The estimation for the nonlinear dynamic system with time-varying input time-delay is an important issue for system identification. In order to estimate the dynamics of the process, a dynamic neural network with exter...
详细信息
The estimation for the nonlinear dynamic system with time-varying input time-delay is an important issue for system identification. In order to estimate the dynamics of the process, a dynamic neural network with external recurrent structure is applied to the modelling procedure. In the case where time-delay is time varying, a useful way is to develop on-line time-delay estimation mechanisms to track the input time-delay variation. In this paper, two schemes respectively called direct as well as indirect time-delay estimators are proposed. Finally, two numerical examples are illustrated for the test of the proposed methods.
In this paper, a procedure for rule extraction from radial basis function networks (RBFNs) is proposed. The algorithm is based on the use of a support vector machine (SVM) as a frontier pattern selector. By using geom...
详细信息
Soccer robot system is a tremendously challenging intelligent system developed to mimic human soccer competition based on the multi discipline research: robotics, intelligentcontrol, computer vision, etc. robot path ...
详细信息
Soccer robot system is a tremendously challenging intelligent system developed to mimic human soccer competition based on the multi discipline research: robotics, intelligentcontrol, computer vision, etc. robot path planning strategy is a very important subject concerning to the performance and intelligence degree of the multi robot system. Therefore, this paper studies the path planning strategy of soccer system by using fuzzy logic. After setting up two fuzziers and two sorts of fuzzy rules for soccer system, fuzzy logic is applied to workspace partition and path revision. The experiment results show that this technique can well enhance the performance and intelligence degree of the system.
Proposes an adaptive learning method based on reinforcement learning for robot path planning problem, which enables the robot to adaptively learn and perform effective path planning, to avoid the moving obstacles and ...
详细信息
Proposes an adaptive learning method based on reinforcement learning for robot path planning problem, which enables the robot to adaptively learn and perform effective path planning, to avoid the moving obstacles and reach the target. Thereby achieving automatic construction of path planning strategy and making the system adaptive to multi robots system dynamic environments, and concludes from computer simulation experiment that the method is powerful to solve the problem of multi robot path planning, and it is a meaningful try to apply reinforcement learning techniques in multi robot systems to develop the system’s intelligence degree.
A novel control technique of brushless dc motors is proposed in this paper. The design of the fuzzy controller combined with a gray predictor is used to improve the response of a brushless dc motor. Using a gray predi...
详细信息
A novel control technique of brushless dc motors is proposed in this paper. The design of the fuzzy controller combined with a gray predictor is used to improve the response of a brushless dc motor. Using a gray predictor to predict the speed errors of the motor and then a compensated energy will be generated which can be used in adjustment of the control energy of the system. Simulation results show that the performance of the control energy and the motor speed is ameliorated.
As to product design itself has quite complexity and many domain influence factors are integrated in concurrent design (CD), conflict phenomena exists in any process of carrying out CD. Conflict elimination is an impo...
详细信息
As to product design itself has quite complexity and many domain influence factors are integrated in concurrent design (CD), conflict phenomena exists in any process of carrying out CD. Conflict elimination is an important key to carrying out CD effectively. Conflict usually relates to many members in multi-function group of CD. Negotiation that is a process of multiple iteration and repeated alternation is utilized in CD conflict elimination. Many objects and constraints are considered in the process of negotiation and it is very hard to have no problem in the process of calculation, reasoning, evaluation and decision-making. As to the updating error is a tracing process and a lot of work done before is needed to repeat, efficiency of conflict elimination is very low. In this paper, a method of conflict elimination of product CD based on blackboard model is put forward. Design conflict producing, system and mechanism of conflict elimination based on blackboard model are analyzed and described. It takes gear CD conflict elimination as an example to illustrate the concrete application of the method and system.
With the increasing of global market competition and dynamic change of market environment, consumer needs are more personal and diversified, enterprise production is more flexible. At present, the production cycle per...
详细信息
With the increasing of global market competition and dynamic change of market environment, consumer needs are more personal and diversified, enterprise production is more flexible. At present, the production cycle period of traditional manufacturing industry is long, delivering goods is not in time, product quality is not good and resource are not used in reason. Because of the phenomena, products are not met the requirements of market and lack of market competition ability. For changing the situation, the development direction is building concurrent agility dynamic alliance of product development. So this paper puts forward an improved fuzzy reform optimization method of design task in Concurrent engineering (CE). Using this method, enterprise can develop product rapidly to satisfy consumer requirements and have high quality, low cost, reasonable price and good service, that is because it can assign right task to right person in right time for shortening development time of product.
In this paper, a new fuzzy reaching law for discrete-time variable structure controlsystems is developed. Based on this law, a discrete controller and its control algorithm that satisfies the Lyapunov stability can b...
详细信息
In this paper, a new fuzzy reaching law for discrete-time variable structure controlsystems is developed. Based on this law, a discrete controller and its control algorithm that satisfies the Lyapunov stability can be easily derived and developed. Compare with the traditional reaching law, the new fuzzy reaching law we proposed has much better performance. The steady state error caused by delay of sampling of discrete system could be greatly reduced.
This paper provide a description of an approach for the realisation of bio-inspired systems on programmable logic devices. Initially a proposed embedded system architecture is presented followed by an outline of the b...
详细信息
ISBN:
(纸本)0970789009
This paper provide a description of an approach for the realisation of bio-inspired systems on programmable logic devices. Initially a proposed embedded system architecture is presented followed by an outline of the bio-inspired approach that will be employed. The paper then describes the difficulties associated with this strategy and offers some suggested solutions for its realisation.
In this paper we concentrate on some important timing characteristics of Elevator Group control (EGC) systems. The main discussion and calculations should be considered as a further development of Three Passages (TP) ...
详细信息
ISBN:
(纸本)0780365763
In this paper we concentrate on some important timing characteristics of Elevator Group control (EGC) systems. The main discussion and calculations should be considered as a further development of Three Passages (TP) concept, already presented in our previous papers. To achieve better global performance of EGC system, especially to reduce hall call waiting time, calculation methodology of car kinematics is presented. The importance of detailed kinematics considerations is demonstrated with data taken from real high-speed EGC system, existent in 63-floor building - Seoul, Korea.
暂无评论