• Nuclear Engineering and Technology
• /
• v.52 no.4
• /
• pp.846-855
• /
• 2020

A loose part monitoring system is used to detect unexpected loose parts in a reactor coolant system in a nuclear power plant. It is still necessary to develop a new methodology for the localization and mass estimation of loose parts owing to the high estimation error of conventional methods. In addition, model-based diagnostics recently emphasized the importance of a model describing the behavior of a mechanical system or component. The purpose of this study is to propose a new localization and mass-estimation method based on finite element analysis (FEA) and optimization technique. First, an FEA model to simulate the propagation behavior of the bending wave generated by a metal sphere impact is validated by performing an impact test and a corresponding FEA and optimization for a downsized steam-generator structure. Second, a novel methodology based on FEA and optimization technique was proposed to estimate the impact location and mass of a loose part at the same time. The usefulness of the methodology was then validated through a series of FEAs and some blind tests. A new feature vector, the cross-correlation function, was also proposed to predict the impact location and mass of a loose part, and its usefulness was then validated. It is expected that the proposed methodology can be utilized in model-based diagnostics for the estimation of impact parameters such as the mass, velocity, and impact location of a loose part. In addition, the FEA-based model can be used to optimize the sensor position to improve the collected data quality in the site of nuclear power plants.

• Journal of Korean Association for Spatial Structures
• /
• v.8 no.4
• /
• pp.73-80
• /
• 2008

The objective of current study is to develop an optimization technique for the seismic actively controlled building structures using active tendon devices by an efficient solution of LQR control gain. In order to solve the active control system, the Ricatti closed-loop algorithm has been applied, and the state vector has been formulated by the transfer matrix and solved by a numerical technique of the trapezoidal rule. The time-delay problem has been also considered by phase compensation. To optimize the performance index, the ratio of the weighted matrix is the design variable, allowable story drift limits of IBC 2000 and tendon forces have been applied as restraint conditions, and the optimum control program has been developed with the algorithm of the SUMT technique. In examples of the optimization problem of eight stories shear buildings, it is evaluated that the optimum controlled building is more suitable in the control of earthquake response than the uncontrolled system and can reduce the performance index to compare with the controlled system with a constant ratio of the weighted matrix.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.11C
• /
• pp.1077-1084
• /
• 2006

This paper proposed a fast algorithm to reduce the amount of calculation for inter prediction which takes a great deal of the operational time in H.264/AVC. This algorithm decides a search range according to the direction of predicted motion vector, and then performs an adaptive spiral search for the candidates with JM(Joint Model) FME(Fast Motion Estimation) which employs the rate-distortion optimization(RDO) method. Simultaneously, it decides a threshold cost value for each of the variable block sizes and performs the motion estimation for the variable search ranges with the threshold. These activities reduce the great amount of the complexity in inter prediction encoding. Experimental results by applying the proposed method .to various video sequences showed that the process time was decreased up to 80% comparing to the previous prediction methods. The degradation of video quality was only from 0.05dB to 0.19dB and the compression ratio decreased as small as 0.58% in average. Therefore, we are sure that the proposed method is an efficient method for the fast inter prediction.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.3C
• /
• pp.419-425
• /
• 2004

This paper presents a new method which is calculated to use only three vanishing points in order to compute the dimensions of object and its pose from a single image of perspective projection taken by a camera. Our approach is to only compute three vanishing points without informations such as the focal length and rotation matrix from images in the case of perspective projection. We assume that the object can be modeled as a linear function of a dimension vector v. The input of reconstruction is a set of correspondences between features in the model and features in the image. To minimize each the dimensions of the parameterized models, this reconstruction of optimization can be solved by standard nonlinear optimization techniques with a multi-start method which generates multiple starting points for the optimizer by sampling the parameter space uniformly.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2002.04a
• /
• pp.123-130
• /
• 2002

A general formulation for shape design sensitivity analysis over three dimensional beam structure is developed based on a variational formulation of the beam in linear elasticity. Sensitivity formula is derived based on variational equations in cartesian coordinates using the material derivative concept and adjoint variable method for the displacement and Von-Mises stress functionals. Shape variation is considered for the beam shape in general 3-dimensional direction as well as for the orientation angle of the beam cross section. In the sensitivity expression, the end points evaluation at each beam segment is added to the integral formula, which are summed over the entire structure. The sensitivity formula can be evaluated with generality and ease even by employing piecewise linear design velocity field despite the bending model is fourth order differential equation. For the numerical implementation, commercial software ANSYS is used as analysis tool for the primal and adjoint analysis. Once the design variable set is defined using ANSYS language, shape and orientation variation vector at each node is generated by making finite difference to the shape with respect to each design parameter, and is used for the computation of sensitivity formula. Several numerical examples are taken to show the advantage of the method, in which the accuracy of the sensitivity is evaluated. The results are found excellent even by employing a simple linear function for the design velocity evaluation. Shape optimization is carried out for the geometric design of an archgrid and tilted bridge, which is to minimize maximum stress over the structure while maintaining constant weight. In conclusion, the proposed formulation is a useful and easy tool in finding optimum shape in a variety of the spatial frame structures.

• Steel and Composite Structures
• /
• v.51 no.6
• /
• pp.679-695
• /
• 2024

This paper presents a novel technique that combines machine learning (ML) with moth-flame optimization (MFO) methods to predict the axial compressive strength (ACS) of concrete filled double skin steel tubes (CFDST) columns. The proposed model is trained and tested with a dataset containing 125 tests of the CFDST column subjected to compressive loading. Five ML models, including extreme gradient boosting (XGBoost), gradient tree boosting (GBT), categorical gradient boosting (CAT), support vector machines (SVM), and decision tree (DT) algorithms, are utilized in this work. The MFO algorithm is applied to find optimal hyperparameters of these ML models and to determine the most effective model in predicting the ACS of CFDST columns. Predictive results given by some performance metrics reveal that the MFO-CAT model provides superior accuracy compared to other considered models. The accuracy of the MFO-CAT model is validated by comparing its predictive results with existing design codes and formulae. Moreover, the significance and contribution of each feature in the dataset are examined by employing the SHapley Additive exPlanations (SHAP) method. A comprehensive uncertainty quantification on probabilistic characteristics of the ACS of CFDST columns is conducted for the first time to examine the models' responses to variations of input variables in the stochastic environments. Finally, a web-based application is developed to predict ACS of the CFDST column, enabling rapid practical utilization without requesting any programing or machine learning expertise.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.39-55
• /
• 2019

Recently banks and large financial institutions have introduced lots of Robo-Advisor products. Robo-Advisor is a Robot to produce the optimal asset allocation portfolio for investors by using the financial engineering algorithms without any human intervention. Since the first introduction in Wall Street in 2008, the market size has grown to 60 billion dollars and is expected to expand to 2,000 billion dollars by 2020. Since Robo-Advisor algorithms suggest asset allocation output to investors, mathematical or statistical asset allocation strategies are applied. Mean variance optimization model developed by Markowitz is the typical asset allocation model. The model is a simple but quite intuitive portfolio strategy. For example, assets are allocated in order to minimize the risk on the portfolio while maximizing the expected return on the portfolio using optimization techniques. Despite its theoretical background, both academics and practitioners find that the standard mean variance optimization portfolio is very sensitive to the expected returns calculated by past price data. Corner solutions are often found to be allocated only to a few assets. The Black-Litterman Optimization model overcomes these problems by choosing a neutral Capital Asset Pricing Model equilibrium point. Implied equilibrium returns of each asset are derived from equilibrium market portfolio through reverse optimization. The Black-Litterman model uses a Bayesian approach to combine the subjective views on the price forecast of one or more assets with implied equilibrium returns, resulting a new estimates of risk and expected returns. These new estimates can produce optimal portfolio by the well-known Markowitz mean-variance optimization algorithm. If the investor does not have any views on his asset classes, the Black-Litterman optimization model produce the same portfolio as the market portfolio. What if the subjective views are incorrect? A survey on reports of stocks performance recommended by securities analysts show very poor results. Therefore the incorrect views combined with implied equilibrium returns may produce very poor portfolio output to the Black-Litterman model users. This paper suggests an objective investor views model based on Support Vector Machines(SVM), which have showed good performance results in stock price forecasting. SVM is a discriminative classifier defined by a separating hyper plane. The linear, radial basis and polynomial kernel functions are used to learn the hyper planes. Input variables for the SVM are returns, standard deviations, Stochastics %K and price parity degree for each asset class. SVM output returns expected stock price movements and their probabilities, which are used as input variables in the intelligent views model. The stock price movements are categorized by three phases; down, neutral and up. The expected stock returns make P matrix and their probability results are used in Q matrix. Implied equilibrium returns vector is combined with the intelligent views matrix, resulting the Black-Litterman optimal portfolio. For comparisons, Markowitz mean-variance optimization model and risk parity model are used. The value weighted market portfolio and equal weighted market portfolio are used as benchmark indexes. We collect the 8 KOSPI 200 sector indexes from January 2008 to December 2018 including 132 monthly index values. Training period is from 2008 to 2015 and testing period is from 2016 to 2018. Our suggested intelligent view model combined with implied equilibrium returns produced the optimal Black-Litterman portfolio. The out of sample period portfolio showed better performance compared with the well-known Markowitz mean-variance optimization portfolio, risk parity portfolio and market portfolio. The total return from 3 year-period Black-Litterman portfolio records 6.4%, which is the highest value. The maximum draw down is -20.8%, which is also the lowest value. Sharpe Ratio shows the highest value, 0.17. It measures the return to risk ratio. Overall, our suggested view model shows the possibility of replacing subjective analysts's views with objective view model for practitioners to apply the Robo-Advisor asset allocation algorithms in the real trading fields.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.241-254
• /
• 2011

Financial time-series forecasting is one of the most important issues because it is essential for the risk management of financial institutions. Therefore, researchers have tried to forecast financial time-series using various data mining techniques such as regression, artificial neural networks, decision trees, k-nearest neighbor etc. Recently, support vector machines (SVMs) are popularly applied to this research area because they have advantages that they don't require huge training data and have low possibility of overfitting. However, a user must determine several design factors by heuristics in order to use SVM. For example, the selection of appropriate kernel function and its parameters and proper feature subset selection are major design factors of SVM. Other than these factors, the proper selection of instance subset may also improve the forecasting performance of SVM by eliminating irrelevant and distorting training instances. Nonetheless, there have been few studies that have applied instance selection to SVM, especially in the domain of stock market prediction. Instance selection tries to choose proper instance subsets from original training data. It may be considered as a method of knowledge refinement and it maintains the instance-base. This study proposes the novel instance selection algorithm for SVMs. The proposed technique in this study uses genetic algorithm (GA) to optimize instance selection process with parameter optimization simultaneously. We call the model as ISVM (SVM with Instance selection) in this study. Experiments on stock market data are implemented using ISVM. In this study, the GA searches for optimal or near-optimal values of kernel parameters and relevant instances for SVMs. This study needs two sets of parameters in chromosomes in GA setting : The codes for kernel parameters and for instance selection. For the controlling parameters of the GA search, the population size is set at 50 organisms and the value of the crossover rate is set at 0.7 while the mutation rate is 0.1. As the stopping condition, 50 generations are permitted. The application data used in this study consists of technical indicators and the direction of change in the daily Korea stock price index (KOSPI). The total number of samples is 2218 trading days. We separate the whole data into three subsets as training, test, hold-out data set. The number of data in each subset is 1056, 581, 581 respectively. This study compares ISVM to several comparative models including logistic regression (logit), backpropagation neural networks (ANN), nearest neighbor (1-NN), conventional SVM (SVM) and SVM with the optimized parameters (PSVM). In especial, PSVM uses optimized kernel parameters by the genetic algorithm. The experimental results show that ISVM outperforms 1-NN by 15.32%, ANN by 6.89%, Logit and SVM by 5.34%, and PSVM by 4.82% for the holdout data. For ISVM, only 556 data from 1056 original training data are used to produce the result. In addition, the two-sample test for proportions is used to examine whether ISVM significantly outperforms other comparative models. The results indicate that ISVM outperforms ANN and 1-NN at the 1% statistical significance level. In addition, ISVM performs better than Logit, SVM and PSVM at the 5% statistical significance level.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.1
• /
• pp.1-8
• /
• 2020

A derivation method for a quantized gradient for machine learning on an embedded system is proposed, in this paper. The proposed differentiation method induces the quantized gradient vector to an objective function and provides that the validation of the directional derivation. Moreover, mathematical analysis shows that the sequence yielded by the learning equation based on the proposed quantization converges to the optimal point of the quantized objective function when the quantized parameter is sufficiently large. The simulation result shows that the optimization solver based on the proposed quantized method represents sufficient performance in comparison to the conventional method based on the floating-point system.

• Journal of Electrical Engineering and Technology
• /
• v.4 no.3
• /
• pp.365-369
• /
• 2009

Identification is considered to be among the main applications of inverse theory and its objective for a given physical system is to use data which is easily observable, to infer some of the geometric parameters which are not directly observable. In this paper, a parameter identification method using inverse problem methodology is proposed. The minimisation of the objective function with respect to the desired vector of design parameters is the most important procedure in solving the inverse problem. The conjugate gradient method is used to determine the unknown parameters, and Tikhonov's regularization method is then used to replace the original ill-posed problem with a well-posed problem. The simulation and experimental results are presented and compared.