• Computers and Concrete
• /
• v.5 no.6
• /
• pp.573-597
• /
• 2008

Among artificial intelligence-based computational techniques, adaptive neuro-fuzzy inference systems (ANFIS) are particularly suitable for modelling complex systems with known input-output data sets. Such systems can be efficient in modelling non-linear, complex and ambiguous behaviour of cement-based materials undergoing single, dual or multiple damage factors of different forms (chemical, physical and structural). Due to the well-known complexity of sulfate attack on cement-based materials, the current work investigates the use of ANFIS to model the behaviour of a wide range of self-consolidating concrete (SCC) mixture designs under various high-concentration sodium sulfate exposure regimes including full immersion, wetting-drying, partial immersion, freezing-thawing, and cyclic cold-hot conditions with or without sustained flexural loading. Three ANFIS models have been developed to predict the expansion, reduction in elastic dynamic modulus, and starting time of failure of the tested SCC specimens under the various high-concentration sodium sulfate exposure regimes. A fuzzy inference system was also developed to predict the level of aggression of environmental conditions associated with very severe sodium sulfate attack based on temperature, relative humidity and degree of wetting-drying. The results show that predictions of the ANFIS and fuzzy inference systems were rational and accurate, with errors not exceeding 5%. Sensitivity analyses showed that the trends of results given by the models had good agreement with actual experimental results and with thermal, mineralogical and micro-analytical studies.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1991.10a
• /
• pp.29-32
• /
• 1991

It is well known that the fatigue damage process in composite materials is very complicated due to complex failure mechanisms that comprise debounding, matrix cracking, delamination and fiber splitting of laminates. Therefore, the residual strength, instead of a single dominant crack length, is chosen to describe the criticality of the damage accumulated in the sublaminate. In this study, two models for residual strength degradation established by Yang-Liu and Tanimoto-Ishikawa that are capable of predicting the statistical distribution of both fatigue life and residual strength have been investigated and compared. Statistical methodologies for fatigue life prediction of composite materials have frequently been adopted. However, these are usually based on a simplified probabilistic approach considering only the variation of fatigue test data. The main object of this work is to propose a fatigue reliability analysis model which accounts for the effect of all sources of variation such as fabrication and workmanship, error in the fatigue model, load itself, etc. The proposed model is examined using the previous experimental data of GFRP and it is shown that it can be practically applied for fatigue problems in composite materials.

• ETRI Journal
• /
• v.5 no.1
• /
• pp.10-16
• /
• 1983

When analyzing a complex system with repair environments, it is necessary to calculate such parameters as availability and various kinds of failure time measures. These measures are defined and methods of calculating them using Markov process are presented. Analyzing the various system states, numerical values of the reliability measures can be obtained by calculating the state probabilities. And these techniques are widely applied to reliability prediction and also to maintenance strategy.

• Smart Structures and Systems
• /
• v.22 no.2
• /
• pp.193-200
• /
• 2018

From the viewpoint of engineering applications, the prediction of the failure of bogies plays an important role in preventing the occurrence of fatigue. Fatigue is a complex phenomenon affected by many uncertainties (such as load, environment, geometrical and material properties, and so on). The key to predict fatigue damage accurately is how to quantify these uncertainties. A Bayesian model is used to account for the uncertainty of various sources when predicting fatigue damage of structural components. In spite of improvements in the design of fatigue-sensitive structures, periodic non-destructive inspections are required for components. With the help of modern nondestructive inspection techniques, the fatigue flaws can be detected for bogie structures, and fatigue reliability can be updated by using Bayesian theorem with inspection data. A practical fatigue analysis of welded bogies is utilized to testify the effectiveness of the proposed methods.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.20 no.3
• /
• pp.273-279
• /
• 2007

Probabilistic Risk Assessment considering statistically random variables is performed for the preliminary design of an Arch Bridge. Component reliabilities of girders have been evaluated using the response surfaces of the design variables at the selected critical sections based on the maximum shear and negative moment locations. Response Surface Method (RSM) is successfully applied for reliability analyses lot this relatively small probability of failure of the complex structure, which is hard to be calculated by Monte-Carlo Simulations or by First Order Second Moment method that can not easily calculate the derivative terms in implicit limit state functions. For the analysis of system reliability, parallel resistance system composed of girders is modeled as a parallel series connection system. The upper and lower probabilities of failure for the structural system have been evaluated and compared with the suggested prediction method for the combination of failure modes. The suggested prediction method for the combination of failure modes reveals the unexpected combinations of element failures in significantly reduced time and efforts, compared with the previous permutation method or conventional system reliability analysis method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.8
• /
• pp.4881-4894
• /
• 2014

This study selected 83 manufacturing firms that had been delisted from the KOSDAQ market from 2009 to 2012 and the sample firms for the two-paired sampling method were compared with 83 normal firms running businesses with same items or in same industry. The 75 financial ratios for five years immediately before delisting were used for Mean Difference Analysis with those of normal firms. Fifteen variables assumed to be significant variables for five consecutive years out of the analysis were used to in the Dichotomous Classification Technique, Logistic Regression Analysis and Discriminant Analysis. As a result of those three analyses, the Logistic Regression Analysis model was found to show the greatest discrimination. This study is differentiated from previous studies as it assumed that the firm's failure proceeded slowly over long period of time and it tried to predict the firm's failure earlier using the five years' historical data immediately before failure, whereas previous studies predicted it using three years' data only. This study is also differentiated from the proceeding comparative studies by its statistically complex Multi-Variate Analysis and Dichotomous Classification Analysis, which general stakeholders can easily approach.

• Korean Journal of Construction Engineering and Management
• /
• v.10 no.1
• /
• pp.78-90
• /
• 2009

Recently, operation of highway is the complex digital Infrastructure based on complicated IT. The application of IT is increasing more and more in digital Infrastructure. Though IT is very convenient, if unpredicted operating risk of highway occurs, widespread damage can be large. When operating risk of highway occurs, road users are out of smoothly-run service because of the operating interruption. This risk causes unpredicted operating management cost and additional maintenance cost. It will excess over the planned operating cost, which may leads to users's unsafety and operator's insolvency because of income loss. Until now, related studies to find out the risk are not sufficient. The purpose of this study is to suggest risk cost items and to estimate the reasonable risk cost by using simulation method in case of occurring the huge power failure at the operating digitalized highway. This study indicates the several plans to hedge against risk cost and the management of highway project. From now on, it will be used as basic data to confirm the soundness of operating system in Digital Infrastructure.

• Advances in materials Research
• /
• v.11 no.1
• /
• pp.59-73
• /
• 2022

In the construction industry, thin-walled frame elements with very slender open cross-sections and low torsional stiffness are often subjected to a complex loading condition where axial, bending, shear and torsional stresses are present simultaneously. Hence, these often fail in instability even before the yield capacity is reached. One of the most common instability conditions associated with thin-walled structures is Lateral Torsional Buckling (LTB). In this study, a first order Generalized Beam Theory (GBT) formulation and numerical analysis of cold-formed steel lipped channel beams (C80×40×10×1, C90×40×10×1, C100×40×10×1, C80×40×10×1.6, C90×40×10×1.6 and C100×40×10×1.6) subjected to uniform moment is carried out to predict pure Lateral Torsional Buckling (LTB). These results are compared with the Finite Element Analysis of the beams modelled with shell elements using ABAQUS and analytical results based on Euler's buckling formula. The mode wise deformed shape and modal participation factors are obtained for comparison of the responses along with the effect of varying the length of the beam from 2.5 m to 10 m. The deformed shapes of the beam for different modes and GBTUL plots are analyzed for comparative conclusions.

• Journal of Digital Contents Society
• /
• v.19 no.4
• /
• pp.789-799
• /
• 2018

This article presents machine learning based approach on Big data to analyzing time series data for anomaly detection in such industrial complex system. Long Short-Term Memory (LSTM) network have been demonstrated to be improved version of RNN and have become a useful aid for many tasks. This LSTM based model learn the higher level temporal features as well as temporal pattern, then such predictor is used to prediction stage to estimate future data. The prediction error is the difference between predicted output made by predictor and actual in-coming values. An error-distribution estimation model is built using a Gaussian distribution to calculate the anomaly in the score of the observation. In this manner, we move from the concept of a single anomaly to the idea of the collective anomaly. This work can assist the monitoring and management of Smart Factory in minimizing failure and improving manufacturing quality.

• Journal of Intelligence and Information Systems
• /
• v.9 no.1
• /
• pp.157-177
• /
• 2003

This paper presents a comprehensive and successful application of data mining methodologies to improve and predict wafer yield in a semiconductor wafer fabrication system. As the wafer fabrication process is getting more complex and the volume of technological data gathered continues to be vast, it is difficult to analyze the cause of yield deterioration effectively by means of statistical or heuristic approaches. To begin with this paper applies a clustering method to automatically identify AUF (Area Uniform Failure) phenomenon from data instead of naked eye that bad chips occurs in a specific area of wafer. Next, sequential pattern analysis and classification methods are applied to and out machines and parameters that are cause of low yield, respectively. Furthermore, radial bases function method is used to predict yield of wafers that are in process. Finally, this paper demonstrates an information system, Y2R-PLUS (Yield Rapid Ramp-up, Prediction, analysis & Up Support), that is developed in order to analyze and predict wafer yield in a korea semiconductor manufacturer.