基于多Agent的磨矿过程智能控制系统研究
|
摘要
磨矿过程是选矿作业中的重要生产过程，其控制效果的优劣对选矿厂的生产能耗、经济和技术指标具有决定性的作用。而磨矿过程的大时滞、多变量耦合、生产不确定性等特点给磨矿过程控制带来了很大的困难。随着降低生产能耗、提高资源可利用率等更高的生产要求的提出，磨矿过程控制技术更需要不断改进，预测控制、自适应控制及人工智能控制等技术逐步替代了传统简单的自动控制等方法，尤其是人工智能控制技术在磨矿控制领域得到了极大的关注。
通过对磨矿生产过程的剖析，综合各类磨矿智能控制方法研究的基础上，本文提出了构建基于多Agent技术的磨矿过程智能控制系统。从多Agent系统应用的观点出发，磨矿过程具有复杂的、连续的、动态的不确定的特点；磨矿过程控制影响因素多，控制和决策依赖于专家经验的判断；磨矿过程中大量的信息以分布式方式存在。这些特性都属于多Agent系统的应用范畴，使得多Agent系统研究具有可行性。有别于其他的智能控制系统，本文将磨矿过程的整体控制过程进行局部分解，采取全局和局部结合的控制策略，并将故障诊断、生产控制、运行态势分析等功能进行融合，使系统成为一个集成的综合性的信息平台。这种构想体现了多Agent系统技术的方便灵活、组织协调和综合决策的特点，充分发挥了多Agent系统解决复杂问题的能力，并最终建立了基于多Agent的磨矿智能控制系统模型。系统应用结果表明：多Agent系统理论可以很好的进行信息融合，合理调整生产参数，在全过程实现智能决策控制，提高生产效率，降低生产能耗，产生了可观的经济效益。
论文完成的工作如下：
（1）论文对国内外磨矿过程控制的研究现状进行了分析和总结，着重对人工智能控制方法进行了研究对比，探讨了多Agent技术在磨矿过程控制应用的可行性。根据多Agent技术在磨矿过程控制中应用的研究，认为多Agent技术对多个问题的协调和综合解决能力较为突出，特别是在信息融合和综合决策方面符合磨矿过程控制的要求，因此提出建立基于多Agent的磨矿智能控制系统模型。
（2）论文对磨矿过程进行了深入的剖析，建立了面向多任务分解的磨矿控制策略：先将磨矿生产全过程的几个控制环节划分成几个相对独立的子控制任务，如给矿控制任务、液位控制任务、压力控制任务，以及磨矿故障诊断、控制决策等任务，而后将各个子控制任务按照一定的协作规则进行融合，最终在各个子任务完成的基础上实现对磨矿过程全局的控制。
（3）论文在面向任务的磨矿控制策略基础上，研究了多Agent系统的建模方法，建立了基于多Agent的磨矿智能控制系统模型，设计完成了系统的模型结构、功能模块和数据流程模型等。该模型建立的思想是：将磨矿过程的子任务抽象为多Agent系统的个体Agent，如：给矿控制Agent、液位控制Agent、压力控制Agent、故障诊断Agent等，个体Agent独立完成各自的控制任务，多个个体Agent再通过协商合作完成整体的控制任务。
（4）论文在多Agent磨矿智能控制系统的框架下，完成了对个体Agent的模型建立和功能实现。
完成故障诊断Agent模型研究：论文对磨矿过程故障特点进行了研究，针对其故障多源性、不确定性及数据分布式等特点，提出基于数据融合的磨矿故障诊断方法；通过资料收集和经验总结，制定了磨矿故障诊断的目标和策略；采用模糊专家系统技术，建立磨矿故障诊断知识体系，根据诊断规则及特征数据进行故障的不确定性推理；对磨矿故障诊断Agent进行建模，实现基于Jess的故障诊断推理过程。
完成任务处理Agent模型研究：提出了基于自适应神经模糊网络的控制模型，并对数据样本聚类算法进行了改进，提出了相似融合算法进行聚类辨识。该模型根据模糊规则采用基于数据的建模方法，能在系统辨识过程中确定和优化模型的各类参数，从而得到最佳输入和输出变量。论文对模型进行了仿真试验和对比测试，结果显示模型具有更强的适应性和准确性。
（5）论文对多Agent系统的协商过程和协作机制进行了研究，比较集中式、分布式等几种协作方式，制定了基于黑板的数据传递、结果共享和信息共享的任务分担的协作策略。在黑板模型结构下，建立了数据服务Agent、黑板控制Agent和控制决策Agent，在黑板控制Agent集中式协调下，各个子任务Agent通过数据服务Agent进行通信和数据请求，借助黑板共享数据库进行数据和结果交换；控制决策Agent对子任务执行结果进行控制决策和冲突消解。对黑板系统模型的各个功能测试和试验结果表明：本文的协作机制既能较好的发挥个体Agent的自主执行能力，还能避免发生资源竞争和结果冲突，这种协作方式适应磨矿生产的功能需要，提升了各个Agent的执行效率，提高了全局控制决策能力。
（6）基于JADE多Agent系统开发技术建立了多Agent磨矿控制系统模型。论文构建了给矿控制Agent、压力控制Agent、液位控制Agent、黑板控制Agent、数据服务Agent、控制决策Agent及人机交互Agent等模块，实现了系统各项功能。借助磨矿过程实际生产数据对系统进行了综合测试，测试结果表明：系统达到了选矿厂的设计要求，在相同工况下，多Agent磨矿智能控制系统控制下的磨矿生产更为平稳，能合理的调节给矿量、压力值和液位值，使得球磨机处理量增加，生产效率和产品质量得到提高，并具有较好的稳定性。
在本文的研究和实践的基础上，未来可以在以下几个方面进行改进和完善。
（1）多Agent磨矿智能控制系统具有良好的应用前景。今后可进一步加深对磨矿生产环节的研究，增加更多生产过程的智能控制。
（2）多Agent磨矿智能控制系统设计基于多Agent系统的组织架构，具有良好的可扩展性，可通过增加个体Agent来实现对系统功能的扩充。
（3）进一步加深对故障诊断分析的研究，补充机械自动化知识，积累更多的生产操作经验，减少生产过程出现的故障。
（4）进一步优化磨矿控制结果，来满足未来选矿厂对磨矿生产目标的提高，从而带来更大的经济效益。
（5）继续Agent理论和多Agent技术的研究。提高多Agent系统的性能，及推理、规划、学习的能力。
多Agent控制技术丰富了磨矿智能控制的手段，是对这一领域应用的新突破。同时，多Agent磨矿智能控制系统改变了传统的磨矿控制理念，是集合了计算机技术、自动化技术、智能控制等多种学科的综合性技术，对磨矿生产技术革新起到了积极的推动作用，具有广泛的应用前景。科技是第一生产力，今后选矿作业乃至整个矿山冶金行业，也必将走进智能控制的新时代！
Ore Grinding is an important manufacturing process in mineral processing,which decides the energy consumption, economic and technical indexes of amineral processing plant. It makes Grinding process hard with long time delay,Multivariable coupling and production uncertainty. With the requirements oflowering manufacturing energy consumption and improving energy utility, it iseven necessary to improve Grinding process control technology. Predictive control,adaptive control, artificial intelligent control have replaced the traditional simpleautocontrol techniques gradually and artificial intelligent control has been focusedgreatly in Grinding processing.
Based on analysis on Grinding process and integrative study on various oreGrinding intelligent controlling techniques, this paper proposes to construct anintelligent control system with Multi-Agent technique. In terms of Multi-Agentsystem application, an ore Grinding process is complicated, continuous anddynamic. There are various factors in controlling ore Grinding process and controland decision are made by experts with experience. Information in ore Grindingprocess exists in distributed form. These features are included in Multi-Agentsystem application, which makes it feasible to study Multi-Agent system.Differing from the other intelligent control systems, this paper makes localanalysis on the entire control process in ore Grinding and follows the controlstrategy combing local and overall， integrating trouble diagnosis, production control and operation status analysis, which makes the system an integrative andcomprehensive information platform. This concept embodies the flexibletechnique, coordinative organization and comprehensive decision of Multi-Agentsystem, which fulfils the capabilities of Multi-Agent system to solve complicatedproblems and constructs an intelligent control system model of Multi-AgentGrinding process. The system application shows the theory of Multi-Agent systemcan perform better information merging, adjusting production parameters andfulfill intelligent decision in overall process to improve productivity, lower energyconsumption and bring considerable economic benefit.
The following studies have been conducted in the paper:
1. The analysis and summary have been made in Grinding process controlboth home and abroad, and a special comparison study in artificial intelligentcontrol and application feasibility of Multi-Agent technology in Grinding processcontrol. Based on the study of application of Multi-Agent technique in Grindingprocess, this paper proposes that Multi-Agent technique performs well incoordinating and solving various problems, which satisfies the requirements ofinformation merging and integrative deciding in Grinding process control.Therefore, a Multi-Agent intelligent control system model had been proposed toconstruct.
2. A deeper analysis has been made in Grinding process and Grinding controlstrategy established in terms of multi-task decomposition. First, divide Grindingprocess control into several individual sub-control tasks, such as feeding control,level control, pressure control and Grinding trouble diagnosis and control decision.Then, integrate sub-control tasks according to coordination rules. Finally, the control of entire Grinding process can be realized when sub-tasks are conducted.
3. Modeling method of Multi-Agent system has been studied in this paperbased on task-oriented Grinding control strategy. An intelligent control systemmodel of Multi-Agent Grinding has been established and model structure, functionmode and data flow model have been designed. The concept of establishing themodel: abstract the sub-tasks into individual Agent of Multi-Agent system fromGrinding process, namely feed control Agent, level control Agent, pressure controlAgent, trouble diagnosis Agent. An individual Agent performs its control taskindependently, and the system control tasks can be performed throughcoordination of individualAgents.
4. This paper has conducted modeling construction and function realization ofan individual Agent in the frame of Multi-Agent Grinding intelligent controlsystem.
Model study of trouble diagnosis: features of trouble in Grinding process areunder study in this paper. Considering Multi-source of trouble, uncertainty anddata distribution mode, a Grinding trouble diagnosis method based on datamerging has been put forward in this paper. The target and strategy of Grindingtrouble diagnosis have been made through data collection and experience summary.With the application of fuzzy expert system, a knowledge system of Grindingtrouble diagnosis has been established to perform reasoning of uncertainty oftroubles based on diagnosis rules and feature data. A model for Grinding troublediagnosis Agent has been constructed to perform Jess-based reasoning of troublediagnosis.
Model study of task processing Agent: A control model based on adaptiveneural fuzzy network has been put forward, a clustering algorithm of data sample improved and similarity fusion algorithm introduced to perform clusteridentification. This model, based on fuzzy rules and data modeling, can decide andoptimize parameters in system identification and the best input and outputvariables can be obtained. A simulation test and comparison test have beenconducted in this paper, which shows the model has better adaptability andaccuracy.
5. This paper has performed a study on coordinating and consulting processof Multi-Agent system, which compares centralized and distributed coordinatingmethods and makes a task-sharing coordination strategy of data transfer, resultsharing and information sharing based on blackboard. In blackboard model, dataservice Agent, blackboard control Agent and control decision Agent areestablished; by blackboard Agent centralized coordination, sub-task Agents makecommunication and data demands through data service Agent and perform dataand result exchange through blackboard sharing database, and control decisionAgent performs control decision and conflict resolution on the operation results ofsub-tasks. The test and experiment on functions of blackboard system modelshows the coordination mechanism proposed in this paper can exerciseindependent executive ability of an individual Agent and avoid resourcecompetition and result conflict, which satisfies the function need of Grindingproduction, improves performance efficiency of individual Agents and the abilityof overall control decision.
6. A model of Multi-Agent Grinding control system based on JADEMulti-Agent system development technology has been established. Modules offeed control Agent, pressure control Agent, level control Agent, blackboard controlAgent, data service Agent, control decision Agent and human-machine interactionAgent have been constructed in this paper and the functions of the system can be fulfilled. Production data in Grinding process is applied to perform comprehensivetest on the system and the test result shows: the system has satisfied the designrequirements of the mineral processing plant. In the same operating condition,Grinding production under Multi-Agent intelligent control system becomes steadyto regulate feeding, pressure and level values, increase the processing amount ofthe ball grinder and improve production efficiency and product quality with betterstability.
Based on the study and practice conducted in this paper, followingimprovement can be made in the future:
1. Multi-Agent Grinding intelligent control system has a better applicationprospect. Further study should be done in Grinding production process and moreintelligent control in production process conducted.
2. Multi-Agent Grinding intelligent control system, based on Multi-Agentsystem organization, has better extendibility and system function extension can berealized through increasing the number ofAgents.
3. Further study should be conducted on trouble diagnosis, adding mechanicalautomation knowledge and accumulating more operation experience and reducetroubles in production process.
4. Further optimize Grinding control results to satisfy the higher demand ofGrinding production target in future mineral processing plants in order to bringmore economic benefit.
5. Further study in Agent theory and Multi-Agent technology to improve theMulti-Agent system performance and reasoning, planning and learning abilities.
The study of Multi-Agent control technology enriches the means of Grindingintelligent control, which is an application breakthrough in the field. Besides, the Multi-Agent Grinding intelligent control system changes the traditional concept ofGrinding control, which is a comprehensive technology integrating computertechnology, automation technology and intelligent control and plays an active rolein developing technical innovation in Grinding production with a wide applicationprospect. Science and technology is the first productivity and future mineralprocessing and mining and metallurgy are destined to step into a new era ofintelligent control.
通过对磨矿生产过程的剖析，综合各类磨矿智能控制方法研究的基础上，本文提出了构建基于多Agent技术的磨矿过程智能控制系统。从多Agent系统应用的观点出发，磨矿过程具有复杂的、连续的、动态的不确定的特点；磨矿过程控制影响因素多，控制和决策依赖于专家经验的判断；磨矿过程中大量的信息以分布式方式存在。这些特性都属于多Agent系统的应用范畴，使得多Agent系统研究具有可行性。有别于其他的智能控制系统，本文将磨矿过程的整体控制过程进行局部分解，采取全局和局部结合的控制策略，并将故障诊断、生产控制、运行态势分析等功能进行融合，使系统成为一个集成的综合性的信息平台。这种构想体现了多Agent系统技术的方便灵活、组织协调和综合决策的特点，充分发挥了多Agent系统解决复杂问题的能力，并最终建立了基于多Agent的磨矿智能控制系统模型。系统应用结果表明：多Agent系统理论可以很好的进行信息融合，合理调整生产参数，在全过程实现智能决策控制，提高生产效率，降低生产能耗，产生了可观的经济效益。
论文完成的工作如下：
（1）论文对国内外磨矿过程控制的研究现状进行了分析和总结，着重对人工智能控制方法进行了研究对比，探讨了多Agent技术在磨矿过程控制应用的可行性。根据多Agent技术在磨矿过程控制中应用的研究，认为多Agent技术对多个问题的协调和综合解决能力较为突出，特别是在信息融合和综合决策方面符合磨矿过程控制的要求，因此提出建立基于多Agent的磨矿智能控制系统模型。
（2）论文对磨矿过程进行了深入的剖析，建立了面向多任务分解的磨矿控制策略：先将磨矿生产全过程的几个控制环节划分成几个相对独立的子控制任务，如给矿控制任务、液位控制任务、压力控制任务，以及磨矿故障诊断、控制决策等任务，而后将各个子控制任务按照一定的协作规则进行融合，最终在各个子任务完成的基础上实现对磨矿过程全局的控制。
（3）论文在面向任务的磨矿控制策略基础上，研究了多Agent系统的建模方法，建立了基于多Agent的磨矿智能控制系统模型，设计完成了系统的模型结构、功能模块和数据流程模型等。该模型建立的思想是：将磨矿过程的子任务抽象为多Agent系统的个体Agent，如：给矿控制Agent、液位控制Agent、压力控制Agent、故障诊断Agent等，个体Agent独立完成各自的控制任务，多个个体Agent再通过协商合作完成整体的控制任务。
（4）论文在多Agent磨矿智能控制系统的框架下，完成了对个体Agent的模型建立和功能实现。
完成故障诊断Agent模型研究：论文对磨矿过程故障特点进行了研究，针对其故障多源性、不确定性及数据分布式等特点，提出基于数据融合的磨矿故障诊断方法；通过资料收集和经验总结，制定了磨矿故障诊断的目标和策略；采用模糊专家系统技术，建立磨矿故障诊断知识体系，根据诊断规则及特征数据进行故障的不确定性推理；对磨矿故障诊断Agent进行建模，实现基于Jess的故障诊断推理过程。
完成任务处理Agent模型研究：提出了基于自适应神经模糊网络的控制模型，并对数据样本聚类算法进行了改进，提出了相似融合算法进行聚类辨识。该模型根据模糊规则采用基于数据的建模方法，能在系统辨识过程中确定和优化模型的各类参数，从而得到最佳输入和输出变量。论文对模型进行了仿真试验和对比测试，结果显示模型具有更强的适应性和准确性。
（5）论文对多Agent系统的协商过程和协作机制进行了研究，比较集中式、分布式等几种协作方式，制定了基于黑板的数据传递、结果共享和信息共享的任务分担的协作策略。在黑板模型结构下，建立了数据服务Agent、黑板控制Agent和控制决策Agent，在黑板控制Agent集中式协调下，各个子任务Agent通过数据服务Agent进行通信和数据请求，借助黑板共享数据库进行数据和结果交换；控制决策Agent对子任务执行结果进行控制决策和冲突消解。对黑板系统模型的各个功能测试和试验结果表明：本文的协作机制既能较好的发挥个体Agent的自主执行能力，还能避免发生资源竞争和结果冲突，这种协作方式适应磨矿生产的功能需要，提升了各个Agent的执行效率，提高了全局控制决策能力。
（6）基于JADE多Agent系统开发技术建立了多Agent磨矿控制系统模型。论文构建了给矿控制Agent、压力控制Agent、液位控制Agent、黑板控制Agent、数据服务Agent、控制决策Agent及人机交互Agent等模块，实现了系统各项功能。借助磨矿过程实际生产数据对系统进行了综合测试，测试结果表明：系统达到了选矿厂的设计要求，在相同工况下，多Agent磨矿智能控制系统控制下的磨矿生产更为平稳，能合理的调节给矿量、压力值和液位值，使得球磨机处理量增加，生产效率和产品质量得到提高，并具有较好的稳定性。
在本文的研究和实践的基础上，未来可以在以下几个方面进行改进和完善。
（1）多Agent磨矿智能控制系统具有良好的应用前景。今后可进一步加深对磨矿生产环节的研究，增加更多生产过程的智能控制。
（2）多Agent磨矿智能控制系统设计基于多Agent系统的组织架构，具有良好的可扩展性，可通过增加个体Agent来实现对系统功能的扩充。
（3）进一步加深对故障诊断分析的研究，补充机械自动化知识，积累更多的生产操作经验，减少生产过程出现的故障。
（4）进一步优化磨矿控制结果，来满足未来选矿厂对磨矿生产目标的提高，从而带来更大的经济效益。
（5）继续Agent理论和多Agent技术的研究。提高多Agent系统的性能，及推理、规划、学习的能力。
多Agent控制技术丰富了磨矿智能控制的手段，是对这一领域应用的新突破。同时，多Agent磨矿智能控制系统改变了传统的磨矿控制理念，是集合了计算机技术、自动化技术、智能控制等多种学科的综合性技术，对磨矿生产技术革新起到了积极的推动作用，具有广泛的应用前景。科技是第一生产力，今后选矿作业乃至整个矿山冶金行业，也必将走进智能控制的新时代！
Ore Grinding is an important manufacturing process in mineral processing,which decides the energy consumption, economic and technical indexes of amineral processing plant. It makes Grinding process hard with long time delay,Multivariable coupling and production uncertainty. With the requirements oflowering manufacturing energy consumption and improving energy utility, it iseven necessary to improve Grinding process control technology. Predictive control,adaptive control, artificial intelligent control have replaced the traditional simpleautocontrol techniques gradually and artificial intelligent control has been focusedgreatly in Grinding processing.
Based on analysis on Grinding process and integrative study on various oreGrinding intelligent controlling techniques, this paper proposes to construct anintelligent control system with Multi-Agent technique. In terms of Multi-Agentsystem application, an ore Grinding process is complicated, continuous anddynamic. There are various factors in controlling ore Grinding process and controland decision are made by experts with experience. Information in ore Grindingprocess exists in distributed form. These features are included in Multi-Agentsystem application, which makes it feasible to study Multi-Agent system.Differing from the other intelligent control systems, this paper makes localanalysis on the entire control process in ore Grinding and follows the controlstrategy combing local and overall， integrating trouble diagnosis, production control and operation status analysis, which makes the system an integrative andcomprehensive information platform. This concept embodies the flexibletechnique, coordinative organization and comprehensive decision of Multi-Agentsystem, which fulfils the capabilities of Multi-Agent system to solve complicatedproblems and constructs an intelligent control system model of Multi-AgentGrinding process. The system application shows the theory of Multi-Agent systemcan perform better information merging, adjusting production parameters andfulfill intelligent decision in overall process to improve productivity, lower energyconsumption and bring considerable economic benefit.
The following studies have been conducted in the paper:
1. The analysis and summary have been made in Grinding process controlboth home and abroad, and a special comparison study in artificial intelligentcontrol and application feasibility of Multi-Agent technology in Grinding processcontrol. Based on the study of application of Multi-Agent technique in Grindingprocess, this paper proposes that Multi-Agent technique performs well incoordinating and solving various problems, which satisfies the requirements ofinformation merging and integrative deciding in Grinding process control.Therefore, a Multi-Agent intelligent control system model had been proposed toconstruct.
2. A deeper analysis has been made in Grinding process and Grinding controlstrategy established in terms of multi-task decomposition. First, divide Grindingprocess control into several individual sub-control tasks, such as feeding control,level control, pressure control and Grinding trouble diagnosis and control decision.Then, integrate sub-control tasks according to coordination rules. Finally, the control of entire Grinding process can be realized when sub-tasks are conducted.
3. Modeling method of Multi-Agent system has been studied in this paperbased on task-oriented Grinding control strategy. An intelligent control systemmodel of Multi-Agent Grinding has been established and model structure, functionmode and data flow model have been designed. The concept of establishing themodel: abstract the sub-tasks into individual Agent of Multi-Agent system fromGrinding process, namely feed control Agent, level control Agent, pressure controlAgent, trouble diagnosis Agent. An individual Agent performs its control taskindependently, and the system control tasks can be performed throughcoordination of individualAgents.
4. This paper has conducted modeling construction and function realization ofan individual Agent in the frame of Multi-Agent Grinding intelligent controlsystem.
Model study of trouble diagnosis: features of trouble in Grinding process areunder study in this paper. Considering Multi-source of trouble, uncertainty anddata distribution mode, a Grinding trouble diagnosis method based on datamerging has been put forward in this paper. The target and strategy of Grindingtrouble diagnosis have been made through data collection and experience summary.With the application of fuzzy expert system, a knowledge system of Grindingtrouble diagnosis has been established to perform reasoning of uncertainty oftroubles based on diagnosis rules and feature data. A model for Grinding troublediagnosis Agent has been constructed to perform Jess-based reasoning of troublediagnosis.
Model study of task processing Agent: A control model based on adaptiveneural fuzzy network has been put forward, a clustering algorithm of data sample improved and similarity fusion algorithm introduced to perform clusteridentification. This model, based on fuzzy rules and data modeling, can decide andoptimize parameters in system identification and the best input and outputvariables can be obtained. A simulation test and comparison test have beenconducted in this paper, which shows the model has better adaptability andaccuracy.
5. This paper has performed a study on coordinating and consulting processof Multi-Agent system, which compares centralized and distributed coordinatingmethods and makes a task-sharing coordination strategy of data transfer, resultsharing and information sharing based on blackboard. In blackboard model, dataservice Agent, blackboard control Agent and control decision Agent areestablished; by blackboard Agent centralized coordination, sub-task Agents makecommunication and data demands through data service Agent and perform dataand result exchange through blackboard sharing database, and control decisionAgent performs control decision and conflict resolution on the operation results ofsub-tasks. The test and experiment on functions of blackboard system modelshows the coordination mechanism proposed in this paper can exerciseindependent executive ability of an individual Agent and avoid resourcecompetition and result conflict, which satisfies the function need of Grindingproduction, improves performance efficiency of individual Agents and the abilityof overall control decision.
6. A model of Multi-Agent Grinding control system based on JADEMulti-Agent system development technology has been established. Modules offeed control Agent, pressure control Agent, level control Agent, blackboard controlAgent, data service Agent, control decision Agent and human-machine interactionAgent have been constructed in this paper and the functions of the system can be fulfilled. Production data in Grinding process is applied to perform comprehensivetest on the system and the test result shows: the system has satisfied the designrequirements of the mineral processing plant. In the same operating condition,Grinding production under Multi-Agent intelligent control system becomes steadyto regulate feeding, pressure and level values, increase the processing amount ofthe ball grinder and improve production efficiency and product quality with betterstability.
Based on the study and practice conducted in this paper, followingimprovement can be made in the future:
1. Multi-Agent Grinding intelligent control system has a better applicationprospect. Further study should be done in Grinding production process and moreintelligent control in production process conducted.
2. Multi-Agent Grinding intelligent control system, based on Multi-Agentsystem organization, has better extendibility and system function extension can berealized through increasing the number ofAgents.
3. Further study should be conducted on trouble diagnosis, adding mechanicalautomation knowledge and accumulating more operation experience and reducetroubles in production process.
4. Further optimize Grinding control results to satisfy the higher demand ofGrinding production target in future mineral processing plants in order to bringmore economic benefit.
5. Further study in Agent theory and Multi-Agent technology to improve theMulti-Agent system performance and reasoning, planning and learning abilities.
The study of Multi-Agent control technology enriches the means of Grindingintelligent control, which is an application breakthrough in the field. Besides, the Multi-Agent Grinding intelligent control system changes the traditional concept ofGrinding control, which is a comprehensive technology integrating computertechnology, automation technology and intelligent control and plays an active rolein developing technical innovation in Grinding production with a wide applicationprospect. Science and technology is the first productivity and future mineralprocessing and mining and metallurgy are destined to step into a new era ofintelligent control.
引文
[1]李艳姣,王建民,张杰.磨矿过程磨机负荷的优化计算与智能控制[J]自动化与仪表2013,10,173-175
[2]孙晋美.提高磨矿分级效率,改善磨矿选别指标[J].中国科技投资,2013,20:43-46
[3]刘金琨.智能控制[M].北京:电子工业出版社,2014:11-17
[4] Zhou, P.,Chai, T.,Sun, J.Intelligence-Based Supervisory Control for OptimalOperation of a DCS-Controlled Grinding System[J] IEEE transactions oncontrol systems technology.2013,21(1):143-148
[5]薛杰.模糊自调整二自由度PID控制器及在磨矿分级中的应用[D].昆明:昆明理工大学,2002
[6]陈夕松,魏彬,王露露,李奇.模糊PID在选矿球磨浓度控制中的应用[J].工业仪表与自动化装置,2005,2:15-17
[7]马天雨,桂卫华,王雅琳,阳春华.磨矿分级过程动态优化控制[J]控制与决策2012,02,:30-34
[8]胡海波,黄友锐.基于神经网络分数阶PID控制器在磨矿分级系统中的应用研究[J].煤矿机械,2009,30(11):198-201
[9] Maksoud, T.M.A, Atia, M.R, Koura, M.M,Applications of artificial intelligenceto Grinding operations via neural networks [J].Machining Science andTechnology,2003,7,(3):361-387
[10]李娟娟,于淳,郭纲,杨东平.基于BP神经网络的球磨机浓度预测分析[J].节能.2010,8:20-22
[11] Mohanasundararaju, N. Sivasubramanian, R. Gnanaguru, R. Alagumurthy, N.A neural network and fuzzy-based methodology for the prediction of workroll surface roughness in a Grinding process[J]. International Journal ofComputational Methods in Engineering Science and Mechanics.2008,9(2):103-110
[12] Nagasaka Kazunori,Harada Naohiko, Ichihashi Hidetomo, LeonardRaymond.Adaptive learning networks of Multi-stage fuzzy production rulesin expert system of Grinding characteristics[J]. Computers and IndustrialEngineering,1994,27,(1-4):433-436
[13] Lezanski Pawe, Lajmert Pawe.An intelligent system for Grinding processcontrol and optimization[C]. Modern Trends in Manufacturing, SecondInternational CAMT Conference (Centre for Advanced ManufacturingTechnologies),2003:231-238
[14]王云峰,李战明,袁占亭,万维汉.RBF神经网络与模糊理论相结合的磨矿分级智能控制方法[J].重庆大学学报,2010,33,(3):124-128
[15]丁进良,岳恒,齐玉涛,柴天佑,郑秀萍.基于遗传算法的磨矿粒度神经网络软测量[J].仪器仪表学报,2006,27,(9):981-984
[16]景广军,梁雪梅,周贤渭,李松仁.神经网络专家系统在矿业中的应用[J].金属矿山,2001,296,(2):46-48
[17]周平,柴天佑.基于案例推理的磨矿分级系统智能设定控制[J].东北大学学报(自然科学版).2007,28,(5):613-616
[18] M. Ramasamy a, S.S. Narayanan, Ch.D.P. Rao.Control of ball mill Grindingcircuit using model predictive control scheme[J]. Journal of Process Control2005,15:273-283
[19] Arup Bhaumik,Suman Banerjee,Jaya Sil.Designing of intelligent expertcontrol system using petri net for Grinding mill operation[J] World Scientificand Engineering Academy and Society,2005:147-150
[20] Marvin Minsky.Society Of Mind[D]. Simon&Schuster1988;18-25
[21] M Wooldridge.Intellgent Agents:Theory and Practice[J].Knowledgeengineering Review,1995,10(2):115-152
[22] D M Lane, A G Mcfadzean. Distributed problem solving and real-timemechanisms in robot architectures[J].Engineering Application Intelligence,1994,7,(2):105-117.
[23] N R Jennings，L Z Vagar,R P Aarnts et al.Transforming standalone expertsystem into a community of cooperating Agents[J].Engineerin ApplicationArtificial Intelligence,1993,6,(4):317-331
[24] F Polat,S Shekhar,H A Guvenir.Distributed conflict resolution amongcooperating expert systems[J].Expert Systems,1993,10,(4):227-236
[25]卿小霞.基于Multi-Agent的分布式污水处理智能化系统研究[D].重庆大学,2007
[26]王海东.水泥生产过程多Agent控制系统的研究[D].中南大学,2004
[27] V Sahasrabudhe.A Multi-Agent control system framework for smartstructures[C].AIAA,USA,1998,4202-4215
[28] Draa B C,Millot P.A Framework for cooperative work:An approach based onthe intentionality[J].Artificial Intelligence in Engineering,1990,5,(4):199-205
[29] Russell S J，Subramanian D，Parr R.Provably boundd optimal Agents[C].InIJCAII eds.Proceeding of the13thInternational Joint Conference on ArtificialIntelligence.Chambery:Morgan Kaufmann Publ Inc,1993.338-343
[30] Wang H,Wang C.APACS:A Multi-Agent system with respositorysupport[J].Knowledge-based System,1996,9,(3):329-337
[31]王鲁,王志良,杨溢.一种多agent系统框架与协商机制研究[J]计算机应用研究.2012,03:253-256
[32]刘金琨,尔联洁.多智能体技术应用综述[J].控制与决策,2001,16,(2),133-140
[33]闫博.半导体生产线调度的多智能体建模方法研究[D].同济大学,2007
[34]王鹏,罗军舟,李伟,卞正皑,曲延盛.可控网络中多Agent系统信念可达性和收敛速度分析[J]软件学报,2010,04,78-83
[35] N M Avouris.Cooperating knowledge-based systems for environmentaldecision suppot[J].Knowledge-based System，1995,8,(1):39-54
[36]孙喁喁,刘萍萍基于黑板的多Agent智能决策支持系统的Agent实现[J].电子设计工程,2009,17,(2):22-24
[37] G Hartvigsen, D Johansen. Cooperation in a distributed artificial intelligenceenvironment-The stormcast application[J]. Engineering Application ofArtificial Intelligence,1990,3(3):229-237.
[38]晁进,刘文颖.基于多智能体和专家系统的电网智能报警系统研究[J].现代电力,2010,27,(5):1-5
[39] Lambert M Surhone, Mariam T Tennoe, Susan F Henssonow. Agent orientedprogramming[M] Betascript Publishing.2010,12,12-18
[40]吴海宝.磨矿分级控制算法研究[J]昆明理工大学,2007,11
[41]段希祥.碎矿与磨矿[M].北京:冶金工业出版社,2012,46-50
[42]许时.矿石可选性研究[M].北京:冶金工业出版社,2007,87-95
[43]周金华,张静.多传感器数据融合技术在电厂状态监测和故障诊断中的应用[J]煤矿机械2011,11:27-34
[44]张碧波.设备状态监测与故障诊断[M].北京:化学工业出版社,2011
[45]栾家辉,王立梅,刘红梅.故障诊断与预测:原理,技术及应用[M].北京:北京航空航天大学出版社,2012
[46]扶晓,刘劲,张明慧.多Agent信息融合的故障诊断研究[J]电脑知识与技术.2010,11,145-153
[47]杨小强,姜海宝,蒋国良,邓伟,高亚明.基于多传感器数据融合的液压泵故障诊断[J]机械制造,2010,01:56-63
[48]李伟.复杂系统的智能故障诊断技术现状及其发展趋势[J].计算机仿真,2004,10:4-11
[49]吴斌,于春梅,李强.过程工业故障诊断[M].北京:科学出版社,2012
[50] George Vachtsevanos, Frank L.Lewis, Michael Roemer, Andrew Hess.Intellgent Fault Diagnosis and Prognosis for Engineering Systems[M]北京:国防工业出版社,2013
[51] Kassidas A,P.A.Talyor and J.F.MacGreger. Off-line diagnosis of deterministicfaults in continuous dynamic Multi variable Process using Speechrecognition methods[J].Process Control,1998,8,(5-6):351-393
[52] Rehbein D.Expert system in Process Control[J].ISATrans,1992,31,(2):49-55
[53] Ding S X and Jeinsch T.Application of observer FDI schemes to the three tanksystem[C].Proc.of European Control Conefrence,Karisurhe,Germany,1999
[54] Dalton,T Kremer N,Alcort-Garcia E and Frank P M.Application of fuzzyresidual analysis to the winding machine[C].Submitted to European controlconference,Karlsurhe,Germany,1999
[55] Frank,PM. Application of fuzzylogic to Process[M].1994:531-538
[56] Schneider H.,Frank,PM. Obsevrer based supervision and fault detection ofrobots[C]Proc of lnt.Conefrence on fault diagnosis,1993:773-779
[57]范庚,马登武,张继军,邓力.基于决策树和相关向量机的智能故障诊断方法[J]计算机工程与应用,2012,18,(5):9-13
[58]薛寒,谢利理,叶留义.基于模糊推理的电机故障诊断专家系统研究[J].计算机测量与控制,2010,01,:26-29
[59]鄂加强.智能故障诊断及其应用[M]湖南:湖南大学出版社2006
[60]瓦克塞万诺斯,袁海文.工程系统中的智能故障诊断与预测[M]北京:国防工业出版社,2013
[61]杨万海.多传感器数据融合及其应用[M]西安:西安电子科技大学出版社2004
[62]余翀,高翔,邱其文.基于多传感器数据融合的机器人里程计设计与实现[J]传感技术学报,2012,01,213-218
[63] HU Zhong-hui,CAI Yun-ze,LI Yuan-gui,XU Xiao-ming.Data fusion for faultdiagnosis using multi-class Support Vector Machines [J] Journal of ZhejiangUniversity Science A：Applied Physics&Engineering.2005,6(10):56-64
[64] Chen Yukun,Si Xicai,Li Zhigang.Research on Kalman-filter basedmultisensor data fusion[J]Journal of Systems Engineering and Electronics2007,18(3):231-237
[65] Zhao F, Koutsoukos X, Haussecker H, Reich J, Cheung P. Monitoring andfault diagnosis of hybrid systems[J]. IEEE Trans Syst Man Cybern BCybern.2005;35(6):1225-40.
[66]朱大奇等.应用模糊数据融合实现电子电路的故障诊断[J].小型微型计算机系统,2002,23,(5):633-635
[67] Aldenderfer M S，Blashfield R K，Cluste Analysis[M].Sage Publications,London,1984
[68]张杰,高宪军,姚劲勃,张卓.基于神经网络与专家系统的故障诊断技术[J]吉林大学学报(信息科学版),2009,03:165-168
[69] LIU Ke-ming. YANG Wei-hong. XU Guang-ming. XU Wei-guo[2] GAOLei-fu.Fuzzy Fault Diagnosis of a Diesel Engine Non-start [J].InternationalJournal of Plant Engineering and Management.2009.18,(1).142-147
[70]陈安华,蒋玲莉,刘义伦,李学军.基于知识网格的故障诊断专家系统模型[J]仪器仪表学报,2009,11,132-135
[71] Shi Zhongzhi,ZhongHan,WangJun.Applying case-based reasoning to engineoil design[J].Artifical intelligence in engineering.2006.7,(11):167-172
[72]王东,刘怀亮,徐国华.案例推理在故障诊断中的应用[J].计算机工程,2003,29,(12):10-12
[73]江志农,徐文明.基于CBR的旋转机械故障诊断专家系统的设计[J]组合机床与自动化加工技术,2011,08,66-68
[74]刘青志,周招磊,沐阿华.基于ANN的组合智能故障诊断专家系统的设计[J].计算机测量与控制,2004,12,(7):613-622
[75]路志英,赵智超,郝为,林孔元,刘还珠.基于人工神经网络的多模型综合预报方法[J].计算机应用,2004,24:50-51
[76] A.J.Gonzalez,S.Lowenfeld.On-line Diagnosis of Turbine-Generators UsingArtificial Intelligence[J].IEEE Transaction on Energy Conversion,2011,2:150-161
[77]孙红岩.大型旋转机械智能诊断多Agent系统的研究[D].重庆大学,2007,4,6-8
[78]方斌,多Agent平台下基于CBR的机车故障诊断系统研究[D]中南大学,2009,6
[79] Tsukanmto Y,Terano T.Failure diagnosis by using fuzzy logic[C].ProceedingsIEEE decision&control.NeWOrlearns.England.2003:1390-1395
[80]马岩,曹金成,黄勇,李斌.基于BP神经网络的无人机故障诊断专家系统研究[J]长春理工大学学报(自然科学版),2011,04,14-18
[81]吴明强,史慧,朱晓华,肖开清.故障诊断专家系统研究的现状与展望[J].计算机测量与控制,2005,13,(12):1301-1304
[82]宗群,李光宇,郭萌.基于故障树的电梯故障诊断专家系统设计[J]控制工程2013,02:26-31
[83] M J Pazzni.Failure Driven leaning of fault diagnosis heuristics[C].IEEE Transon systems Minand cybemetics,1998.17,(3):380-384
[84]刘有才,刘增良.模糊专家系统原理与设计[M].北京:北京航空航天大学出版社,1995
[85] ErnestJ,Friedman-Hill.Jess,The Rule Engine for the Java Platform[EB/OL].http://herzberg.ca.sandia.gov/jess.Version6.1p7(7May2004)
[86]武星星.模糊系统和ANFIS的改进及其在加工参数智能选择中的应用研究[D].吉林大学,2007,6:40-42
[87]翟东海，李力，靳蕃.基于模糊神经网络的非线性系统模型的辨识.计算机学报.2004，27(4),561-565.
[88] Wong C. C, Chen C.A hybid clustering and gradient descent approach forfuzzy modeling[C].IEEE Transactions on System, Man and Cybernetics–Part B,2008,29,(6):686-693
[89] Li Ying, Bai Ben Du, Li-Cheng. A model identification approach of nonlinearsystems based on fuzzy neural networks[J].Journal of Electronics andInformation Technology,2002.24,(3):355-360.
[90] K.P. Rajurkar, W.M. Wang, W.S. Zhao WEDM-Adaptive Control with aMultiple Input Model for Indentification of Workpiece Height CIRPAnnals-Manufacturing Technology1997,147–150
[91] H.Ishibuehi,R.Fujioka,H.Tanaka.Structure Optimization of Fuzzy NeuralNetwork by Genetic Algorithm[J].Fuzzy Sets and Systems,1995,7,(l):257-264
[92] Wooldridge Michael.多Agent系统引论[M]北京:电子工业出版社.2003,
[93]王汝传,徐小龙,黄海平.智能Agent机器在信息网络中的应用[M],北京:北京邮电大学出版社.2006,53-67
[94]杨丽君,刘建超,曹良晶,卢志刚.基于黑板模型的配电网故障恢复多代理协作机制设计[J]电力系统自动化.2012,06,21-25
[95]蒋丽娟,刘卫国.基于层次黑板模型的多Agent系统研究[J]计算机系统应用.2008,05,41-46
[96]杨斯博,基于自组织多Agent系统的智能控制与决策研究[D].天津大学2012,6
[97]耿建鲁.基于黑板系统的多智能体系实现方法的研究[D].哈尔滨工程大学,2003,3
[98]郭建.基于多Agent的智能管理信息系统研究[D].天津大学,2004,12
[99] Tore Knabe, Michael Schillo, Klaus Fischer Improvements to the FIPAContract Net Protocol for Performance Increase and Cascading Applications
[C]In International Workshop for Multi-Agent Interoperability at the GermanConference onAI (KI-2002),2002:175-182.
[100] Paurobally, S., Cunningham, J. and Jennings, N. R.Verifying the contract netprotocol: a case study in interaction protocol and agent communicationsemantics.[C]2nd International Workshop on Logic and Communication inMulti-Agent Systems, Nancy, France.2004.98-117
[101] Technical Committee of FIPA. FIPA Abstract Architecture Specification.SC00001.2002.
[102] Fabio Bellifemine, Giovanni Caire, Tiziana Trucco.JADE Program Guide
[2]孙晋美.提高磨矿分级效率,改善磨矿选别指标[J].中国科技投资,2013,20:43-46
[3]刘金琨.智能控制[M].北京:电子工业出版社,2014:11-17
[4] Zhou, P.,Chai, T.,Sun, J.Intelligence-Based Supervisory Control for OptimalOperation of a DCS-Controlled Grinding System[J] IEEE transactions oncontrol systems technology.2013,21(1):143-148
[5]薛杰.模糊自调整二自由度PID控制器及在磨矿分级中的应用[D].昆明:昆明理工大学,2002
[6]陈夕松,魏彬,王露露,李奇.模糊PID在选矿球磨浓度控制中的应用[J].工业仪表与自动化装置,2005,2:15-17
[7]马天雨,桂卫华,王雅琳,阳春华.磨矿分级过程动态优化控制[J]控制与决策2012,02,:30-34
[8]胡海波,黄友锐.基于神经网络分数阶PID控制器在磨矿分级系统中的应用研究[J].煤矿机械,2009,30(11):198-201
[9] Maksoud, T.M.A, Atia, M.R, Koura, M.M,Applications of artificial intelligenceto Grinding operations via neural networks [J].Machining Science andTechnology,2003,7,(3):361-387
[10]李娟娟,于淳,郭纲,杨东平.基于BP神经网络的球磨机浓度预测分析[J].节能.2010,8:20-22
[11] Mohanasundararaju, N. Sivasubramanian, R. Gnanaguru, R. Alagumurthy, N.A neural network and fuzzy-based methodology for the prediction of workroll surface roughness in a Grinding process[J]. International Journal ofComputational Methods in Engineering Science and Mechanics.2008,9(2):103-110
[12] Nagasaka Kazunori,Harada Naohiko, Ichihashi Hidetomo, LeonardRaymond.Adaptive learning networks of Multi-stage fuzzy production rulesin expert system of Grinding characteristics[J]. Computers and IndustrialEngineering,1994,27,(1-4):433-436
[13] Lezanski Pawe, Lajmert Pawe.An intelligent system for Grinding processcontrol and optimization[C]. Modern Trends in Manufacturing, SecondInternational CAMT Conference (Centre for Advanced ManufacturingTechnologies),2003:231-238
[14]王云峰,李战明,袁占亭,万维汉.RBF神经网络与模糊理论相结合的磨矿分级智能控制方法[J].重庆大学学报,2010,33,(3):124-128
[15]丁进良,岳恒,齐玉涛,柴天佑,郑秀萍.基于遗传算法的磨矿粒度神经网络软测量[J].仪器仪表学报,2006,27,(9):981-984
[16]景广军,梁雪梅,周贤渭,李松仁.神经网络专家系统在矿业中的应用[J].金属矿山,2001,296,(2):46-48
[17]周平,柴天佑.基于案例推理的磨矿分级系统智能设定控制[J].东北大学学报(自然科学版).2007,28,(5):613-616
[18] M. Ramasamy a, S.S. Narayanan, Ch.D.P. Rao.Control of ball mill Grindingcircuit using model predictive control scheme[J]. Journal of Process Control2005,15:273-283
[19] Arup Bhaumik,Suman Banerjee,Jaya Sil.Designing of intelligent expertcontrol system using petri net for Grinding mill operation[J] World Scientificand Engineering Academy and Society,2005:147-150
[20] Marvin Minsky.Society Of Mind[D]. Simon&Schuster1988;18-25
[21] M Wooldridge.Intellgent Agents:Theory and Practice[J].Knowledgeengineering Review,1995,10(2):115-152
[22] D M Lane, A G Mcfadzean. Distributed problem solving and real-timemechanisms in robot architectures[J].Engineering Application Intelligence,1994,7,(2):105-117.
[23] N R Jennings，L Z Vagar,R P Aarnts et al.Transforming standalone expertsystem into a community of cooperating Agents[J].Engineerin ApplicationArtificial Intelligence,1993,6,(4):317-331
[24] F Polat,S Shekhar,H A Guvenir.Distributed conflict resolution amongcooperating expert systems[J].Expert Systems,1993,10,(4):227-236
[25]卿小霞.基于Multi-Agent的分布式污水处理智能化系统研究[D].重庆大学,2007
[26]王海东.水泥生产过程多Agent控制系统的研究[D].中南大学,2004
[27] V Sahasrabudhe.A Multi-Agent control system framework for smartstructures[C].AIAA,USA,1998,4202-4215
[28] Draa B C,Millot P.A Framework for cooperative work:An approach based onthe intentionality[J].Artificial Intelligence in Engineering,1990,5,(4):199-205
[29] Russell S J，Subramanian D，Parr R.Provably boundd optimal Agents[C].InIJCAII eds.Proceeding of the13thInternational Joint Conference on ArtificialIntelligence.Chambery:Morgan Kaufmann Publ Inc,1993.338-343
[30] Wang H,Wang C.APACS:A Multi-Agent system with respositorysupport[J].Knowledge-based System,1996,9,(3):329-337
[31]王鲁,王志良,杨溢.一种多agent系统框架与协商机制研究[J]计算机应用研究.2012,03:253-256
[32]刘金琨,尔联洁.多智能体技术应用综述[J].控制与决策,2001,16,(2),133-140
[33]闫博.半导体生产线调度的多智能体建模方法研究[D].同济大学,2007
[34]王鹏,罗军舟,李伟,卞正皑,曲延盛.可控网络中多Agent系统信念可达性和收敛速度分析[J]软件学报,2010,04,78-83
[35] N M Avouris.Cooperating knowledge-based systems for environmentaldecision suppot[J].Knowledge-based System，1995,8,(1):39-54
[36]孙喁喁,刘萍萍基于黑板的多Agent智能决策支持系统的Agent实现[J].电子设计工程,2009,17,(2):22-24
[37] G Hartvigsen, D Johansen. Cooperation in a distributed artificial intelligenceenvironment-The stormcast application[J]. Engineering Application ofArtificial Intelligence,1990,3(3):229-237.
[38]晁进,刘文颖.基于多智能体和专家系统的电网智能报警系统研究[J].现代电力,2010,27,(5):1-5
[39] Lambert M Surhone, Mariam T Tennoe, Susan F Henssonow. Agent orientedprogramming[M] Betascript Publishing.2010,12,12-18
[40]吴海宝.磨矿分级控制算法研究[J]昆明理工大学,2007,11
[41]段希祥.碎矿与磨矿[M].北京:冶金工业出版社,2012,46-50
[42]许时.矿石可选性研究[M].北京:冶金工业出版社,2007,87-95
[43]周金华,张静.多传感器数据融合技术在电厂状态监测和故障诊断中的应用[J]煤矿机械2011,11:27-34
[44]张碧波.设备状态监测与故障诊断[M].北京:化学工业出版社,2011
[45]栾家辉,王立梅,刘红梅.故障诊断与预测:原理,技术及应用[M].北京:北京航空航天大学出版社,2012
[46]扶晓,刘劲,张明慧.多Agent信息融合的故障诊断研究[J]电脑知识与技术.2010,11,145-153
[47]杨小强,姜海宝,蒋国良,邓伟,高亚明.基于多传感器数据融合的液压泵故障诊断[J]机械制造,2010,01:56-63
[48]李伟.复杂系统的智能故障诊断技术现状及其发展趋势[J].计算机仿真,2004,10:4-11
[49]吴斌,于春梅,李强.过程工业故障诊断[M].北京:科学出版社,2012
[50] George Vachtsevanos, Frank L.Lewis, Michael Roemer, Andrew Hess.Intellgent Fault Diagnosis and Prognosis for Engineering Systems[M]北京:国防工业出版社,2013
[51] Kassidas A,P.A.Talyor and J.F.MacGreger. Off-line diagnosis of deterministicfaults in continuous dynamic Multi variable Process using Speechrecognition methods[J].Process Control,1998,8,(5-6):351-393
[52] Rehbein D.Expert system in Process Control[J].ISATrans,1992,31,(2):49-55
[53] Ding S X and Jeinsch T.Application of observer FDI schemes to the three tanksystem[C].Proc.of European Control Conefrence,Karisurhe,Germany,1999
[54] Dalton,T Kremer N,Alcort-Garcia E and Frank P M.Application of fuzzyresidual analysis to the winding machine[C].Submitted to European controlconference,Karlsurhe,Germany,1999
[55] Frank,PM. Application of fuzzylogic to Process[M].1994:531-538
[56] Schneider H.,Frank,PM. Obsevrer based supervision and fault detection ofrobots[C]Proc of lnt.Conefrence on fault diagnosis,1993:773-779
[57]范庚,马登武,张继军,邓力.基于决策树和相关向量机的智能故障诊断方法[J]计算机工程与应用,2012,18,(5):9-13
[58]薛寒,谢利理,叶留义.基于模糊推理的电机故障诊断专家系统研究[J].计算机测量与控制,2010,01,:26-29
[59]鄂加强.智能故障诊断及其应用[M]湖南:湖南大学出版社2006
[60]瓦克塞万诺斯,袁海文.工程系统中的智能故障诊断与预测[M]北京:国防工业出版社,2013
[61]杨万海.多传感器数据融合及其应用[M]西安:西安电子科技大学出版社2004
[62]余翀,高翔,邱其文.基于多传感器数据融合的机器人里程计设计与实现[J]传感技术学报,2012,01,213-218
[63] HU Zhong-hui,CAI Yun-ze,LI Yuan-gui,XU Xiao-ming.Data fusion for faultdiagnosis using multi-class Support Vector Machines [J] Journal of ZhejiangUniversity Science A：Applied Physics&Engineering.2005,6(10):56-64
[64] Chen Yukun,Si Xicai,Li Zhigang.Research on Kalman-filter basedmultisensor data fusion[J]Journal of Systems Engineering and Electronics2007,18(3):231-237
[65] Zhao F, Koutsoukos X, Haussecker H, Reich J, Cheung P. Monitoring andfault diagnosis of hybrid systems[J]. IEEE Trans Syst Man Cybern BCybern.2005;35(6):1225-40.
[66]朱大奇等.应用模糊数据融合实现电子电路的故障诊断[J].小型微型计算机系统,2002,23,(5):633-635
[67] Aldenderfer M S，Blashfield R K，Cluste Analysis[M].Sage Publications,London,1984
[68]张杰,高宪军,姚劲勃,张卓.基于神经网络与专家系统的故障诊断技术[J]吉林大学学报(信息科学版),2009,03:165-168
[69] LIU Ke-ming. YANG Wei-hong. XU Guang-ming. XU Wei-guo[2] GAOLei-fu.Fuzzy Fault Diagnosis of a Diesel Engine Non-start [J].InternationalJournal of Plant Engineering and Management.2009.18,(1).142-147
[70]陈安华,蒋玲莉,刘义伦,李学军.基于知识网格的故障诊断专家系统模型[J]仪器仪表学报,2009,11,132-135
[71] Shi Zhongzhi,ZhongHan,WangJun.Applying case-based reasoning to engineoil design[J].Artifical intelligence in engineering.2006.7,(11):167-172
[72]王东,刘怀亮,徐国华.案例推理在故障诊断中的应用[J].计算机工程,2003,29,(12):10-12
[73]江志农,徐文明.基于CBR的旋转机械故障诊断专家系统的设计[J]组合机床与自动化加工技术,2011,08,66-68
[74]刘青志,周招磊,沐阿华.基于ANN的组合智能故障诊断专家系统的设计[J].计算机测量与控制,2004,12,(7):613-622
[75]路志英,赵智超,郝为,林孔元,刘还珠.基于人工神经网络的多模型综合预报方法[J].计算机应用,2004,24:50-51
[76] A.J.Gonzalez,S.Lowenfeld.On-line Diagnosis of Turbine-Generators UsingArtificial Intelligence[J].IEEE Transaction on Energy Conversion,2011,2:150-161
[77]孙红岩.大型旋转机械智能诊断多Agent系统的研究[D].重庆大学,2007,4,6-8
[78]方斌,多Agent平台下基于CBR的机车故障诊断系统研究[D]中南大学,2009,6
[79] Tsukanmto Y,Terano T.Failure diagnosis by using fuzzy logic[C].ProceedingsIEEE decision&control.NeWOrlearns.England.2003:1390-1395
[80]马岩,曹金成,黄勇,李斌.基于BP神经网络的无人机故障诊断专家系统研究[J]长春理工大学学报(自然科学版),2011,04,14-18
[81]吴明强,史慧,朱晓华,肖开清.故障诊断专家系统研究的现状与展望[J].计算机测量与控制,2005,13,(12):1301-1304
[82]宗群,李光宇,郭萌.基于故障树的电梯故障诊断专家系统设计[J]控制工程2013,02:26-31
[83] M J Pazzni.Failure Driven leaning of fault diagnosis heuristics[C].IEEE Transon systems Minand cybemetics,1998.17,(3):380-384
[84]刘有才,刘增良.模糊专家系统原理与设计[M].北京:北京航空航天大学出版社,1995
[85] ErnestJ,Friedman-Hill.Jess,The Rule Engine for the Java Platform[EB/OL].http://herzberg.ca.sandia.gov/jess.Version6.1p7(7May2004)
[86]武星星.模糊系统和ANFIS的改进及其在加工参数智能选择中的应用研究[D].吉林大学,2007,6:40-42
[87]翟东海，李力，靳蕃.基于模糊神经网络的非线性系统模型的辨识.计算机学报.2004，27(4),561-565.
[88] Wong C. C, Chen C.A hybid clustering and gradient descent approach forfuzzy modeling[C].IEEE Transactions on System, Man and Cybernetics–Part B,2008,29,(6):686-693
[89] Li Ying, Bai Ben Du, Li-Cheng. A model identification approach of nonlinearsystems based on fuzzy neural networks[J].Journal of Electronics andInformation Technology,2002.24,(3):355-360.
[90] K.P. Rajurkar, W.M. Wang, W.S. Zhao WEDM-Adaptive Control with aMultiple Input Model for Indentification of Workpiece Height CIRPAnnals-Manufacturing Technology1997,147–150
[91] H.Ishibuehi,R.Fujioka,H.Tanaka.Structure Optimization of Fuzzy NeuralNetwork by Genetic Algorithm[J].Fuzzy Sets and Systems,1995,7,(l):257-264
[92] Wooldridge Michael.多Agent系统引论[M]北京:电子工业出版社.2003,
[93]王汝传,徐小龙,黄海平.智能Agent机器在信息网络中的应用[M],北京:北京邮电大学出版社.2006,53-67
[94]杨丽君,刘建超,曹良晶,卢志刚.基于黑板模型的配电网故障恢复多代理协作机制设计[J]电力系统自动化.2012,06,21-25
[95]蒋丽娟,刘卫国.基于层次黑板模型的多Agent系统研究[J]计算机系统应用.2008,05,41-46
[96]杨斯博,基于自组织多Agent系统的智能控制与决策研究[D].天津大学2012,6
[97]耿建鲁.基于黑板系统的多智能体系实现方法的研究[D].哈尔滨工程大学,2003,3
[98]郭建.基于多Agent的智能管理信息系统研究[D].天津大学,2004,12
[99] Tore Knabe, Michael Schillo, Klaus Fischer Improvements to the FIPAContract Net Protocol for Performance Increase and Cascading Applications
[C]In International Workshop for Multi-Agent Interoperability at the GermanConference onAI (KI-2002),2002:175-182.
[100] Paurobally, S., Cunningham, J. and Jennings, N. R.Verifying the contract netprotocol: a case study in interaction protocol and agent communicationsemantics.[C]2nd International Workshop on Logic and Communication inMulti-Agent Systems, Nancy, France.2004.98-117
[101] Technical Committee of FIPA. FIPA Abstract Architecture Specification.SC00001.2002.
[102] Fabio Bellifemine, Giovanni Caire, Tiziana Trucco.JADE Program Guide