• Design & Manufacturing
• /
• 제15권3호
• /
• pp.1-6
• /
• 2021

An artificial neural network model based on a deep learning algorithm is known to be more accurate than humans in image classification, but there is still a limit in the sense that there needs to be a lot of training data that can be called big data. Therefore, various techniques are being studied to build an artificial neural network model with high precision, even with small data. The transfer learning technique is assessed as an excellent alternative. As a result, the purpose of this study is to develop an artificial neural network system that can classify burr images of light guide plate products with 99% accuracy using transfer learning technique. Specifically, for the light guide plate product, 150 images of the normal product and the burr were taken at various angles, heights, positions, etc., respectively. Then, after the preprocessing of images such as thresholding and image augmentation, for a total of 3,300 images were generated. 2,970 images were separated for training, while the remaining 330 images were separated for model accuracy testing. For the transfer learning, a base model was developed using the NASNet-Large model that pre-trained 14 million ImageNet data. According to the final model accuracy test, the 99% accuracy in the image classification for training and test images was confirmed. Consequently, based on the results of this study, it is expected to help develop an integrated AI production management system by training not only the burr but also various defective images.

• 한국산업정보학회논문지
• /
• 제23권5호
• /
• pp.119-134
• /
• 2018

오늘날 기업은 기술의 급속한 발전, 고객의 다양한 요구로 인해 높은 불확실성과 경쟁 상황에 놓여 있다. 이러한 기업 환경 속에서 지속적인 경쟁우위와 미래 성장 동력을 확보하는 방안 중 가장 중요한 것이 NPD (신제품 개발)와 관련된 문제로, 이는 기업과 학계에 매우 중요한 이슈이다. 이에 본 연구는 NPD 분야의 기존 연구 흐름과 앞으로의 동향을 파악하여 NPD와 관련된 실무자와 연구자들에게 새로운 가치를 제공하고자 한다. 이를 위해 본 연구는 Scopus 데이터베이스를 활용하여 해외 저명한 저널에 게재된 논문의 키워드를 수집하여 키워드 네트워크 분석을 실시하였다. 이를 통해 NPD 분야의 기존 연구 흐름을 파악할 수 있었고, 각 키워드 간의 연결 관계와 시간의 흐름에 따른 변화를 바탕으로 구체적인 연구주제들의 변화 과정을 제시하였다. 또한, NPD 분야에서 선호되는 키워드를 바탕으로 앞으로의 연구 동향을 제시하였다. 본 연구를 통해 NPD 키워드 네트워크는 멱함수 법칙의 분포를 따르고 있는 좁은 세상 네트워크이고, 키워드의 선호에 의해서 링크가 형성되어 네트워크의 성장이 이루어졌음을 확인할 수 있었다. 또한, 컴포넌트 분석 및 중심성분석을 통해 NPD 키워드 네트워크에서는 주로 Innovation(혁신), New Product Innovation(신제품 혁신), Risk Management(리스크 관리), Concurrent engineering(동시공학), Research and Development(연구개발), Product Life Cycle Management(제품 수명주기 관리) 등과 같은 키워드들이 중심성이 높음을 확인하였다. 한편, 시간의 흐름에 따른 키워드의 선호적 연결의 변화를 살펴본 결과, Innovation(혁신), New Product Introduction(신제품 출시), Project Management(프로젝트 관리) 등의 주제를 중심으로 i) 공급업체와 NPD 협업, ii) 시장의 불확실성을 고려한 NPD, iii) 기술 경영 및 지식경영 분야와 통섭을 고려한 NPD, iv) 중소기업 관점의 NPD 등과 같은 주제의 연구가 요구됨을 확인하였다. 본 연구의 분석 결과는 NPD의 연구 동향, 다른 분야와의 학제간 연구를 위한 새로운 연구주제를 결정하는데 유용하게 쓰일 수 있다.

• 한국생활과학회지
• /
• 제19권2호
• /
• pp.311-323
• /
• 2010

This study includes definitions and major issues relating to product safety, and reviews about product safety laws of Korea and of other countries. In addition, this study suggests several ideas for a future governmental policy concerning product safety and the government policies to guide in securing consumers' safety of products. First, we need to set up consumer safety policies and laws dealing with complex consumer safety issues and to integrate existing laws for the safety of products. Second, opening a consumer safety agency and training workers who have relation to the safety policy, as a profession, are necessary. Third, it is required to redefine the product safety guidelines, strengthen the safety policy and to minimize safety regulations by the government directly. Fourth, each product of the safety management policies must be regularly evaluated and given feedback for improving its effectiveness. Fifth, information gathering, disclosing, and having a feedback system related to product safety should be rebuilt for the effective management of unsafe products. In addition, laws and the aims of product safety management being changed to focus on the consumers, control on imported products, collaboration with network and mutual-assistance systems of product safety-related agencies including international organizations and major countries and taking leading roles in the world are essential.

• 한국산학기술학회논문지
• /
• 제13권9호
• /
• pp.4234-4243
• /
• 2012

USN(Ubiquitous Sensor Network) 응용 S/W는 다양한 타겟 운영체제의 핵심모듈들을 기반으로, 다양한 종류의 센서 노드들을 유기적으로 제어하는 복잡한 특징을 가진다. 현재 USN 응용 분야에서도 효율적으로 S/W를 개발하기 위한 다양한 연구가 진행되고 있다. S/W의 개발생산성을 높이기 위해서는 프로덕트라인 기반 개발과 같이 도메인에 따라 어플리케이션들의 핵심 공통기능을 명세하고, 어플리케이션의 워크플로우에 따라 핵심 공통기능에 가변적인 기능만을 취사 선택하여 개발하는 방법이 효율적이다. 이러한 방법을 USN 도메인에 적용하기 위해서는 USN 응용 S/W의 특성과 프로덕트라인 기반 개발의 특성을 일관성 있는 하나의 뷰로 명세 가능하여야 한다. 그러나 일반적인 UML 표기법만으로는 이러한 특성을 효과적으로 명세하기 어렵다. 본 논문에서는 이러한 문제점을 해결하기 위하여 기존 UML의 확장 메카니즘인 프로파일을 이용하여 USN 어플리케이션의 특성과 프로덕트라인 기반 개발의 특성을 효과적으로 명세할 수 있는 기법을 제시한다. 제시하는 프로덕트라인 기반 USN 응용 개발을 위한 UML 프로파일은 어플리케이션 개발자에게 USN이나 프로덕트라인 기반 개발에 특화된 새로운 설계기법이나 도구 등의 추가적인 자원을 요구하지 않고, 기존의 UML과 지원도구를 활용하여 효과적으로 프로덕트라인 기반의 USN 응용 개발을 가능하게 한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1061-1066
• /
• 2004

It is certain that the future manufacturing environment will be network-centric and spatially distributed based on Internet. Today, wide variety of distributed computing and communication technologies are available for implementing a system for product data exchange and sharing. One of the technologies that have been received most attentions for product data exchange and sharing is Product Data Management (PDM). PDM tries to integrate and manage process of data and technical documents that are connected to physical product components. In accordance to previous researches about PDM, it can be regarded as an integration tool of many different areas, which ensures that the right information is available to the right person at the right time and in the right form throughout the enterprise. PDM with Web-enabled CAD system is proposed in this paper in order to acknowledge the usefulness of the system mentioned. The system will use Web service on Visual Studio C#.Net to invoke the web application system.

• Asian Journal of Business Environment
• /
• 제4권3호
• /
• pp.27-37
• /
• 2014

Purpose - In the past, designs for traditional products have usually focused on historic techniques. However, this tradition of using historic techniques has now been replaced by the trend of using the innovative design concept. Research design, data, and methodology - To measure future market trends and quality requirements, we apply the results of the questionnaires and analyze them with various experimental processes and a design methodology. In this way, we gauge the impact of the innovative product value chain on the promotion of new products. Results - Accompanied with an innovative product value chain, the product can stimulate the development of enterprise management, which has become the main issue in social and economic development in every developed country, and can facilitate the progress of enterprise management throughout the enterprise. Conclusions - Customer demand should be emphasized as the primary means to solve design problems, to design optimal solutions, to create differentiation with competitors, and to pursue optimal marketing strategies.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 하계종합학술대회논문집
• /
• pp.297-300
• /
• 1998

A honeycomb network is considered as a multiprocessor interconnection network. The network cost defined as the product of degree and diameter is better for honeycomb networks than for other types of meshes. Parallel paths offer us bypasses when the networks have faulty nodes or edges. In this paper, we present a method to construct a parallel path in honeycomb network, and show that the fault diameter for the honeycomb network is d+8, where d is diameter of the honeycomb network.

• 한국CDE학회논문집
• /
• 제5권1호
• /
• pp.12-22
• /
• 2000

Network and Internet technology opens up another domain for building future CAD/CAM environment. The environment will be global, network-centric, and spatially distributed. In this paper, we present an approach for network-centric feature-based modeling in a distributed design environment. The presented approach combines the current feature-based modeling technique with distributed computing and communication technology for supporting product modeling and collaborative design activities over the network. The approach is implemented in a client/server architecture, in which Web-enabled feature modeling clients, neutral feature model server, and other applications communicate with one another via a standard communication protocol. The paper discusses how the neutral feature model supports multiple views and maintains naming consistency between geometric entities of the server and clients. Moreover, it explains how to minimize the network delay between the server and client according to incremental feature modeling operations.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.174-176
• /
• 2006

Sensor network supports data delivery from Physical world to cyber space. Sensors get physical events then wireless network transfers sensor data to service server. We use sensor network technology to light control system for intelligent building. In ubiquitous computing environment. wireless sensor network is basic tool for intelligent service. In this paper, we propose intelligent building light control system based on wireless sensor network. It is implemented using previous light control product, can be adopted to present building light system.

• 한국산업융합학회 논문집
• /
• 제23권5호
• /
• pp.773-787
• /
• 2020

In the injection molding process, the controlling stability of products quality is a very important factor in terms of productivity. Even when the optimum process conditions for the desired product quality are applied, uncontrollable external factors such as ambient temperature and humidity cause inevitable changes in the state of the melt resin, mold temperature. etc. Therefore, it is very difficult to maintain prodcut quality. In this study, a system that learns the correlation between process variables and product weight through artificial neural networks and predicts process conditions for the target weight was established. Then, when a disturbance occurs in the injection molding process and fluctuations in the weight of the product occur, the stability control of the product quality was performed by ANN predicting a new process condition for the change of weight. In order to artificially generate disturbance in the injection molding process, controllable factors were selected and changed among factors not learned in the ANN model. Initially, injection molding was performed with a polypropylene having a melt flow index of 10 g/10min, and then the resin was replaced with a polypropylene having a melt floiw index of 33 g/10min to apply disturbance. As a result, when the disturbance occurred, the deviation of the weight was -0.57 g, resulting in an error of -1.37%. Using the control method proposed in the study, through a total of 11 control processes, 41.57 g with an error of 0.00% in the range of 0.5% deviation of the target weight was measured, and the weight was stably maintained with 0.15±0.07% error afterwards.