• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.152-159
• /
• 2024

Cracks in structural materials present a critical challenge to infrastructure safety and long-term durability. Timely and precise crack detection is essential for proactive maintenance and the prevention of catastrophic structural failures. This study introduces an innovative approach to tackle this issue using U-Net deep learning architecture. The primary objective of the intended research is to explore the potential of U-Net in enhancing the precision and efficiency of crack detection across various concrete crack detection under various environmental conditions. Commencing with the assembling by a comprehensive dataset featuring diverse images of concrete cracks, optimizing crack visibility and facilitating feature extraction through advanced image processing techniques. A wide range of concrete crack images were collected and used advanced techniques to enhance their visibility. The U-Net model, well recognized for its proficiency in image segmentation tasks, is implemented to achieve precise segmentation and localization of concrete cracks. In terms of accuracy, our research attests to a substantial advancement in automated of 95% across all tested concrete materials, surpassing traditional manual inspection methods. The accuracy extends to detecting cracks of varying sizes, orientations, and challenging lighting conditions, underlining the systems robustness and reliability. The reliability of the proposed model is measured using performance metrics such as, precision(93%), Recall(96%), and F1-score(94%). For validation, the model was tested on a different set of data and confirmed an accuracy of 94%. The results shows that the system consistently performs well, even with different concrete types and lighting conditions. With real-time monitoring capabilities, the system ensures the prompt detection of cracks as they emerge, holding significant potential for reducing risks associated with structural damage and achieving substantial cost savings.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10b
• /
• pp.1705-1711
• /
• 1991

On-line fault detection and diagnosis has an increasing interest in a chemical process industry, especially for a process control and automation. The chemical process needs an intelligent operation-aided workstation which can do such tasks as process monitoring, fault detection, fault diagnosis and action guidance in semiautomatic mode. These tasks can increase the performance of a process operation and give merits in economics, safety and reliability. Aiming these tasks, series of researches have been done in our lab. Main results from these researches are building appropriate knowledge representation models and a diagnosis mechanism for fault detection and diagnosis in a chemical process. The knowledge representation schemes developed in our previous research, the symptom tree model and the fault-consequence digraph, showed the effectiveness and the usefulness in a real-time application, of the process diagnosis, especially in large and complex plants. However in our previous approach, the diagnosis speed is its demerit in spite of its merits of high resolution, mainly due to using two knowledge models complementarily. In our current study, new knowledge representation scheme is developed which integrates the previous two knowledge models, the symptom tree and the fault-consequence digraph, into one. This new model is constructed using a material balance, energy balance, momentum balance and equipment constraints. Controller related constraints are included in this new model, which possesses merits of the two previous models. This new integrated model will be tested and verified by the real-time application in a BTX process or a crude unit process. The reliability and flexibility will be greatly enhanced compared to the previous model in spite of the low diagnosis speed. Nexpert Object for the expert system shell and SUN4 workstation for the hardware platform are used. TCP/IP for a communication protocol and interfacing to a dynamic simulator, SPEEDUP, for a dynamic data generation are being studied.

• Sleep Medicine and Psychophysiology
• /
• v.26 no.2
• /
• pp.86-103
• /
• 2019

Objectives: The objective of this study was to develop evidence- and consensus-based clinical safety usage guidelines for sedative hypnotics using the Delphi technique. Methods: A group of 15 sleep experts from Korean Academy of Sleep Medicine were chosen for this study comprising a three-round web-based Delphi survey. The first round survey was composed of 39 questions to identify problems with sedative hypnotics usage in Korean clinical practice and the result roughly outlined what should be included in the guidelines. The second round survey was composed of 21 questions to collect specific opinions of experts on clinically important issues in prescribing sedative hypnotics, and its result provided the basis for the guidelines. A third round survey aimed to evaluate the reliability and validity of the established guidelines. Results: In the third round, all 17 items showed a median of 4 or more, with an average of 4.12 and a standard deviation of 0.32. Thus we present safety usage guidelines with 13 propositions for prescription, maintenance, and withdrawal of sedative hypnotics. Conclusion: The safety usage guidelines on sedative hypnotics developed from this study could lead to safe and effective prescription of hypnotics in clinical practice, especially for the non-experts in sleep medicine. Furthermore, the guidelines will help to improve the quality of insomnia treatment by contributing to the establishment of a safe regime for sedative hypnotics without excessive use of drugs.

• Geomechanics and Engineering
• /
• v.31 no.2
• /
• pp.129-147
• /
• 2022

The properties of soil are naturally highly variable and thus, to ensure proper safety and reliability, we need to test a large number of samples across the length and depth. In pile foundations, conducting field tests are highly expensive and the traditional empirical relations too have been proven to be poor in performance. The study proposes a state-of-art Particle Swarm Optimization (PSO) hybridized Artificial Neural Network (ANN), Extreme Learning Machine (ELM) and Adaptive Neuro Fuzzy Inference System (ANFIS); and comparative analysis of metaheuristic models (ANN-PSO, ELM-PSO, ANFIS-PSO) for prediction of bearing capacity of pile foundation trained and tested on dataset of nearly 300 dynamic pile tests from the literature. A novel ensemble model of three hybrid models is constructed to combine and enhance the predictions of the individual models effectively. The authenticity of the dataset is confirmed using descriptive statistics, correlation matrix and sensitivity analysis. Ram weight and diameter of pile are found to be most influential input parameter. The comparative analysis reveals that ANFIS-PSO is the best performing model in testing phase (R² = 0.85, RMSE = 0.01) while ELM-PSO performs best in training phase (R² = 0.88, RMSE = 0.08); while the ensemble provided overall best performance based on the rank score. The performance of ANN-PSO is least satisfactory compared to the other two models. The findings were confirmed using Taylor diagram, error matrix and uncertainty analysis. Based on the results ELM-PSO and ANFIS-PSO is proposed to be used for the prediction of bearing capacity of piles and ensemble learning method of joining the outputs of individual models should be encouraged. The study possesses the potential to assist geotechnical engineers in the design phase of civil engineering projects.

• Journal of Hydrogen and New Energy
• /
• v.28 no.3
• /
• pp.252-272
• /
• 2017

Fuel cell systems have to satisfy acceptable operating reliability, sufficient lifetime and price to enter the market in competition with existing products. Fuel cells are made up of complex element technologies and various problems related to the failure of the components can affect the reliability and safety of the system. This problem can be overcome by introducing a monitoring and supervisory control system in addition to automatic control to detect the failure of the fuel cell quickly and properly diagnose the performance degradation. For the fault detection and diagnosis of polymer electrolyte fuel cells, the model based method using the theoretical superposition value and the non-model based method of checking the signal tendency or the converted signal characteristic can be applied. The methods analyzed in this paper can contribute to the development of integrated monitoring and control technology for the whole system as well as the stack.

• Structural Engineering and Mechanics
• /
• v.56 no.5
• /
• pp.707-726
• /
• 2015

There is a growing trend of considering uncertainty in optimization process since last few decades. In this regard, Robust Design Optimization (RDO) scheme has gained increasing momentum because of its virtue of improving performance of structure by minimizing the variation of performance and ensuring necessary safety and feasibility of constraint under uncertainty. In the present study, RDO of reinforced concrete folded plate and shell structure has been carried out incorporating uncertainty in the relevant parameters by Monte Carlo Simulation. Folded plate and shell structures are among the new generation popular structures often used in aesthetically appealing constructions. However, RDO study of such important structures is observed to be scarce. The optimization problem is formulated as cost minimization problem subjected to the force and displacements constraints considering dead, live and wind load. Then, the RDO is framed by simultaneously optimizing the expected value and the variation of the performance function using weighted sum approach. The robustness in constraint is ensured by adding suitable penalty term and through a target reliability index. The RDO problem is solved by Sequential Quadratic Programming. Subsequently, the results of the RDO are compared with conventional deterministic design approach. The parametric study implies that robust designs can be achieved by sacrificing only small increment in initial cost, but at the same time, considerable quality and guarantee of the structural behaviour can be ensured by the RDO solutions.

• Korean Medical Education Review
• /
• v.23 no.3
• /
• pp.185-193
• /
• 2021

Students must be familiar with clinical skills before starting clinical practice to ensure patients' safety and enable efficient learning. However, performance is mainly tested in the third or fourth years of medical school, and studies using the validity framework have not been reported in Korea. We analyzed the validity of a performance test conducted among second-year students classified into content, response process, internal structure, relationships with other variables, and consequences according to Messick's framework. As results of the analysis, content validity was secured by developing cases according to a pre-determined blueprint. The quality of the response process was controlled by training and calibrating raters. The internal structure showed that (1) reliability by generalizability theory was acceptable (coefficients of 0.724 and 0.786, respectively, for day 1 and day 2), and (2) the relevant domains had proper correlations, while the clinical performance examination (CPX) and objective structured clinical examination (OSCE) showed weaker relationships. OSCE/CPX scores were correlated with other variables, especially grade point average and oral structured exam scores. The consequences of this assessment were (1) making students learn clinical skills and study themselves, while causing too much stress for students due to lack of motivation; (2) reminding educators of the need to apply practical teaching methods and to give feedback on the test results; and (3) providing an opportunity for faculty to consider developing support programs. It is necessary to develop the blueprint more precisely according to students' level and to verify the validity of the response process with statistical methods.

• Journal of Radiation Protection and Research
• /
• v.43 no.2
• /
• pp.50-58
• /
• 2018

Background: In terms of the Level 3 probabilistic safety assessment (Level 3 PSA), ingestion of food that had been exposed to radioactive materials is important to assess the intermediate- and long-term radiological dose. Because the ingestion dose is considerably dependent upon the agricultural and dietary characteristics of each country, the reliability of the assessment results may become diminished if the characteristics of a foreign country are considered. Thus, this study intends to evaluate and analyze the ingestion dose of Korean during a severe accident by completely considering the available agricultural and dietary characteristics in Korea. Materials and Methods: This study uses COMIDA2, which is a program based on dynamic food chain model. It sets the parameters that are appropriate to Korean characteristics so that we can evaluate the inherent ingestion dose of Korean. The results were analyzed by considering the accident date and food category with regard to the $^{137}Cs$. Results and Discussion: The dose and contribution of the food category depicted distinctive differences based on the accident date. Particularly, the ingestion dose during the first and second years depicted a considerable difference by the accident date. However, after the third year, the effect of foliar absorption was negligible and exhibited a similar tendency along with the order of root uptake rate based on the food category. Conclusion: In this study, the agricultural and dietary characteristics of Korea were analyzed and evaluated the ingestion dose of Korean during a severe accident using COMIDA2. By considering the inherent characteristics of Korean, it can be determined that the results of this study will significantly contribute to the reliability of the Level 3 PSA.

• Journal of The Korea Institute of Healthcare Architecture
• /
• v.25 no.3
• /
• pp.75-83
• /
• 2019

Purpose: There are no clear criteria for slip performance in the BF certification process, so the evaluator relies on subjective judgments depending on the field situation. Physical criteria for determining the slip performance of various floor finishes are not clear. C.S.R., the only criterion currently being used to check slip performance, may raise questions about its coverage, feasibility and reliability. Method: For an analysis of domestic standards and status, KS L 1001, KS M 3510, and KS F 2375. External standards are analyzed for ADA Standard, ANSI Standard, and BS EN Standard. Analyze the test methods and evaluation criteria of O-Y-PSM, BPT, and the dynamic slip resistance test used in these criteria. It also presents an improvement plan for the rational presentation of standards. Results: To date, various kinds of test methods and measuring devices of the slip resistance coefficient have been developed, but there are not many ways to trust useful results related to user safety. Reliability and thoroughly verified test methods and criteria should be used to assess the slip performance of the floor. In order to improve the standard for the evaluation of slip performance in Korea, the existing standard should first be raised to the same level as the overseas standard, and the application of the discriminatory standard should be applied considering the characteristics and usage patterns of each space. Implication: Currently, Korean standards propose various test methods, but the proper use of test methods, scope and assessment criteria are not established, so improvement of the comprehensive standard is necessary.

• Journal of Welding and Joining
• /
• v.29 no.1
• /
• pp.85-89
• /
• 2011

Waste water is disposed to sewage disposal plant by underground PE double wall pipes. Various processes have been introduced to join PE pipes, but most of these methods have many disadvantages such as costs, lack of reliability and difficulties in joining, etc. Recently butt welding has been paid much attention to joint PE pipes as this process has many advantages such as cost, safety and reliability. In this study, newly developed heat plate, a patent-pending heat plate with a groove, was used to butt-weld PE double wall pipes with different misalignment gaps to simulate real underground conditions, and the butt welding temperature of PE pipe was determined by thermal analysis (Thermal Gravimetric Analysis, Differential Scanning Calorimetry and Dynamic Mechanical Analysis). The resulting joining characteristics of double wall pipes were compared with those from a conventional heat plate, in terms of stiffness, flattening and leakage tests. The results from the stiffness and flattening test showed that there were no big differences between the butt-welded joints made from these two plates. From the leakage test, although PE pipes welded with a conventional heat plate did leak below the required test conditions (10 min. at 0.75kgf/cm2), the pipes welded with a patent-pending grooved heat plate did not show any leakage even at a pressure 1.5 times higher than the required conditions. It was noted that by utilizing a grooved heat plate more complete fusion at the pipe joints could be obtained, which in turn induced a high quality joints.