中南工业大学学报(自然科学版)
中南工業大學學報(自然科學版)
중남공업대학학보(자연과학판)
JOURNAL OF CENTRAL SOUTH UNIVERSITY OF TECHNOLGY(NATURAL SCIENCE)
2001年
1期
20-24
,共5页
李松仁%梁雪梅%景广军%陈松乔
李鬆仁%樑雪梅%景廣軍%陳鬆喬
리송인%량설매%경엄군%진송교
智能体%multi-agent%选矿%分布式专家系统
智能體%multi-agent%選礦%分佈式專傢繫統
지능체%multi-agent%선광%분포식전가계통
基于Intemet/Intranet松耦合环境设计分布式选矿专家系统,采用面向agent(智能体)的系统开发方法和multi-agent分布协作求解模式,采用异构异质agent,即agent可建构于广域网、局域网和单处理器紧耦合模式,且求解agent可以是基于符号系统、神经网络、遗传算法等agent的协作.此外,建立了统一的知识库标准,基于关系数据模式表征了传统的规则、框架、语义网络及谓词逻辑等知识表示方法.其中,基于数据库引导及搜索技术实现了正向推理机制及反向推理机制,易于agent之间知识的传输,大大提高了通信效率;基于DCOM技术,以C++构建框架类加速了agent的实现.以矿石可选性预测求解为例,实现了多agent协作求解的仿真系统,较好地验证了所提出的理论模型及框架.
基于Intemet/Intranet鬆耦閤環境設計分佈式選礦專傢繫統,採用麵嚮agent(智能體)的繫統開髮方法和multi-agent分佈協作求解模式,採用異構異質agent,即agent可建構于廣域網、跼域網和單處理器緊耦閤模式,且求解agent可以是基于符號繫統、神經網絡、遺傳算法等agent的協作.此外,建立瞭統一的知識庫標準,基于關繫數據模式錶徵瞭傳統的規則、框架、語義網絡及謂詞邏輯等知識錶示方法.其中,基于數據庫引導及搜索技術實現瞭正嚮推理機製及反嚮推理機製,易于agent之間知識的傳輸,大大提高瞭通信效率;基于DCOM技術,以C++構建框架類加速瞭agent的實現.以礦石可選性預測求解為例,實現瞭多agent協作求解的倣真繫統,較好地驗證瞭所提齣的理論模型及框架.
기우Intemet/Intranet송우합배경설계분포식선광전가계통,채용면향agent(지능체)적계통개발방법화multi-agent분포협작구해모식,채용이구이질agent,즉agent가건구우엄역망、국역망화단처리기긴우합모식,차구해agent가이시기우부호계통、신경망락、유전산법등agent적협작.차외,건립료통일적지식고표준,기우관계수거모식표정료전통적규칙、광가、어의망락급위사라집등지식표시방법.기중,기우수거고인도급수색기술실현료정향추리궤제급반향추리궤제,역우agent지간지식적전수,대대제고료통신효솔;기우DCOM기술,이C++구건광가류가속료agent적실현.이광석가선성예측구해위례,실현료다agent협작구해적방진계통,교호지험증료소제출적이론모형급광가.
The design of distributed Mineral Processing Expert System based on Internet/Intranet has been explored underslack coupling with agent-oriented programming (AOP) method and multi-agent distributed cooperating solution pattern.Isomery and alloplasm agent is proposed, that is, agent may be built on WAN, LAN and single CPU by tense couplingmode, and solution agent can work among agents based on symbol system, neural network, genetic algorithm. Unifiedknowledge base standard of mineral processing is built. Based on relational data pattern and search engine, traditionalrule, frame, semantic model and predicate logic knowledge representation methods, and forward inference engine, back-ward reasoning mechanism are realized. This makes it easy for knowledge to transfer among agents, and improves commu-nicating efficiency greatly. Based on DCOM (distributed component object model) technology, building frame class byC + + , it accelerates the execution of agent. Take ore beneficiability prediction problems for example. The simulatingsystem of multi-agent cooperating solution has been carried out, which can preferably verify the theoretic models andframes in this thesis.