• Journal of Korean Institute of Industrial Engineers
• /
• v.39 no.5
• /
• pp.361-366
• /
• 2013

Prediction of process parameters is very important in parameter design. If predictions are fairly accurate, the quality improvement process will be useful to save time and reduce cost. The concept of dual response approach based on response surface methodology has widely been investigated. Dual response approach may take advantages of optimization modeling for finding optimum setting of input factor by separately modeling mean and variance responses. This study proposes an alternative dual response approach based on machine learning techniques instead of statistical analysis tools. A hybrid neural network-genetic algorithm has been proposed for the purpose of parameter design. A neural network is first constructed to model the relationship between responses and input factors. Mean and variance responses correspond to output nodes while input factors are used for input nodes. Using empirical process data, process parameters can be predicted without performing real experimentations. A genetic algorithm is then applied to find the optimum settings of input factors, where the neural network is used to evaluate the mean and variance response. A drug formulation example from pharmaceutical industry has been studied to demonstrate the procedures and applicability of the proposed approach.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.1
• /
• pp.96-102
• /
• 2018

For efficient operating strategy of electric power system, forecasting of daily peak electric load is an important but difficult problem. Therefore a daily peak electric load forecasting system using a neural network and fuzzy system is presented in this paper. First, original peak load data is interpolated in order to overcome the shortage of data for effective prediction. Next, the prediction of peak load using these interpolated data as input is performed in parallel by a neural network predictor and a fuzzy predictor. The neural network predictor shows better performance at drastic change of peak load, while the fuzzy predictor yields better prediction results in gradual changes. Finally, the superior one of two predictors is selected by the rules based on rough sets at every prediction time. To verify the effectiveness of the proposed method, the computer simulation is performed on peak load data in 2015 provided by KPX.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.23 no.4
• /
• pp.213-224
• /
• 1998

Since the late 1980s, an Increasing number of neural network models have been studied in the areas of financial prediction and analysis. The purpose of this study is to Investigate the possibility of building a neural network model that is able to construct a profitable trading strategy in the Korean Stock Market. This study classifies stocks into the future market winners and losers from the publicly available accounting information and builds portfolios based on this information. The performances of the winner portfolios and the loser portfolios are compared with each other and against the market index. The empirical result of this research is consistent with the traditional fundamental analysis where it is claimed that the financial statements contain firm values that may not be fully reflected In stock prices without delay. Despite the supporting empirical evidence. It is somewhat Inconclusive as to whether or not the abnormal return in excess of market return is the result of the extra knowledge obtained in the neural network models derived from the historical accounting data. This research attempts to open another avenue using neural network models for searching for evidence against market efficiency where statistics and intuition have played a major role.

• Steel and Composite Structures
• /
• v.28 no.5
• /
• pp.517-525
• /
• 2018

The specimens made by Z2CND18.12N austenitic stainless steel were conducted on a 100 kN closed loop servo hydraulic tension-compression testing machine with a digital controller. Uniaxial tension and uniaxial ratcheting effect tests were carried out at $25^{\circ}C$. Moreover, Uniaxial tension tests were conducted at $150^{\circ}C$, $250^{\circ}C$ and $350^{\circ}C$. Based on these experimental data, the prediction models of stress-strain curve and the relationship of ratcheting strain and number of cycles were established by the algorithm principle of BP neural network. The results indicated that the predicted results of neural network model were in well agreement with experimental data. It was found that the BP neural network model had high validity and accuracy.

• Structural Engineering and Mechanics
• /
• v.17 no.3_4
• /
• pp.483-492
• /
• 2004

This paper presents an efficient algorithm for the estimation of damage location and severity in bridge structures using Probabilistic Neural Network (PNN). Generally, the Back Propagation Neural Network (BPNN)-based damage detection methods need a lot of training patterns for neural network learning process and the optimum architecture of a BPNN is selected by trial and error. In this paper, the PNN instead of the conventional BPNN is used as a pattern classifier. The modal properties of damaged structure are somewhat different from those of undamaged one. The basic idea of proposed algorithm is that the PNN classifies a test pattern which consists of the modal characteristics from damaged structure, how close it is to each training pattern which is composed of the modal characteristics from various structural damage cases. In this algorithm, two PNNs are sequentially used. The first PNN estimates the damage location using mode shape and the results of the first PNN are put into the second PNN for the damage severity estimation using natural frequency. The proposed damage assessment algorithm using the PNN is applied to a cable-stayed bridge to verify its applicability.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.290-294
• /
• 1997

Chromosomes, as the genetic vehicles, provide the basic material for a large proportion of genetic investigations. The human chromosome analysis is widely used to diagnose genetic disease and various congenital anomalies. Many researches on automated chromosome karyotype analysis has been carried out, some of which produced commercial systems. However, there still remains much room for improving the accuracy of chromosome classification. In this paper, we propose an optimal pattern classifier by neural network to improve the accuracy of chromosome classification. The proposed pattern classifier was built up of two-step multi-layer neural network(TMANN). We are employed three morphological feature parameters ; centromeric index(C.I.), relative length ratio(R.L.), and relative area ratio(R.A.), as input in neural network by preprocessing twenty human chromosome images. The results of our experiments show that our TMANN classifier is much more useful in neural network learning and successful in chromosome classification than the other classification methods.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.282-284
• /
• 2006

Generally PI controller is used to control the speed of an induction motor. It has the good performance of speed control in case of adjusting the control parameters. But it occurred the problem to change the control parameters in the change of operation condition. In order to solve this problem, Fuzzy control or Artificial neural network is introduced in the speed control of an induction motor. However, Fuzzy control have the problems as the difficulties to change the membership function and fuzzy rule and the remaining error. Also Neural network has the problem as the difficulties to analyze the behavior of inner part. Therefore, the study on the combination of two controller is proceeded. In this paper, Speed controller of an induction motor based fuzzy-neural network is proposed and the speed control of an induction motor is performed using the proposed controller. Through the experiment, the fast response and good stability of the proposed speed controller is proved.

• Proceedings of the KIEE Conference
• /
• 1998.11c
• /
• pp.910-912
• /
• 1998

In this paper, we purpose automatic diagnosis in online, as the fundamental study to diagnose the partial discharge mechanism and to predict the lifetime, by introduction a neural network. In the proposed method, Ire use acoustic emission sensing system and calculate a fixed quantity statistic operator by pulse number and amplitude. Using statically operators such as the center of gravity(G) and the gradient of the discharge distribute(C), we analyzed the early stage and the middle stage. the fixed quantity statistic operators are learned by a neural network. The diagnosis of insulation degradation and a lifetime prediction by the early stage time are achieved. On the basis of revealed excellent diagnosis ability through the neural network learning for the patterns during degradation, it was proved that the neural network is appropriate for degradation diagnosis and lifetime prediction in partial discharge.

• Proceedings of the KWS Conference
• /
• 2002.10a
• /
• pp.301-306
• /
• 2002

This paper presents the use of the neural network technology to establish a mathematical model for predicting bead geometry (top-bead width, top-bead height, back-bead width and back-bead height) for multi-pass welding, and understand relationships between process parameters and bead geometry for robotic GMA welding process. Using a series of robotic arc welding, additional multi-pass butt welds were carried out in order to verify the performance of the developed neural network model. The results show that not only the proposed model can predict the bead geometry with reasonable accuracy and guarantee the uniform weld quality, but also the neural network model could be better than the linear and curvilin ear equations developed from Lee [8].

• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.731-736
• /
• 1994

Experiment on a lab-scale pH process is carried out to evaluate the control performance of the neural linearizing control scheme(NLCS) using a radial basis function(RBF) network which was previously proposed by Kim and Park. NLCS was developed to overcome the difficulties of the conventional neural controllers which occur when they are applied to chemical processes. Since NLCS is applicable for the processes which are already controlled by a linear controller and of which the past operating data are enough, we first control the pH process with PI controller. Using the operating data with PI controller, the linear reference model is determined by optimization. Then, a IMC controller replaces the PI controller as a feedback controller. NLCS consists of the IMC controller and a RBF network. After the learning of the neural network is fully achieved, the dynamics of the process combined with the neural network becomes linear and close to that of the linear reference model and the control performance of the linear control improves. During the training, NLCS maintains the stability and the control performance of the closed loop system. Experimental results show that the NLCS performs better than PI controller and IMC for both the servo and the regulator problems.