• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2022년도 가을 학술논문 발표대회
• /
• pp.223-224
• /
• 2022

The occurrence of defect, one of the major risk elements, gives rise to construction delays and additional costs. Although construction companies generally prefer to use a method of identifying and classifying the causes of defects, a system for predicting the rise of defects becomes important matter to reduce this harmful issue. However, the currently used methods are kinds of reactive systems that are focused on the defects which occurred already, and there are few studies on the occurrence of defects with prediction systems. This paper is about preliminary study on the development of judgemental algorithm that informs us whether additional works related to defect issue are needed or not. Among machine learning techniques, deep neural network was utilized as prediction model which is a major component of algorithm. It is the most suitable model to be applied to the algorithm when there are 8 hidden layers and the average number of nodes in each hidden layer is 70. Ultimately, the algorithm can identify and defects that may arise in later and contribute to minimize defect frequency.

• 소성∙가공
• /
• 제14권6호
• /
• pp.533-540
• /
• 2005

The hemming process, composed of flanging, pre-hemming and main hemming, is the last one of a series of forming processes conducted on the automotive panels, having greater influence on the outward appearance of cars rather than on their performance. The hem quality can be quantitatively defined by the hemming defects including turn-down/up, warp and roll-in/out. However, it is difficult to evaluate and predict the hem quality through an experimental measurement or a numerical calculation since the size of defects is very small. This study aims to precisely evaluate the hemming defects, especially turn-down and roll-in, through numerical and experimental approaches and to investigate the influence of process parameters on the hem quality, focused on how to simulate the same conditions as in the experiment by the finite element analysis (FEA). The FEA results on the turn-down and roll-in obtained from a model composed of the optimum-sized elements, including a spring element linked to the flanging pad, and given the double master contact condition between the inner and outer panels, had a good correlation with the experimental data. It is thought possible to make an early estimate of the hem quality in a practical automotive design by applying the methodology proposed in this study.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.11-16
• /
• 2022

Applying predictive analytics to predict software defects has improved the overall quality and decreased maintenance costs. Many supervised and unsupervised learning algorithms have been used for defect prediction on publicly available datasets. Most of these datasets suffer from an imbalance in the output classes. We study the impact of class imbalance in the defect datasets on the efficiency of the defect prediction model and propose a CPP method for handling imbalances in the dataset. The performance of the methods is evaluated using measures like Matthew's Correlation Coefficient (MCC), Recall, and Accuracy measures. The proposed sampling technique shows significant improvement in the efficiency of the classifier in predicting defects.

• Journal of Information Processing Systems
• /
• 제14권3호
• /
• pp.751-770
• /
• 2018

Web applications are indispensable in the software industry and continuously evolve either meeting a newer criteria and/or including new functionalities. However, despite assuring quality via testing, what hinders a straightforward development is the presence of defects. Several factors contribute to defects and are often minimized at high expense in terms of man-hours. Thus, detection of fault proneness in early phases of software development is important. Therefore, a fault prediction model for identifying fault-prone classes in a web application is highly desired. In this work, we compare 14 machine learning techniques to analyse the relationship between object oriented metrics and fault prediction in web applications. The study is carried out using various releases of Apache Click and Apache Rave datasets. En-route to the predictive analysis, the input basis set for each release is first optimized using filter based correlation feature selection (CFS) method. It is found that the LCOM3, WMC, NPM and DAM metrics are the most significant predictors. The statistical analysis of these metrics also finds good conformity with the CFS evaluation and affirms the role of these metrics in the defect prediction of web applications. The overall predictive ability of different fault prediction models is first ranked using Friedman technique and then statistically compared using Nemenyi post-hoc analysis. The results not only upholds the predictive capability of machine learning models for faulty classes using web applications, but also finds that ensemble algorithms are most appropriate for defect prediction in Apache datasets. Further, we also derive a consensus between the metrics selected by the CFS technique and the statistical analysis of the datasets.

• 품질경영학회지
• /
• 제52권2호
• /
• pp.185-199
• /
• 2024

Purpose: The improvement of yield and quality in product manufacturing is crucial from the perspective of process management. Controlling key variables within the process is essential for enhancing the quality of the produced items. In this study, we aim to identify key variables influencing product defects and facilitate quality enhancement in CNC machining process using SHAP(SHapley Additive exPlanations) Methods: Firstly, we conduct model training using boosting algorithm-based models such as AdaBoost, GBM, XGBoost, LightGBM, and CatBoost. The CNC machining process data is divided into training data and test data at a ratio 9:1 for model training and test experiments. Subsequently, we select a model with excellent Accuracy and F1-score performance and apply SHAP to extract variables influencing defects in the CNC machining process. Results: By comparing the performances of different models, the selected CatBoost model demonstrated an Accuracy of 97% and an F1-score of 95%. Using Shapley Value, we extract key variables that positively of negatively impact the dependent variable(good/defective product). We identify variables with relatively low importance, suggesting variables that should be prioritized for management. Conclusion: The extraction of key variables using SHAP provides explanatory power distinct from traditional machine learning techniques. This study holds significance in identifying key variables that should be prioritized for management in CNC machining process. It is expected to contribute to enhancing the production quality of the CNC machining process.

• 소성∙가공
• /
• 제20권1호
• /
• pp.48-53
• /
• 2011

Fasteners are used to join the various electronic products and machines. So, the quality and reliability of the fastener are strongly requested. In this study, the analyses of the multi-stage cold forging of TORX screws for storage parts are carried out. In manufacturing of TORX screws, crack and folding defects are observed. Therefore, the analysis is focused on the prediction of the defects. Based on the analysis results, the upper die and process conditions are redesigned to reduce the defects. The upper die shape for preform forming is redesigned to prevent folding and sharp shape change. The Cockroft-Latham damage criterion is introduced to predict the crack initiation. Analysis results shows that the maximum Cockroft-Latham damage value is decreased by 40% in the forming using the modified upper die.

• Design & Manufacturing
• /
• 제13권3호
• /
• pp.29-34
• /
• 2019

Cell phone injection is characterized by its small size and thinness. In addition, the product has a short cycle time, requiring a very short production schedule. To produce more accurate products faster, data from experience in producing similar products is required. In this study, two mobile phone models are presented. In this study, the quality problems caused by molding analysis and actual injection molding were analyzed and made into a database. As a result, it was considered that all the defects in the molding analysis do not affect the product in some cases, rather than appear as defects in the actual product. All defects shown in the molding analysis can be made into a database, and based on this data, it will be possible to obtain an effect that can predict more accurately whether it will cause problems after injection.

• 한국신뢰성학회지:신뢰성응용연구
• /
• 제16권2호
• /
• pp.98-103
• /
• 2016

Purpose: The purpose of this paper is to get a meaningful information for improving manufacturing quality of the products before they are produced in client's manufacturing process. Methods: A variety of data mining techniques have been being used for wide range of industries from process data in manufacturing factories for quality improvement. One application of those is to get meaningful information from process data in manufacturing factories for quality improvement. In this paper, the failure rate at client's manufacturing process is predicted by using the parameters of the characteristics of the product based on PCA (Principle Component Analysis) and regression analysis. Results: Through a case study, we proposed the predicting methodology and regression model. The proposed model is verified through comparing the failure rates of actual data and the estimated value. Conclusion: This study can provide the guidance for predicting the failure rate on the manufacturing process. And the manufacturers can prevent the defects by confirming the factor which affects the failure rate.

• 한국주조공학회지
• /
• 제42권1호
• /
• pp.61-66
• /
• 2022

Hydraulic units are important components of agricultural and construction machinery, and thus require high-quality castings. However, gas defects occurring inside the sand cores of the castings due to the resin used is a problem. This study therefore aimed to develop a casting simulation method that can clarify the gas defect positions. Gas defects are thought to be caused by gas generated after the molten metal fills up the mold cavity. The gas constant is the most effective factor for simulating this gas generated from sand cores. It is calculated by gas generating temperature and analysis of composition in the inert gas atmosphere modified according to the mold filling conditions of molten metal. It is assumed that gases generated from the inside of castings remain if the following formula is established. [Time of occurrence of gas generation] + [Time of occurrence of gas floating] > [Time of occurrence of casting surface solidification] The possibility of gas defects is evaluated by the time of occurrence of gas generation and gas floating calculated using the gas constant. The residual position of generated gases is decided by the closed loops indicating the final solidification location in the casting simulation. The above procedure enables us to suggest suitable casting designs with zero gas defects, without the need to repeat casting tests.

• International journal of advanced smart convergence
• /
• 제12권2호
• /
• pp.47-55
• /
• 2023

The automotive industry is undergoing a paradigm shift due to the convergence of IT and rapid digital transformation. Various components, including embedded structures and systems with complex architectures that incorporate IC semiconductors, are being integrated and modularized. As a result, there has been a significant increase in vehicle defects, raising expectations for the quality of automotive parts. As more and more data is being accumulated, there is an active effort to go beyond traditional reliability analysis methods and apply machine learning models based on the accumulated big data. However, there are still not many cases where machine learning is used in product development to identify factors of defects in performance and durability of products and incorporate feedback into the design to improve product quality. In this paper, we applied a prediction algorithm to the defects of automotive door devices equipped with automatic responsive sensors, which are commonly installed in recent electric and hydrogen vehicles. To do so, we selected test items, built a measurement emulation system for data acquisition, and conducted comparative evaluations by applying different machine learning algorithms to the measured data. The results in terms of R² score were as follows: Ordinary multiple regression 0.96, Ridge regression 0.95, Lasso regression 0.89, Elastic regression 0.91.