• Journal of the Korean Data and Information Science Society
• /
• v.18 no.3
• /
• pp.773-782
• /
• 2007

The statistical process control charts are very extensively used for monitoring of process mean, deviation, defect rate or reject rate. In this paper we consider a control chart to monitor the process reject rate in the high yield process, which is based on the observed cumulative probability of the number of items inspected until r defective items are observed. We first propose selection of the optimal value of r in the CPC-r charts, and also consider the usefulness of the chart in high yield process such as semiconductor or TFT-LCD manufacturing process.

• The Journal of Information Systems
• /
• v.26 no.2
• /
• pp.105-121
• /
• 2017

Purpose It is a major goal to improve the product yields during production operations in the manufacturing industry. Therefore, factory is trying to keep the good quality materials and proper production resources, also find the proper condition of facilities and manufacturing environment for yields improvement. Design/methodology/approach We propose the hybrid framework to analyze to dataset extracted from MES. Those data is about the alarm information generated from equipment, both measurement and equipment process value from production and cycle/pitch time measured from production data these covered products during production. We adapt a data warehousing techniques for organizing dataset, a logistic regression for finding out the significant factors, and a association analysis for drawing the rules which affect the product yields. And then we validate the framework by applying the real data generated from the discrete process in secondary cell battery manufacturing. Findings This paper deals with challenges to apply the full potential of modeling and simulation within CPPS(Cyber-Physical Production System) and Smart Factory implementation. The framework is being applied in one of the most advanced and complex industrial sectors like semiconductor, display, and automotive industry.

• 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 Biosystems Engineering
• /
• v.28 no.4
• /
• pp.325-334
• /
• 2003

Pinosylvin, a stilbenoid phytoalexin, is a health ingredient to be extracted from pine leaves. In this study, ultrasonication-assisted extraction process for manufacturing extracts with high content of pinosylvin from pine leaves was investigated. As process and system variables, ultrasonic power, sonication time and solvent ratio were selected. According to the experimental results, the effective yield of pinosylvin increased with the increase of ultrasonic power and sonication time and the decrease of solvent ratio. When the ultrasonic power of 2400 W/L was added to the solution of pulverized pine leaves of 8 g per 1 L of a solvent for 10 minutes, yield of extracts and purity, effective yield and concentration ratio of pinosylvin were 0.3166 g/g, 0.7247 mg/g, 0.2294 mg/g and 23.0, respectively.

• Journal of Korean Institute of Industrial Engineers
• /
• v.20 no.3
• /
• pp.93-104
• /
• 1994

One of the typical assumptions of the studies to determine economic production quantity is that yield rate of a given manufacturing process is 100% or constant after setup. However, in the real world, there are many manufacturing processes of which yield rates are quite low just after setup and then increasing with time until they reach the target rates which are set strategically. This period is usually called "stabilization period". During the stabilization period, defectives are produced, which incur cost (defective cost). In this study, an optimal production quantity for this situation is presented. Also, it is shown that defective cost acts like setup cost and therefore, increases the economic production quantity.

• Journal of Institute of Convergence Technology
• /
• v.3 no.1
• /
• pp.41-44
• /
• 2013

Process and manufacturing data are numerously accumulated to the enterprise database in industries but little of those data are utilized. Data mining can support a decision to manager in process from the data. However, it is not easy to field managers because a proper adoption of various schemes is very difficult. In this paper, six scenarios are conducted using data mining schemes for the various situations of field claims such as yield problem, trend analysis and prediction of yield according to changes of operating conditions, etc. Scenarios, like templates, of various analysis situations are helpful to users.

• Journal of Electrical Engineering and information Science
• /
• v.2 no.3
• /
• pp.14-21
• /
• 1997

In delay-optimized designs, timing failures due to manufacturing delay defects are more likely to occur because the average timing slacks of paths decrease and the system becomes more sensitive to smaller delay defect sizes. In this paper, the impact of delay optimized logic circuits on delay fault testing will be discussed and compared to the case for non-optimized designs. First, we provide a timing optimization procedure and show that the resultant density function of path delays is a delta function. Next we also discuss the impact of timing optimization on the yield of a manufacturing process and the defect level for delay faults. Finally, we will give some recommendations on the determination of the system clock time so that the delay-optimized design will have the same manufacturing yield as the non-optimized design and on the determination of delay fault coverage in the delay-optimized design in order to have the same defect-level for delay faults as the non-optimized design, while the system clock time is the same for both designs.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.13 no.6
• /
• pp.82-87
• /
• 2014

Small MR dampers with a simple structure were designed and manufactured. The Bingham model was used to represent the dynamic characteristics of the damper, and the parameters of the model were estimated from experimental data which were obtained by harmonic tests. The value of the estimated yield shear force remains positive when no electric current is applied, and it increases slowly with the current. The estimated viscous damping coefficient has a value close to zero when no electric current is applied, and it increases almost linearly with the current.

• Journal of the Korea Society for Simulation
• /
• v.14 no.1
• /
• pp.1-8
• /
• 2005

In the semiconductor manufacturing, yield enhancement is an urgent issue. It is ideal to prevent all the failures. However, when a failure occurs, it is important to quickly specify the cause stage and take countermeasure. Reviewing wafer level and composite lot level yield patterns has always been an effective way of identifying yield inhibitors and driving process improvement. This process is very time consuming and as such generally occurs only when the overall yield of a device has dropped significantly enough to warrant investigation. The automatic method of failure pattern extraction from fail bit map provides reduced time to analysis and facilitates yield enhancement. The automatic method of failure pattern extraction from fail bit map provides reduced time to analysis and facilitates yield enhancement. This paper describes the techniques to automatically classifies a failure pattern using a fail bit map.

• Journal of Korean Institute of Industrial Engineers
• /
• v.36 no.3
• /
• pp.154-163
• /
• 2010

Process monitoring of output variables affecting final performance have been mainly executed in semiconductor manufacturing process. However, even earlier detection of causes of output variation cannot completely prevent yield loss because a number of wafers after detecting them must be re-processed or cast away. Semiconductor manufacturers have put more attention toward monitoring process inputs to prevent yield loss by early detecting change-point of the process. In the paper, we propose the method to efficiently monitor functional input variables in multi-phase semiconductor manufacturing process. Measured input variables in the multi-phase process tend to be of functional structured form. After data pre-processing for these functional input data, change-point analysis is practiced to the pre-processed data set. If process variation occurs, key variables affecting process variation are selected using contribution plot for monitoring efficiency. To evaluate the propriety of proposed monitoring method, we used real data set in semiconductor manufacturing process. The experiment shows that the proposed method has better performance than previous output monitoring method in terms of fault detection and process monitoring.