124 results
Search Results
Now showing 1 - 10 of 124
Item Intelligent Control for Anti-lock Braking Systems to Track Dynamic Optimal Slip Ratio(2007-01-01) W.-Y. Wang; I-H. Li; D.-F. Chung; M.-C. ChenItem MIMO Robust Control via T-S Fuzzy Models for Nonaffine Nonlinear Systems(2007-07-26) W.-Y. Wang; L.-C. Chien; I-H. Li; S.-F. SuThis paper proposes on-line modeling via Takagi-Sugeno (T-S) fuzzy models and robust adaptive control for a class of generalized multiple input multiple output (MIMO) nonlinear dynamic systems with external disturbances. The T-S fuzzy model is established to approximate the nonaffine nonlinear dynamic system in a linearized way and is used to be an error compensator for external disturbances and system uncertainly, i.e. the unmodeled dynamics, modeling errors and external disturbances. In second type adaptive laws, fuzzy B-spline membership functions (BMFs) are developed for on-line tuning. In this paper, we can prove that the closed-loop system which is controlled by the proposed controller is stable and the tracking error will converge to zero.Item Genetic algorithms-derived digital integrators and their applications in discretization of continuous systems(2002-01-01) C.-C. Hsu; W.-Y. Wang; C.-Y. YuA set of enhanced digital integrators (EDI) with improved accuracy via genetic algorithms are proposed in this paper. By specifying a desired power for the integrator to be sought and the interval for comparison, chromosomes consisting of parameters of the enhanced digital integrator are then searched by the genetic algorithm based on root mean squared (RMS) error between the original integrator and candidates of the enhanced digital integrator. Thus, all the best parameters of an optimal enhanced digital integrator can be evolutionarily obtained. To demonstrate the effectiveness of the proposed approach, the derived enhanced digital integrators are used to obtain the discrete approximation for continuous systems.Item A dynamic hierarchical fuzzy neural network for a general continuous function(2008-06-06) W.-Y. Wang; I-H. Li; S.-C. Li; M.-S. Tsai; S.-F. SuA serious problem limiting the applicability of the fuzzy neural networks is the "curse of dimensionality", especially for general continuous functions. A way to deal with this problem is to construct a dynamic hierarchical fuzzy neural network. In this paper, we propose a two-stage genetic algorithm to intelligently construct the dynamic hierarchical fuzzy neural network (HFNN) based on the merged-FNN for general continuous functions. First, we use a genetic algorithm which is popular for flowshop scheduling problems (GAFSP) to construct the HFNN. Then, a reduced-form genetic algorithm (RGA) optimizes the HFNN constructed by GAFSP. For a real-world application, the presented method is used to approximate the Taiwanese stock market.Item Distance Measurement Using Single Non-metric CCD Camera(2007-08-26) T.-H. Wang; M.-C. Lu; W.-Y. Wang; C.-Y. TsaiA novel measuring system based on a single non-metric CCD camera and a laser projector is proposed in this paper for measuring distance of a remote object. The setup of the measuring system is relatively easy, in which the laser pointer is positioned beside the CCD camera so that laser beam projected is parallel to the optical axis of the camera in a fixed distance. Based on a fast and effective algorithm proposed in this paper, the central position of the projected laser spot in images due to the laser beam can be accurately identified for calculating the distance of a targeted object according to an established formula. Because of the relationship of pixels counts of the diameter of the laser spot at different distances, processing of a sub-frame comprising a fraction of scan lines, rather than the whole image, is only required. Significant savings of computation time can therefore be achieved. Simulation results show satisfactory measurements can be obtained, where averaged absolute measurement errors via the proposed approach lie within 0.502%.Item B-spline Adaptive Backstepping Controllers for Affine Nonlinear Systems(2009-06-01) Z.-H. Li; W.-Y. Wang; Y.-G. LeuItem Observer-Based Direct Adaptive Fuzzy-Neural Control for Anti-lock Braking Systems(中華民國模糊學會, 2006-12-01) G.-M. Chen; W.-Y. Wang; T.-T. Lee; C.-W. TaoIn this paper, an observer-based direct adaptive fuzzy-neural controller (ODAFNC) for an anti-lock braking system (ABS) is developed under the constraint that only the system output, i.e., the wheel slip ratio, is measurable. The main control strategy is to force the wheel slip ratio to well track the optimal value, which may vary with the environment. The observer-based output feedback control law and update law for on-line tuning of the weighting factors of the direct adaptive fuzzy-neural controller are derived. By using the strictly-positive-real (SPR) Lyapunov theory, the stability of the closed-loop system can be guaranteed. Simulation results demonstrate the effectiveness of the proposed control scheme forABS control.Item Fuzzy neural network genetic approach to design the SOC estimator for battery powered electric scooter(2004-01-01) Y.-S. Lee; T.-Y. Kuo; W.-Y. WangThis paper presents a new method for estimating the individual battery state-of-charge (SOC) of electric scooter (ES). The proposed method is to model ES batteries by using the fuzy inference neural network system. A reduced form genetic algorithm (RGA) is employed to tune control point of the B-spline membership functions (BMFs) and the weightings of the fuzzy neural network (FNN). The proposed FNN with RGA (FNNRGA) optimization approach can achieve the faster learning rate and lower estimating error than the conventional gradient descent method. The validity of the SOC estimator is further verified by a constructed multiple input multiple output (MIMO) FNN structure for estimating the SOCs of battery powered ES. A fixed velocity discharging profiles of the ES batteries are investigated to train the FNN for precise estimating the SOCs of the battery strings. Furthermore, a testing data profile is used to demonstrate the superior robust and over-fitting suppressed performance of the proposed method. The estimated SOCs are directly compared with the actual SOCs under different FNN methods, verifying the accuracy and the effectiveness of the proposed intelligent modeling method.Item GA-based evolutionary design of PID controller for twin rotor multi-input multi-output system(私立輔仁大學理工學院, 2001-12-01) W.-Y. Wang; H.-C. HuangItem 線上基因演算法之模糊類神經控制器設計(2004-01-01) W.-Y. Wang; Y.-H. Li