面向多智能体和神经网络的智能控制研究
|
摘要
在智能控制领域，智能信息集成技术和智能控制算法是构成智能控制系统的两大核心技术。本论文正是从面向多智能体的信息集成和面向神经网络的控制算法两个不同的角度，展开对智能控制和智能系统的研究。通过面向多智能体的研究，提供了一种理论方法与体系结构，用于分布式智能控制系统的信息集成。而通过对神经网络的结构和学习算法的研究，结合模糊逻辑、进化计算和随机优化等方法，探讨了智能控制中的重要的分支——神经网络控制的有关理论与技术。
本论文的第一章为绪论，对智能控制、神经网络、分布式人工智能和多智能体的发展和研究概况进行了回顾和讨论，提出了本文的研究路线。
第二章的研究对象为多层前向神经网络。主要研究前向神经网络的权值学习和结构学习方法。介绍了神经网络原理和遗传BP算法。提出了样本划分启发式遗传BP算法和复合结构学习方法(CSL)，并进行了仿真实验。
第三章研究对象为递归神经网络。主要研究递归神经网络原理、结构及其学习算法。探讨了几种全局递归和局部递归神经网络的结构原理和学习算法。在模拟迟火及Alopex算法基础上，提出了用于一般递归神经网络的基于模糊逻辑的Alopex学习算法(FLA)，给出了仿真实验。在局部递归神经网络结构方面，提出了一种递归神经网络结构——自环对角递归神经网络结构(SDRNN)，给出了相应的学习算法，证明了算法的收敛性，并进行了仿真实验。
第四章研究基于神经网络的辨识和控制。在分析了神经网络控制的一些关键技术基础上，提出了预去模糊FAM原理和FAM神经控制器，给出了预去模糊FAM和一般FAM的等价性的构造性证明。提出了基于第三章提出的SDRNN的递归神经网络控制结构和实现方法，证明了算法的收敛性。分别以小车倒立摆系统和non-BIBO动态对象为控制对象对两种方法进行了仿真实验。
第五章研究分布式人工智能、智能体和多智能体的理论基础。侧重研究智能体的精神状态及其形式表示方法。首先分析探讨了智能体的基本概念、基本观点、结构分类、研究内容和应用领域。研究了智能体的精神(心智)状态的几种形式化表示。在已有的形式模型基础上，提出了多智能体系统的形式模型MASCL，该模型是一种多类的一阶分支时序模态逻辑BDI理论，综合了单智能体和多智能体的精神状态和动作规划表示，并体现了社会规范的约束作用。以MASCL为基础，定义了多智能体的协作过程的协作承诺等相关概念，提出了协作承诺的形式化模型。
第六章研究智能体和多智能体的体系结构、求解过程、实现技术及其在工业过程控制中的应用。首先探讨了基于多智能体的分布式智能控制在工业控制应用中的意义和特点。以第五章提出的MASCL模型为基础，提出了一种智能体的概念模型，设计了相应的智能体体系结构和智能体的求解过程，并
文敦伟：面向多宫能体和神经冈络的了能控饲研究
以面向对象的代码形式给出了智能体信息与行为的描述。以烧结过程为对象，提出了多智能体建模与
控制的框架。开发了一套用于智能控制和多智能体研究测试的实验系统，进行了实验演示。
第七章对全文进行了总结，指出了今后进一步研究的方向。
In the field of intelligent control, there are two kinds of core technology: intelligent information integration and intelligent control algorithms, which construct intelligent control systems. Multi-agent oriented intelligent information integration and neural network oriented control algorithms are studied in this paper. On the one hand, theory methods and architecture are proposed for integration of information in distributed intelligent control systems. On the other hand, by combining fuzzy logic, evolutionary computation and stochastic optimal methods, structure and learning algorithms of neural networks are studied for neural control, which is one of the important branches of intelligent control.
Chapter 1, based on a survey on intelligent control, neural networks, distributed artificial intelligence and multi-agent systems, presents the study tasks of this paper.
Chapter 2 focuses on weight learning and structure learning of multi-layer feed-forward neural networks. The genetic BP algorithm are discussed. Then two novel algorithms, samples division based heuristic genetic BP and composition structure learning, are proposed. Simulations are performed respectively.
Chapter 3 studies structure and learning algorithms of recurrent neural networks. Based on simulated annealing and alopex learning, a novel leaning algorithm, fuzzy logic alopex learning (FLA), is proposed and simulated.
A new recurrent neural network structure, self-feedback diagonal recurrent neural networks (SDRNN), is also designed in this chapter. The learning algorithm of SDRNN is given and the convergence of this algorithm is proved. The simulation results show the validation of the structure and the learning algorithm.
Chapter 4 deals with neural network based identification and control. After the analysis of several important aspects of neural control, two novel neural controllers are then proposed. The first controller FAM neural controller (FAMNC), based on Pre-defuzzifing FAM, is presented for bridging the gap between FAM and NN. The equivalence of pre-defuzzifing and general FAM is proved constructively. The simulation research on inverted pendulum control is performed. The simulation results show that the FAMNC is sound. The second controller is SDRNN based neural controller. The control architecture is given and the convergence of the control algorithm is proven. The simulation research on a non-BIBO dynamic plant control is performed. The simulation results show the availability of this controller.
Chapter 5 turns to distributed artificial intelligence, intelligent agent and multi-agent. First, the concepts, structure categories, research content and application of intelligent agent are introduced. Several formulation of mental states of intelligent agent are discussed. Second, based on former logic theories, a improved formal model, MASCL, is proposed in this chapter. MASCL is a many-sorted first-order branching-time BDI logic, which can capture the requirements for representation mental states, acts, plans and social laws of multi-agent systems. With the use of MASCL, the concept of cooperation commitment of cooperation process in multi-agent systems is defined, and the formal model of cooperation commitment is proposed.
Chapter 6 researches into the architecture, solving process and implementation of intelligent agent and
multi-agent systems, and the application to industry process control. First, the significance and characteristics of the application of multi-agent based distributed intelligent control to industry control are discussed. Second, a concept model of intelligent agent is proposed, the architecture and solving process are designed and the information and acts of intelligent agent are described by object-oriented code. Third, a multi-agent modeling and controlling framework are designed for agglomeration process. An experiment system is developed for intelligent control and multi-agent systems studies, and tests are performed on this system.
The conclusions of this paper are drawn and the futur
本论文的第一章为绪论，对智能控制、神经网络、分布式人工智能和多智能体的发展和研究概况进行了回顾和讨论，提出了本文的研究路线。
第二章的研究对象为多层前向神经网络。主要研究前向神经网络的权值学习和结构学习方法。介绍了神经网络原理和遗传BP算法。提出了样本划分启发式遗传BP算法和复合结构学习方法(CSL)，并进行了仿真实验。
第三章研究对象为递归神经网络。主要研究递归神经网络原理、结构及其学习算法。探讨了几种全局递归和局部递归神经网络的结构原理和学习算法。在模拟迟火及Alopex算法基础上，提出了用于一般递归神经网络的基于模糊逻辑的Alopex学习算法(FLA)，给出了仿真实验。在局部递归神经网络结构方面，提出了一种递归神经网络结构——自环对角递归神经网络结构(SDRNN)，给出了相应的学习算法，证明了算法的收敛性，并进行了仿真实验。
第四章研究基于神经网络的辨识和控制。在分析了神经网络控制的一些关键技术基础上，提出了预去模糊FAM原理和FAM神经控制器，给出了预去模糊FAM和一般FAM的等价性的构造性证明。提出了基于第三章提出的SDRNN的递归神经网络控制结构和实现方法，证明了算法的收敛性。分别以小车倒立摆系统和non-BIBO动态对象为控制对象对两种方法进行了仿真实验。
第五章研究分布式人工智能、智能体和多智能体的理论基础。侧重研究智能体的精神状态及其形式表示方法。首先分析探讨了智能体的基本概念、基本观点、结构分类、研究内容和应用领域。研究了智能体的精神(心智)状态的几种形式化表示。在已有的形式模型基础上，提出了多智能体系统的形式模型MASCL，该模型是一种多类的一阶分支时序模态逻辑BDI理论，综合了单智能体和多智能体的精神状态和动作规划表示，并体现了社会规范的约束作用。以MASCL为基础，定义了多智能体的协作过程的协作承诺等相关概念，提出了协作承诺的形式化模型。
第六章研究智能体和多智能体的体系结构、求解过程、实现技术及其在工业过程控制中的应用。首先探讨了基于多智能体的分布式智能控制在工业控制应用中的意义和特点。以第五章提出的MASCL模型为基础，提出了一种智能体的概念模型，设计了相应的智能体体系结构和智能体的求解过程，并
文敦伟：面向多宫能体和神经冈络的了能控饲研究
以面向对象的代码形式给出了智能体信息与行为的描述。以烧结过程为对象，提出了多智能体建模与
控制的框架。开发了一套用于智能控制和多智能体研究测试的实验系统，进行了实验演示。
第七章对全文进行了总结，指出了今后进一步研究的方向。
In the field of intelligent control, there are two kinds of core technology: intelligent information integration and intelligent control algorithms, which construct intelligent control systems. Multi-agent oriented intelligent information integration and neural network oriented control algorithms are studied in this paper. On the one hand, theory methods and architecture are proposed for integration of information in distributed intelligent control systems. On the other hand, by combining fuzzy logic, evolutionary computation and stochastic optimal methods, structure and learning algorithms of neural networks are studied for neural control, which is one of the important branches of intelligent control.
Chapter 1, based on a survey on intelligent control, neural networks, distributed artificial intelligence and multi-agent systems, presents the study tasks of this paper.
Chapter 2 focuses on weight learning and structure learning of multi-layer feed-forward neural networks. The genetic BP algorithm are discussed. Then two novel algorithms, samples division based heuristic genetic BP and composition structure learning, are proposed. Simulations are performed respectively.
Chapter 3 studies structure and learning algorithms of recurrent neural networks. Based on simulated annealing and alopex learning, a novel leaning algorithm, fuzzy logic alopex learning (FLA), is proposed and simulated.
A new recurrent neural network structure, self-feedback diagonal recurrent neural networks (SDRNN), is also designed in this chapter. The learning algorithm of SDRNN is given and the convergence of this algorithm is proved. The simulation results show the validation of the structure and the learning algorithm.
Chapter 4 deals with neural network based identification and control. After the analysis of several important aspects of neural control, two novel neural controllers are then proposed. The first controller FAM neural controller (FAMNC), based on Pre-defuzzifing FAM, is presented for bridging the gap between FAM and NN. The equivalence of pre-defuzzifing and general FAM is proved constructively. The simulation research on inverted pendulum control is performed. The simulation results show that the FAMNC is sound. The second controller is SDRNN based neural controller. The control architecture is given and the convergence of the control algorithm is proven. The simulation research on a non-BIBO dynamic plant control is performed. The simulation results show the availability of this controller.
Chapter 5 turns to distributed artificial intelligence, intelligent agent and multi-agent. First, the concepts, structure categories, research content and application of intelligent agent are introduced. Several formulation of mental states of intelligent agent are discussed. Second, based on former logic theories, a improved formal model, MASCL, is proposed in this chapter. MASCL is a many-sorted first-order branching-time BDI logic, which can capture the requirements for representation mental states, acts, plans and social laws of multi-agent systems. With the use of MASCL, the concept of cooperation commitment of cooperation process in multi-agent systems is defined, and the formal model of cooperation commitment is proposed.
Chapter 6 researches into the architecture, solving process and implementation of intelligent agent and
multi-agent systems, and the application to industry process control. First, the significance and characteristics of the application of multi-agent based distributed intelligent control to industry control are discussed. Second, a concept model of intelligent agent is proposed, the architecture and solving process are designed and the information and acts of intelligent agent are described by object-oriented code. Third, a multi-agent modeling and controlling framework are designed for agglomeration process. An experiment system is developed for intelligent control and multi-agent systems studies, and tests are performed on this system.
The conclusions of this paper are drawn and the futur
引文
1 Abe S., Lan M-S. Fuzzy rules extraction directly from numerical date for function approximation. IEEE Trans. On SMC, 1995,25(1) :119-129
2 Ahmed M S. Block partial derivative and its application to neural-net-based direct-model-reference adaptive control. IEE Proc.-Control Theory Appl, 1994,141(5) :305-314
3 Ahmed M S. Neural-net controller for nolinear plants: design approach through linearisation. IEE Proc. Control Theory Appl, 1994,141(5) :315-322
4 Angeline P J, et al. An evolutionary algorithm that constructs recurrent neural network. IEEE Trans. On NN, 1994,5(1) :54-65
5 Astrom K J, Auton J J, Arzen K E. Expert control. Automatica, 1986,22(3) :277-286
6 Astrom K J. Intelligent Control. ECC91 ,P2328-2339, Grenoble, France, 1991
7 Austaklis P J. Intelligent Learning Control. IEEE Control systems, 1995,15(3) :5-8
8 Autsaklis P J. Defining intelligent control. IEEE control systems, 1994,14(3) :4-5,58-66
9 Bartlett E B. Dynamic node architecture learning: an information theoretic approach. Neural Networks, 1994,7(1) :129-140
10 Batro A G.et al. Neuronlike adaptive element that can solve difficult learning control problems. IEEE Trans. On SMC, 1983,13(5) :834-846
11 Bratman M E. Intentions, plans, and practical reason. Harvard University Press: Cambridge, MA, 1987
12 Cai Zixing. Intelligent Control: Principles, Techniques and Applications. Singapore: World Scientific, 1997
13 Catfolis T. A method for improving the red-time recurrent learning algorithm. Neural Networks, 1993,6:807-821
14 Chen C L. Hybrid learning alorithm for Gaussian potential function networks. IEE Proc.-D, 1993,140(6) :442-448
15 Chen D, etal. Constructive learning of recurrent neural networks. IEEE Int. Conf. On Neural Networks, 1993,3:1196-1201
16 Chen F C, et al. Adaptively controlling nonlinear continuous time system using multilayer neural networks. IEEE Trans. On AC, 1994,39(6) :1306-1310
17 Chen J Q, Lu L J. Analysis and syntesis of fuzzy closed-loop control systems. IEEE Trans. On SMC, 1995,25(5) :881-888
18 Chen S. et al. Paralled recursive prediction error algorothm for trovining layered neural networks. Int J. Control, 1990,5(6) :1215-1228
19 Chorafas D N. Agent technology handbook. McGraw-Hill Book Co., 1998
20 Chung E L, Lee T. Network-growth approach to design of feed-forward networks. IEE Proc.-Control Theory Appl, 1995,142(5) :486-492
21 Cohen M A, Grossberg S. Abosolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Trans. SMC, 1983,13(5) :815-826
22 Cohen P R, Levesque H J. Intention is choice with commitment Artificial Intelligence, 1990,42:213-261
23 Cohen PR, Levesque HJ. Teamwork. Nous 1991,25:487-512
24 Cybenko G. Approximation by superpositions of a Sigmoidal function. Math. Of Control, signals, systems, 1989,2(4) :303-314
25 Delgado A, et al. Dynamic recurrent networks for system identification and control. IEE Proc.-control Theory Appl, 1995,142(4) :307-314
26 Dirion J L, et al. Design of a neural controller by inverse modelling. Computers.Chem. Engng, 1995,19(supple): 5797-5802
27 Elman J L. Find structure in time. Cognitive Science, 1990,14(2) : 179-211
28 Enab Y M. Intelligent controller design for the ship steering problem. IEE: Proc. Control Theory Appl,
29 Etxebarria V. Adaptive control of discrete systems using neural networks. IEE Proc. Control Theory Appl., 1994,141(4) :209-215
30 Fabri S, Kadirkamanathan V. Dynamic structure neural networks for stable adaptive control of nonlinear systems. IEEE Trans. On Neural Networks, 1996,7(5) :1151-1167
31 Fagin R, Halpern J Y, Vardi M Y. What can machines know? on the Properties of Knowledge in Distributed Systems. Journal of the ACM, 1992,39(2) :328-376
32 Ferguson I A. Touring Machines: an architecture for dynamic rational mobile agent. Ph.D. Thesis, Computer Lab. University of Cambridge, UK, 1992
33 Finin T, Fritzson R, etal. KQML as an agent communication language. The proceedings of the Third International Conference on Information and Knowledge Management (CIKM'94) , ACM Press, 1994, November
34 Fogel G B, Fogel D B. Continuous evolution programming: analyses and experiments. Cybern. Syst, 1995,26:79-90
35 Fu K S, Walts M A. A heuristic approach to reinforcement learning control system. IEEE Trans. AC, 1965,10(4) :390-398
36 Fu K S. Learning control systems and intelligent control systems: An intersection of artificial intelligent control. IEEE Trans. AC, 1971,16(1) :70-72
37 Fu L M. Rule generation from neural networks. IEEE Trans. On SMC, 1994,24(8) :1114-1124
38 Gallent S I. Connectiouist expert systems. Commu. Of the ACM, 1998,31(2) : 152-169
39 Giles C L, et al. Dynamic recurrent networks: theory and application. IEEE Trans on NN, 1994,5(2) : 153-155
40 Girosi F, Poggio T. Network and the best approximation property. Biological Cybernetics, 1990,63(3) : 169-176
41 Goldberg D E. Genetic algorithms in search, optimization and machine learning. Mass: Addision-Wesley, 1989
42 Handelman D A, et al. Integrating neural networks and knowledge-based systems for intelligent robotic control. IEEE Control System Magazine, 1990,4,76-87
43 Happel B L M, Murre J M J. Design and evolution of modular neural network architectures. Neural Networks, 1994,7(617) :985-1004
44 Harth E, Tzanakou E. Alopex: A stochastic method for determing visual receptive fields. Vision Res. 1974:14(10) 1475-1482
45 Hewitt C. Open information systems semantics for distributed artificial intelligence. Artificial Intelligence, 1991,47:79-106
46 Honik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Networks, 1989,2(3) :359-336
47 Honik K. Capabilities of Multilayer Feedforward Networks. Neural networks, 1992,4(2) :251-257
48 Hopfield J J. Neural networks and physical systems with emergent collective computational abilities. Proc.of the national academy of sciences, 1982,79(8) :2554-2558
49 Hopfield J J. Neurons with graded response have collective computational abilities. Proc. Of the National Academy of Sciences, 1984,81(10) :3088-3092
50 Houck C R, Joines J A, Kay M G. A genetic algorithm for function optimization: a matlab implementation. ACM Transactions on Mathmatical Software, Submitted. 1996
51 Hsin H-C et al. An adaptive training algorithm for back-propagation neural networks. IEEE. Trans. SMC, 1995,25(3) :512-514
52 Huang Y L, Fan L T. Artificial intelligence for waste minimization in the process industry. Computers in industry, 1992
53 Hunt K J, etal. Neural networks for control systems-A survey. Automatica, 1992． 28(5) : 1083-1112
54 Hunt K J, Sbarbane D. Neural networks for nonlinear internal model control. IEE Proc.-D, 1991,138(5) :431-438
55 Hunt K J. Neural networks for control systems-A survey . Automatica, 1992,28(6) : 1083-1112
56 Ishikawa M. Structural learning with forgetting. Neural Networks, 1996,9(3) :509-521
57 Jang J-S R. AVFIS: adaptive-network-based fuzzy inference system. IEEE Trans. SMC, 1993,23(3) :665-654
58 Jennings N R. Controlling cooperative problem solving in industrial multi-agent systems using joint intentions. Artificial Intelligence, 1995,75:195-240
59 Jennings N R. Controlling cooperative problem solving in industrial multi-agent systems using joint intentions. Artificial Intelligence, 1995,75:195-240
60 Jennings N R. On being responsible, in Decentralized AI 3-Proceedings of the Third European Workshop on Modeling Autonomous Agents in a Multi-Agent World(MAAMAW-91) , pp93-102, Elsevier Science Publishers B. V. Amsterdam, The Netherlands, 1992
61 Jennings N R-Specification and implementation of a belief-desire-joint-intention architecture for collaborative problem solving. International Journal of Intelligent and Cooperative Information Systems, 1993,2(3) :289-318
62 Jennings N R. Towards a cooperation knowledge level for collaborative problem solving. Proc. 10th European Conference on Artificial Intelligence(ECAI'92) , Vienna, Austria, 1992, August
63 Jin L, et al. Absolute stability condition for discrete-time recurrent neural network. IEEE Trans. NN, 1994,5(6) :954-963
64 Johannsen G. Integrated automation in complex man-machine systems. ECC'91, Grenoble, France, P1013-1021, 1991
65 Karnin E D. A simple procedure for pruning back-propagation trained neural networks. IEEE Trans. On NN, 1990,1(2) :239-242
66 Kendra S J, et al. Intelligent process control with supervisory knowledge-based systems. IEEE control system, 1994
67 Kim Y H, Lewis F L, Abdallah C T. A dynamic recurrent neural-network-based adaptive observer for a class of nonlinear systems. Automatica. 1997． 33(8) : 1539-1543
68 Konolige K. A deduction model of belief. Pitman Publishing: London and Morgan Kaufman: San Mateo, CA, 1986
69 Kosko B. Neural networks and fuzzy systems. NJ-Prentice-Hall, 1992
70 Ku C.-C, Lee K Y. Diagonal recurrent neural networks for dynamic systems control. IEEE Trans. On Neural Networks, 1995,6(1) :144-155
71 Levesque H J, Cohen P R, Nunes J H. On acting together, in Proceedings AAAI-90, Boston, MA( 1990) :94-99 1990
72 Levin A U, Narendra K S. Control of nonlinear dynamical systems using neural networks-part2: observability, identification, and control. IEEE Trans. On Neural Networks, 1996,7( 1 ):30-42
73 Li Q, et al. Developing a neurocompensator for the adaptive control of robots. IEE Proc.-Control Theory Appl, 1995,142(6) :562-568
74 Lightbody G, Inrin G W. Direct neural model reference adaptive control. IEE Proc.-Control Theory Appl, l995,142(1) :31-43
75 Ling K-V, Dexter AL. Expert control of Air-Conditioning plant. Automatica, 1994,30(5) :761-773
76 Linkens D A, Nie J. Back-propagation neural-network based fuzzy controller with a self-learning teacher. Int. J. Control, 1994,60(1) : 17-39
77 Maeda Y, Figueiredo R J P. Learning rules for neuro-controller via simultaneous perturbation. IEEE Trans, on Neural Networks, 1997,8(5) . 1119-1130
78 Mills P M, et al. Adaptive model-based control using neural network. Int. J. Control, 1994,60(6) :1163-1192
79 Mueller J P. The design of intelligent agents: a layered approach. Springer-Verlag, 1996
80 Musliner C J, Durfee E H, Shin K G. CIRCA: A cooperative intelligent real-time control architecture. IEEE Trans. On SMC, 1993,23(6) :1561-1573
81 Nabhan T M, et al. Toward generating neural network structures for function approximation. Neural Networks, 1994,7(1) :89-99
82 Nagano T, et al. A neural network model for the developmental process of hypercomplex cells. IEEEE Trans. SMC, 1983:113(5) :847-851
83 Narendra K S, et al. Adaption and Learning using multiple nodes, swithing and turning. IEE Control System, 1995,Jane, 37-51
84 Narendra K S. Identification and control for dynamic systems using neural networks. IEEE Trans. On Neural Networks, 1990,1(1) :4-27
85 Nie J, Linkens D A. Fast self-learning multivariable fuzzy controllers constructed from a modified CPN networks. Int. J. Control, 1994,60(3) :369-393
86 Nie J. Constructing Fuzzy model by self-organizing counter propagation network. IEEE Trans. SMC, 1995,25(6) :963-970
87 Nwana H S. Software agent: an overview. Knowledge Engineering Review, 1996,11(3) :205-244
88 Obradovic D. On-line training of recurrent neural networks with continuous topology adaptation. IEEE Trans. On Neural Networks, 1996,7(1) :222-228
89 Ollero A, et al. Design of rule-based expert controllers. ECC91 .PP578-583, Grenoble, France, 1991
90 Omlin C W, et al. Extraction of rules from discrete-time recurrent neural networks. Neural Networks, 1996,9(4) :41-52
91 Ozart B. Chemical plant fault diagnosis through a hybrid symbolic-connectionist approach and comparison with neural networks. Computers. Chem Engng, 1995,19(sup): s753-s758
92 Park D, et al. Genetic-Based new fuzzy reasoning models with application to fuzzy control. IEEE Trans, SMC, 1994,24(1) :39-47
93 Parunak H V D. Distributed AI and manufacturing control: some issue and insights. Proc. First European Workshop on Modeling an Autonomouse Agent in a Multi-Agent Worlds, 1989
94 Pedrycz W. Distributed fuzzy system modeling. IEEE Trans SMC, 1995,25(5) :769-780
95 Pham D T, Lin X. Training of elman networks and dynamic system modeling. Int. J. Of Systems Science, 1996,27(2) :221-226
96 Prokhorov D V, et al. Adaptive Critic Designs: A case study for neurocontrol. Neural Network, 1995,8(9) :1367-1372
97 Rao A S, Georgeff M P, Sonenberg E A. Social plans: A preliminary report, in E. Werner and Y. Demazeau, editors, Decentralized AI 3-Proceedings of the Third European Workshop on Modeling Autonomous Agents in a Multi-Agent World(MAAMAW-91) . Pp57-76, Elsevier Science Publishers, B. V. Amsterdam, The Netherlands, 1992
98 Rao A S, Georgeff M P. BDI Agents: from theory to practice. Tech. Note 5, Australian Artificial Intelligence Institute, 1995
99 Rao A S, Georgeff M P. Formal models and decision procedures for multi-agent systems. Tech. Note 61, Australian AI Institute, Level 6, 171 LaTrobe Street, Melbourne, Australia, 1995, June
100 Rao A S, Georgeff M P. Modeling rational agents with in a BDI-architecture. Tech. Note 14, Australian Artificial Intelligence Institute, 1991
101 Rao A S, Murray G. Multiagent mental state recognition and its application to air-combat modeling. Tech. Rep. 50, Australian Artificial Intelligence Institute, Melbourne, Australia, 1994, Jun
102 Rao M et al. Integrated distributed intelligent platform for CIPS.ICIA' 93． 科学出版社, P595-600, 1993
103 Rorithakis G A, et al. Adaptive control of unknown plants using dynamical neural network. IEEE Trans. On SMC, 1994,24(3) :400-411
104 Rosenschein J S. Formal theories of knowledge in AI and robotics. New Generation Computing, 1985:345-357
105 Rosenschein J S. Rational interaction: cooperation among intelligent agents. Ph.D. Thesis, Stanford University, 1986
106 Rovithaki G A, et al. Direct adaptive regulation of unknown nonlinear dynamical systems via dynamic neural networks. IEEE Trans on SMC, 1995,25( 12) : 1578-1594
107 Rovithakis B A, Christodoulou M A. Neural adaptive regulation of unknown nonlinear dynamical systems. IEEE Trans. On SMC Part B, 1997,27(5) :810-822
108 Ruskorius G V, et al. Neurocontrol of nonlinear dynamical systems with kalman filter trained recurrent networks. IEEE Trans. On NN, 1994,5(2) :279-297
109 Russell R. Pruning algorithms-a survey. IEEE Trans on NN, 1993,4(5) :740-747
110 Sadegh N. A nodal link perceptron network with applications to control of a Norholonmic system. IEEE Trans. On Neural Network, 1995,6(6) : 1516-1523
111 Santini S, et al. Block-structured recurrent neural networks. Neural Networks, 1995,8(1) :135-147
112 Saridis G N. Analytic formulation of principle of increasing precision with decreasing intelligence for intelligent machines. Automatica, 1989,25(3) : 11-34
113 Saridis G N. Entropy formulation of optimal and adaptive control. IEEE Trans. AC, 1988,33(8) :713-721
114 Saridis G N. Intelligent Robotic Control. IEE Trans, AC, 1983,28(5) :547-557
115 Saridis G N. Toward the realization of intelligent control. Proc.of the IEEE, 1979,67(8) : 1115-1133
116 Shoham Y, Tennenholtz M. On social laws for artificial agent societies: off-line design. Artificial Intelligence, 1995,73:231-252
117 Shoham Y. Agent oriented programming. Artificial Intelligence, 1993,60:51-92
118 Siestma J, et al. Creating artificial neural networks that generalize. Neural Networks, 1991,(4) :67-76
119 Sima J. Neural expert system. Neural Network, 1995,8(2) :261-271
120 Stothert A, Macleod M. Distributed intelligent control system for a continuous-stat plant. IEEE Trans. SMC, PART B, 1997,27(3) :395-401
121 Suykens J A K, et al. Static and dynamic stabilizing neural controllers, applicable to transition between equilibrium points. Neural Networks, 1994,7(5) :819-831
122 Teshnehlab M, Watanabe K. Self tuning of computed torque gains by using neural networks with flexible structures. IEE Proc.-Control Theory Appl, 1994,14(4) :235-242
123 Theocharis J, Petridis V. Neural network observer for induction motorcontrol. IEEE Control system, 1994,4,P26-37
124 Tsai L-S, et al.Dynamic process diagnosis via integerated neural networks. Computers. Chem. engng,1995,19(5up):s747-952
125 Tseng H C.A learning scheme for dynamic neural networks equilibrium manifold and connective stability. Neural Network, 1995,8(6):853-864
126 Tsoi A C, Back A D. Locally recurrent globally feedforward networks: a review of architectures. IEEE Trans. On Neural Networks, 1994,5(2):229-239
127 Venugopal K P, et al. A recurrent neural network controller and learning algorithm for the on-line learning control of autonomous underwater vehicles. Neural Networks, 1994,7(5):833-846
128 Wang C-H, et al. Fuzzy B-Spline membership function(BMF) and its applications in fuzzy-neural control
129 Wang J-C, et al. A new methods on automatically building neural network structure. Acta Automatic Sinica,1996,22(1):19-25
130 Wang K, et al. Robustness and perturbation analysis of a class of artificial neural networks. Neural Networks,1994,7(2):251-259
131 Wang L-X. Fuzzy systems are universal approxiamators.IEEE Fuzzy92,1992:1163-1170
132 Wang P P, Tyan C-Y. Fuzzy dynamic system and fuzzy linguistic controller classification. Automatica,1994,30(11):1769-1774
133 Wen D-W, Cai Z-X.A composite structure learning method of neural networks for control application. CWC ICIA'97, Xian, China,1997,6
134 Wooldridge M J.The logic modeling of computational multi-agent systems. Ph.D. Thesis, University of Manchester,1992
135 Wooldridge M, Jennings N R. Agent theories, architectures, and languages: a survey, in Intelligent Agents,Springer-Verlag, 1995
136 Wooldridge M, Jennings N R. Intelligent agents: Theory and Practive. The knowledge Engineering Review,1995,10(2):115-152
137 Wooldridge M. Coherent social action, in Proceedings of the Eleventh European Conference on Artificial Intelligence(ECAI-94), pp279-283, Amsterdam, The Netherlands,1994
138 Wooldridge M. Practical reasoning with procedural knowledge, in Proceedings of the International Conference on Formal and Applied Practical Reasoning. Springer-Verlag. 1996, June
139 Xinyao, Yongliu. A new evolutionary systems for evolving artificial neural networks. IEEE Trans. Neural Networks,1997,8(3):694-713
140 Yager R R. Modeling and formulating fuzzy knowledge bases using neural networks. Neural Networks, 1994,7(8): 1273-1283
141 Yang Y Y, Linkens D A. Adaptive neural-network-based approach for the control of continuously stirred tawk reactor-Ⅲ.Proc.-Control Theory Appl, 1994,141(5):341-349
142 Yesildirek A, Leuis F L. Feedback Lirearization Osing neural networks. Automatica, 1995,31(11): 1659-1664
143 Yuan M, et al. Direct neural control system, nonlinear extension of adaptive control, IEE Proc.-Control Theory Appl,1995, 142(6):661-667
144 Yuano A E B, et al. Connectionist approach to PID autotuning. IEE Proc.-D,1992,139(3):279-285
145 Zadeh I A. Fuzzy sets. Information and Control, 1965,(8):330-353
146 Zhang B S, Edmunds J M. Self-organizing fuzzy logic controller. IEE Proc.-D,1992,139(5):460-464
147 Zhang J. Fuzzy neural networks for nonlinear systems modelling, IEE Proc.-Control Theory Appl,1995,142(6):551-561
148 Zhou Q J, Bai J K. An intelligent cintrol of novel design. Proc. Of Multinational Instrumentional conference,1983,137-150
149 蔡自兴，徐光祐．人工智能及其应用(第二版)．北京：清华大学出版社，1996，5
150 蔡自兴，张钟俊．智能控制的若干问题．模式识别与人工智能，1988，1(2)：45-51
151 蔡自兴．智能控制．北京：电子工业出版社，1990
152 蔡自兴．智能控制的结构理论．中国计算机视觉与智能控制学会首届学术年会论文集．29-32．重庆，1989
153 蔡自兴．智能控制—基础与应用．北京：国防工业出版社，1998
154 陈根杜，陈新海．遗传算法的研究与进展．信息与控制，1994，23(4)：2115-222
155 陈国良，王煦法，庄镇泉，王东生．遗传算法及其应用．北京：人民邮电出版社，1996
156 陈建勤，陈来九．基于自适应神经元学习模糊控制规则．控制与决策，1994，9(5)：350-354
157 陈理君，符健豪．微机模糊控制．武汉：武汉工业大学出版社，1992
158 陈荣，徐用懋，兰鸿森．多层前向网络的研究．遗传BP算法和结构优化策略．自动化学报，1997，23(1)：43-49
159 陈宗基，俞新尧，王戟，周巢尘．混合控制新系统及其分析与设计方法．计算机学报，1996，19(4)：254-262
160 戴琼海，张寿，柴天佑．基于动态神经网络的鲁棒直接自适应控制．控制与决策，1996，11(6)：650-653
161 戴汝为，王珏．关于智能系统的综合集成．科学通报，1993，38(14)：1249-1256
162 戴汝为．从定性到定量的综合集成技术．模式识别与人工智能，1991，4(1)：5-10
163 戴汝为．智能控制系统．模式识别与人工智能，1990，3(3)：1-7
164 邓志东，孙增圻，刘建伟．神经网络异步自学习控制系统．自动化学报，1995，21(5)：629-633
165 樊晓聪，徐殿祥，郑国梁．Agent的行为自信度及其修改规则．计算机学报，1998，21(1)：40-46
166 方建安，邵世煌．采用遗传算法学习神经网络控制器．控制与决策，1993，8(3)208-212
167 方剑，席裕庚．神经网络结构设计的准则和方法．信息与控制，1996，25(3)：156-164
168 冯纯伯．复杂工业生产过程的控制问题．控制理论与应用，1992，9(3)：303-305
169 冯恩波，愈金寿，蒋慰孙．基于神经网络技术的解耦及容错解耦控制策略．控制与信息，1992，21(6)：363-368
170 高文忠，顾树生．前馈神经网络的新算法及其收敛性．控制与决策，1995，10(3)：284-288
171 关守平，柴天佑．一种数字网络推理技术．控制与决策，1996，11：125-131
172 郭莉，李清泉．神经网络在机器人控制中的应用．控制与决策，1994，9(2)：89-93
173 韩崇昭，胡保生．泛函分析及其在自动控制中的应用．西安：西安交通大学出版社，1991
174 何述东，瞿坦，黄献清，黄思汉．多层前向网络结构的研究进展．控制理论与应用，1998，15(3)：313-319
175 胡蓬，石纯一，王克宽．开放的分布式人工智能．软件学报，1995，6(10)：605-613
176 黄战，戴冠中．神经网络控制器研究．信息与控制，1991，20(6)：27-31
177 焦李成．神经网络的应用与实现．西安：西安电子科技大学出版社，1993
178 焦李成．神经网络计算．西安：西安电子科技大学出版社，1993
179 焦李成．神经网络系统理论．西安：西安电子科技大学出版社，1992
180 李建民，石纯一．DAI中多Agent协调方法及其分类．计算机科学，1998，25(2)：9-12
181 李慷．席裕庚，张钟俊．复杂工业过程控制结构的综合．控制与决策，1995，10(4)：296-302
182 李明忠，王福利．基于递归神经网络得一类非线性无模型系统的自适应控制．控制与决策，1997，12(1)：64-67
183 李奇，李世华．一类神经网络智能PID控制算法的分析与改进．控制与决策，1998，1(4)：311-315
184 李人厚．复杂大系统的集成控制．控制理论与应用，1994，11(2)：222-225
185 李士勇．模糊控制、神经控制和智能控制论．哈尔滨工业大学出版社，1996，10
186 李运华等．神经网络离散变结构控制的算法及其应用．控制与决策，1994，9(4)：301-305
187 李卓，萧德云，何世忠．基于神经网络的模糊自适应PID控制方法．控制与决策，1996，11(3)：340-345
188 梁泉，许小鸣，张钟俊．多智能体系统协作及控制机理和基本问题分析．控制与决策，1996，11(5)：521-526
189 梁泉，许小鸣，张钟俊．分布式智能控制及其系统 中国控制与决策会议，1995
190 刘宝坤，石红瑞，王惠，赵从．基于遗传算法的神经网络自适应控制器的研究．信息与控制，1997，26(4)：311-314
191 刘海燕，王献昌，王兵山．多 Agent 系统研究．计算机科学，1995，22(2)：57-62
192 刘建勤．人工生命及其应用．北京：冶金工业出版社，1997
193 刘金琨，王树青．钢铁工业过程多智能体系统研究．信息与控制，1998，27(6)：427-432
194 刘立志，蒋玉珍．一种新的智能模糊控制算法及其应用．控制与决策，1995，10(1)：93-96
195 刘释明，黄一夫．基于 Adaline 的模型跟踪自适应控制．信息与控制，1993，22(6)：378-382
196 刘延年，忻欣，冯纯伯．基于神经网络的一类非线性连续系统的稳定性自适应控制．控制理论与应用，1996，13(1)：70-75
197 刘振凯，贵忠华，蔡青．神经网络专家系统的现状及发展趋势．计算机科学，1996，23(3)：70-72
198 陆汝钤．人工智能 (下册)．北京：科学出版社，1996．9
199 罗小青，孙优贤．基于神经网络的前馈学习控制．信息与控制，1994，23(5)：311-314
200 毛新军，王怀民，陈火旺，刘风岐．Agent在多Agent系统中计算的意愿理论．软件学报，1999，10(1)：43-48
201 孟祥武，程虎．联接机制与符号机制相结合的机器学习系统发展与展望．计算机科学，1996，23(3)：6-9
202 钱大群，孙振飞．一个垃圾焚烧智能控制系统．信息与控制， 1993，22(6)：174-377
203 秦世引，罗公亮，孙增圻．智能控制研究中的几个问题．信息与控制，1996，25(3)：131-142
204 秦世引．一类智能控制系统的集成方法研究．模式识别与人工智能，1996，9(2)：105-111
205 任雪梅，高为炳．一类非线性系统神经网络控制的稳定性分析．控制与决策，1995，10(5)：466-469
206 韶关冶炼厂．烧结μXL系统设计说明书．技术资料．1997
207 邵世煌，方建安．采用遗传算法学习和调整神经网络模糊控制器．智能控制与智能自动化．P895-906．北京：科学出版社，1992
208 石纯一，王克宏等．分布式人工智能进展．模式识别与人工智能，1995，8(suppl)：73-92
209 史国庆．赵庆生．基于神经网络的模型算法控制．信息与控制，1994，23(3)：173-177
210 史忠值．智能主体及其应用 北京：科学出版社，2000，12
211 史忠植，王文杰，田启家．智能主体研究现状与发展趋势．计算机世界，1998，1，26
212 史忠植．高级人工智能．科学出版社，1998
213 苏伯琪，石纯一．一种分布式问题求解系统体系结构与算法的研究．计算机学报，1991，14(8)：605-614
214 孙德保，高超．一种实用的克服局部极小的BP算法研究．信息与控制，1995，24(5)：283-287
215 孙增圻，张再兴，邓志东．智能控制理论与技术．北京：清华大学出版社，1997
216 田华，蒋慰孙．智能控制系统的若干新近发展．信息与控制，1992，21(2)：95-100
217 田华，席裕庚，张钟俊．试论Ⅰ—型智能控制系统．信息与控制．1994，23(2)：101-107
218 田明，戴汝为．基于动态BP神经网络的系统辨识方法．自动化学报，1993，19(4)：450-453
219 田明，戴汝为．神经网络控制系统．信息与开展控制，1992，21(6)：156-160
220 王殿辉，柴天佑．自适应模糊神经网络控制器设计的线性化方法．控制与决策，1995，10(1)：21-27
221 王怀民，陈火旺，高洪奎．面向智能主体的程序设计．计算机学报，1994，17(5)：367-375
222 王怀民，吴泉源，高洪奎，邹鹏．基于Agent的分布式计算环境．计算机学报，1996，19(3)：197-201
223 王继成，蔡义发，吕维雪．一种自动生成神经网络的新方法．自动化学报．1996，22(1)：19-24
224 王继成，吕维雷．一种神经网络学习过程的数学描述，计算机研究与发展，1996，33(6)：56-61
225 王继成，吕维雪．一种基于符号神经网络的知识获取方法．计算机学报，1995，18(12)：949-952
226 王俭，田华，许维胜，吴启迪．并行工程基于Agent的集成框架的研究．信息与控制，1997，26(3)161-167
227 王矛，李人厚．递阶结构智能控制系统的控制器设计．信息与控制，1994，23(2)：125-128
228 王文杰，田起家，史忠植．多主体系统中对其他主体的研究．计算机研究与发展，1998，35(11)：971-974
229 王小立，邱光谊．专家系统的多模型集成技术．湖南大学学报，1996，23(2)：123-128
230 王耀南，童调生，蔡自兴．基于神经网络的智能控制PID控制及其应用．信息与控制，1994，23(3)：185-189
231 王耀南．一类动态递归网络的智能控制器．控制与决策，1995，10(6)：508-513
232 王耀南．智能控制系统—模糊逻辑，专家系统，神经网络控制．长沙：湖南大学出版社，1996
233 王元元．计算机科学中的逻辑学．北京：科学出版社，1989．9
234 韦巍，蒋静坪．非线性系统的多神经网络学习控制．信息与控制，1995，24(5)：294-299
235 文敦伟，蔡自兴．基于自适应神经网络的规则自修正模糊控制器．有色金属学报，1995，5(s4)：414-418
236 吴锋，郑应平，毛绪谨．一类混杂系统的建模与控制器设计．控制与决策，1996，11(1)：81-84
237 徐秉铮，张白灵，韦岗．神经网络理论与应用．广州：华中理工大学出版社，1994，12
238 徐冬玲，方建安，邵世煌．交通系统的模糊控制及其神经网络实现．信息与控制，1992，21(2)：74-77
239 徐立新．人工神经元网络理论及其在控制中的应用研究．哈尔滨工业大学工学博士论文，1996
240 徐丽娜．神经网络控制．哈尔滨：哈尔滨工业大学出版社，1999，5
241 姚郑，高文．多功能感知系统中面对对象的多Agent技术．软件学报，1996，7(3)：163-167
242 袁曾任，姜莉楠．基于人工神经网络的控制系统模型简化．专家系统，1992，21(5)：278-282
243 袁曾任．智能控制研究的新进展．信息与控制，1994，23(5)：257-261
244 张钹．传统人工智能与控制技术的结合．控制理论与应用，1994，11(2)：247-250
245 张钹．近十年人工智能进展．模式识别与人工智能，1995，8(suppl)：1-8
246 张璟，李人厚．基于专家-神经网的递阶智能控制系统．信息与控制，1993，22(6)：314-345
247 张立明．人工神经网络的模型及其应用．上海：复旦大学出版社，1993
248 张良杰，李衍达．模糊神经网络技术的新近发展．信息与控制，1995，24(1)：39-46
249 张晓兰等，一种改进的单个神经元的控制算法．控制与决策，1994，9(6)：442-446
250 章云．非线性系统的神经网络建模与控制．华南理工大学博士学位论文．1997，12
251 周立，吴泉源．面向智能体逻辑程序设计系统GKD-AOPLS．计算机研究与发展，1995，32(12)：10-14
252 祝明发．分布式人工智能．计算机研究与发展，1990，27(10)：7-18
2 Ahmed M S. Block partial derivative and its application to neural-net-based direct-model-reference adaptive control. IEE Proc.-Control Theory Appl, 1994,141(5) :305-314
3 Ahmed M S. Neural-net controller for nolinear plants: design approach through linearisation. IEE Proc. Control Theory Appl, 1994,141(5) :315-322
4 Angeline P J, et al. An evolutionary algorithm that constructs recurrent neural network. IEEE Trans. On NN, 1994,5(1) :54-65
5 Astrom K J, Auton J J, Arzen K E. Expert control. Automatica, 1986,22(3) :277-286
6 Astrom K J. Intelligent Control. ECC91 ,P2328-2339, Grenoble, France, 1991
7 Austaklis P J. Intelligent Learning Control. IEEE Control systems, 1995,15(3) :5-8
8 Autsaklis P J. Defining intelligent control. IEEE control systems, 1994,14(3) :4-5,58-66
9 Bartlett E B. Dynamic node architecture learning: an information theoretic approach. Neural Networks, 1994,7(1) :129-140
10 Batro A G.et al. Neuronlike adaptive element that can solve difficult learning control problems. IEEE Trans. On SMC, 1983,13(5) :834-846
11 Bratman M E. Intentions, plans, and practical reason. Harvard University Press: Cambridge, MA, 1987
12 Cai Zixing. Intelligent Control: Principles, Techniques and Applications. Singapore: World Scientific, 1997
13 Catfolis T. A method for improving the red-time recurrent learning algorithm. Neural Networks, 1993,6:807-821
14 Chen C L. Hybrid learning alorithm for Gaussian potential function networks. IEE Proc.-D, 1993,140(6) :442-448
15 Chen D, etal. Constructive learning of recurrent neural networks. IEEE Int. Conf. On Neural Networks, 1993,3:1196-1201
16 Chen F C, et al. Adaptively controlling nonlinear continuous time system using multilayer neural networks. IEEE Trans. On AC, 1994,39(6) :1306-1310
17 Chen J Q, Lu L J. Analysis and syntesis of fuzzy closed-loop control systems. IEEE Trans. On SMC, 1995,25(5) :881-888
18 Chen S. et al. Paralled recursive prediction error algorothm for trovining layered neural networks. Int J. Control, 1990,5(6) :1215-1228
19 Chorafas D N. Agent technology handbook. McGraw-Hill Book Co., 1998
20 Chung E L, Lee T. Network-growth approach to design of feed-forward networks. IEE Proc.-Control Theory Appl, 1995,142(5) :486-492
21 Cohen M A, Grossberg S. Abosolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Trans. SMC, 1983,13(5) :815-826
22 Cohen P R, Levesque H J. Intention is choice with commitment Artificial Intelligence, 1990,42:213-261
23 Cohen PR, Levesque HJ. Teamwork. Nous 1991,25:487-512
24 Cybenko G. Approximation by superpositions of a Sigmoidal function. Math. Of Control, signals, systems, 1989,2(4) :303-314
25 Delgado A, et al. Dynamic recurrent networks for system identification and control. IEE Proc.-control Theory Appl, 1995,142(4) :307-314
26 Dirion J L, et al. Design of a neural controller by inverse modelling. Computers.Chem. Engng, 1995,19(supple): 5797-5802
27 Elman J L. Find structure in time. Cognitive Science, 1990,14(2) : 179-211
28 Enab Y M. Intelligent controller design for the ship steering problem. IEE: Proc. Control Theory Appl,
29 Etxebarria V. Adaptive control of discrete systems using neural networks. IEE Proc. Control Theory Appl., 1994,141(4) :209-215
30 Fabri S, Kadirkamanathan V. Dynamic structure neural networks for stable adaptive control of nonlinear systems. IEEE Trans. On Neural Networks, 1996,7(5) :1151-1167
31 Fagin R, Halpern J Y, Vardi M Y. What can machines know? on the Properties of Knowledge in Distributed Systems. Journal of the ACM, 1992,39(2) :328-376
32 Ferguson I A. Touring Machines: an architecture for dynamic rational mobile agent. Ph.D. Thesis, Computer Lab. University of Cambridge, UK, 1992
33 Finin T, Fritzson R, etal. KQML as an agent communication language. The proceedings of the Third International Conference on Information and Knowledge Management (CIKM'94) , ACM Press, 1994, November
34 Fogel G B, Fogel D B. Continuous evolution programming: analyses and experiments. Cybern. Syst, 1995,26:79-90
35 Fu K S, Walts M A. A heuristic approach to reinforcement learning control system. IEEE Trans. AC, 1965,10(4) :390-398
36 Fu K S. Learning control systems and intelligent control systems: An intersection of artificial intelligent control. IEEE Trans. AC, 1971,16(1) :70-72
37 Fu L M. Rule generation from neural networks. IEEE Trans. On SMC, 1994,24(8) :1114-1124
38 Gallent S I. Connectiouist expert systems. Commu. Of the ACM, 1998,31(2) : 152-169
39 Giles C L, et al. Dynamic recurrent networks: theory and application. IEEE Trans on NN, 1994,5(2) : 153-155
40 Girosi F, Poggio T. Network and the best approximation property. Biological Cybernetics, 1990,63(3) : 169-176
41 Goldberg D E. Genetic algorithms in search, optimization and machine learning. Mass: Addision-Wesley, 1989
42 Handelman D A, et al. Integrating neural networks and knowledge-based systems for intelligent robotic control. IEEE Control System Magazine, 1990,4,76-87
43 Happel B L M, Murre J M J. Design and evolution of modular neural network architectures. Neural Networks, 1994,7(617) :985-1004
44 Harth E, Tzanakou E. Alopex: A stochastic method for determing visual receptive fields. Vision Res. 1974:14(10) 1475-1482
45 Hewitt C. Open information systems semantics for distributed artificial intelligence. Artificial Intelligence, 1991,47:79-106
46 Honik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Networks, 1989,2(3) :359-336
47 Honik K. Capabilities of Multilayer Feedforward Networks. Neural networks, 1992,4(2) :251-257
48 Hopfield J J. Neural networks and physical systems with emergent collective computational abilities. Proc.of the national academy of sciences, 1982,79(8) :2554-2558
49 Hopfield J J. Neurons with graded response have collective computational abilities. Proc. Of the National Academy of Sciences, 1984,81(10) :3088-3092
50 Houck C R, Joines J A, Kay M G. A genetic algorithm for function optimization: a matlab implementation. ACM Transactions on Mathmatical Software, Submitted. 1996
51 Hsin H-C et al. An adaptive training algorithm for back-propagation neural networks. IEEE. Trans. SMC, 1995,25(3) :512-514
52 Huang Y L, Fan L T. Artificial intelligence for waste minimization in the process industry. Computers in industry, 1992
53 Hunt K J, etal. Neural networks for control systems-A survey. Automatica, 1992． 28(5) : 1083-1112
54 Hunt K J, Sbarbane D. Neural networks for nonlinear internal model control. IEE Proc.-D, 1991,138(5) :431-438
55 Hunt K J. Neural networks for control systems-A survey . Automatica, 1992,28(6) : 1083-1112
56 Ishikawa M. Structural learning with forgetting. Neural Networks, 1996,9(3) :509-521
57 Jang J-S R. AVFIS: adaptive-network-based fuzzy inference system. IEEE Trans. SMC, 1993,23(3) :665-654
58 Jennings N R. Controlling cooperative problem solving in industrial multi-agent systems using joint intentions. Artificial Intelligence, 1995,75:195-240
59 Jennings N R. Controlling cooperative problem solving in industrial multi-agent systems using joint intentions. Artificial Intelligence, 1995,75:195-240
60 Jennings N R. On being responsible, in Decentralized AI 3-Proceedings of the Third European Workshop on Modeling Autonomous Agents in a Multi-Agent World(MAAMAW-91) , pp93-102, Elsevier Science Publishers B. V. Amsterdam, The Netherlands, 1992
61 Jennings N R-Specification and implementation of a belief-desire-joint-intention architecture for collaborative problem solving. International Journal of Intelligent and Cooperative Information Systems, 1993,2(3) :289-318
62 Jennings N R. Towards a cooperation knowledge level for collaborative problem solving. Proc. 10th European Conference on Artificial Intelligence(ECAI'92) , Vienna, Austria, 1992, August
63 Jin L, et al. Absolute stability condition for discrete-time recurrent neural network. IEEE Trans. NN, 1994,5(6) :954-963
64 Johannsen G. Integrated automation in complex man-machine systems. ECC'91, Grenoble, France, P1013-1021, 1991
65 Karnin E D. A simple procedure for pruning back-propagation trained neural networks. IEEE Trans. On NN, 1990,1(2) :239-242
66 Kendra S J, et al. Intelligent process control with supervisory knowledge-based systems. IEEE control system, 1994
67 Kim Y H, Lewis F L, Abdallah C T. A dynamic recurrent neural-network-based adaptive observer for a class of nonlinear systems. Automatica. 1997． 33(8) : 1539-1543
68 Konolige K. A deduction model of belief. Pitman Publishing: London and Morgan Kaufman: San Mateo, CA, 1986
69 Kosko B. Neural networks and fuzzy systems. NJ-Prentice-Hall, 1992
70 Ku C.-C, Lee K Y. Diagonal recurrent neural networks for dynamic systems control. IEEE Trans. On Neural Networks, 1995,6(1) :144-155
71 Levesque H J, Cohen P R, Nunes J H. On acting together, in Proceedings AAAI-90, Boston, MA( 1990) :94-99 1990
72 Levin A U, Narendra K S. Control of nonlinear dynamical systems using neural networks-part2: observability, identification, and control. IEEE Trans. On Neural Networks, 1996,7( 1 ):30-42
73 Li Q, et al. Developing a neurocompensator for the adaptive control of robots. IEE Proc.-Control Theory Appl, 1995,142(6) :562-568
74 Lightbody G, Inrin G W. Direct neural model reference adaptive control. IEE Proc.-Control Theory Appl, l995,142(1) :31-43
75 Ling K-V, Dexter AL. Expert control of Air-Conditioning plant. Automatica, 1994,30(5) :761-773
76 Linkens D A, Nie J. Back-propagation neural-network based fuzzy controller with a self-learning teacher. Int. J. Control, 1994,60(1) : 17-39
77 Maeda Y, Figueiredo R J P. Learning rules for neuro-controller via simultaneous perturbation. IEEE Trans, on Neural Networks, 1997,8(5) . 1119-1130
78 Mills P M, et al. Adaptive model-based control using neural network. Int. J. Control, 1994,60(6) :1163-1192
79 Mueller J P. The design of intelligent agents: a layered approach. Springer-Verlag, 1996
80 Musliner C J, Durfee E H, Shin K G. CIRCA: A cooperative intelligent real-time control architecture. IEEE Trans. On SMC, 1993,23(6) :1561-1573
81 Nabhan T M, et al. Toward generating neural network structures for function approximation. Neural Networks, 1994,7(1) :89-99
82 Nagano T, et al. A neural network model for the developmental process of hypercomplex cells. IEEEE Trans. SMC, 1983:113(5) :847-851
83 Narendra K S, et al. Adaption and Learning using multiple nodes, swithing and turning. IEE Control System, 1995,Jane, 37-51
84 Narendra K S. Identification and control for dynamic systems using neural networks. IEEE Trans. On Neural Networks, 1990,1(1) :4-27
85 Nie J, Linkens D A. Fast self-learning multivariable fuzzy controllers constructed from a modified CPN networks. Int. J. Control, 1994,60(3) :369-393
86 Nie J. Constructing Fuzzy model by self-organizing counter propagation network. IEEE Trans. SMC, 1995,25(6) :963-970
87 Nwana H S. Software agent: an overview. Knowledge Engineering Review, 1996,11(3) :205-244
88 Obradovic D. On-line training of recurrent neural networks with continuous topology adaptation. IEEE Trans. On Neural Networks, 1996,7(1) :222-228
89 Ollero A, et al. Design of rule-based expert controllers. ECC91 .PP578-583, Grenoble, France, 1991
90 Omlin C W, et al. Extraction of rules from discrete-time recurrent neural networks. Neural Networks, 1996,9(4) :41-52
91 Ozart B. Chemical plant fault diagnosis through a hybrid symbolic-connectionist approach and comparison with neural networks. Computers. Chem Engng, 1995,19(sup): s753-s758
92 Park D, et al. Genetic-Based new fuzzy reasoning models with application to fuzzy control. IEEE Trans, SMC, 1994,24(1) :39-47
93 Parunak H V D. Distributed AI and manufacturing control: some issue and insights. Proc. First European Workshop on Modeling an Autonomouse Agent in a Multi-Agent Worlds, 1989
94 Pedrycz W. Distributed fuzzy system modeling. IEEE Trans SMC, 1995,25(5) :769-780
95 Pham D T, Lin X. Training of elman networks and dynamic system modeling. Int. J. Of Systems Science, 1996,27(2) :221-226
96 Prokhorov D V, et al. Adaptive Critic Designs: A case study for neurocontrol. Neural Network, 1995,8(9) :1367-1372
97 Rao A S, Georgeff M P, Sonenberg E A. Social plans: A preliminary report, in E. Werner and Y. Demazeau, editors, Decentralized AI 3-Proceedings of the Third European Workshop on Modeling Autonomous Agents in a Multi-Agent World(MAAMAW-91) . Pp57-76, Elsevier Science Publishers, B. V. Amsterdam, The Netherlands, 1992
98 Rao A S, Georgeff M P. BDI Agents: from theory to practice. Tech. Note 5, Australian Artificial Intelligence Institute, 1995
99 Rao A S, Georgeff M P. Formal models and decision procedures for multi-agent systems. Tech. Note 61, Australian AI Institute, Level 6, 171 LaTrobe Street, Melbourne, Australia, 1995, June
100 Rao A S, Georgeff M P. Modeling rational agents with in a BDI-architecture. Tech. Note 14, Australian Artificial Intelligence Institute, 1991
101 Rao A S, Murray G. Multiagent mental state recognition and its application to air-combat modeling. Tech. Rep. 50, Australian Artificial Intelligence Institute, Melbourne, Australia, 1994, Jun
102 Rao M et al. Integrated distributed intelligent platform for CIPS.ICIA' 93． 科学出版社, P595-600, 1993
103 Rorithakis G A, et al. Adaptive control of unknown plants using dynamical neural network. IEEE Trans. On SMC, 1994,24(3) :400-411
104 Rosenschein J S. Formal theories of knowledge in AI and robotics. New Generation Computing, 1985:345-357
105 Rosenschein J S. Rational interaction: cooperation among intelligent agents. Ph.D. Thesis, Stanford University, 1986
106 Rovithaki G A, et al. Direct adaptive regulation of unknown nonlinear dynamical systems via dynamic neural networks. IEEE Trans on SMC, 1995,25( 12) : 1578-1594
107 Rovithakis B A, Christodoulou M A. Neural adaptive regulation of unknown nonlinear dynamical systems. IEEE Trans. On SMC Part B, 1997,27(5) :810-822
108 Ruskorius G V, et al. Neurocontrol of nonlinear dynamical systems with kalman filter trained recurrent networks. IEEE Trans. On NN, 1994,5(2) :279-297
109 Russell R. Pruning algorithms-a survey. IEEE Trans on NN, 1993,4(5) :740-747
110 Sadegh N. A nodal link perceptron network with applications to control of a Norholonmic system. IEEE Trans. On Neural Network, 1995,6(6) : 1516-1523
111 Santini S, et al. Block-structured recurrent neural networks. Neural Networks, 1995,8(1) :135-147
112 Saridis G N. Analytic formulation of principle of increasing precision with decreasing intelligence for intelligent machines. Automatica, 1989,25(3) : 11-34
113 Saridis G N. Entropy formulation of optimal and adaptive control. IEEE Trans. AC, 1988,33(8) :713-721
114 Saridis G N. Intelligent Robotic Control. IEE Trans, AC, 1983,28(5) :547-557
115 Saridis G N. Toward the realization of intelligent control. Proc.of the IEEE, 1979,67(8) : 1115-1133
116 Shoham Y, Tennenholtz M. On social laws for artificial agent societies: off-line design. Artificial Intelligence, 1995,73:231-252
117 Shoham Y. Agent oriented programming. Artificial Intelligence, 1993,60:51-92
118 Siestma J, et al. Creating artificial neural networks that generalize. Neural Networks, 1991,(4) :67-76
119 Sima J. Neural expert system. Neural Network, 1995,8(2) :261-271
120 Stothert A, Macleod M. Distributed intelligent control system for a continuous-stat plant. IEEE Trans. SMC, PART B, 1997,27(3) :395-401
121 Suykens J A K, et al. Static and dynamic stabilizing neural controllers, applicable to transition between equilibrium points. Neural Networks, 1994,7(5) :819-831
122 Teshnehlab M, Watanabe K. Self tuning of computed torque gains by using neural networks with flexible structures. IEE Proc.-Control Theory Appl, 1994,14(4) :235-242
123 Theocharis J, Petridis V. Neural network observer for induction motorcontrol. IEEE Control system, 1994,4,P26-37
124 Tsai L-S, et al.Dynamic process diagnosis via integerated neural networks. Computers. Chem. engng,1995,19(5up):s747-952
125 Tseng H C.A learning scheme for dynamic neural networks equilibrium manifold and connective stability. Neural Network, 1995,8(6):853-864
126 Tsoi A C, Back A D. Locally recurrent globally feedforward networks: a review of architectures. IEEE Trans. On Neural Networks, 1994,5(2):229-239
127 Venugopal K P, et al. A recurrent neural network controller and learning algorithm for the on-line learning control of autonomous underwater vehicles. Neural Networks, 1994,7(5):833-846
128 Wang C-H, et al. Fuzzy B-Spline membership function(BMF) and its applications in fuzzy-neural control
129 Wang J-C, et al. A new methods on automatically building neural network structure. Acta Automatic Sinica,1996,22(1):19-25
130 Wang K, et al. Robustness and perturbation analysis of a class of artificial neural networks. Neural Networks,1994,7(2):251-259
131 Wang L-X. Fuzzy systems are universal approxiamators.IEEE Fuzzy92,1992:1163-1170
132 Wang P P, Tyan C-Y. Fuzzy dynamic system and fuzzy linguistic controller classification. Automatica,1994,30(11):1769-1774
133 Wen D-W, Cai Z-X.A composite structure learning method of neural networks for control application. CWC ICIA'97, Xian, China,1997,6
134 Wooldridge M J.The logic modeling of computational multi-agent systems. Ph.D. Thesis, University of Manchester,1992
135 Wooldridge M, Jennings N R. Agent theories, architectures, and languages: a survey, in Intelligent Agents,Springer-Verlag, 1995
136 Wooldridge M, Jennings N R. Intelligent agents: Theory and Practive. The knowledge Engineering Review,1995,10(2):115-152
137 Wooldridge M. Coherent social action, in Proceedings of the Eleventh European Conference on Artificial Intelligence(ECAI-94), pp279-283, Amsterdam, The Netherlands,1994
138 Wooldridge M. Practical reasoning with procedural knowledge, in Proceedings of the International Conference on Formal and Applied Practical Reasoning. Springer-Verlag. 1996, June
139 Xinyao, Yongliu. A new evolutionary systems for evolving artificial neural networks. IEEE Trans. Neural Networks,1997,8(3):694-713
140 Yager R R. Modeling and formulating fuzzy knowledge bases using neural networks. Neural Networks, 1994,7(8): 1273-1283
141 Yang Y Y, Linkens D A. Adaptive neural-network-based approach for the control of continuously stirred tawk reactor-Ⅲ.Proc.-Control Theory Appl, 1994,141(5):341-349
142 Yesildirek A, Leuis F L. Feedback Lirearization Osing neural networks. Automatica, 1995,31(11): 1659-1664
143 Yuan M, et al. Direct neural control system, nonlinear extension of adaptive control, IEE Proc.-Control Theory Appl,1995, 142(6):661-667
144 Yuano A E B, et al. Connectionist approach to PID autotuning. IEE Proc.-D,1992,139(3):279-285
145 Zadeh I A. Fuzzy sets. Information and Control, 1965,(8):330-353
146 Zhang B S, Edmunds J M. Self-organizing fuzzy logic controller. IEE Proc.-D,1992,139(5):460-464
147 Zhang J. Fuzzy neural networks for nonlinear systems modelling, IEE Proc.-Control Theory Appl,1995,142(6):551-561
148 Zhou Q J, Bai J K. An intelligent cintrol of novel design. Proc. Of Multinational Instrumentional conference,1983,137-150
149 蔡自兴，徐光祐．人工智能及其应用(第二版)．北京：清华大学出版社，1996，5
150 蔡自兴，张钟俊．智能控制的若干问题．模式识别与人工智能，1988，1(2)：45-51
151 蔡自兴．智能控制．北京：电子工业出版社，1990
152 蔡自兴．智能控制的结构理论．中国计算机视觉与智能控制学会首届学术年会论文集．29-32．重庆，1989
153 蔡自兴．智能控制—基础与应用．北京：国防工业出版社，1998
154 陈根杜，陈新海．遗传算法的研究与进展．信息与控制，1994，23(4)：2115-222
155 陈国良，王煦法，庄镇泉，王东生．遗传算法及其应用．北京：人民邮电出版社，1996
156 陈建勤，陈来九．基于自适应神经元学习模糊控制规则．控制与决策，1994，9(5)：350-354
157 陈理君，符健豪．微机模糊控制．武汉：武汉工业大学出版社，1992
158 陈荣，徐用懋，兰鸿森．多层前向网络的研究．遗传BP算法和结构优化策略．自动化学报，1997，23(1)：43-49
159 陈宗基，俞新尧，王戟，周巢尘．混合控制新系统及其分析与设计方法．计算机学报，1996，19(4)：254-262
160 戴琼海，张寿，柴天佑．基于动态神经网络的鲁棒直接自适应控制．控制与决策，1996，11(6)：650-653
161 戴汝为，王珏．关于智能系统的综合集成．科学通报，1993，38(14)：1249-1256
162 戴汝为．从定性到定量的综合集成技术．模式识别与人工智能，1991，4(1)：5-10
163 戴汝为．智能控制系统．模式识别与人工智能，1990，3(3)：1-7
164 邓志东，孙增圻，刘建伟．神经网络异步自学习控制系统．自动化学报，1995，21(5)：629-633
165 樊晓聪，徐殿祥，郑国梁．Agent的行为自信度及其修改规则．计算机学报，1998，21(1)：40-46
166 方建安，邵世煌．采用遗传算法学习神经网络控制器．控制与决策，1993，8(3)208-212
167 方剑，席裕庚．神经网络结构设计的准则和方法．信息与控制，1996，25(3)：156-164
168 冯纯伯．复杂工业生产过程的控制问题．控制理论与应用，1992，9(3)：303-305
169 冯恩波，愈金寿，蒋慰孙．基于神经网络技术的解耦及容错解耦控制策略．控制与信息，1992，21(6)：363-368
170 高文忠，顾树生．前馈神经网络的新算法及其收敛性．控制与决策，1995，10(3)：284-288
171 关守平，柴天佑．一种数字网络推理技术．控制与决策，1996，11：125-131
172 郭莉，李清泉．神经网络在机器人控制中的应用．控制与决策，1994，9(2)：89-93
173 韩崇昭，胡保生．泛函分析及其在自动控制中的应用．西安：西安交通大学出版社，1991
174 何述东，瞿坦，黄献清，黄思汉．多层前向网络结构的研究进展．控制理论与应用，1998，15(3)：313-319
175 胡蓬，石纯一，王克宽．开放的分布式人工智能．软件学报，1995，6(10)：605-613
176 黄战，戴冠中．神经网络控制器研究．信息与控制，1991，20(6)：27-31
177 焦李成．神经网络的应用与实现．西安：西安电子科技大学出版社，1993
178 焦李成．神经网络计算．西安：西安电子科技大学出版社，1993
179 焦李成．神经网络系统理论．西安：西安电子科技大学出版社，1992
180 李建民，石纯一．DAI中多Agent协调方法及其分类．计算机科学，1998，25(2)：9-12
181 李慷．席裕庚，张钟俊．复杂工业过程控制结构的综合．控制与决策，1995，10(4)：296-302
182 李明忠，王福利．基于递归神经网络得一类非线性无模型系统的自适应控制．控制与决策，1997，12(1)：64-67
183 李奇，李世华．一类神经网络智能PID控制算法的分析与改进．控制与决策，1998，1(4)：311-315
184 李人厚．复杂大系统的集成控制．控制理论与应用，1994，11(2)：222-225
185 李士勇．模糊控制、神经控制和智能控制论．哈尔滨工业大学出版社，1996，10
186 李运华等．神经网络离散变结构控制的算法及其应用．控制与决策，1994，9(4)：301-305
187 李卓，萧德云，何世忠．基于神经网络的模糊自适应PID控制方法．控制与决策，1996，11(3)：340-345
188 梁泉，许小鸣，张钟俊．多智能体系统协作及控制机理和基本问题分析．控制与决策，1996，11(5)：521-526
189 梁泉，许小鸣，张钟俊．分布式智能控制及其系统 中国控制与决策会议，1995
190 刘宝坤，石红瑞，王惠，赵从．基于遗传算法的神经网络自适应控制器的研究．信息与控制，1997，26(4)：311-314
191 刘海燕，王献昌，王兵山．多 Agent 系统研究．计算机科学，1995，22(2)：57-62
192 刘建勤．人工生命及其应用．北京：冶金工业出版社，1997
193 刘金琨，王树青．钢铁工业过程多智能体系统研究．信息与控制，1998，27(6)：427-432
194 刘立志，蒋玉珍．一种新的智能模糊控制算法及其应用．控制与决策，1995，10(1)：93-96
195 刘释明，黄一夫．基于 Adaline 的模型跟踪自适应控制．信息与控制，1993，22(6)：378-382
196 刘延年，忻欣，冯纯伯．基于神经网络的一类非线性连续系统的稳定性自适应控制．控制理论与应用，1996，13(1)：70-75
197 刘振凯，贵忠华，蔡青．神经网络专家系统的现状及发展趋势．计算机科学，1996，23(3)：70-72
198 陆汝钤．人工智能 (下册)．北京：科学出版社，1996．9
199 罗小青，孙优贤．基于神经网络的前馈学习控制．信息与控制，1994，23(5)：311-314
200 毛新军，王怀民，陈火旺，刘风岐．Agent在多Agent系统中计算的意愿理论．软件学报，1999，10(1)：43-48
201 孟祥武，程虎．联接机制与符号机制相结合的机器学习系统发展与展望．计算机科学，1996，23(3)：6-9
202 钱大群，孙振飞．一个垃圾焚烧智能控制系统．信息与控制， 1993，22(6)：174-377
203 秦世引，罗公亮，孙增圻．智能控制研究中的几个问题．信息与控制，1996，25(3)：131-142
204 秦世引．一类智能控制系统的集成方法研究．模式识别与人工智能，1996，9(2)：105-111
205 任雪梅，高为炳．一类非线性系统神经网络控制的稳定性分析．控制与决策，1995，10(5)：466-469
206 韶关冶炼厂．烧结μXL系统设计说明书．技术资料．1997
207 邵世煌，方建安．采用遗传算法学习和调整神经网络模糊控制器．智能控制与智能自动化．P895-906．北京：科学出版社，1992
208 石纯一，王克宏等．分布式人工智能进展．模式识别与人工智能，1995，8(suppl)：73-92
209 史国庆．赵庆生．基于神经网络的模型算法控制．信息与控制，1994，23(3)：173-177
210 史忠值．智能主体及其应用 北京：科学出版社，2000，12
211 史忠植，王文杰，田启家．智能主体研究现状与发展趋势．计算机世界，1998，1，26
212 史忠植．高级人工智能．科学出版社，1998
213 苏伯琪，石纯一．一种分布式问题求解系统体系结构与算法的研究．计算机学报，1991，14(8)：605-614
214 孙德保，高超．一种实用的克服局部极小的BP算法研究．信息与控制，1995，24(5)：283-287
215 孙增圻，张再兴，邓志东．智能控制理论与技术．北京：清华大学出版社，1997
216 田华，蒋慰孙．智能控制系统的若干新近发展．信息与控制，1992，21(2)：95-100
217 田华，席裕庚，张钟俊．试论Ⅰ—型智能控制系统．信息与控制．1994，23(2)：101-107
218 田明，戴汝为．基于动态BP神经网络的系统辨识方法．自动化学报，1993，19(4)：450-453
219 田明，戴汝为．神经网络控制系统．信息与开展控制，1992，21(6)：156-160
220 王殿辉，柴天佑．自适应模糊神经网络控制器设计的线性化方法．控制与决策，1995，10(1)：21-27
221 王怀民，陈火旺，高洪奎．面向智能主体的程序设计．计算机学报，1994，17(5)：367-375
222 王怀民，吴泉源，高洪奎，邹鹏．基于Agent的分布式计算环境．计算机学报，1996，19(3)：197-201
223 王继成，蔡义发，吕维雪．一种自动生成神经网络的新方法．自动化学报．1996，22(1)：19-24
224 王继成，吕维雷．一种神经网络学习过程的数学描述，计算机研究与发展，1996，33(6)：56-61
225 王继成，吕维雪．一种基于符号神经网络的知识获取方法．计算机学报，1995，18(12)：949-952
226 王俭，田华，许维胜，吴启迪．并行工程基于Agent的集成框架的研究．信息与控制，1997，26(3)161-167
227 王矛，李人厚．递阶结构智能控制系统的控制器设计．信息与控制，1994，23(2)：125-128
228 王文杰，田起家，史忠植．多主体系统中对其他主体的研究．计算机研究与发展，1998，35(11)：971-974
229 王小立，邱光谊．专家系统的多模型集成技术．湖南大学学报，1996，23(2)：123-128
230 王耀南，童调生，蔡自兴．基于神经网络的智能控制PID控制及其应用．信息与控制，1994，23(3)：185-189
231 王耀南．一类动态递归网络的智能控制器．控制与决策，1995，10(6)：508-513
232 王耀南．智能控制系统—模糊逻辑，专家系统，神经网络控制．长沙：湖南大学出版社，1996
233 王元元．计算机科学中的逻辑学．北京：科学出版社，1989．9
234 韦巍，蒋静坪．非线性系统的多神经网络学习控制．信息与控制，1995，24(5)：294-299
235 文敦伟，蔡自兴．基于自适应神经网络的规则自修正模糊控制器．有色金属学报，1995，5(s4)：414-418
236 吴锋，郑应平，毛绪谨．一类混杂系统的建模与控制器设计．控制与决策，1996，11(1)：81-84
237 徐秉铮，张白灵，韦岗．神经网络理论与应用．广州：华中理工大学出版社，1994，12
238 徐冬玲，方建安，邵世煌．交通系统的模糊控制及其神经网络实现．信息与控制，1992，21(2)：74-77
239 徐立新．人工神经元网络理论及其在控制中的应用研究．哈尔滨工业大学工学博士论文，1996
240 徐丽娜．神经网络控制．哈尔滨：哈尔滨工业大学出版社，1999，5
241 姚郑，高文．多功能感知系统中面对对象的多Agent技术．软件学报，1996，7(3)：163-167
242 袁曾任，姜莉楠．基于人工神经网络的控制系统模型简化．专家系统，1992，21(5)：278-282
243 袁曾任．智能控制研究的新进展．信息与控制，1994，23(5)：257-261
244 张钹．传统人工智能与控制技术的结合．控制理论与应用，1994，11(2)：247-250
245 张钹．近十年人工智能进展．模式识别与人工智能，1995，8(suppl)：1-8
246 张璟，李人厚．基于专家-神经网的递阶智能控制系统．信息与控制，1993，22(6)：314-345
247 张立明．人工神经网络的模型及其应用．上海：复旦大学出版社，1993
248 张良杰，李衍达．模糊神经网络技术的新近发展．信息与控制，1995，24(1)：39-46
249 张晓兰等，一种改进的单个神经元的控制算法．控制与决策，1994，9(6)：442-446
250 章云．非线性系统的神经网络建模与控制．华南理工大学博士学位论文．1997，12
251 周立，吴泉源．面向智能体逻辑程序设计系统GKD-AOPLS．计算机研究与发展，1995，32(12)：10-14
252 祝明发．分布式人工智能．计算机研究与发展，1990，27(10)：7-18