• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.6
• /
• pp.465-469
• /
• 2001

In injection molding short shot is one of the frequent and fatal defects. Experts of Injection molding usually adjust process conditions such as injection time, mold temperature, and melt temperature because it is most economic way in time and cost. However, it is difficult task to find appropriate process conditions for troubleshooting of short shot as injection molding process is a highly nonlinear system and process conditions are coupled. In this paper, a modular fuzzy neural network (MFNN) has been applied to injection molding process to shorten troubleshooting time of short shot. Based on melt temperature and fill time, a reasonable initial mo이 temperature is recommenced by the NFNN, and then the mold temperature is inputted to injection molding process. Depending on injection molding result, specifically the insufficient quantity of an injection molded part. and appropriate mold temperature is recommend repeatedly through the NFNN.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.2
• /
• pp.37-45
• /
• 2016

Control chart is representative tools of statistical process control (SPC). It is a graph that plotting the characteristic values from the process. It has two steps (or Phase). First step is a procedure for finding a process parameters. It is called Phase I. This step is to find the process parameters by using data obtained from in-controlled process. It is a step that the standard value was not determined. Another step is monitoring process by already known process parameters from Phase I. It is called Phase II. These control chart is the process quality characteristic value for management, which is plotted dot whether the existence within the control limit or not. But, this is not given information about the economic loss that occurs when a product characteristic value does not match the target value. In order to meet the customer needs, company not only consider stability of the process variation but also produce the product that is meet the target value. Taguchi's quadratic loss function is include information about economic loss that occurred by the mismatch the target value. However, Taguchi's quadratic loss function is very simple quadratic curve. It is difficult to realistically reflect the increased amount of loss that due to a deviation from the target value. Also, it can be well explained by only on condition that the normal process. Spiring proposed an alternative loss function that called reflected normal loss function (RNLF). In this paper, we design a new control chart for overcome these disadvantage by using the Spiring's RNLF. And we demonstrate effectiveness of new control chart by comparing its average run length (ARL) with ${\bar{x}}-R$ control chart and expected loss control chart (ELCC).

• Journal of Information Technology and Architecture
• /
• v.10 no.3
• /
• pp.295-303
• /
• 2013

This paper presents a new approach to managing dynamic business process changes based on business process change patterns. We identify and categorize business process change patterns that occur recurrently in a dynamic business environment. Several issues regarding management of process versions are discussed, and a pattern-based version management method for handling process changes more flexibly is explained in detail. We propose a mechanism for abstract process execution with runtime encapsulation of a business process, which can maximize the flexibility of process execution using multiple process versions. In addition, we propose a concept of process promotion and demotion that can dynamically choose an actual version of the process at run-time. With our pattern-based process change management and versioning approach, it is expected that the flexibility and efficiency of BPM systems can be enhanced significantly.

• Journal of Environmental Science International
• /
• v.28 no.3
• /
• pp.291-301
• /
• 2019

This study was conducted to investigate the effect of salt concentration and turbidity on the inactivation of Artemia sp. by electrolysis, UV photolysis, electrolysis+UV process to treat ballast water in the presence of brackish water or muddy water caused by rainfall. The inactivation at different salt concentrations (30 g/L and 3 g/L) and turbidity levels (0, 156, 779 NTU) was compared. A decrease in salt concentration reduced RNO (OH radical generation index) degradation and TRO (Total Residual Oxidant) production, indicating that a longer electrolysis time is required to achieve a 100% inactivation rate in electrolysis process. In the UV process, the higher turbidity results in lower UV transmittance and lower inactivation efficiency of Artemia sp. Higher the turbidity resulted in lower ultraviolet transmittance in the UV process and lower inactivation efficiency of Artemia sp. A UV exposure time of over 30 seconds was required for 100% inactivation. Factors affecting inactivation efficiency of Artemia sp. in low salt concentration are in the order: electrolysis+UV > electrolysis > UV process. In the case of electrolysis+UV process, TRO is lower than the electrolysis process, but RNO is more decomposed, indicating that the OH radical has a greater effect on the inactivation effect. In low salt concentrations and high turbidity conditions, factors affecting Artemia sp. inactivation were in the order electrolysis > electrolysis+UV > UV process. When the salt concentration is low and the turbidity is high, the electrolysis process is affected by the salt concentration and the UV process is affected by turbidity. Therefore, the synergy due to the combination of the electrolysis process and the UV process was small, and the inactivation was lower than that of the single electrolysis process only affected by the salt concentration.

• Journal of Korean Society for Quality Management
• /
• v.50 no.3
• /
• pp.473-490
• /
• 2022

Purpose: The purpose of this study is to propose a new useful suggestion to monitor the stability of process by developing a stability ratio or index related to investigating how well the process is controlled or operated to the specified target. Methods: The proposed method to monitor the stability of process is building up a new measure index which is making up for the weakness of the existing index in terms of short or long term period of production. This new index is a combined one considering both stability and capability of process to the specification limits. We suppose that both process mean and process variation(or deviation) are changing on time period. Results: The results of this study are as follows: regarding the stability of process as well as capability of process, it was shown that two indices, called SI(stability index) and PI(performance index), can be expressed in two-dimensional X-Y graph simultaneously. This graph is categorized as 4 separated partitions, which are characterized by its numerical value intervals of SI and PI which are evaluated by test statistics. Conclusion: The new revised index is more robust than the existing one in investigating the stability of process in terms of short and long period of production, even in case both process mean and variation are changing.

• Transactions of Materials Processing
• /
• v.18 no.7
• /
• pp.556-564
• /
• 2009

Flexible forming process for sheet material using reconfigurable die is introduced based on numerical simulation. In general, this flexible forming process using the reconfigurable die has been utilized for manufacturing of curved thick plates used for hull structures, architectural structures and so on. In this study, numerical simulation of sheet metal forming process is carried out by using flexible dies model instead of conventional matched die set. The numerical simulation and experimental verification for sheet metal forming process using a flexible forming machine that is more suitable for thick plate forming process are carried out to confirm the appropriateness of the simulation process. As an elastic cushion, urethane pads are utilized using hyperelastic material model in the simulation for smoothing the forming surface which is discrete due to characteristics of the flexile die. In the flexible forming process for sheet metal, effect of a blank holder is also investigated according to blank holding methods. Formability in view of occurrence of dimples is compared with regard to the various punch sizes. Consequently, it is confirmed that the flexible forming for sheet material using urethane pad has enough capability and feasibility for manufacturing of smoothly curved surface instead of conventional die forming method.

• Journal of Korean Society for Quality Management
• /
• v.51 no.1
• /
• pp.55-65
• /
• 2023

Purpose: The purpose of this study is to propose an optimization process to improve product yield in the process using process data. Recently, research for low-cost and high-efficiency production in the manufacturing process using machine learning or deep learning has continued. Therefore, this study derives major variables that affect product defects in the manufacturing process using eXplainable Artificial Intelligence(XAI) method. After that, the optimal range of the variables is presented to propose a methodology for improving product yield. Methods: This study is conducted using the injection molding machine AI dataset released on the Korea AI Manufacturing Platform(KAMP) organized by KAIST. Using the XAI-based SHAP method, major variables affecting product defects are extracted from each process data. XGBoost and LightGBM were used as learning algorithms, 5-6 variables are extracted as the main process variables for the injection process. Subsequently, the optimal control range of each process variable is presented using the ICE method. Finally, the product yield improvement methodology of this study is proposed through a validation process using Test Data. Results: The results of this study are as follows. In the injection process data, it was confirmed that XGBoost had an improvement defect rate of 0.21% and LightGBM had an improvement defect rate of 0.29%, which were improved by 0.79%p and 0.71%p, respectively, compared to the existing defect rate of 1.00%. Conclusion: This study is a case study. A research methodology was proposed in the injection process, and it was confirmed that the product yield was improved through verification.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.1
• /
• pp.91-97
• /
• 2016

This study is concerned about the process capability index in single process. Previous process capability indices have been developed for the consistency with the nonconforming rate due to the process target value and skewness. These indices calculate the process capability by measuring one spot in an item. But the only one datum in an item reduces the representativeness of the item. In addition to the lack of representativeness, there are many cases that the uniformity of the item such as flatness of panel is absolutely important. In these cases, we have to measure several spots in an item. Also the nonconforming judgment to an item is mainly due to the range not due to the standard variation or the shift from the specifications. To imply the uniformity concept to the process capability index, we should consider only the variation in an item. It is the within subgroup variation. When the universe is composed of several subgroups, the sample standard deviation is the sum of the within subgroup variation and the between subgroup variation. So the range R which represents only the within subgroup variation is the much better measure than that of the sample standard deviation. In general, a subgroup contains a couple of individual items. But in our cases, a subgroup is an item and R is the difference between the maximum and the minimum among the measured data in an item. Even though our object is a single process index, causing by the subgroups, its analytic structure looks like a system process capability index. In this paper we propose a new process capability index considering the representativeness and uniformity.

• IE interfaces
• /
• v.21 no.4
• /
• pp.365-377
• /
• 2008

In this paper, for constructing the Korean Hazard Information System (KHIS), we conceptually design a hazard evaluation process. We first deal with a hazard evaluation process focused on flood hazard to give the most immense damage and loss. The hazard evaluation process is consist of a damage evaluation process and a loss evaluation process, and is used for transforming hazards from natural disasters into economic measures. The proposed process is developed based on the famous FEMA (Federal Emergency Management Agency)'s $HAZAS^{@MH}$methodology. We modify the FEMA's process to be mutually exclusive and collectively exhaustive, that is all losses from the hazards are included into the estimation process but the losses are not duplicated in the process. In addition to this, we define the loss process specifically by considering the characteristics from the hazard environments of Korea. We can expect that KHIS for evaluating economic losses from natural hazards can be developed based on the conceptual design for the economic loss evaluation process, and KHIS can be used as a useful tool for analyzing the feasibilities of mitigation plans in central/local governments.

• Industrial Engineering and Management Systems
• /
• v.12 no.2
• /
• pp.112-117
• /
• 2013

The $\overline{x}$ control chart for the process mean and either the R or s control chart for the process dispersion have been used together to monitor the manufacturing processes. However, it has been pointed out that this procedure is flawed by a fault that makes it difficult to capture the behavior of process condition visually by considering the relationship between the shift in the process mean and the change in the process dispersion because the respective characteristics are monitored by an individual control chart in parallel. Then, the ($\overline{x}$, s) control chart has been proposed to enable the process managers to monitor the changes in the process mean, process dispersion, or both. On the one hand, identifying which process parameters are responsible for out-of-control condition of process is one of the important issues in the process management. It is especially important in the ($\overline{x}$, s) control chart where some parameters are monitored at a single plane. The previous literature has proposed the multiple decision method based on the statistical hypothesis tests to identify the parameters responsible for out-of-control condition. In this paper, we propose how to identify parameters responsible for out-of-control condition using the information criterion. Then, the effectiveness of proposed method is shown through some numerical experiments.