Inspired by the biological immune system, the artificial endocrine system (AES) has drawn great research interest from different communities during the past decade. The AES is a novel branch of computational intellige...
详细信息
Inspired by the biological immune system, the artificial endocrine system (AES) has drawn great research interest from different communities during the past decade. The AES is a novel branch of computational intelligence methods. This paper gives a comprehensive overview of the AES under a preliminary theoretical framework, which is based on the interpretative models of biological endocrine system. Some typical AES-based algorithms with their applications are discussed here. We address a few key issues in the current state-of-the-art AES research work. The possible future directions of the AES are also pointed out.
control of turbocharged diesel engines is a challenging task due to system nonlinearities and constraints on the inputs and process variables. In this paper nonlinear model predictive control is applied to control a d...
详细信息
control of turbocharged diesel engines is a challenging task due to system nonlinearities and constraints on the inputs and process variables. In this paper nonlinear model predictive control is applied to control a diesel engine with a variable geometry turbocharger and an exhaust gas recirculation valve. The overall control objective is to regulate the setpoints of the air-fuel ratio and the amount of recirculated exhaust gas in order to obtain low exhaust emission values and low fuel consumption without smoke generation. Simulation results are presented to study the advantages and disadvantages of nonlinear model predictive control. The achieved performance is compared in simulations with a linear state feedback controller and an input-output linearization based control method. As shown, nonlinear model predictive control achieves good overall control performance and constraint satisfaction.
Reinforcement learning is a powerful method for solving sequential decision making problems. But it is difficult to apply to practical problems such as multi-agent systems with continuous state space problems. In this...
详细信息
Reinforcement learning is a powerful method for solving sequential decision making problems. But it is difficult to apply to practical problems such as multi-agent systems with continuous state space problems. In this paper we present a cooperative strategy learning method to solve the problem. It combines WoLF-PHC algorithms with function approximation of RL techniques. By this method an agent could learn cooperative behavior in the multi-agent environment with continuous state space. Using a subtask of RoboCup soccer,Keepaway, we demonstrate the effective of this learning method and the experiment results show that the algorithm converges.
The complete dynamic model in link space for a general six degree of freedom Stewart platform is developed and a multi-input multi-output (MIMO) nonlinear controller equipped with friction domination is proposed to re...
详细信息
In this paper, a new sliding mode controller design is proposed for sampled-data LTI systems based on the digital redesign methodology. With this controller, chattering is eliminated. LMI (linear matrix inequality) is...
详细信息
In this paper, a new sliding mode controller design is proposed for sampled-data LTI systems based on the digital redesign methodology. With this controller, chattering is eliminated. LMI (linear matrix inequality) is employed to derive the controller. The simulation results have demonstrated the effectiveness of the proposed algorithm
The no-wait hybrid flowshop scheduling problem is studied to minimize the makespan. This class of problem is characterized by the processing of n jobs through m stages with one or more machines at each stage, and ther...
详细信息
The no-wait hybrid flowshop scheduling problem is studied to minimize the makespan. This class of problem is characterized by the processing of n jobs through m stages with one or more machines at each stage, and there is no-wait restriction between stages. An integer programming model is first formulated. Then the complete scheduling scheme for a given job sequence is built, and a new heuristic based on the scheduling scheme is proposed. Computational experience demonstrates the effectiveness of the heuristic algorithm in finding near optimal schedules.
The detection of small current ground fault line is one of important problem in power system. This paper presents a novel method to give the correct decision when the fault happened. This method only use of the energy...
详细信息
The detection of small current ground fault line is one of important problem in power system. This paper presents a novel method to give the correct decision when the fault happened. This method only use of the energy variation, unlike other method use of the waveform, phase, and amplitude in particular time domain, or harmonics in special frequency domain. This method is advantageous to use neural network to give the correct decision. The validity of fault line detection principle and method are verified by the theory and experiment data
In this paper, a novel testing method for on-ground test of space manipulator is introduced. The configurations of the testbed and the manipulator are described in detail. To accomplish the test of three-dimensional m...
详细信息
In this paper, a novel testing method for on-ground test of space manipulator is introduced. The configurations of the testbed and the manipulator are described in detail. To accomplish the test of three-dimensional movement, a modified testbed using air-bearings is designed. By adopting the two-step testing method, which is presented in this paper, the three-dimensional positioning accuracy and the three-dimensional attitude accuracy of the space manipulator can be measured. The main idea of this method is to divide a three-dimensional movement into two planar movements, which can be performed on the testbed. The equations of data processing are deduced. The analysis shows that the mentioned testing method is practical for the research of space manipulators
The Chinese experimental space system for on-orbit robotistic services (CESSORS) is to be developed by Shenzhen Space technology Center. CESSORS consists of two satellites and a mounted robotic manipulator. In this pa...
详细信息
The Chinese experimental space system for on-orbit robotistic services (CESSORS) is to be developed by Shenzhen Space technology Center. CESSORS consists of two satellites and a mounted robotic manipulator. In this paper, the design of the two satellites and the manipulator is described in detail, as well as the target detecting system and the ground teleoperation system. The planned missions include calibration of robot manipulator, teleoperation of the manipulator, coordinated control, on-orbit robotistic services, on-orbit target chasing and approaching, and flying around inspection. This paper introduces the components of CESSORS, and shows the on-orbit missions
Even the support vector machine (SVM) has been proved to improve the classification performance greatly than a single SVM, the classification result of the practically implemented SVM is often far from the theoretical...
详细信息
Even the support vector machine (SVM) has been proved to improve the classification performance greatly than a single SVM, the classification result of the practically implemented SVM is often far from the theoretically expected level because they don't evaluate the importance degree of the output of individual component SVMs classifier to the final *** paper proposes a boosting least square support vectormachine (LS-SVM) ensemble method based on fuzzy integral to improve the limited classification performance. In general,the proposed method is built in 3 steps: construct the component LS-SVM;obtain the probabilistic outputs model of each component LS-SVM;combine the component predictions based on fuzzy integral. The trained individual LS-SVMs are aggregated to make a final decision. The simulating results demonstrate that the proposed LS-SVM ensemble with boosting outperforms a single SVM and traditional SVM (or LS-SVM) ensemble technique via majority voting in terms of classification accuracy.
暂无评论