This paper presents a method to compute sub-optimal control strategies of discrete time large scale nonlinear systems by neural networks. The method is based on the principle of decomposition of the global system into...
详细信息
This paper presents a method to compute sub-optimal control strategies of discrete time large scale nonlinear systems by neural networks. The method is based on the principle of decomposition of the global system into interconnected subsystems for which we consider that non-linearities are located in the interconnection terms. Then, a mixed method is considered to coordinate between different subsystems in order to compute the optimal control. So, for each subsystem, local optimal feedback gains are expressed in terms of the interconnection vector. For this purpose, neural networks have been used in order to identify these gains. Simulation results of a rotary crane show that the proposed method yields to satisfactory performances. The robustness of the proposed approach is analysed.
This work proposes a new methodology to evaluate and improve the QMS (Quality Management System) effectiveness and efficiency to succeed for a factual approach including all monitoring parameters. This idea is justifi...
详细信息
This work proposes a new methodology to evaluate and improve the QMS (Quality Management System) effectiveness and efficiency to succeed for a factual approach including all monitoring parameters. This idea is justified by the difficulties incurred by the organizations to establish a continuous improvement's system based on the objectives and the process approach. In addition, the guidelines defined by the FDX 50-174 part published by AFNOR to assess the QMS effectiveness, still guides defining the assessment criteria and progress levels. Indeed, to facilitate the continuous improvement system's integration, we propose a new methodology based on a broad range of monitoring tools (functional and operational indicators, audits, quality control, customer satisfaction) and including the requirements of the process and the system approach.
In this paper, we present a VSS-based tracking control for a fixed point regulation of 2-DOF underactuated manipilators The design approach is systematic and relies on the selection of appropriate choice of two slidin...
详细信息
ISBN:
(纸本)9781424426270
In this paper, we present a VSS-based tracking control for a fixed point regulation of 2-DOF underactuated manipilators The design approach is systematic and relies on the selection of appropriate choice of two sliding surface. The controller is designed for the both sliding surfaces are attractive. Lyapunov theory is used to study and demonstrate the stability of the system. Convergence of state space is proved and robustness issues to bounded disturbances are also investigated. Simulation results on 2-DOF whirling pendulum are presented to chow the effectiveness of this approach.
This work is aimed at looking into the use of fuzzy systems for the study of nonlinear systems. In a first step, zero-order and first-order Sugeno fuzzy models are defined as approximators of nonlinear systems. It has...
详细信息
ISBN:
(纸本)9781424422050
This work is aimed at looking into the use of fuzzy systems for the study of nonlinear systems. In a first step, zero-order and first-order Sugeno fuzzy models are defined as approximators of nonlinear systems. It has been found that zero-order fuzzy systems are equivalent to the classical interpolation approach. Nonlinear terms have been limited by two fuzzy systems. The mean fuzzy system gives good accuracy. As illustrations, some numerical applications have been considered to show the efficiency of the use of fuzzy systems to study nonlinear problems.
In this paper, an optimization method based on multi objective genetic algorithm (MOGA) is proposed in the design of a filter bank discrete wavelet transform (DWT). The different criteria are related to wavelet perfec...
详细信息
In this paper, an optimization method based on multi objective genetic algorithm (MOGA) is proposed in the design of a filter bank discrete wavelet transform (DWT). The different criteria are related to wavelet perfect reconstruction condition and minimization of the total number of non zero bits. Simulation results illustrate the optimization process applied to a case study : the Biorthogonal 9/7 DWT. They reveal improvement of compression performance and minimization of the number of non-zero bits. Performance measurements of the introduced method are even better than the original unquantized filter itself. Implementation results show a reducing hardware cost in comparison of proposed quantization method with trivial ones.
Localization is one of the most important functions for the mobile robot navigation. Most of previous position estimation methods calculate current position and orientation of mobile robot by applying various localiza...
详细信息
Localization is one of the most important functions for the mobile robot navigation. Most of previous position estimation methods calculate current position and orientation of mobile robot by applying various localization schemes with the information obtained from internal sensors which are set on the mobile robot, or by recognizing an artificial landmark attached on the environment. Several drawbacks about them have been brought up. To avoid these inconvenient, a new localization method that calculate in real time the absolute position of the mobile robot by using external camera fixed on the ceiling in the indoor environment is proposed. Besides, this approach provide a low expensive solution using a Webcam. The effectiveness of the proposed localization algorithm is demonstrated through the experiments.
This paper deals with two approaches for on line structure identification of fuzzy models. In the first one, a constructive algorithm is adopted to generate the fuzzy rules: it starts with a single pattern and a singl...
详细信息
This paper deals with two approaches for on line structure identification of fuzzy models. In the first one, a constructive algorithm is adopted to generate the fuzzy rules: it starts with a single pattern and a single fuzzy rule and grows progressively to reduce the system error within the specified tolerance. In the second one, an evolutionary algorithm is applied based on an alternation between incremental and pruning criteria. Indeed, the rule base is expanded when the model can not reduce the system error and one rule is removed if it has a petty contribution in the model output along some patterns. The presented approaches have been applied for two examples of dynamic systems to compare the identification performance.
In this paper, we present a VSS-based tracking control for a fixed point regulation of 2-DOF underactuated manipulators. The design approach is systematic and relies on the selection of appropriate choice of two slidi...
详细信息
In this paper, we present a VSS-based tracking control for a fixed point regulation of 2-DOF underactuated manipulators. The design approach is systematic and relies on the selection of appropriate choice of two sliding surface. The controller is designed for the both sliding surfaces are attractive. Lyapunov theory is used to study and demonstrate the stability of the system. Convergence of state space is proved and robustness issues to bounded disturbances are also investigated. Simulation results on 2-DOF whirling pendulum are presented to chow the effectiveness of this approach.
This paper presents a design approach to hybrid controlsystems, combining analytical feedback linearization control techniques with neural networks. Such a mixed implementation leads to a more effective control desig...
详细信息
This paper presents a design approach to hybrid controlsystems, combining analytical feedback linearization control techniques with neural networks. Such a mixed implementation leads to a more effective control design with improved system performance and robustness. The main objective of integrating neural networks is to overcome the problems with uncertainties in the plant parameters and structure encountered in the analytical model-based design. Shunt DC motor is characterized by complex nonlinear and time-varying dynamics and inaccessibility of some model parameters for on line measurements, and hence can be considered as an important challenging engineering topic. The input-state feedback linearization technique is known for its good results locally in a neighborhood of an operating point. However, these results are sensitive to model parameter variations and so performances may deteriorate. Neural network-based controllers are considered as candidates for this parameters sensitivity. In a first step, an algorithm for analytical exact input-state linearizing control is formulated. The following step is dedicated to the robust neural feedback controller design. A simulation study of these methods is presented. The effectiveness of the neural controller with respect to the analytical one is demonstrated for a large armature resistance variation.
In this paper, a new SVM (Support Vector Machines) synthesis method is presented. This method is based essentially on training criterion optimization of this machine by a set of hierarchical structures of learning aut...
详细信息
In this paper, a new SVM (Support Vector Machines) synthesis method is presented. This method is based essentially on training criterion optimization of this machine by a set of hierarchical structures of learning automata. This methodology is adopted for the development of off-line isolated handwritten digits recognition system. A comparison is taken between this new approach and that of a standard approach for SVM synthesis. These two methodologies are also compared with a neural network based classification method. The obtained results show the performances of the new suggested method for SVM synthesis.
暂无评论