• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.78-81
• /
• 2021

Through the smart factory construction project, sensors can be installed in manufacturing production facilities and various process data can be collected in real time. Through this, research on real-time facility anomaly detection is being actively conducted to reduce production interruption due to facility abnormality in the manufacturing process. In this paper, to detect abnormalities in production facilities, the manufacturing data was applied to deep learning models Autoencoder(AE), VAE(Variational Autoencoder), and AAE(Adversarial Autoencoder) to derive the results. Manufacturing data was used as input data through a simple moving average technique and preprocessing process, and performance analysis was conducted according to the window size of the simple movement average technique and the feature vector size of the AE model.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.173-180
• /
• 2023

Smart factory companies are installing various sensors in production facilities and collecting field data. However, there are relatively few companies that actively utilize collected data, academic research using field data is actively underway. This study seeks to develop a model that detects anomalies in the process by analyzing spindle power data from a company that processes shafts used in automobile throttle valves. Since the data collected during machining processing is time series data, the model was developed through unsupervised learning by applying the Holt Winters technique and various deep learning algorithms such as RNN, LSTM, GRU, BiRNN, BiLSTM, and BiGRU. To evaluate each model, the difference between predicted and actual values was compared using MSE and RMSE. The BiLSTM model showed the optimal results based on RMSE. In order to diagnose abnormalities in the developed model, the critical point was set using statistical techniques in consultation with experts in the field and verified. By collecting and preprocessing real-world data and developing a model, this study serves as a case study of utilizing time-series data in small and medium-sized enterprises.

• Journal of the Korean Society of Industry Convergence
• /
• v.7 no.4
• /
• pp.425-432
• /
• 2004

This study for Customer Satisfaction(Customer Focus) by Profit security' in the field Process improvement activity and man-power upgrade in the learning of organization activity or upgrading ability of each peoples. This thesis study on the focus of KAPEC which introduce Toyota system can apply to VM, 3jeong, Right Box and Right Position), 5S, JIT(Just In Time), KAlZEN, KANBAN System, CIM, ERP, DAS an output of Factory. For strategic changes to take place in industry 3 key important factors need to be included ; integration of tasks functions and process, decentralization of information and responsibility and finally simplification of products and product structures. These describes how CIM can be implemented using these factors. This study for (1)System Integration, (2) Help Logistic Problems, (3) Partly facilitated growth. (4) Improved production planning (5) Real-time management. (6) Fast reporting (7) Productivity. Quality. Delivery Up, Cost reduction and Autonomy management, FMS in the Plant etc.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.9 no.3
• /
• pp.103-110
• /
• 2000

Shaft encoder which encodes the rotational angle of a shaft becomes more important recently due to factory automation and office automation. Although an absolute type encoder is more dsirable due to its convenience an incremental encoder is commonly used because of its cost and technical difficulties Fabricating a high resolution absolute encoder is very diff-cult because the physical size is limited by currently available technology. In order to overcome this difficulty Moire fringe can be used incorporated with gray code. In order to measure the position of fringes which move as the code disk rotates a neural network was developed in this paper. Formerly fringe position is usually measured by a sophisticated software which needs a little long calculation time. However using nerual network method can eliminate such calculation time even though it needs learning job The pro-posed method is verified through several experiments.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.7-13
• /
• 2021

Machine vision is a technology that helps the computer as if a person recognizes and determines things. In recent years, as advanced technologies such as optical systems, artificial intelligence and big data advanced in conventional machine vision system became more accurate quality inspection and it increases the manufacturing efficiency. In machine vision systems using deep learning, the image quality of the input image is very important. However, most images obtained in the industrial field for quality inspection typically contain noise. This noise is a major factor in the performance of the machine vision system. Therefore, in order to improve the performance of the machine vision system, it is necessary to eliminate the noise of the image. There are lots of research being done to remove noise from the image. In this paper, we propose an autoencoder based machine vision system to eliminate noise in the image. Through experiment proposed model showed better performance compared to the basic autoencoder model in denoising and image reconstruction capability for MNIST and fashion MNIST data sets.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.242-252
• /
• 2021

Following the intuition that the local information in time instances is hardly incorporated into the posterior sequence in long short-term memory (LSTM), this paper proposes an attention augmented mechanism for fault diagnosis of the complex chemical process data. Unlike conventional fault diagnosis and classification methods, an attention mechanism layer architecture is introduced to detect and focus on local temporal information. The augmented deep network results preserve each local instance's importance and contribution and allow the interpretable feature representation and classification simultaneously. The comprehensive comparative analyses demonstrate that the developed model has a high-quality fault classification rate of 95.49%, on average. The results are comparable to those obtained using various other techniques for the Tennessee Eastman benchmark process.

• Journal of Information Processing Systems
• /
• v.15 no.4
• /
• pp.717-723
• /
• 2019

Smart systems and services aim to facilitate growing urban populations and their prospects of virtual-real social behaviors, gig economies, factory automation, knowledge-based workforce, integrated societies, modern living, among many more. To satisfy these objectives, smart systems and services must comprises of a complex set of features such as security, ease of use and user friendliness, manageability, scalability, adaptivity, intelligent behavior, and personalization. Recently, artificial intelligence (AI) is realized as a data-driven technology to provide an efficient knowledge representation, semantic modeling, and can support a cognitive behavior aspect of the system. In this paper, an integration of AI with the smart systems and services is presented to mitigate the existing challenges. Several novel researches work in terms of frameworks, architectures, paradigms, and algorithms are discussed to provide possible solutions against the existing challenges in the AI-based smart systems and services. Such novel research works involve efficient shape image retrieval, speech signal processing, dynamic thermal rating, advanced persistent threat tactics, user authentication, and so on.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.147-150
• /
• 2022

최근 들어 다양한 제약 조건이 있는 스마트 시티나 스마트 팩토리와 같은 도메인들 내에서 태스크들을 효과적으로 처리하기 위해서 MEC 기술이 많이 사용되고 있다. 그러나 이러한 도메인에서 발생하는 복잡하고 동적인 시나리오는 기존의 휴리스틱이나 메타 휴리스틱 기법을 이용하여 해결하기엔 계산 복잡도가 증가하는 문제점을 가지고 있다. 따라서 최근 들어 이러한 문제점을 해결하기 위한 방법 중 하나로 강화학습과 딥러닝이 결합된 DRL 기법이 주목을 받고 있다. 본 연구는 스마트 팩토리 환경에서 종속성을 가진 태스크들이 실행시간과 태스크가 처리되는 MEC 서버들의 로드 표준편차를 최소화하는 태스크 스케줄링 기법을 제안한다. 모의실험을 통하여 제안 기법은 태스크가 증가하는 동적인 환경에서도 좋은 성능을 보임을 증명하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.333-336
• /
• 2024

스마트팩토리는 기존 제조산업에 ICT 기술이 융합된 지능형 공장이다. 이는 IT(Information Technology)영역과 OT(Operation Technology)으로 구분되고, 영역 간 연결을 통해 제조공정 자동화 및 지능화를 수행한다. IT영역은 외부 네트워크와 연결되어 스마트팩토리의 전사업무 관리를 수행하며, OT영역은 폐쇄망 네트워크로 구성되어 직접적인 제조과정을 수행한다. 이는 2개의 영역으로 구분되어 자동화 및 지능화된 제조공정 과정을 수행함에 따라 구조가 복잡해지고 있으며, 이로 인해 스마트팩토리 보안위협이 발생 가능한 공격 표면이 증가하고 있다. 이에 대응하기 위해서는 스마트팩토리 IT영역과 OT영역의 특징을 분석하고, 영역별 적합한 보안위협 대응체계를 수립해야 한다. 이에 따라, 본 논문에서는 다수의 장치에 대한 학습이 용이하고, 세부적으로 학습기법을 구분할 수 있는 연합학습을 활용하여 스마트팩토리 영역별 적합한 보안위협 대응방안을 제안한다.

• Journal of Korea Multimedia Society
• /
• v.13 no.10
• /
• pp.1494-1505
• /
• 2010

A variety of sounds take place in medium and small-sized manufactories producing many kinds of parts in a small quantity with one press. We developed the identification system for the quality of parts using HTM(Hierarchical Temporal Memory)-based sound recognition. HTM is the theory that the operation principle of human brain's neocortex is applied to computer, suggested by Jeff Hopkins. This theory memorizes temporal and spatial patterns hierarchically about the real world, which is known for its cognitive power superior to the previous recognition technologies in many cases. By applying the HTM model to the sound recognition, we developed the identification system for the quality of molding parts. In order to verify its performance we recorded the various sounds at the moment of producing parts in the real factory, constructed the HTM network of sound, and then identified the quality of parts by repeating learning and training. It reveals that this system gets an excellent and accurate results at the noisy factory.