We propose a BPNN based adaptive sliding mode control scheme for speed tracking of a DC motor with unknown system nonlinearities. The input-output linearization technique is used to cancel the nonlinearities, and outp...
详细信息
We propose a BPNN based adaptive sliding mode control scheme for speed tracking of a DC motor with unknown system nonlinearities. The input-output linearization technique is used to cancel the nonlinearities, and output of the BPNN is incorporated into the controller in the proposed scheme. It is shown that the rotor speed of a DC motor can follow any arbitrarily selected trajectories under variable load torque. Then the application of the approach is tested via some simulations.
An BP neural-network-based adaptive control (NNAC) design method is described whose aim is to control a class of partially unknown nonlinear systems. Making use of the online identification of BP neural networks, the ...
详细信息
An BP neural-network-based adaptive control (NNAC) design method is described whose aim is to control a class of partially unknown nonlinear systems. Making use of the online identification of BP neural networks, the results of the identification could be used into the parameters of the controller. Not only the strong robustness with respect to uncertain dynamics and nonlinearities can be obtained, but also the output tracking error between the plant output and the desired reference output can asymptotically converge to zero by Lyapunov theory in the process of this design *** a simulation example is also presented to evaluate the effectiveness of the design.
This paper presents an approach that is useful for the identification of a fuzzy model in SISO system. The initial values of cluster centers are identified by the Hough transformation, which considers the linearity an...
详细信息
This paper presents an approach that is useful for the identification of a fuzzy model in SISO system. The initial values of cluster centers are identified by the Hough transformation, which considers the linearity and continuity of given input-output data, respectively. For the premise parts parameters identification, we use fuzzy-C-means clustering method. The consequent parameters are identified based on recursive least square. This method not only makes approximation more accurate, but also let computation be simpler and the procedure is realized more easily. Finally, it is shown that this method is useful for the identification of a fuzzy model by simulation.
Traditional optimal thresholding methods are very computationally expensive when extended to multilevel thresholding for their exhaustively search mode. So their applications are limited. In this paper, a relative ent...
详细信息
The electronic ballasts for HID lamps need a protection circuit to prevent from high voltage and/or current stresses on circuit components in case that the HID lamps or the electronic ballasts are in faults. In this p...
详细信息
This Letter presents a novel VQ-based digital image watermarking method. By modifying the conventional GLA algorithm, a codeword-labeled codebook is first generated. Each input image block is then reconstructed by the...
详细信息
This Letter presents a novel VQ-based digital image watermarking method. By modifying the conventional GLA algorithm, a codeword-labeled codebook is first generated. Each input image block is then reconstructed by the nearest codeword whose label is equal to the watermark bit. The watermark extraction can be performed blindly. Simulation results show that the proposed method is robust to JPEG compression, vector quantization (VQ) compression and some spatial-domain processing operations.
We propose a pairwise codebook partitioning technique for robust watermarking based on vector quantization. We group codewords in pairs by similarity. One is labeled '0' and the other labeled '1'. For ...
详细信息
We propose a pairwise codebook partitioning technique for robust watermarking based on vector quantization. We group codewords in pairs by similarity. One is labeled '0' and the other labeled '1'. For each image block, we first find the pair that owns the nearest codeword. The watermark is then embedded by selecting from the pair the codeword whose label equals the corresponding watermark bit. The extraction process can be performed blindly. Simulation results show that the proposed method can survive JPEG compression, high-quality VQ compression and some common signal processing operations.
It is very important to carry out a fuzzy control experiment in HVAC based on the functioning-fuzzy-subset inference (FFSI). This paper presents a simulation model of the testing room dynamic thermal system (TRDTS), w...
详细信息
It is very important to carry out a fuzzy control experiment in HVAC based on the functioning-fuzzy-subset inference (FFSI). This paper presents a simulation model of the testing room dynamic thermal system (TRDTS), which has been founded to meet the requirements of the fuzzy control experiments in HVAC, and analyzes the dynamic responding characteristics of the model in variable-water-volume systems. Then the simulations of the fuzzy control for the TRDTS are carried out, which are based on the FFSI and compositional rule inference (CRI). The experimental principle, some preparatory experiments, and the experimental processes of the FFSI control and PID control for the TRDTS are introduced in detail The main factors that affect the performance of the fuzzy control are discussed, and some corresponding improved methods are suggested. According to the experiments, the fuzzy control based on the FFSI is an effective method to be used in HVAC.
Traditional optimal thresholding methods are very computationally expensive when extended to multilevel thresholding for their exhaustively search mode. So their applications are limited. In this paper, a relative ent...
详细信息
ISBN:
(纸本)0780377028
Traditional optimal thresholding methods are very computationally expensive when extended to multilevel thresholding for their exhaustively search mode. So their applications are limited. In this paper, a relative entropy multilevel thresholding method based on genetic algorithm (RE-GA) is developed. The proposed method makes use of GA's properties such as high efficiency, rapid convergence and global optimization. The relative entropy is treated as the fitness function. Applying the proposed method to process image, the computation speed is accelerated and the quality is improved. Simulation results verify the performance of the proposed method by comparison with the traditional optimal thresholding methods.
An advanced midcourse guidance law based on genetic algorithm (GA) and singular perturbation technique (SPT) is proposed in this paper. The proposed midcourse guidance formulation minimizes the flight time and maximiz...
详细信息
ISBN:
(纸本)0780378652
An advanced midcourse guidance law based on genetic algorithm (GA) and singular perturbation technique (SPT) is proposed in this paper. The proposed midcourse guidance formulation minimizes the flight time and maximizes terminal energy subject to a terminal intercept condition. GA is used to search the optimal attack angle for the flight trajectory, and SPT is applied to approximate the terminal flight time. By combining GA and SPT, the optimal flight guidance law is obtained consequently. Meanwhile, the paper completely eliminates the need for solving two-point boundary-value problems (TBPVP), which is too complex for derivation and implementation. The simulation results show that the resulting guidance law is near-optimal and the proposed method is valid.
暂无评论