• Structural Engineering and Mechanics
• /
• 제91권5호
• /
• pp.443-457
• /
• 2024

At present, the traditional concrete surface inspection methods based on artificial vision have the problems of high cost and insecurity, while the computer vision methods rely on artificial selection features in the case of sensitive environmental changes and difficult promotion. In order to solve these problems, this paper introduces deep learning technology in the field of computer vision to achieve automatic feature extraction of structural damage, with excellent detection speed and strong generalization ability. The main contents of this study are as follows: (1) A method based on DeepLabV3+ convolutional neural network model is proposed for surface detection of post-earthquake structural damage, including surface damage such as concrete cracks, spaling and exposed steel bars. The key semantic information is extracted by different backbone networks, and the data sets containing various surface damage are trained, tested and evaluated. The intersection ratios of 54.4%, 44.2%, and 89.9% in the test set demonstrate the network's capability to accurately identify different types of structural surface damages in pixel-level segmentation, highlighting its effectiveness in varied testing scenarios. (2) A semantic segmentation model based on DeepLabV3+ convolutional neural network is proposed for the detection and evaluation of post-earthquake structural components. Using a dataset that includes building structural components and their damage degrees for training, testing, and evaluation, semantic segmentation detection accuracies were recorded at 98.5% and 56.9%. To provide a comprehensive assessment that considers both false positives and false negatives, the Mean Intersection over Union (Mean IoU) was employed as the primary evaluation metric. This choice ensures that the network's performance in detecting and evaluating pixel-level damage in post-earthquake structural components is evaluated uniformly across all experiments. By incorporating deep learning technology, this study not only offers an innovative solution for accurately identifying post-earthquake damage in civil engineering structures but also contributes significantly to empirical research in automated detection and evaluation within the field of structural health monitoring.

• Journal of Information Technology Applications and Management
• /
• 제14권2호
• /
• pp.151-168
• /
• 2007

The corporate credit rating represents an assessment of the relative level of risk associated with the timely payments required by the debt obligation. In this study, the corporate credit rating model employs artificial intelligence methods including Neural Network (NN) and Case-Based Reasoning (CBR). At first we suggest three classification models, as partitioned neural networks, all of which convert multi-group classification problems into two group classification ones: Ordinal Pairwise Partitioning (OPP) model, binary classification model and simple classification model. The experimental results show that the partitioned NN outperformed the conventional NN. In addition, we put to use CBR that is widely used recently as a problem-solving and learning tool both in academic and business areas. With an advantage of the easiness in model design compared to a NN model, the CBR model proves itself to have good classification capability through the highest hit ratio in the corporate credit rating.

• Journal of Electrical Engineering and Technology
• /
• 제11권6호
• /
• pp.1527-1534
• /
• 2016

Online voltage stability monitoring using real-time measurements is one of the most important tasks in a smart grid system to maintain the grid stability. Loading margin is a good indicator for assessing the voltage stability level. This paper presents an Extreme Learning Machine (ELM) approach for estimation of voltage stability level under credible contingencies using real-time measurements from Phasor Measurement Units (PMUs). PMUs enable a much higher data sampling rate and provide synchronized measurements of real-time phasors of voltages and currents. Depth First (DF) algorithm is used for optimally placing the PMUs. To make the ELM approach applicable for a large scale power system problem, Mutual information (MI)-based feature selection is proposed to achieve the dimensionality reduction. MI-based feature selection reduces the number of network input features which reduces the network training time and improves the generalization capability. Voltage magnitudes and phase angles received from PMUs are fed as inputs to the ELM model. IEEE 30-bus test system is considered for demonstrating the effectiveness of the proposed methodology for estimating the voltage stability level under various loading conditions considering single line contingencies. Simulation results validate the suitability of the technique for fast and accurate online voltage stability assessment using PMU data.

• 한국환경보건학회지
• /
• 제41권2호
• /
• pp.102-115
• /
• 2015

Objectives: A learning organization was designed and implemented on the basis of the selection criteria and essential elements of knowledge translation theory. Methods: The learning organization was designed on the basis of biosafety harmonization criteria and risk management strategy and was implemented as the learning organization for biosafety management by the National Institute of Health, Korea Centers for Disease Control & Prevention. The effect of knowledge translation in the research institutions by evidence-based policy was verified. Results: The result of applying the knowledge translation theory involving all stakeholders showed a positive reaction in establishing and implementing biosafety management strategy and embodied risk assessment criteria and evoked sympathy with the necessity of learning and using of expert knowledge about risk assessment and risk management. All stakeholders initiated voluntarily action toward new human-network construction and communication between similar organizations. The learning organization's capability expanded the base of knowledge translation. Conclusion: These results showed that a learning organization could enhance the autonomous safety management system by diffusion of knowledge translation.

• 대한조선학회논문집
• /
• 제48권5호
• /
• pp.404-413
• /
• 2011

It is important to assess and improve the warship survivability for the weapon threats which have a critical effect on warship. The survivability of the warship is defined as the capability of a warship to avoid or withstand a man-made hostile environment. The survivability of the warship consists of three categories (Susceptibility, Vulnerability and Recoverability). Firstly, the susceptibility is defined as the inability of a warship to avoid radars, guns, missiles and etc. Secondly, the vulnerability is defined as the inability of a warship to withstand the man-made hostile environment. Finally, the recoverability is defined as the ability of a warship to recover the damaged components and systems. Among them, this paper has described the vulnerability assessment for the hypothetical system which is composed of critical components. Also, the procedure which is suggested to calculate the vulnerable probability of the damaged warship is based on the Vulnerable Area Method.

• 비파괴검사학회지
• /
• 제26권3호
• /
• pp.153-161
• /
• 2006

A simulation program SIMULTSONIC is under development at CNDE to help determine and/or help optimize ultrasonic probe locations for inspection of complex components. SIMULTSONIC provides a ray-trace based assessment for immersion and contact modes of inspection. The code written in Visual C++ operating in Microsoft Windows environment provides an interactive user interface. In this paper, a description of the various features of SIMULTSONIC is given followed by examples illustrating the capability of SIMULTSONIC to deal with inspection of canonical objects such as pipes. In particular, the use of SIMULTSONIC in the inspection of very thin-walled pipes (with 450 urn wall thickness) is described. Ray trace based assessment was done using SIMULTSONIC to determine the standoff distance and the angle of oblique incidence for an immersion mode focused transducer. A 3-cycle Hanning window pulse was chosen for simulations. Experiments were carried out to validate the simulations. The A-scans and the associated B-Scan images obtained through simulations show good correlation with experimental results, both with the arrival time of the signal as well as with the signal amplitudes.

• Structural Engineering and Mechanics
• /
• 제60권1호
• /
• pp.31-50
• /
• 2016

During the recent years, resistance mechanisms of reinforced concrete (RC) buildings against progressive collapse are investigated extensively. Although a general agreement is observed about their qualitative behavior in technical literature, there is not such a comprehensive point of view regarding the quantitative methods for predicting collapse resistance of RC members. Therefore, in the present study a simplified theoretical method is developed in order to predict general behavior of RC frames under the column removal scenario. In the introduced method, the robustness of the frame is extracted based on the capacity of the beams. The proposed method expresses ultimate arching and catenary capacities of the beams and also obtains the corresponding vertical displacements. Based on the calculated capacities, the introduced method also provides a quantitative assessment of structural robustness and determines whether or not the collapse occurs. The capability of the method is evaluated using experimental results in the literature. The evaluation study indicates that the proposed theoretical procedure can establish a reliable foundation for progressive collapse assessment of RC frame structures.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 1996년도 춘계학술발표회논문집(2)
• /
• pp.325-330
• /
• 1996

The existing CHF correlations for internally heated concentric annulus channels are assessed using KAIST CHF database for uniformly heated vertical annuli. Six annulus correlations (Jannsen-Kervinen. Barnett, Levitan-Lantsman, Kumamaru et al., Doerffer et al., and Bobkov et at.) are chosen for assessment based on literature survey and Groeneveld et al.'s CHF table for round tube is also assessed for comparison. Among the above correlations, two are inlet-condition type and others local conditions type. To make the comparison meaningful, the local-condition-type correlations are assessed in two ways: direct substitution method (DSM) and heat balance condition method (HBM). Totally 1174 data are classified into 10 groups based on pressure and mass flux conditions and correlations are assessed to each group separately. Prediction capability of each correlation depends on the data group and none shows the best prediction over the entire group. In overall, the correlations by Doerffer et al. and Jannsen et al. appear to be the best, but Barnett or Levitan-Lantsman correlations also show reasonable prediction for most groups. However, the low-pressure, ]ow flow CHFs are not well predicted by any correlations. The CHF table for round tubes overpredicts the CHF in annuli at fixed local conditions.

• Earthquakes and Structures
• /
• 제14권2호
• /
• pp.155-165
• /
• 2018

Methods based on nonlinear static analysis as simple tools could be used for the seismic analysis and assessment of structures. In the present study, capability of the N2 method as a well-known nonlinear analysis procedure examines for the estimation of the damage index of multi-storey reinforced concrete frames. In the implemented framework, equivalent single-degree-of-freedom (SDOF) models are utilized for the global damage estimation of multi-degree-of-freedom (MDOF) systems. This method does not require high computational analysis and subsequently decreases the required time of seismic design and assessment process. To develop the methodology, RC frames with period range from 0.4 to 2.0 s under 40 records are studied. The effectiveness of proposed technique is evaluated through numerical study under near- and far-field earthquake ground motions. Finally, the results of developed models are compared with two other simplified schemes along with nonlinear time history analysis results of multi-storey frames. To improve the accuracy of damage estimation, a modified relation is presented based on the N2 method results for near- and far-field earthquakes.

• 한국멀티미디어학회:학술대회논문집
• /
• 한국멀티미디어학회 2004년도 춘계학술발표대회논문집
• /
• pp.709-713
• /
• 2004

This Paper Presents an Internet-based Java self-learning educational system which consists of a management system named Java Web Player (JWP) and creative multimedia contents fer Java language. The JWP Is a Java application program free from security problems by the Java Web Start technologies that supports an Integrated learning environment including three Important learning Procedures: Java concept learning Process, Programming practice process and assessment process. This JWP enables the learners to achieve efficient and Interesting self-learning since the learning process is designed to enhance the multimedia capabilities on the basis of various educational technologies. On-line voice presentation and its related texts together with moving images are synchronized for efficiently conveying creative contents to learners. Furthermore, a simple and useful compiler is included in the JWP fur providing user-friendly language practice environment enabling such as coding, editing, executing and debugging Java source files on the Web. The assessment process with various items helps the learners not only to increase their academic capability but also to appreciate their current degree of understanding. Finally, simple multiple choices are given suddenly to the learners while they are studying through the JWP and the test results are displayed on the message box. The proposed system can be used for an efficient tool for learning system on the Web.