• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.4
• /
• pp.1648-1653
• /
• 2012

In general, fault of a virtually finished product that is value-added one, since it has gone throughout the most of processes, may give rise to quality cost nearly amount to its selling price and can be a main cause that decreases the efficiency of manufacturing process. This paper proposes a dispatching algorithm for manufacturing process with quality volatilities with consideration of due-dates and required quality level. In order to evaluate the proposed algorithm, this paper examines the performance of the proposed method by comparing it with that of the existing dispatching algorithms in terms of minimizing the mean tardiness. In addition, from the perspective of process capability based on required quality level, this study shows the superiority of the proposed dispatching algorithm.

• Journal of Korean Society for Quality Management
• /
• v.42 no.3
• /
• pp.311-324
• /
• 2014

Purpose: It can deduce improvement plan that recognizes any risk factors in initial production and mass production by using FMEA and through this process, the appropriate criteria for defence items can be established. Methods: It proposes two methodology - Apply DT/OT data achieved from the beginning mass production stage based on FMECA data of the design stage, to risk management, and risk management plan that reflected line and field faliure data in case of is offered. Results: It proposes the risk management plan through Bayesian method and the risk identification that considered MTTF estimated value in case of initial production process. In case of mass production process, both risk identification by using fault occurrence frequency scores and Byaesian method, In case of the Initial production and mass production, it proposes use both two methods. Conclusion: A more realistic risk identification method can be applied, and by this method the quality improvement effect is expected.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.55-67
• /
• 2022

Sensor data can provide fault diagnosis for equipment. However, the cause analysis for fault results of equipment is not often provided. In this study, we propose an explainable convolutional neural network framework for the sensor-based time series classification model. We used sensor-based time series dataset, acquired from vehicles equipped with sensors, and the Wafer dataset, acquired from manufacturing process. Moreover, we used Cycle Signal dataset, acquired from real world mechanical equipment, and for Data augmentation methods, scaling and jittering were used to train our deep learning models. In addition, our proposed classification models are convolutional neural network based models, FCN, 1D-CNN, and ResNet, to compare evaluations for each model. Our experimental results show that the ResNet provides promising results in the context of time series classification with accuracy and F1 Score reaching 95%, improved by 3% compared to the previous study. Furthermore, we propose XAI methods, Class Activation Map and Layer Visualization, to interpret the experiment result. XAI methods can visualize the time series interval that shows important factors for sensor data classification.

• Journal of Digital Convergence
• /
• v.11 no.12
• /
• pp.431-438
• /
• 2013

In this paper we proposed a intelligent recommendation processor that the type of auto parts failures that may occur in the checkout process is represented by association relationship and the relationship was implemented with ontology. For this purpose, we defined 10 kinds of failure types and their associated parts, and we designed to simulate the recommendation process of five views. For components to be checked with the type of fault, it was possible to be expansion recommendation to the intelligent by controlling the weight value according to the relationship on the components.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.6 no.1
• /
• pp.1-12
• /
• 2010

Recently, large amount of information in IDS(Intrusion Detection System) can be un manageable and also be mixed with false prediction error. In this paper, we propose a data mining methodology for IDS, which contains uncertainty based on training process and post-processing analysis additionally. Our system is trained to classify the existing attack for misuse detection, to detect the new attack pattern for anomaly detection, and to define border patter between attack and normal pattern. In experimental results show that our approach improve the performance against existing attacks and new attacks,from 0.62 to 0.84 about 35%.

• Health Policy and Management
• /
• v.2 no.1
• /
• pp.80-114
• /
• 1992

Current compensation schemes for medical malpractice based on negligence is absolutely malfunctioning in Korea. Focussing on the reform of present tort systems for resolving medical malpractice disputes, this paper discusses the alternative models of the Social Relief Schemes for Medical Malpractice (SRSMM). Alternative models of SRSMM should fundamentally be based on either negligence or nofalult compensation principle. On the foundation of the previous relief principle, the SRSMM should be equupped with three major components-the preventio/reduction of the sharp increasing medical malpractice, the effective and efficient resolving process for malpractice disputes and the proper social financing scheme for compensation. The paper deals with pros and cons of the possible alternative models for reform centering on the three major components of the scheme. As conclusions, administrative arbitration machinaries and a compulsory fund for compensating the injured under the negligence principle are proposed to resolve the current problems Korea has faced.

• Korean Management Science Review
• /
• v.34 no.2
• /
• pp.57-66
• /
• 2017

The purpose of this study is to analyze the multidimensional productivity of the shipbuilding performance and to explain the role of different factors, such as man-hour, dock period, number of building block, launching process rate, automatic welding percent, and drawing fault rate which are important production-related variables in most shipbuilding companies. The shipbuilding productivity is obtained using Data Envelopment Analysis (DEA) approach. Then, a Tobit model is considered to measure the influence of different factors on the measured productivity. The results reveal that this productivity measure can substitute a representative shipbuilding productivity index (CGT/man-hour) in shipbuilding industries. Also, this multidimensional productivity analysis using DEA and Tobit reveals complex relationships between production-related variables and CGT and sale.

• Journal of Korean Society for Quality Management
• /
• v.19 no.2
• /
• pp.96-107
• /
• 1991

At the design stage of a plant, the plausible causes and pathways of release of hazardous materials are not clearly known. Thus there exist large amount of uncertainties on the consequences resulting from the operation of a fusion plant. In order to better handle such uncertain circumstances, we utilize the Probabilistic Risk Assessment(PRA) for the safety analyses on fusion power plant. In this paper, we concentrate on the tritium release accident. We develop a simple model that describes the process and flow of tritium, by which we figure out the locations of tritium inventory and their vulnerability. We construct event tree models that lead to various levels of tritium release from abnormal initiating events. Branch parameters on the event tree are assessed from the fault tree analysis. Based on the event tree models we construct influence diagram models which are more useful for the parameter updating and analysis. We briefly discuss the parameter updating scheme, and finally develop the methodology to obtain the predictive distribution of consequences resulting from the operating a fusion power plant. We also discuss the way to utilize the results of testing on sub-systems to reduce the uncertain ties on over all system.

• Journal of the Korea Safety Management & Science
• /
• v.16 no.4
• /
• pp.167-173
• /
• 2014

Hydrogen energy is expanding in range for civil use together with development of pollution-free power sources recently, and it is judged that the use of hydrogen will increase more as a part of carbon dioxide reduction measures according to the Climatic Change Convention. Especially, it is thought that the securement of safety of the used dispenser will be the biggest obstacle in the use of high-pressure hydrogen because the hydrogen station is operated in a high pressure. This study found risks in the process and problems on operation by making use of HAZOP(6 kinds), a qualitative safety evaluation technique, and FMEA(5 kinds), a fault mode effect analysis, for the hydrogen charging system at a hydrogen gas station, derived 6 risk factors from HAZOP and 5 risk factors from FMEA, and prepared measures for it.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.7 no.4
• /
• pp.7-14
• /
• 2011

Infinite failure NHPP models presented in the literature exhibit either constant, monotonic increasing or monotonic decreasing failure occurrence rate per fault (hazard function). This infinite non-homogeneous Poisson process is model which reflects the possibility of introducing new faults when correcting or modifying the software. In this paper, polynomial hazard function have been proposed, which can efficiency application for software reliability. Algorithm for estimating the parameters used to maximum likelihood estimator and bisection method. Model selection based on mean square error and the coefficient of determination for the sake of efficient model were employed. In numerical example, log power time model of the existing model in this area and the polynomial hazard function model were compared using failure interval time. Because polynomial hazard function model is more efficient in terms of reliability, polynomial hazard function model as an alternative to the existing model also were able to confirm that can use in this area.