• 대한전기학회논문지:시스템및제어부문D
• /
• 제52권7호
• /
• pp.424-433
• /
• 2003

Evolutionary design related to the optimal design of Polynomial Neural Networks (PNNs) structure for model identification of complex and nonlinear system is studied in this paper. The PNN structure is consisted of layers and nodes like conventional neural networks but is not fixed and can be changable according to the system environments. three types of polynomials such as linear, quadratic, and modified quadratic is used in each node that is connected with various kinds of multi-variable inputs. Inputs and order of polynomials in each node are very important element for the performance of model. In most cases these factors are decided by the background information and trial and error of designer. For the high reliability and good performance of the PNN, the factors must be decided according to a logical and systematic way. In the paper evolutionary algorithm is applied to choose the optimal input variables and order. Evolutionary (genetic) algorithm is a random search optimization technique. The evolved PNN with optimally chosen input variables and order is not fixed in advance but becomes fully optimized automatically during the identification process. Gas furnace and pH neutralization processes are used in conventional PNN version are modeled. It shows that the designed PNN architecture with evolutionary structure optimization can produce the model with higher accuracy than previous PNN and other works.

• Computers and Concrete
• /
• 제20권4호
• /
• pp.449-459
• /
• 2017

Fresh and hardened behaviors of a new hybrid fiber (steel fiber, polyvinyl alcohol fiber and calcium carbonate whisker) reinforced cementitious composites (HyFRCC) with admixtures (fly ash, silica fume and water reducer) have been studied. Within the limitations of the equipment and testing program, it is illustrated that the rheological properties of the new HyFRCC conform to the modified Bingham model. The relations between flow spread and yield stress as well as flow rate and plastic viscosity both conform well with negative exponent correlation, justifying that slump flow and flow rate test can be applied to replace the other two as simple rheology measurement and control method in jobsite. In addition, for the new HyFRCC with fly ash and water reducer, the mathematical model between the rheological and mechanical properties conform well with the quadratic function, and these quadratic function curves are always concave upward. Based on mathematical analysis, an optimal range of rheology/ flowability can be identified to achieve ideal mechanical properties. In addition, this optimization method can be extended to PVA fiber reinforced cement-based composites.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 B
• /
• pp.433-436
• /
• 2003

The estimation of the position and the orientation for the mobile robot constitutes an important problem in mobile robot navigation. Although the odometry can be used to describe the motions of the mobile robots, there inherently exist the gaps between the real robots and the mathematical model, which may be caused by a number of error sources contaminating the encoder outputs. Hence, applying the standard extended Kalman filter for the nominal model is not supposed to give the satisfactory performance. As a solution to this problem, a new robust extended Kalman filter is proposed based on the Krein space approach. We consider the uncertain discrete time nonlinear model of the mobile robot that contains the uncertainties represented as sum quadratic constraints. The proposed robust filter has the merit of being constructed by the same recursive structure as the standard extended Kalman filter and can, therefore, be easily designed to effectively account for the uncertainties. The simulations will be given to verify the robustness against the parameter variation as veil as the reliable performance of the proposed robust filter.

• 대한전기학회논문지:전기물성ㆍ응용부문C
• /
• 제52권7호
• /
• pp.424-424
• /
• 2003

Evolutionary design related to the optimal design of Polynomial Neural Networks (PNNs) structure for model identification of complex and nonlinear system is studied in this paper. The PNN structure is consisted of layers and nodes like conventional neural networks but is not fixed and can be changable according to the system environments. three types of polynomials such as linear, quadratic, and modified quadratic is used in each node that is connected with various kinds of multi-variable inputs. Inputs and order of polynomials in each node are very important element for the performance of model. In most cases these factors are decided by the background information and trial and error of designer. For the high reliability and good performance of the PNN, the factors must be decided according to a logical and systematic way. In the paper evolutionary algorithm is applied to choose the optimal input variables and order. Evolutionary (genetic) algorithm is a random search optimization technique. The evolved PNN with optimally chosen input variables and order is not fixed in advance but becomes fully optimized automatically during the identification process. Gas furnace and pH neutralization processes are used in conventional PNN version are modeled. It shows that the designed PNN architecture with evolutionary structure optimization can produce the model with higher accuracy than previous PNN and other works.

• 한국지능시스템학회논문지
• /
• 제27권1호
• /
• pp.59-64
• /
• 2017

본 논문은 이산 Takagi-Sugeno (T-S) 퍼지 모델의 제어기 설계 시 시스템과 제어기가 상이한 소속 함수를 가지는 불완전한 전반부 정합 하에서의 제어기 설계에 대해 다룬다. 이산 T-S 퍼지 모델의 안정화 조건을 구할 때, 단일 Lyapunov 함수를 이용하여 구한 기존의 보수적인 안정화 조건보다 완화된 안정화 조건을 구하기 위해 퍼지 Lyapunov 함수를 고려한다. 퍼지 Lyapunov 함수를 이용하여 선형 행렬 부등식 기반의 완화된 안정화 조건을 구하고 시뮬레이션을 통해 제안한 방법의 타당성을 검증한다.

• Journal of Ship and Ocean Technology
• /
• 제9권3호
• /
• pp.1-13
• /
• 2005

A design procedure for a ship with minimum total resistance has been developed using a numerical optimization method called SQP (Sequential Quadratic Programming) to search for optimized hull form and CFD(Computational Fluid Dynamics) technique. The friction resistance is estimated using the ITTC 1957 model-ship correlation line formula and the wave making resistance is evaluated using a potential-flow panel method based on Rankine sources with nonlinear free surface boundary conditions. The geometry of hull surface is represented and modified using B-spline surface patches during the optimization process. Using the Series 60 hull ($C_B$ =0.60) as a base hull, the optimization procedure is applied to obtain an optimal hull that produces the minimum total resistance for the given constraints. To verify the validity of the result, the original model and the optimized model obtained by the optimization process have been built and tested in a towing tank. It is shown that the optimal hull obtained around $13\%$ reduction in the total resistance and around $40\%$ reduction in the residual resistance at a speed tested compared with that of the original one, demonstrating that the present optimization tool can be effectively used for efficient hull form designs.

• Communications for Statistical Applications and Methods
• /
• 제29권3호
• /
• pp.287-299
• /
• 2022

In radiation epidemiology, the excess relative risk (ERR) model is used to determine the dose-response relationship. In general, the dose-response relationship for the ERR model is assumed to be linear, linear-quadratic, linear-threshold, quadratic, and so on. However, since none of these functions dominate other functions for expressing the dose-response relationship, a Bayesian semiparametric method using splines has recently been proposed. Thus, we improve the Bayesian semiparametric method for the selection of the tuning parameters for splines as the number and location of knots using a Bayesian knot selection method. Equally spaced knots cannot capture the characteristic of radiation exposed dose distribution which is highly skewed in general. Therefore, we propose a nonparametric Bayesian knot selection method based on a Dirichlet process mixture model. Inference of the spline coefficients after obtaining the number and location of knots is performed in the Bayesian framework. We apply this approach to the life span study cohort data from the radiation effects research foundation in Japan, and the results illustrate that the proposed method provides competitive curve estimates for the dose-response curve and relatively stable credible intervals for the curve.

• Asian-Australasian Journal of Animal Sciences
• /
• 제26권8호
• /
• pp.1172-1180
• /
• 2013

Two experiments were conducted to determine the standardized ileal digestible (SID) lysine (Lys) requirement and the ideal SID threonine (Thr) to Lys ratio for finishing barrows. In Exp. 1, 120 barrows with an average body weight of $72.8{\pm}3.6$ kg were allotted to one of six dietary treatments in a randomized complete block design conducted for 35 d. Each diet was fed to five pens of pigs containing four barrows. A normal crude protein (CP) diet providing 15.3% CP and 0.71% SID Lys and five low CP diets providing 12% CP with SID Lys concentrations of 0.51, 0.61, 0.71, 0.81 and 0.91% were formulated. Increasing the SID Lys content of the diet resulted in an increase in weight gain (linear effect p = 0.04 and quadratic effect p = 0.08) and an improvement in feed conversion ratio (FCR) (linear effect p = 0.02 and quadratic effect p = 0.02). For weight gain and FCR, the estimated SID Lys requirement of finishing barrows were 0.71 and 0.71% (linear broken-line analysis), 0.79 and 0.78% (quadratic analysis), respectively. Exp. 2 was a 26 d dose-response study using SID Thr to Lys ratios of 0.56, 0.61, 0.67, 0.72 and 0.77. A total of 138 barrows weighing $72.5{\pm}4.4$ kg were randomly allotted to receive one of the five diets. All diets were formulated to contain 0.61% SID Lys (10.5% CP), which is slightly lower than the pig's requirement. Weight gain was quadratically (p = 0.03) affected by SID Thr to Lys ratio while FCR was linearly improved (p = 0.02). The SID Thr to Lys ratios for maximal weight gain and minimal FCR and serum urea nitrogen (SUN) were 0.67, 0.71 and 0.64 using a linear broken-line model and 0.68, 0.78 and 0.70 using a quadratic model, respectively. Based on the estimates obtained from the broken-line and quadratic analysis, we concluded that the dietary SID Lys requirement for both maximum weight gain and minimum FCR was 0.75%, and an optimum SID Thr to Lys ratio was 0.68 to maximize weight gain, 0.75 to optimize FCR and 0.67 to minimize SUN for finishing barrows.

• Advances in aircraft and spacecraft science
• /
• 제7권6호
• /
• pp.553-570
• /
• 2020

To address the problems caused by the strong coupling of an airbreathing hypersonic vehicle's airframe and propulsion to the integrated control system design, an integrated airframe-propulsion model is established, and the coupling characteristics between the aircraft and engine are analyzed. First, the airframe-propulsion integration model is established based on the typical nonlinear longitudinal dynamical model of an air-breathing hypersonic vehicle and the one-dimensional dual-mode scramjet model. Thrust, moment, angle of attack, altitude, and velocity are used as transfer variables between the aircraft model and the engine model. The one-dimensional scramjet model can accurately reflect the working state of the engine and provide data to support the coupling analysis. Second, owing to the static instability of the aircraft model, the linear quadratic regulator (LQR) controller of the aircraft is designed to ensure attitude stability and height tracking. Finally, the coupling relationship between the aircraft and the engine is revealed through simulation examples. The interaction between vehicle attitude and engine working condition is analyzed, and the influence of vehicle attitude on engine safety is considered. When the engine is in a critical working state, the attitude change of the aircraft will not affect the engine safety without considering coupling, whereas when coupling is considered, the attitude change of the aircraft may cause the engine unstart, which demonstrates the significance of considering coupling characteristics.

• 전기학회논문지
• /
• 제60권1호
• /
• pp.184-192
• /
• 2011

In this study, we introduce a identification methodology for FCM-based fuzzy model. The two underlying design mechanisms of such networks involve Fuzzy C-Means (FCM) clustering method and Particle Swarm Optimization(PSO). The proposed algorithm is based on FCM clustering method for efficient processing of data and the optimization of model was carried out using PSO. The premise part of fuzzy rules does not construct as any fixed membership functions such as triangular, gaussian, ellipsoidal because we build up the premise part of fuzzy rules using FCM. As a result, the proposed model can lead to the compact architecture of network. In this study, as the consequence part of fuzzy rules, we are able to use four types of polynomials such as simplified, linear, quadratic, modified quadratic. In addition, a Weighted Least Square Estimation to estimate the coefficients of polynomials, which are the consequent parts of fuzzy model, can decouple each fuzzy rule from the other fuzzy rules. Therefore, a local learning capability and an interpretability of the proposed fuzzy model are improved. Also, the parameters of the proposed fuzzy model such as a fuzzification coefficient of FCM clustering, the number of clusters of FCM clustering, and the polynomial type of the consequent part of fuzzy rules are adjusted using PSO. The proposed model is illustrated with the use of Automobile Miles per Gallon(MPG) and Boston housing called Machine Learning dataset. A comparative analysis reveals that the proposed FCM-based fuzzy model exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.