• Proceedings of the KIEE Conference
• /
• 2001.11c
• /
• pp.424-427
• /
• 2001

In this study, we introduce a concept of neurofuzzy polynomial networks (NFPN), a hybrid modeling architecture combining neurofuzzy networks (NFN) and polynomial neural networks(PNN). NFN contributes to the formation of the premise part of the rule-based structure of the NFPN. The consequence part of the NFPN is designed using PNN. The parameters of the membership functions, learning rates and momentum coefficients are adjusted with the use of genetic optimization. We introduce two kinds of NFPN architectures, namely the basic and the modified one. Owing to the specific features of two combined architectures, it is possible to consider the nonlinear characteristics of process system and to obtain the better output performance with superb predictive ability.

• 제어로봇시스템학회:학술대회논문집
• /
• 1986.10a
• /
• pp.119-122
• /
• 1986

An algorithm is proposed to find a stable rational function, which is frequently used in the linear system theory, by curve-fitting a given data. This problem is essentially a nonolinear optimization problem. In order to converge faster to the solution, the following method is used. First, the coefficients of the denominator polynomial are fixed and only the coefficients of the numerator polynomial are adjusted by its linear relationships. Then the coefficients of the numerator are fixed and the coefficients of the denominator polynomial are adjusted by nonlinear programming. This whole process is repeated until a convergent solution is found. The solution obtained by this method converges better than by other algorithms and its versatility is demonstrated by applying it to the design of a feedback control system and a low pass filter.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.2 no.4
• /
• pp.59-71
• /
• 1994

A multi-polynomial method is proposed to synthesize DRRD cam profiles. A cam lift duration s divided into 10 sections, each of them is expressed by a polynomial equation. 12 design variables are extracted from the cam profile displacement, velocity, and acceleration curves. Because all the design variables have physical meanings which are familiar to most cam designers, it is easy to imagine a profile shape from the design variables. The design envelope of the method is wide enough to be used in DRRD automotive cam designs. Polydyne cams, widely used in automotive engines, are included into the envelope. Unlike Polydyne cams, the method provides capability of wide velocity factor variations, which gives much flexibility in flat-faced tappet design. Area factor of profiles designed by the method can be increased 5-10% compared to those of Polydyne cams without increasing acceleration factor. The method is especially useful for cam profile optimizations.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.15 no.2
• /
• pp.544-556
• /
• 1991

The optimization of many engineering design problems requires a nonlinear programming algorithm that is robust and efficient. A general-purpose nonlinear optimization program IDOL (Interactive Design Optimization Library) is developed based on the Augmented Lagrange Mulitiplier (ALM) method. The ideas of selecting a good initial design point, using resonable initial values for Lagrange multipliers, constraints scaling, descent vector restarting, and dynamic stopping criterion are employed for computational enhancement to the ALM method. A descent vector is determined by using the Broydon-Fletcher-Goldfarb-Shanno (BFGS) method. For line search, the Incremental-Search method is first used to find bounds on the solution, then the bounds are reduced by the Golden Section method, and finally a cubic polynomial approximation technique is applied to locate the next design point. Seven typical test problems are solved to show IDOL efficient and robust.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.26 no.2
• /
• pp.54-60
• /
• 2018

This paper contains the multi-mission scheduling optimization of UAV within a given operating time. Mission scheduling optimization problem is one of combinatorial optimization, and it has been shown to be NP-hard(non-deterministic polynomial-time hardness). In this problem, as the size of the problem increases, the computation time increases dramatically. So, we applied the genetic algorithm to this problem. For the application, we set the mission scenario, objective function, and constraints, and then, performed simulation with MATLAB. After 1000 case simulation, we evaluate the optimality and computing time in comparison with global optimum from MILP(Mixed Integer Linear Programming).

• International Journal of Aeronautical and Space Sciences
• /
• v.8 no.1
• /
• pp.122-128
• /
• 2007

In this paper, a method of station keeping strategy using relative orbital motion and numerical optimization technique is presented for geostationary satellite. Relative position vector with respect to an ideal geostationary orbit is generated using high precision orbit propagation, and compressed in terms of polynomial and trigonometric function. Then, this relative orbit model is combined with optimization scheme to propose a very efficient and flexible method of station keeping planning. Proper selection of objective and constraint functions for optimization can yield a variety of station keeping methods improved over the classical ones. Nonlinear simulation results have been shown to support such concept.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.11
• /
• pp.1809-1814
• /
• 2003

Differential evolution (DE) algorithm is presented and applied to global optimization in this research. DE suggested initially fur the solution to Chebychev polynomial fitting problem is similar to genetic algorithm(GA) including crossover, mutation and selection process. However, differential evolution algorithm is simpler than GA because it uses a vector concept in populating process. And DE turns out to be converged faster than CA, since it employs the difference information as pseudo-sensitivity In this paper, a trial vector and its control parameters of DE are examined and unconstrained optimization problems of highly nonlinear multimodal functions are demonstrated. To illustrate the efficiency of DE, convergence rates and robustness of global optimization algorithms are compared with those of simple GA.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2891-2893
• /
• 2005

In this paper, we introduce a new category of Self-Organizing Fuzzy Polynomial Neural Networks (SOFPNN) that is based on a genetically optimized multi-layer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology involving mechanisms of genetic optimization. The conventional SOFPNN algorithm leads to a tendency to produce overly complex networks as well as a repetitive computation load by the trial and error method and/or the a repetitive parameter adjustment by designer. In order to generate a structurally and parametrically optimized network, such parameters need to be optimal. In this study, in solving the problems with the conventional SOFPNN, we introduce a new design approach of evolutionary optimized SOFPNN. Optimal parameters design available within FPN (viz. the no. of input variables, the order of the polynomial, input variables, and the no. of membership function) lead to structurally and parametrically optimized network which is more flexible as well as simpler architecture than the conventional SOFPNN. In addition, we determine the initial apexes of membership functions by genetic algorithm.

• Journal of the Korean Society for Precision Engineering
• /
• v.29 no.6
• /
• pp.607-612
• /
• 2012

The wear problem of wheel flange occurs at sharp curves of rail. This paper proposes a procedure for optimum design of a wheel profile wherein flange wear is reduced by improving an interaction between wheel and rail. Application of optimization method to design problem mainly depends on characteristics of design space. This paper compared local optimization method with global optimization according to sensitivity value of objective function for design variables to find out which optimization method is appropriable to minimize wear of wheel flange. Wheel profile is created by a piecewise cubic Hermite interpolating polynomial and dynamic performances are analyzed by a railway dynamic analysis program, VAMPIRE. From the optimization results, it is verified that the global optimization method such as genetic algorithm is more suitable to wheel profile optimization than the local optimization of SQP (Sequential Quadratic Programming) in case of considering the lack of empirical knowledge for initial design value.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.2
• /
• pp.183-194
• /
• 2005

In this study, we introduce an advanced architecture of genetically optimized Hybrid Fuzzy Neural Networks (gHFNN) and develop a comprehensive design methodology supporting their construction. A series of numeric experiments is included to illustrate the performance of the networks. The construction of gHFNN exploits fundamental technologies of Computational Intelligence (CI), namely fuzzy sets, neural networks, and genetic algorithms (GAs). The architecture of the gHFNNs results from a synergistic usage of the genetic optimization-driven hybrid system generated by combining Fuzzy Neural Networks (FNN) with Polynomial Neural Networks (PNN). In this tandem, a FNN supports the formation of the premise part of the rule-based structure of the gHFNN. The consequence part of the gHFNN is designed using PNNs. We distinguish between two types of the linear fuzzy inference rule-based FNN structures showing how this taxonomy depends upon the type of a fuzzy partition of input variables. As to the consequence part of the gHFNN, the development of the PNN dwells on two general optimization mechanisms: the structural optimization is realized via GAs whereas in case of the parametric optimization we proceed with a standard least square method-based learning. To evaluate the performance of the gHFNN, the models are experimented with a representative numerical example. A comparative analysis demonstrates that the proposed gHFNN come with higher accuracy as well as superb predictive capabilities when comparing with other neurofuzzy models.