFFIC ASSIGNMENT
在线阅读 下载PDF
基于WPA的农业运输车辆路径优化模型研究
17
作者 李慧 《农机化研究》 北大核心 2025年第6期252-257,共6页
农业运输车辆路径优化是农业物流领域的关键问题之一。为了实现农产品运输配送成本和碳排放量低等问题,提出了一种基于狼群算法(Wolf Pack Algorithm,WPA)的农业运输车辆路径优化模型,将农业运输车辆路径优化问题建模为一种多目标优化... 农业运输车辆路径优化是农业物流领域的关键问题之一。为了实现农产品运输配送成本和碳排放量低等问题,提出了一种基于狼群算法(Wolf Pack Algorithm,WPA)的农业运输车辆路径优化模型,将农业运输车辆路径优化问题建模为一种多目标优化问题。以最小化总行驶距离和最小化运输时间为研究目标,通过定义适应度函数,并结合狼群算法的搜索策略,实现了农业运输车辆路径的优化。针对黑龙江某农场水稻收获运输配送问题的实际需要,采用所提出的WPA优化模型完成了水稻运输车辆路径方案的优化,并与传统优化方法进行对比,结果表明:基于狼群算法的路径优化模型在农业配送总成本上平均节省了7.97%,碳排放量上平均降低了6.88%。优化后的路径方案可以显著缩短运输距离和时间,提高了农业物流的效率,并最大限度地利用运输资源。 展开更多
关键词 农业运输车 路径规划 狼群算法 多目标优化 适应度函数
在线阅读 下载PDF
融合图神经网络和注意力机制的矿山无人运输车辆路径规划
18
作者 王桃 王霞 米宏军 《金属矿山》 北大核心 2025年第10期159-165,共7页
针对矿山无人运输车辆在复杂动态环境下路径规划效率低、实时性差、安全性不足等问题,提出了一种融合图神经网络(GNN)和注意力机制的路径规划方法。首先构建了基于道路拓扑的动态图结构,利用GNN对路网特征进行深度提取;其次,设计多头注... 针对矿山无人运输车辆在复杂动态环境下路径规划效率低、实时性差、安全性不足等问题,提出了一种融合图神经网络(GNN)和注意力机制的路径规划方法。首先构建了基于道路拓扑的动态图结构,利用GNN对路网特征进行深度提取;其次,设计多头注意力机制捕获路段间的长程依赖关系,并引入时空注意力模块处理动态环境信息;最后,基于强化学习框架实现路径规划的端到端训练。仿真试验表明:与传统A^(∗)算法相比,所提方法计算耗时减少45.3%,路径长度缩短12.7%;与Transformer方法相比,规划成功率提升19.1%,避障准确率提高14.4%。在实际矿区测试中,该方法能够有效应对复杂地形和动态障碍物,平均规划时间仅需0.3 s,为矿山无人运输车辆的安全高效运行提供了参考。 展开更多
关键词 矿山无人运输车辆 路径规划 图神经网络 注意力机制 强化学习
在线阅读 下载PDF
基于内在动机强化学习算法的煤矿井下运输机器人自主避障
19
作者 赵克宝 李灵锋 +2 位作者 陈茁 韩骏 尹瑞 《工矿自动化》 北大核心 2025年第6期81-87,共7页
现有的机器人避障方法多依赖于预设规则或外部奖励信号,难以适应煤矿井下复杂多变的环境。为实现煤矿井下运输机器人自主高效避障,提出了一种基于内在动机强化学习(IM−RL)算法的机器人自主避障方法。煤矿井下运输机器人通过视觉传感器... 现有的机器人避障方法多依赖于预设规则或外部奖励信号,难以适应煤矿井下复杂多变的环境。为实现煤矿井下运输机器人自主高效避障,提出了一种基于内在动机强化学习(IM−RL)算法的机器人自主避障方法。煤矿井下运输机器人通过视觉传感器感知外界环境信息,利用基于好奇心的内在动机取向函数计算判别外界环境属性的内部奖赏值,利用外部动机奖励函数计算其动作属性的外部奖赏值,结合内在动机取向函数的奖励权重和外部动机奖励函数的奖励权重,计算运输机器人执行动作前后状态的综合奖赏值,形成强化学习算法奖励机制,通过深度置信网络对其状态进行训练和学习,激励运输机器人主动探索未知环境,同时利用自身记忆机制存储知识和经验,通过不断学习训练实现自主避障。在静态环境、动态环境和煤矿井下实际环境中分别进行运输机器人自主避障实验,结果表明:基于IM−RL算法的机器人自主避障路径和搜索时间较短,具有较强的泛化性和鲁棒性。 展开更多
关键词 内在动机 强化学习 运输机器人 自主避障 路径规划
在线阅读 下载PDF
基于改进NSGA-Ⅱ的煤矿井下智能无轨辅助调度路径优化方法研究 被引量:4
20
作者 贾纯纯 马超 +2 位作者 张亚邦 易贝贝 王海波 《中国矿业》 北大核心 2025年第5期137-143,共7页
针对现有煤矿井下智能无轨辅助运输系统调度及路径规划效率低、考虑现实约束不足的问题,提出了一种基于改进NSGA-II的调度运输路径规划方法。以最小运输成本、最小电力机车机器人总等待时间、最小煤矿运输期望偏差为目标函数,最小卸货... 针对现有煤矿井下智能无轨辅助运输系统调度及路径规划效率低、考虑现实约束不足的问题,提出了一种基于改进NSGA-II的调度运输路径规划方法。以最小运输成本、最小电力机车机器人总等待时间、最小煤矿运输期望偏差为目标函数,最小卸货量、装货点运出总容量、装货次数、卸货点的最大卸货容量等约束条件建立煤矿井下智能无轨辅助运输系统多目标优化函数。提出了一种改进NSGA-II的多目标优化算法,使用Levy飞行、随机游走、自适应权重等策略分别提高算法的全局和局部搜索能力,加快算法收敛速度。模拟场景实验表明,与无优化方案相比,所提改进NSGA-II优化后的平衡方案使运输成本降低约19%,排队等待时间缩短约56%,最小煤矿运输期望偏差下降约40.5%。实验结果验证了所提改进NSGA-II算法优化结果的有效性和实用性,可为煤矿井下生产管理提供多种优化选择方案,具有广阔的应用前景。 展开更多
关键词 煤矿 智能无轨辅助运输 调度 路径优化 非支配排序遗传算法
在线阅读 下载PDF
上一页 1 2 59 下一页 到第
使用帮助 返回顶部