• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.4 s.193
• /
• pp.93-101
• /
• 2007

Aluminum alloy which is one of the light materials has been tried to apply to light weight vehicle body. In order to do that, welding technology is very important. In case of the aluminum laser welding, the strength of welded part is reduced due to porosity, underfill, and magnesium loss. To overcome these problems, laser welding of aluminum with filler wire was suggested. In this study, experiment about laser welding of AA5182 aluminum alloy with AA5356 filler wire was performed according to process parameters such as laser power, welding speed and wire feed rate. The tensile strength was measured to find the weldability of laser welding with filler wire. The models to estimate tensile strength were suggested using three regression models and one neural network model. For regression models, one was the multiple linear regression model, another was the second order polynomial regression model, and the other was the multiple nonlinear regression model. Neural network model with 2 hidden layers which had 5 and 3 nodes respectively was investigated to find the most suitable model for the system. Estimation performance was evaluated for each model using the average error rate. Among the three regression models, the second order polynomial regression model had the best estimation performance. For all models, neural network model has the best estimation performance.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.55 no.2
• /
• pp.45-51
• /
• 2006

In this paper, we propose a new architecture of Information Granulation based genetically optimized Self-Organizing Fuzzy Polynomial Neural Networks (IG_gSOFPNN) that is based on a genetically optimized multilayer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially information granulation and genetic algorithms. The proposed IG_gSOFPNN gives rise to a structurally optimized structure and comes with a substantial level of flexibility in comparison to the one we encounter in conventional SOFPNNs. The design procedure applied in the construction of each layer of a SOFPNN deals with its structural optimization involving the selection of preferred nodes (or FPNs) with specific local characteristics (such as the number of input variables, the order of the polynomial of the consequent part of fuzzy rules, and a collection of the specific subset of input variables) and addresses specific aspects of parametric optimization. In addition, the fuzzy rules used in the networks exploit the notion of information granules defined over system's variables and formed through the process of information granulation. That is, we determine the initial location (apexes) of membership functions and initial values of polynomial function being used in the premised and consequence part of the fuzzy rules respectively. This granulation is realized with the aid of the hard c-menas clustering method (HCM). To evaluate the performance of the IG_gSOFPNN, the model is experimented with using two time series data(gas furnace process and NOx process data).

• Smart Structures and Systems
• /
• v.29 no.2
• /
• pp.321-336
• /
• 2022

Model uncertainty is a key factor that could influence the accuracy and reliability of numerical model-based analysis. It is necessary to acquire an appropriate updating approach which could search and determine the realistic model parameter values from measurements. In this paper, the Bayesian model updating theory combined with the transitional Markov chain Monte Carlo (TMCMC) method and K-means cluster analysis is utilized in the updating of the structural model parameters. Kriging and polynomial chaos expansion (PCE) are employed to generate surrogate models to reduce the computational burden in TMCMC. The selected updating approaches are applied to three structural examples with different complexity, including a two-storey frame, a ten-storey frame, and the national stadium model. These models stand for the low-dimensional linear model, the high-dimensional linear model, and the nonlinear model, respectively. The performances of updating in these three models are assessed in terms of the prediction uncertainty, numerical efforts, and prior information. This study also investigates the updating scenarios using the analytical approach and surrogate models. The uncertainty quantification in the Bayesian approach is further discussed to verify the validity and accuracy of the surrogate models. Finally, the advantages and limitations of the surrogate model-based updating approaches are discussed for different structural complexity. The possibility of utilizing the boosting algorithm as an ensemble learning method for improving the surrogate models is also presented.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.12 no.1
• /
• pp.106-118
• /
• 2009

Satellite imagery with high resolution of about one meter is used widely in commerce and government applications ranging from earth observation and monitoring to national digital mapping. Due to the expensiveness of IKONOS Pro and Precision products, it is attractive to use the low-cost IKONOS Geo product with vendor-provided rational polynomial coefficients (RPCs), to produce highly accurate mapping products. The imaging geometry of IKONOS high-resolution imagery is described by RFs instead of rigorous sensor models. This paper presents four different polynomial models, that are the offset model, the scale and offset model, the Affine model, and the 2nd-order polynomial model, defined respectively in object space and image space to improve the accuracies of the RF-derived ground coordinates. Not only the algorithm for RF-based ground coordinates but also the algorithm for accuracy improvement of RF-based ground coordinates are developed which is based on the four models, The experiment also evaluates the effect of different cartographic parameters such as the number, configuration, and accuracy of ground control points on the accuracy of geopositioning. As the result of a experimental application, the root mean square errors of three dimensional ground coordinates which are first derived by vendor-provided Rational Function models were averagely 8.035m in X, 10.020m in Y and 13.318m in Z direction. After applying polynomial correction algorithm, those errors were dramatically decreased to averagely 2.791m in X, 2.520m in Y and 1.441m in Z. That is, accuracy was greatly improved by 65% in planmetry and 89% in vertical direction.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.39 no.4
• /
• pp.314-320
• /
• 2011

In this work, optimization of two-stage shock absorption system for lunar lander has been carried out. Because of complexity of impact phenomena of shock absorption system, a 1-D constitutive model is proposed to describe the behavior of shock absorption system. Quadratic polynomial regression meta-model is constructed by using a commercial software ABAQUS with the proposed 1-D constitutive model, and sequential approximate optimization of two-stage shock absorption system has been carried out along with the constructed meta-model. Through the optimization, it is verified that landing impact force on lunar lander can be considerably reduced by changing the cell size and foil thickness of honeycomb structure in two-stage shock absorption system.

• Nuclear Engineering and Technology
• /
• v.55 no.4
• /
• pp.1382-1399
• /
• 2023

Pressure relief valve (PRV) is one of the important control valves used in nuclear power plants, and its sealing performance is crucial to ensure the safety and function of the entire pressure system. For the sealing performance improving purpose, an explicit function that accounts for all design parameters and can accurately describe the relationship between the multi-design parameters and the seal performance is essential, which is also the challenge of the valve seal design and/or optimization work. On this basis, a surrogate model-based design optimization is carried out in this paper. To obtain the basic data required by the surrogate model, both the Finite Element Model (FEM) and the Computational Fluid Dynamics (CFD) based numerical models were successively established, and thereby both the contact stresses of valve static sealing and dynamic impact (between valve disk and nozzle) could be predicted. With these basic data, the polynomial chaos expansion (PCE) surrogate model which can not only be used for inputs-outputs relationship construction, but also produce the sensitivity of different design parameters were developed. Based on the PCE surrogate model, a new design scheme was obtained after optimization, in which the valve sealing stress is increased by 24.42% while keeping the maximum impact stress lower than 90% of the material allowable stress. The result confirms the ability and feasibility of the method proposed in this paper, and should also be suitable for performance design optimizations of control valves with similar structures.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.5
• /
• pp.1035-1040
• /
• 2024

The main objective of inspecting structures is to ensure the safety of all entities that utilize these structures as cracks in structures if not attended to could lead to serious calamities. With that objective in mind, artificial intelligence (AI) based technologies to assist human inspectors are needed especially for retaining walls in structures. In this paper, we predict the crack displacement of retaining walls using an Polynomial Regressive (PR) analysis model, as well as Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) deep learning models, and compare their performance. For the performance comparison, we apply multi-variable feature inputs, by utilizing temperature and rainfall data that may affect the crack displacement of the retaining wall. The training and inference data were collected through measuring sensors such as inclinometers, thermometers, and rain gauges. The results show that the multi-variable feature model had a MAE of 0.00186, 0.00450 and 0.00842, which outperformed the single variable feature model at 0.00393, 0.00556 and 0.00929 for the polynomial regression model, LSTM model and the GRU model respectively from the evaluation performed.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.15 no.6 s.99
• /
• pp.712-717
• /
• 2005

This paper presents a system identification method for multi-input, multi-output (MIMO) systems, by which a rational polynomial transfer function model is identified from experimentally determined frequency response function data. Analytically determined information is incorporated in this method to obtain a more reliable model, even in the frequency range where the excitation energy is limited. To verify the suggested method, shaking table test for an actively controlled two-story, bench-scale building employing an active mass damper is conducted. The results show that the proposed method is quite effective and robust for system identification of MIMO systems.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.24 no.4
• /
• pp.583-589
• /
• 1987

A new approximation method is proposed for the linear model reduction of high order dynamic systems. This mehtod is based upon the denominator table(D-table) and time moment-matching technique. The denominator table(D-table) is used to obtain the denominator polynomial of reduced-order model, and the numerator polynomial is obtained by time moment-matching method. This proposed method does not require the calculation of the alpha-beta expansion and reciprocal transformation which should be calculadted by Routh approximation method. The advantages of the proposed method are that it is computationally every attractive better than Routh approximation method and the reduced model is stable Il the original system is stable.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.3
• /
• pp.253-258
• /
• 2005

In this study, we introduce a new category of fuzzy inference systems based on information granulation to carry out the model identification of complex and nonlinear systems. Informal speaking, information granules are viewed as linked collections of objects (data, in particular) drawn together by the criteria of proximity, similarity, or functionality. To identify the structure of fuzzy rules we use genetic algorithms (GAs). Granulation of information with the aid of Hard C-Means (HCM) clustering algorithm help determine the initial parameters of fuzzy model such as the initial apexes of the membership functions and the initial values of polynomial functions being used in the premise and consequence part of the fuzzy rules. And the initial parameters are tuned effectively with the aid of the genetic algorithms and the least square method (LSM). The proposed model is contrasted with the performance of the conventional fuzzy models in the literature.