فصلنامه روشهای هوشمند در صنعت برق
پیاپی 9 (بهار 1392)

In this paper، an analysis/synthesis system based on the natural Cochlear model and the human auditory perception properties is presented that is capable of coding the speech signal under harsh acoustic conditions. For this purpose، the corrupted signal is decomposed into a number of sub-bands using complex Gammatone filter bank، and the sub-band signals are individually and adaptively denoised. Temporal masking، a combination of a novel non-uniform quantization method and lossless coding algorithms are then applied to reduce the number of coefficients and compression. The proposed system is very robust and effective in dealing with different kinds of noises such as white، colored and periodic noises. Objective and Subjective quality measurements demonstrate significant improvement in the perceptual quality of synthesized speech while considerable reduction in bit-rate to approximately 14. 6 Kbps is achieved.

Inverted pendulum system state equations of the form of quality control standard consist two nonlinear functions. Since، ANFIS network is an universal approximator، in this paper، two ANFIS are used to model nonlinear dynamic functions of inverse pendulum. The adaptive fuzzy rules are applied، such that the feedback linearization control input can be best approximated and the closed-loop system is stable. Simulation results indicate the remarkable capabilities of the proposed control algorithm and good transient response characteristics of the output system.

Most of the existing image resolution enhancement algorithms assume that the image is clean and noise free، but this assumption is not practically valid. One strategy for interpolation of noisy images is to denoise the image first and then interpolate the denoised image. However، this strategy does not lead to satisfying results because denoising may smooth image details and also other artifacts such as blurring and blocking introduced due to image denoising will be amplified in the following interpolation stage. Thus، in this paper we propose a joint salt and pepper noise removal and resolution enhancement algorithm using dual-tree complex wavelet transform and feedforward neural networks. In this algorithm، the wavelet subbands corresponding to noise free high resolution image are estimated from noisy low resolution image by multi-layer perceptron (MLP). Therefore the noise free high resolution image is obtained by complex wavelet reconstruction of the estimated subbands. Takeing advantages of complex wavelet transform such as nearly shift invariance and directional selectivity the subband estimation by neural networks is done with high accuracy. As it is verified in the experimental results، the proposed algorithm has better performance both subjectively and objectively and is able to maintain the image fine structures well.

In order to improve transient stability and increase the system damping، this paper introduces a specific way of coordination between FACTS devices (TCSC and SVC). In order to improve the performance and use all the features of TCSC and SVC (presented in this article)، it is necessary a controller be used in which does not have the limitations of other controllers and simply be also able to quickly respond and adapt to the power system model. Hence، these features can be found in the intelligent controllers in which the ADALINE network is one of them. To better understand the performance of the ADALINE network controller; this controller will be compared with a controller which is designed by the optimal control parameters (LQR). The instruments used for FACTS are from the injection type and therefore، it is possible to use a fixed factorization ybus matrix in the calculations. Simulation results using non-linear network show that the ADALINE neural network controller has better performance than the LQR controller and can cause significant improvement on damping and transmission ability in the power system.

This paper presents an optimized controller around the longitudinal axis of multivariable system in one of the aircraft flight conditions. The controller is introduced in order to control the angle of attack from the pitch attitude angle independently (that is required for designing a set of direct force-modes for the longitudinal axis) based on particle swarm optimization (PSO) algorithm. The autopilot system for military or civil aircraft is an essential component and in this paper، the autopilot system via 6 degree of freedom model for the control and guidance of aircraft in which the autopilot design will perform based on defining the longitudinal and the lateral-directional axes are supposed. The effectiveness of the proposed controller is illustrated by considering HIMAT aircraft. The simulation results verify merits of the proposed controller.

In this work، surge of prevention is a critical problem in oil and gas industries، particularly when return gas flow or gas flow reduces in transportation of gas pipelines. This paper is illustrated new results about surge control of centrifugal compressors. surge phenomenon is flow unsteady state in compressors which causes damages seriously in compressor construction. Furthermore، it also demonstrates in comparison with anti surge control، active surge control expands stability range. Active surge control which based on fuzzy logic،is the main idea that used in this investigation. Using fuzzy controller causes an improvement in compressor''s condition and increase performance range of the compressor، in addition to prevention of any instability in compressor. The simulation results is also satisfactory.

An effective method is introduced to overcome the narrow strip width in unequal Wilkinson power divider with high dividing ratio. In the proposed Wilkinson power divider، the separated microstrip lines are replaced by a uniform asymmetrical microstrip coupled lines. To design the power divider، a suitable error function is defined and then minimized which led to the final dimensions of the proposed unequal Wilkinson power divider. A sample of the proposed power divider with 4:1 dividing ration is designed and simulated، which indicate the effectiveness of the proposed power divider and its design method.

Logo detection and recognition module is a vital requirement in official automation systems for document image archiving and retrieval applications. In this paper، we present a novel framework for logo detection and recognition based on sequential segmentation and classification strategy of document image. In this framework، using a two-stage segmentation algorithm (consisting of wavelet-based and threshold-based segmentation algorithms) and hierarchical classification by two multilayer Perceptron (MLP) classifiers and a k-nearest neighbor (KNN) classifier، a document image divides to text، pure picture and logo candidate regions. Ultimsately، in final decision، class of logo candidate region is determined based on pre-defined classes. In the hierarchical classification and logo recognition stages، the best feature space is selected by forward selection algorithm from a perfect set of texture and shape features. The proposed structure is evaluated on a variety and vast database consisting of the document and non-document images with Persian and international logos. The obtained results show efficiency of the proposed framework in the real and operational conditions.