• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.20-20
• /
• 2000

Back-propagation neural network (BPNN) is the most prevalently used paradigm in modeling semiconductor manufacturing processes, which as a neuron activation function typically employs a bipolar or unipolar sigmoid function in either hidden and output layers. In this study, applicability of another linear function as a neuron activation function is investigated. The linear function was operated in combination with other sigmoid functions. Comparison revealed that a particular combination, the bipolar sigmoid function in hidden layer and the linear function in output layer, is found to be the best combination that yields the highest prediction accuracy. For BPNN with this combination, predictive performance once again optimized by incrementally adjusting the gradients respective to each function. A total of 121 combinations of gradients were examined and out of them one optimal set was determined. Predictive performance of the corresponding model were compared to non-optimized, revealing that optimized models are more accurate over non-optimized counterparts by an improvement of more than 30%. This demonstrates that the proposed gradient-optimized teaming for BPNN with a linear function in output layer is an effective means to construct plasma models. The plasma modeled is a hemispherical inductively coupled plasma, which was characterized by a 24 full factorial design. To validate models, another eight experiments were conducted. process variables that were varied in the design include source polver, pressure, position of chuck holder and chroline flow rate. Plasma attributes measured using Langmuir probe are electron density, electron temperature, and plasma potential.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권9호
• /
• pp.2882-2903
• /
• 2022

Image super-resolution (SR) processing is of great value in the fields of digital image processing, intelligent security, film and television production and so on. This paper proposed a densely connected deep learning network based on cascade architecture, which can be used to solve the problem of super-resolution in the field of image quality enhancement. We proposed a more efficient residual scaling dense block (RSDB) and the multi-channel cascade architecture to realize more efficient feature reuse. Also we proposed a hybrid loss function based on L₁ error and L_∞ error to achieve better L_∞ error performance. The experimental results show that the overall performance of the network is effectively improved on cascade architecture and residual scaling. Compared with the residual dense net (RDN), the PSNR / SSIM of the new method is improved by 2.24% / 1.44% respectively, and the L_∞ performance is improved by 3.64%. It shows that the cascade connection and residual scaling method can effectively realize feature reuse, improving the residual convergence speed and learning efficiency of our network. The L_∞ performance is improved by 11.09% with only a minimal loses of 1.14% / 0.60% on PSNR / SSIM performance after adopting the new loss function. That is to say, the L_∞ performance can be improved greatly on the new loss function with a minor loss of PSNR / SSIM performance, which is of great value in L_∞ error sensitive tasks.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권2호
• /
• pp.140-146
• /
• 2016

This paper proposes a control method of the Segway with unknown control coefficient and input saturation. To design a simple controller for the Segway with the model uncertainty, the prescribed performance function is used. Furthermore, an auxiliary variable is introduced to deal with unknown time-varying control coefficient and input saturation problem. Due to the auxiliary variable, function approximators are not used in this paper although all model uncertainties are unknown. Thus, the controller can be simple. From the Lyapunov stability theory, it is proved that all errors of the proposed control system remain within the prescribed performance bounds. Finally, the simulation results are presented to demonstrate the performance of the proposed scheme.

• 설비공학논문집
• /
• 제13권3호
• /
• pp.200-208
• /
• 2001

In indoor temperature control of a heat pump, a reduction in energy consumption is very important. However, most control schemes for heat pumps have focused only on control performance such s settling time and steady-state error. In this paper, the model predictive control (MPC) which includes the energy-related variable in this cost function is proposed. By computing the control signal minimizing this cost function, the trade-off between energy reduction and temperature control performance can be obtained. Since the MPC required the process model, the dynamic mode of a heat pump is also obtained by the system identification technique. Performance of the proposed MPC considering energy efficiency is compared with the two other control schemes. It si shown that the proposed scheme can consume less energy thant hte others in achieving similar control performance.

• ETRI Journal
• /
• 제38권3호
• /
• pp.425-434
• /
• 2016

A novel average magnitude difference function (AMDF)-based pitch detection scheme (PDS) is proposed to achieve better performance in speech quality. A performance evaluation of the proposed PDS is carried out through both a simulation and a real-time implementation of a speech analysis-synthesis system. The parameters used to compare the performance of the proposed PDS with that of PDSs that are based on either a cepstrum, an autocorrelation function (ACF), an AMDF, or circular AMDF (CAMDF) methods are as follows: percentage gross pitch error (%GPE); a subjective listening test; an objective speech quality assessment; a speech intelligibility test; a synthesized speech waveform; computation time; and memory consumption. The proposed PDS results in lower %GPE and better synthesized speech quality and intelligibility for different speech signals as compared to the cepstrum-, ACF-, AMDF-, and CAMDF-based PDSs. The computational time of the proposed PDS is also less than that for the cepstrum-, ACF-, and CAMDF-based PDSs. Moreover, the total memory consumed by the proposed PDS is less than that for the ACF- and cepstrum-based PDSs.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.823-828
• /
• 1992

A novel steepest descent adaptive filter algorithm, which uses the instantaneous stochastic gradient for the steepest descent direction, is derived from a newly devised performance index function. The performance function for the new algorithm is improved from that for the LMS in consideration that the stochastic steepest descent method is utilized to minimize the performance index iterativly. Through mathematical analysis and computer simulations, it is verified that there are substantial improvements in convergence and misadjustments even though the computational simplicity and the robustness of the LMS algorithm are hardly sacrificed. On the other hand, the new algorithm can be interpreted as a variable step size adaptive filter, and in this respect a heuristic method is proposed in order to reduce the noise caused by the step size fluctuation.

• 제어로봇시스템학회논문지
• /
• 제21권3호
• /
• pp.237-242
• /
• 2015

This paper presents a method to enhance tracking performance of an input-constrained bilinear system using MPC (Model Predictive Control) when a feasible tracking control is known. Since the error dynamics induced by the known tracking control is asymptotically stable, there exists a Lyapunov function for the stable error dynamics. By defining a cost function including the Lyapunov function and describing tracking performance, an MPC law is derived. In simulation, the performance of the proposed MPC law is demonstrated by applying it to a converter model.

• Architectural research
• /
• 제17권3호
• /
• pp.83-91
• /
• 2015

A comprehensive understanding of functions and performances enables a selection of appropriate alternatives to the existing design and can prevent defective design. A performance-based design quality management can ensure successful project completion. This study proposes a new model for design quality management in order to prevent defective design and to minimize design change. The new quality management model defines the requirement about function and performance based on technical characteristic, and assesses suitability for design alternatives. This study attempts to propose a quality matrix assessment method that can compare the alternative design and requirements defined with the new quality management model. This method can judge conformity and suitability of design quality in accordance with the requirements configured.

• 한국자동차공학회논문집
• /
• 제8권5호
• /
• pp.138-147
• /
• 2000

Vehicle suspension systems are parts which effect performances of a vehicle such as ride quality, handing characteristics, straight performance and steering effort etc. Kinematic design is a decision of joints` position for straight performance and steering effort. But, when vehicle is rebounding and bumping, chang of joints` displacement is nonlinear and a surmise of straight performance and steering effort at that joints` position is difficult. So design of suspension systems is done through a inefficient method of tried-and-error depending on designer`s experience. In this paper, kinematic design of suspension systems was done through the optimal design using a genetic algorithm. For this optimal design, the function for quantification of straight performance and steering effort was made, and the kinematic design method of suspension systems having this function as the objective function was suggested.

• 산업경영시스템학회지
• /
• 제12권20호
• /
• pp.71-76
• /
• 1989

In this paper, GERT network in modeled to improve the network of manufacturing process with feedback loop. A lot of Information on the GERT network can be derived from the equivalent W-function and MGF(moment generating function) using Mason's rule. These equations are used in calculating the variations of the performance measure and in improving the system performance. System improvement in manufacturing process is achieved by increasing the equivalent probabilities of each branches and by decreasing the expected equivalent time.