• Structural Engineering and Mechanics
• /
• v.76 no.6
• /
• pp.675-685
• /
• 2020

As the classical response surface method (RSM), the polynomial RSM is so easy-to-apply that it is widely used in reliability analysis. However, the trade-off of accuracy and efficiency is still a challenge and the "curse of dimension" usually confines RSM to low dimension systems. In this paper, based on the univariate decomposition, the polynomial RSM is executed in a new mode, called as DPRSM. The general form of DPRSM is given and its implementation is designed referring to the classical RSM firstly. Then, in order to balance the accuracy and efficiency of DPRSM, its adaptive order revision around the most probable point (MPP) is proposed by introducing the univariate polynomial order analysis, noted as RDPRSM, which can analyze the exact nonlinearity of the limit state surface in the region around MPP. For testing the proposed techniques, several numerical examples are studied in detail, and the results indicate that DPRSM with low order can obtain similar results to the classical RSM, DPRSM with high order can obtain more precision with a large efficiency loss; RDPRSM can perform a good balance between accuracy and efficiency and preserve the good robustness property meanwhile, especially for those problems with high nonlinearity and complex problems; the proposed methods can also give a good performance in the high-dimensional cases.

• Bulletin of the Korean Mathematical Society
• /
• v.46 no.1
• /
• pp.183-198
• /
• 2009

In this paper, we derive a characterization of orthonormal balanced multiwavelets of order p in terms of the continuous moments of the multiscaling function $\phi$. As a result, the continuous moments satisfy the discrete polynomial preserving properties of order p (or degree p - 1) for orthonormal balanced multiwavelets. We derive polynomial reproduction formula of degree p - 1 in terms of continuous moments for orthonormal balanced multiwavelets of order p. Balancing of order p implies that the series of scaling functions with the discrete-time monomials as expansion coefficients is a polynomial of degree p - 1. We derive an algorithm for computing the polynomial of degree p - 1.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.3
• /
• pp.145-156
• /
• 2000

In this paper, we propose a new methodology which includes the optimal design procedure of Polynomial Neural Networks(PNN) structure for model identification of complex and nonlinear system. The proposed PNN algorithm is based on GMDA(Group Method of Data handling) method and its structure is similar to Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and can be generated. The each node of PNN structure uses several types of high-order polynomial such as linear, quadratic and cubic, and is connected as various kinds of multi-variable inputs. In other words, the PNN uses high-order polynomial as extended type besides quadratic polynomial used in GMDH, and the number of input of its node in each layer depends on that of variables used in the polynomial. The design procedure to obtain an optimal model structure utilizing PNN algorithm is shown in each stage. The study is illustrated with the aid of pH neutralization process data besides representative time series data for gas furnace process used widely for performance comparison, and shows that the proposed PNN algorithm can produce the model with higher accuracy than previous other works. And performance index related to approximation and prediction capabilities of model is evaluated and also discussed.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.597-600
• /
• 1997

In this paper, the authors propose a new method for linearizing a nonlinear dynamical system by use of polynomial compensation. In this method, an M-sequence is applied to the nonlinear system and the crosscorrelation function between the input and the output gives us every crosssections of Volterra kernels of the nonlinear system up to 3rd order. We construct a polynomial compensation function from comparison between lst order Volterra kernel and high order kernels. The polynomial compensation function is, in this case, of third order whose coefficients are variable depending on the amplitude of the input signal. Once we can get compensation function of nonlinear system, we can construct a linearization scheme of the nonlinear system. That is. the effect of second and third order Volterra kernels are subtracted from the output, thus we obtain a sort of linearized output. The authors applied this method to a saturation-type nonlinear system by simulation, and the results show good agreement with the theoretical considerations.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.24 no.6
• /
• pp.948-955
• /
• 1987

The model reduction method of the high order linear time invariant systems is proposed. The continuous fraction expansion of Auxiliary denominator polynomial is used to obtain denominator polynomial of the reduced order model, and the numerator polynomial of the reduced order model is obtained by equating the first some moments of the original and the reduced order model, using simplified moment function. This methiod does not require the calculation of the reciprocal transformation which should be calculated in Routh approximation, furthemore the stability of the reduced order model is guaranted if original system is stable. Responses of this method showed us good characteristics.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.4
• /
• pp.534-540
• /
• 2014

In this paper, we propose a fuzzy combined Polynomial Neural Network(PNN) for pattern classification. The fuzzy combined PNN comes from the generic TSK fuzzy model with several linear polynomial as the consequent part and is the expanded version of the fuzzy model. The proposed pattern classifier has the polynomial neural networks as the consequent part, instead of the general linear polynomial. PNNs are implemented by stacking the simple polynomials dynamically. To implement one layer of PNNs, the various types of simple polynomials are used so that PNNs have flexibility and versatility. Although the structural complexity of the implemented PNNs is high, the PNNs become a high order-multi input polynomial finally. To estimate the coefficients of a polynomial neuron, The weighted linear discriminant analysis. The output of fuzzy rule system with PNNs as the consequent part is the linear combination of the output of several PNNs. To evaluate the classification ability of the proposed pattern classifier, we make some experiments with several machine learning data sets.

• Journal of Sensor Science and Technology
• /
• v.21 no.2
• /
• pp.109-113
• /
• 2012

We propose an improved interpolating equation to express temperature-resistance characteristics for modern industrial platinum resistance thermometers (PRTs). Callendar-van Dusen equation which has been widely used for platinum resistance thermometer fails to fully describe temperature characteristics of high quality PRTs and leaves systematic residual when the calibration point include temperatures above $300^{\circ}C$. Expanding Callendar-van Dusen to higher-order polynomial drastically improves the uncertainty of the fitting even with reduced degrees of freedom of the fitting. We found that in the fourth-order polynomial fitting, the third-order and fourth-order coefficients have a strong correlation. Using the correlation, we suggest an improved interpolating equation in the form of fourth-order polynomial, but with three fitting parameters. Applying this interpolating equation reduced the uncertainty of the fitting to 32 % of that resulted from the traditional Callendar-van Dusen. This improvement was better than that from a simple third-order polynomial despite that the degrees of the freedom of the fitting was the same.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.17 no.2
• /
• pp.67-85
• /
• 2013

Reproducing Polynomial Particle Method (RPPM) is one of meshless methods that use meshes minimally or do not use meshes at all. In this paper, the RPPM is employed for free vibration analysis of shear-deformable plates of the first order shear deformation model (FSDT), called Reissner-Mindlin plate. For numerical implementation, we use flat-top partition of unity functions, introduced by Oh et al, and patchwise RPPM in which approximation functions have high order polynomial reproducing property and the Kronecker delta property. Also, we demonstrate that our method is highly effective than other existing results for various aspect ratios and boundary conditions.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.149-151
• /
• 2005

In this paper, we propose the Optimal Polynomial Neural Networks(PNN) for nonlinear process. The PNN is based on Group Method of Data Handling(GMDH) method and its structure is similar to feedforward Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and can be generated. The each node of PNN structure uses several types of high-order polynomial such as linear, quadratic and modified quadratic, and is connected as various kinds of multi-variable inputs. The conventional PNN depends on experience of a designer that select No. of input variable, input variable and polynomial type. Therefore it is very difficult a organizing of optimized network. The proposed algorithm identified and selected No. of input variable, input variable and polynomial type by using Genetic Algorithms(GAs). In the sequel the proposed model shows not only superior results to the existing models, but also pliability in organizing of optimal network. Medical Imaging System(MIS) data is simulated in order to confirm the efficiency and feasibility of the proposed approach in this paper.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.173-174
• /
• 2006

High power amplifier (HPA), which is used in transmitter of wireless communication systems, usually works in near saturation point in order to achieve maximum efficiency. In this region, HPA can introduce undesirable nonlinear effects. In this paper, we present a polynomial modeling method for efficient techniques to compensate for nonlinear distortion introduced by nonlinear HPA. Proposed polynomial predistorter inverses actual amplifier. Namely, we derive polynomials of amplifiers from analytical method and the electrical parameters in the data sheet of an actual amplifier and then can derive polynomial predistorter by inversing them. It is an effective and a simple method to compensate nonlinear distortion. SSPA(Solid-state power amplifier) is considered. We also analyze the effects of predistortion on the SER performance of communication system with 16-QAM modulation format. The results have shown the efficiency of this model.