Papers by Keyword: Multi-Agent (MA)

Abstract: Using the patents with multi-agent, we provide detailed insights into the cooperation of the marine industry, which is also a complicated innovation network with different agents, such as universities, research institutes, companies. Patent applications and publications are used as measures for the innovation output of the industry. We find that the cooperation in the four different stages is getting more and more intent, and companies are the biggest nodes in the networks. Effects are found that the nodes with more independent innovation would cooperate more with other nodes. Company nodes also tend to seek more partners in the interior, and have more cooperation with partners. But the internal cooperation is a little in the universities and research institutes.

Abstract: In view of the process of automatic flatness control and automatic gauge control that is a nonlinear system with multi-dimensions, multi-variables, strong coupling and time variation, a novel control method called self-tuning PID with diagonal recurrent neural network (DRNN-PID) based on Q learning is proposed. It is able to coordinate the coupling of flatness control and gauge control agents to get the satisfactory control requirements without decoupling directly and amend output control laws by DRNN-PID adaptively. Decomposition-coordination is utilized to establish a novel multi-agent system for coordination control including flatness agent, gauge agent and Q learning agent. Simulation result demonstrates the validity of our proposed method.

Abstract: To effectively predict cascading failure in power system, a cascading failure prediction method in power system based on multi-agent and hybrid genetic algorithm is constructed. A cascading failure prediction procedure in power system was established by multi-agent and hybrid genetic algorithm to investigate the emergent behaviors of cascading failures and to further study the prediction and defense of cascading failures. Finally, the cascading failure prediction simulation system of power system based on this method was demonstrated and validated by Flexsim software. The result showed that the proposed method was available, and can provided guidance for avoiding and predict cascading failure in power system, and support for stable performance in power system.

Abstract: It starts at co-operation problem between different transportation enterprises, and sets up the Coordination Transportation concept with its management and administration model based on geography information system technology. Then it analyses and points out that its solution to shortest path may have the aid of intellect algorithm. Finally it studies and analyses the measurements during Coordination Transportation between deferent transportation enterprises. Coordination Transportation will help improve the style of transportation, and it will also help set up comprehensive transportation system in China.

Abstract: This study aims to obtain the evolution of innovation cooperation by constructing and analysing patent cooperation networks for the field of Chinese marine industry. Total patents with universities, industries and research institutes are retrieved from SIPO patent database and patent networks are established by using social network analysis. Effects are found that firm-university-research institution innovation cooperation in the industry has been formed, but nodes have different cooperation preferences.

Abstract: Multi-agent based active noise control (ANC) is investigated in this paper. An enclosure consisting of two flexible plates is discussed. The noise control problem is decomposed into several local control problems on the basis of the dominant structural modal. Each local control problem is solved by an intelligent structure, i.e. agent control unit (ACU). The ACU includes sensor, actuator and controller. The relationship among the ACUs is negotiated by a coordination object. The architecture of multi-agent based active control is established using the coordination object. The control system can work smoothly in dynamic environments. It has the flexibility and robustness. The simulation results indicate that the good control performances are attained.

Abstract: Recent years, as computer science and the development of high-tech communications networks, distributed artificial intelligence field of artificial intelligence research as an important branch, more and more industry attention. One of the Agent and Multi-Agent technology research became a hot topic of distributed artificial intelligence research. Research on Multi-Agent technology is mainly a group of autonomous distributed open Agent in a dynamic environment, through interaction, cooperation, competition, negotiation and other acts perform complex control or task solving. Because of its better reflect human social intelligence, more suitable for an open, dynamic social environment, thus causing researchers in various fields of interest, and is widely used in scientific computing, computer network e-commerce, business management and traffic control, etc

Abstract: Over the years, the traditional computer-assisted teaching can not meet the needs of university teaching, the traditional teaching system software, most of the existence of low intelligence, lack of teaching strategies and other shortcomings.Multi-AGENT technology and intelligent tutoring systems is the current research focus in computer intelligence education. Integrating multi-Agent features and multi-Agent application theories in ITS, this paper proposes a multiple Agent-based intelligent network tutoring system design model, detailedly analyzes the functions of each layer in the system, and presents system database category design and system model features.

Abstract: The demerits and current demand of the traditional decision support system (DSS) for power dispatching are analyzed,and the advantages of incorporating the agent technology and the intelligent decision support system (IDSS) are expatiated in detail. A new intelligent decision system model is put forward consequently and the models framework is also given. An example of the integration of three existed expert systems for power system dispatching management into one MAS is given,and the cooperation activities between the agents are described.

Abstract: This paper investigates multi-agent consensus problem with an active leader as well as external disturbances and some faults. The undirected networks with variable interconnection topology are taken into consideration. Distributed consensus control algorithm is proposed to analyze the disturbance rejection and fault sensitivity problem arising in the coordination control of multi-agent networks. With a proposed control scheme, we then present sufficient conditions under which all agents can reach consensus with the desired performance index. Finally, simulation results are provided to demonstrate the effectiveness of our theoretical results.