基于Multi-Agent协作的井下机器人智能搜救系统  被引量:7

Intelligent search and rescue system of underground robot based on Multi-Agent cooperation

在线阅读下载全文

作  者:曲芳[1,2] 顿国强[2] 沈斌[3] 冯夷宁 王绍胜[4] 

机构地区:[1]黑龙江科技大学工程训练与基础实验中心,哈尔滨150022 [2]东北农业大学工程学院,哈尔滨150030 [3]黑龙江科技大学安全工程学院,哈尔滨150022 [4]黑龙江科技大学现代制造工程中心,哈尔滨150022

出  处:《黑龙江科技大学学报》2015年第4期440-444,共5页Journal of Heilongjiang University of Science And Technology

基  金:黑龙江省教育厅科学技术研究项目(12541710;12533057);黑龙江省青年科学基金项目(QC2012C102)

摘  要:煤矿井下救援与逃生是煤矿安全生产中亟待解决的重大课题之一。发生矿难事故后,第一时间就是搜索并解救井下被困人员。传统的救援方式耗费大量的人力、物力和财力,且容易错过井下最佳救援的"黄金72小时"。通过建立基于Multi-Agent协作的煤矿井下智能搜救模型,设计出两类Agent模块,即SearchAgent和ContolAgent。利用Agent的主动性、自反应、自组织、自学习和协同沟通的特性,在矿难发生后,根据井下地图和多个SearchAgent反馈回来的路径信息进行汇总、分析与计算,精确筛选出最优、最近的搜救路线,并通知其他SearchAgent协同援助。应用多主体建模技术模拟井下救援路线,对于井下被困人员位置的定位、搜救方案的制定、救援人员的调度安排、物资的合理分配都具有十分重要的现实意义。This paper is devoted to a novel study growing out of a deeper understanding that mine es- cape and rescue operation represents one of the major issues demanding immediate solution in the safety production of coal mine. The paper features a novel intelligent search and rescue system as an alternative to currently-used rescue way identified as a waste a lot of manpower, material and financial resources and more likely to miss "golden 72 hours", the best time of underground rescue, suggesting a negative effect on devoting the first time to search and rescue personnel trapped underground after mine accidents. The study consists of developing the intelligent search and rescue model tailored for coal mines based on Muhi-Agent cooperation; designing two kinds of Agent modules, namely SearchAgent and ContolAgent; using the Agent~ advantages such as initiative, self-reaction, self-organization, self-learning and collabo- rative communication and thereby summarizing, analyzing and calculating the path information depending on mine maps and multiple SearchAgent feedback; and selecting the best and the nearest search and res- cue routes and informing other SearchAgent of cooperative rescue operation after the mine accident. This system, capable of simulating the underground rescue route using Multi-Agent modeling technology, is of important practical significance for the location of trapped personnel, the development of the rescue plan, the arrangement of the rescue workers, and the reasonable distribution of the material.

关 键 词:智能搜救 Multi-Agent协作 SearchAgent ControlAgent 

分 类 号:TD77[矿业工程—矿井通风与安全] TP242.6[自动化与计算机技术—检测技术与自动化装置]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象