• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2004년도 추계학술대회 논문집
• /
• pp.170-174
• /
• 2004

Despite the widespread use in the various manufacturing industries, the full automation of the robotic CO$_2$ welding has not yet been achieved partly because the mathematical model for the process parameters of a given welding task is not fully understood and quantified. Several mathematical models to control welding quality, productivity, microstructure and weld properties in arc welding processes have been studied. However, it is not an easy task to apply them to the various practical situations because the relationship between the process parameters and the bead geometry is non-linear and also they are usually dependent on the specific experimental results. Practically, it is difficult, but important to know how to establish a mathematical model that can predict the result of the actual welding process and how to select the optimum welding condition under a certain constraint. In this paper, an attempt has been made to develop an Radial basis function network model to predict the weld top-bead width as a function of key process parameters in the robotic CO$_2$ welding. and to compare the developed model and a simple neural network model using two different training algorithms in order to verify performance. of the developed model.

• 한국기계가공학회지
• /
• 제17권4호
• /
• pp.137-142
• /
• 2018

Recycled synthetic resin materials produced from waste vinyl and waste plastic contain many foreign substances. Plastic products made from this recycled resin materials containing foreign substances are of poor quality, with reduced the strength and rigidity. Foreign substances include heavy metals, cement, foil, dyed paper and dust. In this study, the scratch-Dies process; which remove foreign sbustances, with precision and automation, through a three-stage mesh filter, is designed. The process is evaluated with finite element analysis according to vibration loading and make. After installing the manufactured equipment, recycled resin was producde, and its heavy metal content was evaluated. Recycled synthetic resin materials were also used plastic products and evaluate their strength. In addition, the change in production was assessed.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.333-339
• /
• 2022

The purpose of the article is to identify priority trends of technological innovations and strategic opportunities for using the smart potential to the benefit of the Russian industrial production development in the context of digital transformation. The article substantiates the demand for technological process automation at industrial enterprises in Russia and considers the possibilities of using artificial intelligence and the implementation of smart manufacturing in the industry. The article reveals the priorities of the leading Russian industrial companies in the field of digitalization, namely, an expansion of the use of cloud technologies, predictive analysis, IaaS services (virtual data storage and processing centers), supervisory control, and data acquisition (SCADA), etc. The authors give the characteristics of the monitoring of the smart manufacturing systems development indicators in the Russian Federation, conducted by Rosstat since 2020; presents projected data on the assessment of the required resources in relation to the instruments of state support for the development of smart manufacturing technologies for the period until 2024. The article determines targets for the development of smart technologies within the framework of the Federal Project "Digital Technologies".

• International Journal of Control, Automation, and Systems
• /
• 제4권3호
• /
• pp.372-381
• /
• 2006

The purpose of this study was to develop a process management system to manage ingot fabrication and improve ingot quality. The ingot is the first manufactured material of wafers. Trace parameters were collected on-line but measurement parameters were measured by sampling inspection. The quality parameters were applied to evaluate the quality. Therefore, preprocessing was necessary to extract useful information from the quality data. First, statistical methods were used for data generation. Then, modeling was performed, using the generated data, to improve the performance of the models. The function of the models is to predict the quality corresponding to control parameters. Secondly, rule extraction was performed to find the relation between the production quality and control conditions. The extracted rules can give important information concerning how to handle the process correctly. The dynamic polynomial neural network (DPNN) and decision tree were applied for data modeling and rule extraction, respectively, from the ingot fabrication data.

• 산업공학
• /
• 제21권2호
• /
• pp.229-236
• /
• 2008

Recently, ubiquitous computing paradigm considers as a tool for making innovation and competitive strength in manufacturing industry like other industries. Particularly, the location-based service that enables us to trace real-time logistics make effective management of schedules for inventory control, facilities and equipments, jobs planning, and facilitate the processes of information management and intelligence, which relate with ERP and SCM in organizations. Our study tries to build the location-based system for products of semiconductors in manufacturing place and suggests the good conditions and effective tracking procedures for positions of products. Our study show that the system is good for the saving of time in tracking products, however, it has to be improved in terms of accuracy. The study verifies the application of RFID technology in manufacturing industry and suggests the improvement of photograph process through RFID. In addition, our research introduces the future operation of FAB in semiconductors' processes that relate with real-time automation and RFID in manufacturing company.

• 한국산업융합학회 논문집
• /
• 제21권2호
• /
• pp.53-62
• /
• 2018

This study propose a new approach to control the optimal working path of vertical type articulated robot with translation joint for trimming working process automation in forging manufacturing process. The basic structure of the proposed robotic joints controller consists of a Proportional-Intergral controller and a Proportional-Derivative controller in parallel. The proposed control scheme takes advantage of the properties of the fuzzy PID controllers. The proposed method is suitable to control of the trajectory and path control in cartesian space for vertical type articulated robot manipulator. The results illustrates that the proposed fuzzy computed torque controller is more stable and robust than the conventional computed torque controller. The reliability is varified by simulation test for vertical type s articulated robot with seven joints including one trqanslation joint.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권3호
• /
• pp.1385-1402
• /
• 2019

Quickly picking up some valuable information from massive manufacturing event stream usually faces with the problem of long detection time, high memory consumption and low detection efficiency due to its stream characteristics of large volume, high velocity, many variety and small value. Aiming to solve the problem above for the current complex event processing methods because of not sharing detection during the detecting process for massive manufacturing event streams, an efficient complex event processing method based on multipattern sharing is presented in this paper. The achievement of this paper lies that a multipattern sharing technology is successfully used to realize the quick detection of complex event for massive manufacturing event streams. Specially, in our scheme, we firstly use pattern sharing technology to merge all the same prefix, suffix, or subpattern that existed in single pattern complex event detection models into a multiple pattern complex event detection model, then we use the new detection model to realize the quick detection for complex events from massive manufacturing event streams, as a result, our scheme can effectively solve the problems above by reducing lots of redundant building, storing, searching and calculating operations with pattern sharing technology. At the end of this paper, we use some simulation experiments to prove that our proposed multiple pattern processing scheme outperforms some general processing methods in current as a whole.

• 융합정보논문지
• /
• 제10권5호
• /
• pp.8-15
• /
• 2020

인공지능의 발전과 함께 RPA(Robotic Process Automation)의 광범위한 적용은 필연적인 것이 되었다. 본 연구의 목적은 RPA를 기반으로 하여 교차되는 원가정보의 자동수집, 적시성 및 유연성을 지닌 원가관리의 최적화 방안을 모색하고자 함에 있다. RPA기반의 원가관리시스템은 원가정보 인식의 교차시스템, 클라우드 플랫폼 등을 통하여 원가관리프로세스의 최적화와 개선을 이룩할 수 있을 것이다. RPA 관련기술의 효익, RPA기술과 회계기능에 대한 선행연구를 조사하고, 현행의 원가관리 문제점을 파악하여 경영의사결정을 지원하는 관리회계 실행을 위한 원가관리의 최적화를 구현하는 RPA적용방안을 제시하고자 한다.

• 한국산업융합학회 논문집
• /
• 제25권2_1호
• /
• pp.177-184
• /
• 2022

The automatic defect sorting function of machinery parts is being introduced to the automation of the manufacturing process. In the final stage of automation of the manufacturing process, it is necessary to apply computer vision rather than human visual judgment to determine whether there is a defect. In this paper, we introduce a deep learning method to improve the classification performance of typical mechanical parts, such as welding parts, galvanized round plugs, and electro galvanized nuts, based on the results of experiments. In the case of poor welding, the method to further increase the depth of layer of the basic deep learning model was effective, and in the case of a circular plug, the surrounding data outside the defective target area affected it, so it could be solved through an appropriate pre-processing technique. Finally, in the case of a nut plated with zinc, since it receives data from multiple cameras due to its three-dimensional structure, it is greatly affected by lighting and has a problem in that it also affects the background image. To solve this problem, methods such as two-dimensional connectivity were applied in the object segmentation preprocessing process. Although the experiments suggested that the proposed methods are effective, most of the provided good/defective images data sets are relatively small, which may cause a learning balance problem of the deep learning model, so we plan to secure more data in the future.

• 디지털융복합연구
• /
• 제12권1호
• /
• pp.305-311
• /
• 2014

제조업에서는 경쟁우위 확보를 위해 일찍이 설계, 생산 과정의 자동화와 정보시스템을 도입하였다. 대표적인 정보시스템 중 하나가 제조실행시스템(Manufacturing Execution System)인데, 이러한 제조실행시스템은 진화를 거듭해 왔다. 최근 빅데이터가 등장하면서 MES도 빅데이터 적용 방안이 모색되고 있다. 이에 본 연구는 먼저 제조 분야에서의 빅데이터 활용에 대한 선행 연구 및 사례 분석을 토대로 MES에의 빅데이터 적용모델을 제안할 것이다.