• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.27 no.2
• /
• pp.10-16
• /
• 2004

Data mining technique is the exploration and analysis, by automatic or semiautomatic means, of large quantities of data in order to discover meaningful patterns and rules. This paper uses a data mining technique for the prediction of defect types in manufacturing Process. The Purpose of this Paper is to model the recognition of defect type Patterns and Prediction of each defect type before it occurs in manufacturing process. The proposed model consists of data handling, defect type analysis, and defect type prediction stages. The performance measurement shows that it is higher in prediction accuracy than logistic regression model.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.213-221
• /
• 2022

Defects are the risk factors in the construction process of buildings. They cause damage, delaying the construction duration. They especially cause adverse effects on the top-down construction method. This study analyzed the degree of construction delay induced by each work type, focusing on defects in the top-down method. Then, we derived construction delay induction coefficient from different work types in order by using the severity of construction delay per defect and the occurrence probability of defect; this assessment model measures the impact of defects on construction delay for each work type. Furthermore, by comparing each work type based on the defect frequency and the construction delay induction coefficient, we found work types that need to be administered attentively. We identified that plastering work was easy to overlook, requiring caution in defect management. This study provides an efficient defect management system suitable for the buildings that are built using the top-down construction method.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.157-166
• /
• 2022

In the case of a die-casting process, defects that are difficult to confirm by visual inspection, such as shrinkage bubbles, may occur due to an error in maintaining a vacuum state. Since these casting defects are discovered during post-processing operations such as heat treatment or finishing work, they cannot be taken in advance at the casting time, which can cause a large number of defects. In this study, we propose an approach that can predict the occurrence of casting defects by defect type using machine learning technology based on casting parameter data collected from equipment in the die casting process in real time. Die-casting parameter data can basically be collected through the casting equipment controller. In order to perform classification analysis for predicting defects by defect type, labeling of casting parameters must be performed. In this study, first, the defective data set is separated by performing the primary clustering based on the total defect rate obtained during the post-processing. Second, the secondary cluster analysis is performed using the defect rate by type for the separated defect data set, and the labeling task is performed by defect type using the cluster analysis result. Finally, a classification learning model is created by collecting the entire labeled data set, and a real-time monitoring system for defect prediction using LabView and Python was implemented. When a defect is predicted, notification is performed so that the operator can cope with it, such as displaying on the monitoring screen and alarm notification.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2019.11a
• /
• pp.48-49
• /
• 2019

The number of disputes over defects after completion of construction work in apartment buildings is increasing every year. In this situation, the prediction of reasonable defect repair costs is very important. In this paper, we are going to collect basic data for predicting defect repair costs through the correlation analysis of the construction period and defect repair cost of apartment houses. For this purpose, first of all, the construction period and defect repair cost of apartment houses were analyzed to analyze the construction period for each type of work, the construction period for each project type, and the construction period for each standard calculation. Next, the correlation between defect repair cost and the independent variables of the candidate was conducted. According to the analysis, the ratio of framing air, the ratio of finishing air, and the number of delay days showed strong correlation.

• Journal of Chest Surgery
• /
• v.16 no.4
• /
• pp.511-517
• /
• 1983

For the purpose of clinical analysis of secundum atrial septal defect, the patients with atrial septal defect operated on during the period from Aug. 1959 to Aug. 1983 were analysed. The age of the patients was ranged from 3 months to 60 years and there were 132 males [45.3%] patients and 145 female patients [54.6%] in this series. The most frequent type was oval type defect in 219 [86.9%]. The PAPVC were present in 7 patients of high defect group. Clinical analysis revealed 53 patients [19.9%] were asymptomatic. The QP/QS above than 3.61 were 45 patients and less than 1.5 were 24 patients. The pulmonary artery pressure was 10 to 100 mmHg. The majority of the defects were closed in primary suture and closed with a Dacron patch in 19 patients. The postoperative complications occurred in 35 patients [13.1%] and the most frequent complication was wound problem which was present in 10 patients. The hospital mortality rate was 1.6%.

• Journal of the Korea Institute of Building Construction
• /
• v.15 no.5
• /
• pp.491-500
• /
• 2015

This study investigated defect status by work type, based on the report data of defect inspection results, acquired by consumers' request to safety inspection agencies, before the expiration of legal defect repair warranty period. In fact, the data was not acquired by centering on suppliers, namely, construction companies in relation with the defects becoming causes to increase construction cost of apartments. This study aims to provide objective and basic data for quality improvement at construction stage and for solution to defect disputes. The study results are presented below: (1) The number of defect cases occurring from architectural work among total work types were 1,986, defect occurrence rate was 62.5%, and defect repair cost was KRW $25,851/m^2$, which stood at 78.2% of the total work types. This means the defect occurrence rate and defect repair cost in architectural work are bigger than those of other work types. (2) Major defects in architectural work were revealed in the following order: cracks from frame work, inferior interior finishing work, inferior finishing work of plaster/masonry works, water leak/damage from waterproof work and withering/omission from landscape work. The total repair cost of the major selected defects was KRW $12,220/m^2$, and was analyzed to take up 37% of the total defect repair cost.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.9
• /
• pp.2145-2152
• /
• 2013

Paper manufacturing industries have huge facilities with automatic equipments. Especially, in order to improve the efficiency of the paper manufacturing processes, it is necessary to detect the paper cutting defect effectively and to classify the causes correctly. In this paper, we review the problems of web monitoring system and web inspection system that have been traditionally used in industries for defect detection. Then we propose a novel paper cutting defect detection method based on the local binary pattern analysis and its implementation to mitigate the practical problems in industry environment. The proposed algorithm classifies the defects into edge-type and region-type and then it is shown that the proposed system works stably on the real paper cutting defect detection system.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.7
• /
• pp.1224-1230
• /
• 2007

In this paper, we study the classification of defects at steam generator tube in nuclear power plant using eddy current testing (ECT). We consider 4 defect patterns of SG tube: I-In type, I-Out type, V-In type, and V-Out type. Through numerical analysis program based on finite element modeling, 400 ECT signals are generated by varying width and depth of each defect type. In order to improve the classification performance, we propose new feature extraction technique. After extracting new features from the generated ECT signals, multi-layer perceptron is used to classify the defect patterns. Through the computer simulation study, it is shown that the proposed method achieves 100% classification success rate while the previous method yields 91% success rate.

• Journal of the Korea Institute of Building Construction
• /
• v.13 no.5
• /
• pp.498-505
• /
• 2013

The main processes involved in a defect dispute are consulting, reviewing, and finally judging as an arbiter. This process of defect consulting produces a defect consulting report, but business practices and standards of judgment will differ among consultants, and have many problems. This study reviews the structure of a defect consulting report and considers the structure's problem, which is that it is not standardized. To achieve this, data of sixteen defect consulting report were collected involving defect lawsuit cases before or after 2010. The structure and index of the defect consulting reports were then reviewed, and the results are as follows. As for a structure based on fourteen index, there are suitable that judge a outline, a cost estimate data and a consulting work item by a consulting standard. Furthermore, analysis by each common parts and private parts is considered as appropriate about consulting items and estimate by standard. However, consulting item in construction progress and responsibility period for security that related on a cause and a responsibility of defect need to complement. Meanwhile, the first thing of issues are connected a defect consulting is urgent a standardization for a defect type.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.23 no.3
• /
• pp.91-104
• /
• 2020

This study was conducted to analyze the characteristics of defects according to the type of block and spatial type by quantitatively examining defects occurring in block pavement in apartment complex. According to the research results, depending on the type of block, defects have occurred 1,394.3ea/100㎡ in interlocking paver blocks, 464.8ea/100㎡ in clay brick paver blocks, and 235.1ea/100㎡ in shot blasted paver blocks. By space type, the defects were occurred 1,576.0ea/100㎡ on the access road paved by interlocking paver blocks and the defects were found 1,139.6ea/100㎡ in interlocking paver blocks, 235.1ea/100㎡ in shot blasted paver blocks, and 797.1ea/100㎡ in clay brick paver blocks, on the sidewalk. Also the defects are occurred 455.6ea/100㎡ on the resting space and 403.2ea/100㎡ on the gym space paved by clay brick paver blocks. Through the size analysis of the defects in the block paver, in the case 'peeling', the largest volume of 2,539.0㎣ on the sidewalk paved with shot blasted paver blocks, and 'Subsidence' occurred at the widest area of 2,096.0㎠ on the sidewalk where interlocking paver block was constructed. The difference in defect occurrence according to the type of block is considered to be influenced by the block production process, and the space type is considered to be caused the difference in the occurrence of defects according to the cause of construction and the usage pattern of residents. This study conducted a survey on defects in block and analyzed the defect characteristic according to paver material and space type. Base on this, it is judged that it can be used as an efficient basic data for material replacement, improvement, paver planning and construction in the future.