• 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.

• IE interfaces
• /
• v.25 no.4
• /
• pp.393-404
• /
• 2012

Increasing safety requirements of automobile are asking companies to find out solutions, based on the ISO 26262 which is a functional safety standard. ISO 26262 is an adaptation of the IEC 61508 for automotive electric/electronic systems. ISO 26262 provides a V model for ECU (Electronic Control Unit) development process to secure safety against vehicle. It well describes the requirements, necessary works and their resulting products for each development phase. However, it is difficult to apply to product development for achieving functional safety in the electric/electronic systems of an automobile because it lacks explanation on the working steps to follow and the methodologies and tools to be used in each step. In this paper, we introduce the outline of the ISO 26262 product development process and present a DFSS (Design For Six Sigma) road-map based on the ISO 26262 product development process as a way to operate efficiently the ISO 26262 product development process. The DFSS road-map consists of five phases: Define, Measure, Analyze, Design, and Verify. The detailed activities, tools, inputs, and work products are given for each phase.

• Proceedings of the Korean Society for Quality Management Conference
• /
• 2006.04a
• /
• pp.355-358
• /
• 2006

The emotional quality of the product have become an important factor in purchasing decision. Classical approach of product design has focused on providing proper functions of the product. However, as the life-cycle of products become shorter and the customer's needs get more diversified, it is now necessary to accommodate the customer's emotional requirement in product design. This study aims to analyze and interpret the emotional characteristics based customer preference survey. This study consisted of two part. First part was to search the optimal combination of design variables through DOE of predetermined 5 design variables. In the second part, we developed customer preference index model to measure the customer preferences about 16 different wood flooring product.

• IE interfaces
• /
• v.15 no.2
• /
• pp.126-132
• /
• 2002

The objective of this study is to provide guidelines for expert witness in product liability lawsuits. The expert testimony is one of the powerful methods to mitigate the burden of the proof in product liability litigations. However, it has been seldomly accepted as a reliable evidence by trial judges because the expert's testimony has sometimes turned out to be illogical and unreliable. In order for the expert testimony to be admittable in the court, the expert should have a thorough understanding of his/her role as an expert witness and follow scientific methodology whose soundness has been generally accepted by both industries and academy.

• IE interfaces
• /
• v.16 no.4
• /
• pp.496-506
• /
• 2003

This study examines the background and necessity of the product certification (KS) and the system authentication (ISO 9000), and their characteristic so as to compare and analyze the possibility of interaction of product certification and system authentication. It tries to suggest an efficient operation system as an integrated management system and analyzes the certification case of K, a manufacturer of kitchen utensils. We believe that the study will help companies minimize their expenses and efforts to establish, operate, and maintain the corporate standard system. In addition, to effectively achieve our goal, we have also made a study of both literature and case and suggested technical guidance to get integrated management system certification. By these methods, we analyzed the effects and problems that come with the introduction and application of the integrated system of product certification and system authentication in order to set up a system to fit to the mechanism of Korean companies. Moreover, we have suggested the model of integrated operation and the benefits that come after acquiring certification.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.04a
• /
• pp.411-415
• /
• 1996

User's sensibility has an important effect upon appreciating household electronic appliances and user's feeling of satisfaction with products has a good effect on the choice of product on purchasing those items. In this point of view, the human-oriented approach of product development system can be adopted as Human Sensibility Engineering. The target of changed development system is to define user's sensibility factors and to apply them to design and development. In this study, the human sensibility ergonomics approach and usability test have been applied to the development and evaluation of an electronic product model.

• Journal of Industrial Technology
• /
• v.3
• /
• pp.39-46
• /
• 1983

This paper presents a quantitative measure of the degree of part commonality and redundancy in a product line based on entropy measure of information theory. The several possible methods of analysis are discussed and the use of the entropy measure is discussed. These commonality and redundancy measure can be applied to analyze the usage pattern of part across a product line and to determine which parts have the broadest usage across the firm's product lines. An analysis of the results by entropy statistics is compared with the practical part usage in a simulation of several types of part usage's distributions.

• Journal of Korean Institute of Industrial Engineers
• /
• v.34 no.4
• /
• pp.398-407
• /
• 2008

We consider a product recovery system that a single product is stocked in order to meet a demand from customers who may return products after usage. This paper addresses a problem of when to release a procurement process to replenish serviceable inventory and how many new products to procure. The structure of the optimal procurement policy is examined and numerically identified as a monotonic threshold curve. A numerical procedure is presented to jointly find the optimal procurement order size, optimal procurement policy, and optimal discounted profit. Sensitivity analysis also indicates that these optimal performance measurements have monotonic properties with respect to system parameters.

• IE interfaces
• /
• v.21 no.2
• /
• pp.177-188
• /
• 2008

Recently, due to emerging technologies such as radio frequency identification(RFID), global positioning system(GPS), and wireless mobile communication technologies, it is possible to build up the infrastructure for tracking and tracing product logistics data at any place and at any time. However, for implementing the infrastructure, it is necessary to develop a suitable management method for product logistics data. To this end, this study deals with a resource description framework(RDF) based modeling and application method for product logistics data in the ubiquitous environment. It will give us the capability to control product logistics data, which leads to streamline logistics operations.

• Industrial Engineering and Management Systems
• /
• v.14 no.2
• /
• pp.159-174
• /
• 2015

Remanufacturing used, end-of-life products is a complex problem involving multiple types of products that may share common parts. Recovery targets assigned by market demand and environmental legislation add more difficulty to the problem. Manufacturers now need to achieve specified take-back and recovery rates while fulfilling demands for remanufactured products. To assists in the demand- and legislation-driven remanufacturing of a family of products (i.e., multiple products that share common parts), this paper introduces a bi-objective mixed integer linear programming (MILP) model for optimizing remanufacturing. The model identifies optimal remanufacturing plans for a product family, whereby, the remanufacturer can achieve demand and recovery targets more profitably and in an environmentally-friendly manner. The model can also be used to quantify and justify the economic and environmental benefits of a product family from a remanufacturing perspective. A case study is presented for remanufacturing an alternatorfamily of products.