• 한국산업융합학회 논문집
• /
• 제11권2호
• /
• pp.83-91
• /
• 2008

GMAW(Gas Metal Arc Welding) processes are usually used in industrial side in order to get its high productivity. But those are only adopted in the semi-automated welding equipment because of a lot of welding spatters. Many industrial robot actually percents from being engaged in the welding processes. The welding spatter problem of causes blocking them being a fully automated welding process.This study was carried out to investigate the optimal conditions for minimizing welding spatter generation at GMAW robot. The spatter can be significantly reduced below 2% of welding spatter generation at the following conditions ; First, below 18V at the wire-feed rate 2.0mm/min Second, below 23V at the wire-feed rate 3.6mm/min Third, below 24V at the wire-feed rate 5.5mm/min.

• 전자공학회논문지B
• /
• 제30B권8호
• /
• pp.54-63
• /
• 1993

This paper proposes a method for improving the performances of the neural network for optimization by an optimal estimation of initial states. The optimal initial state that leads to the global minimum is estimated by using the stochastic approximation. And then the update rule of Hopfield model, which is the high speed deterministic algorithm using the steepest descent rule, is applied to speed up the optimization. The proposed method has been applied to the tavelling salesman problems and an optimal task partition problems to evaluate the performances. The simulation results show that the convergence speed of the proposed method is higher than conventinal Hopfield model. Abe's method and Boltzmann machine with random initial neuron output setting, and the convergence rate to the global minimum is guaranteed with probability of 1. The proposed method gives better result as the problem size increases where it is more difficult for the randomized initial setting to give a good convergence.

• Journal of the Korean Statistical Society
• /
• 제20권1호
• /
• pp.29-43
• /
• 1991

Two data-based bandwidth selectors which are optimal in the sense that they achieve n$\^$-$\frac{1}{2}$/ rate of convergence in kernel density estimation are proposed. The proposed bandwidth selectors are constructed by modifying Park and Marron's plug-in method. The first modification is taking Taylor expansion of the mean integrated squared error to two more terms than in the case of plug-in method. The second is estimating more accurately the functionals of the unknown density appeared in the minimizer of the expansion by using higher order kernels. The proposed bandwidth selectors were proved to be optimal in terms of convergence rate. According to small-sample Monte Carlo studies, the proposed bandwidth selectors showed better performance than all the other bandwidth selectors considered in the simulation.

• Journal of Information Processing Systems
• /
• 제16권6호
• /
• pp.1261-1270
• /
• 2020

The physical security layer of industrial wireless sensor networks in the event of an eavesdropping attack has been investigated in this paper. An optimal sensor selection scheme based on the maximum channel capacity is proposed for transmission environments that experience Nakagami fading. Comparing the intercept probabilities of the traditional round robin (TRR) and optimal sensor selection schemes, the system secure performance is analyzed. Simulation results show that the change in the number of sensors and the eavesdropping ratio affect the convergence rate of the intercept probability. Additionally, the proposed optimal selection scheme has a faster convergence rate compared to the TRR scheduling scheme for the same eavesdropping ratio and number of sensors. This observation is also valid when the Nakagami channel is simplified to a Rayleigh channel.

• Communications for Statistical Applications and Methods
• /
• 제3권3호
• /
• pp.271-282
• /
• 1996

this paper deal with the estimation of the power spectral density function of time series. A kernel estimator which is based on local average is defined and the rates of convergence of the pointwise, $$L_2$-norm; and; $L{\infty}$-norm associated with the estimator are investigated by restricting as to kernels with suitable assumptions. Under appropriate regularity conditions, it is shown that the optimal rate of convergence for 0$N^{-r}$ both in the pointwiseand $$L_2$-norm, while; $N^{r-1}(logN)^{-r}$is the optimal rate in the $L{\infty}-norm$. Some examples are given to illustrate the application of main results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권3호
• /
• pp.816-839
• /
• 2023

In a random vector functional link (RVFL) network, shortcomings such as local optimal stagnation and decreased convergence performance cause a reduction in the accuracy of illumination correction by only inputting the weights and biases of hidden neurons. In this study, we proposed an improved regularized random vector functional link (RRVFL) network algorithm with an optimized grey wolf optimizer (GWO). Herein, we first proposed the moth-flame optimization (MFO) algorithm to provide a set of excellent initial populations to improve the convergence rate of GWO. Thereafter, the MFO-GWO algorithm simultaneously optimized the input feature, input weight, hidden node and bias of RRVFL, thereby avoiding local optimal stagnation. Finally, the MFO-GWO-RRVFL algorithm was applied to ameliorate the performance of illumination correction of various test images. The experimental results revealed that the MFO-GWO-RRVFL algorithm was stable, compatible, and exhibited a fast convergence rate.

• Journal of Mechanical Science and Technology
• /
• 제16권10호
• /
• pp.1264-1275
• /
• 2002

This paper is concerned with the investigation on the stability and convergence characteristics of the Crank-Nicolson-Galerkin scheme that is widely being employed for the numerical approximation of parabolic-type partial differential equations. Here, we present the theoretical analysis on its consistency and convergence, and we carry out the numerical experiments to examine the effect of the time-step size △t on the h- and P-convergence rates for various mesh sizes h and approximation orders P. We observed that the optimal convergence rates are achieved only when △t, h and P are chosen such that the total error is not affected by the oscillation behavior. In such case, △t is in linear relation with DOF, and furthermore its size depends on the singularity intensity of problems.

• Journal of applied mathematics & informatics
• /
• 제9권1호
• /
• pp.101-124
• /
• 2002

The convergence rate of a numerical procedure barred on Schwarz Alternating Method (SAM) for solving elliptic boundary value problems (BVP's) depends on the selection of the interface conditions applied on the interior boundaries of the overlapping subdomains. It hee been observed that the Robin condition(mixed interface condition), controlled by a parameter, can optimize SAM's convergence rate. Since the convergence rate is very sensitive to the parameter, Tang[17] suggested another interface condition called over-determined interface condition. Based on the over-determined interface condition, we formulate the two-layer multi-parameterized SAM. For the SAM and the one-dimensional elliptic model BVP's, we determine analytically the optimal values of the parameters. For the two-dimensional elliptic BVP's , we also formulate the two-layer multi-parameterized SAM and suggest a choice of multi-parameter to produce good convergence rate .

• Journal of the Korean Statistical Society
• /
• 제19권2호
• /
• pp.105-112
• /
• 1990

Let (X, Y) be a pair random variables and let f denote the regression function of the response Y on the measurement variable X. Let K(f) denote a derivative of f. The least squares method is used to obtain a tensor spline estimator $\hat{f}$ of f based on a random sample of size n from the distribution of (X, Y). Under some mild conditions, it is shown that $K(\hat{f})$ achieves the optimal rate of convergence for the estimation of K(f) in $L_2$ and $L_{\infty}$ norms.

• Journal of the Korean Statistical Society
• /
• 제21권2호
• /
• pp.153-166
• /
• 1992

Consider an unknown regression function f of the response Y on a d-dimensional measurement variable X. It is assumed that f belongs to a tensor Sobolev space. Let T denote a differential operator. Let $\hat{T}_n$ denote an estimator of T(f) based on a random sample of size n from the distribution of (X, Y), and let $\Vert \hat{T}_n - T(f) \Vert_2$ be the usual $L_2$ norm of the restriction of $\hat{T}_n - T(f)$ to a subset of $R^d$. Under appropriate regularity conditions, the optimal rate of convergence for $\Vert \hat{T}_n - T(f) \Vert_2$ is discussed.