미래기술융합논문지 (Journal of Advanced Technology Convergence)

한국융합학회 (Korea Convergence Society)
권호 표지
DOI QR코드

DOI QR Code

에너지 프로세스 혁신을 통한 제조 핵심 공정의 에너지 효율화 방안 연구

Study on Energy Efficiency Improvement in Manufacturing Core Processes through Energy Process Innovation

  • 조상준 (한국공학대학교 나노반도체공학과) ;
  • 이현무 (한국공학대학교 나노반도체공학과) ;
  • 이진수 (SEP 협동조합)
  • Sang-Joon Cho (Department of Nano Semi-Conductor Engineering, Tech University of Korea) ;
  • Hyun-Mu Lee (Department of Nano Semi-Conductor Engineering, Tech University of Korea) ;
  • Jin-Soo Lee (SEP Cooperative)
  • 투고 : 2023.11.14
  • 심사 : 2023.12.22
  • 발행 : 2023.12.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

전세계적으로 기후변화 대응을 위한 글로벌 탄소중립을 공조하고 있다. 한국의 경우 온실가스 배출량이 빠른 속도로 증가하고 있어 해결이 시급한 상황이다. 이에 본 연구는 스팀트랩이라는 열 에너지 수집 디바이스를 개발하고, 스팀트랩으로 에너지 사용량을 데이터로 수집하여 향후 전력 사용량에 대해서 예측이 가능한 AI 모델을 개발하였다. 해당 AI 모델의 전력 사용량 예측 정확도 평균은 96.7%로 높은 정확도를 보여주었다. 따라서 해당 AI 모델을 통해 어느날 전력 사용량이 높은지와 어떤 설비에서 전력 사용량이 높은지를 예측하고 관리 할 수 있게 되었다. 향후 연구는 스팀트랩의 이상탐지를 통한 효율적인 장비 운용과 에너지 관리 시스템의 표준화를 통해 에너지 소비 효율을 최적화하여 온실가스 배출을 줄이고자 한다.

Globally, there is a collaborative effort to achieve global carbon neutrality in response to climate change. In the case of South Korea, greenhouse gas emissions are rapidly increasing, presenting an urgent situation that requires resolution. In this context, this study developed a thermal energy collection device named a 'steam trap' and created an AI model capable of predicting future electricity usage by collecting energy usage data through steam traps. The average accuracy of electricity usage prediction with this AI model was 96.7%, demonstrating high precision. Consequently, the AI model enables the prediction and management of days with high electricity consumption and identifies which facilities contribute to elevated power usage. Future research aims to optimize energy consumption efficiency through efficient equipment operation using anomaly detection in steam traps and standardizing energy management systems, with the ultimate goal of reducing greenhouse gas emissions.

키워드

과제정보

This paper was carried out in 2023 with the support of the Korea Institute of Environmental Industry and Technology's DX-based carbon supply chain environmental manpower training project (Ministry of Environment) and the Korea Energy Technology Evaluation Institute's energy manpower training project (task name: training specialized manpower for carbon resource based on energy efficiency) for each mid-sized business sector.

참고문헌

  1. T. Y. Jin, J. W. Kim & D. W. Kim. (2023). Analyzing Contribution of RE100 to the Net-Zero Focusing on Electricity Profile Analysis. Journal of Environmental Policy and Administration, 31(3), 1-28. DOI : 10.15301/jepa.2023.31.3.1
  2. S. K. Kim & S. K. Kim. (2022). A Study on Industrial Development through Employment Creation in National Industrial Complexes and Analysis of Transportation Equipment Industry in the Southeast Region. Korean Jouranl of Business Administration, 35(1), 1-27. DOI : 10.18032/kaaba.2022.35.1.1
  3. I. K. Choi & J. H. Kang. (2016). Study of Performance Properties and Steam Condensate Capacity by Orifice Diameters of Free Float Steam Trap Valve. Journal of the Korean Society of Manufacturing Process Engineers, 15(2), 31-37.
  4. H. A. Lee, D. J. Kim, W. J. Cho & J. H. Gu. (2023). Optimization of Energy Consumption Prediction Model of Food Factory based on LSTM for Application to FEMS. Journal of Environmental & Thermal Engineering, 18(1), 7-19.
  5. Y. J. Lee, S. W. Kweon, J. H. Kim, J. E. Cha, K. H. Kang & H. J. Kim. (2023). Spectral Preprocessing and Machine Learning Modeling for Discriminating Manufacturing Origins of Mulberry Bast Fiber. Journal of Korea Technical Association of the Pulp and Paper Industry, 55(5), 61-74. https://doi.org/10.7584/JKTAPPI.2023.10.55.5.61
  6. Y. J. Kim, Julip Jung, S. I. Hwang & Helen Hong. (2023). Improvement of Prostate Cancer Aggressiveness Prediction Based on the Deep Learning Model Using Size Normalization and Multiple Loss Functions on Multi-parametric MR Images. Journal of KIISE, 50(10), 866-873. DOI : 10.5626/JOK.2023.50.10.866
  7. D. H. Kim, Seil Kim & J. H. Koh. (2023). A Study on a Flow Rate Prediction CNN-LSTM Model Based on Deep Learning using Meteorological Data. Journal of the Korea Academia-Industrial cooperation Society, 24(8), 22-31. DOI : 10.5762/KAIS.2023.24.8.22
  8. H. S. Choi. (2019). Implementation of back propagation algorithm for wearable devices using FPGA. The Journal of Korean Institute of Next Generation Computing, 15(2), 7-16.
  9. C. G. Kang & M. K. Kim. (2022). Detecting Foot Contact of Motion Data using Recurrent Neural Network. The Journal of Korean Institute of Information Technology, 20(10), 119-125. DOI : 10.14801/jkiit.2022.20.10.119
  10. J. M. Sohn & S. M. Kim. (2022). MLOps workflow language and platform for time series data anomaly detection. Journal of the Korea Society of Computer and Information , 27(11), 19-27.
  11. Y. N. Kim, Y. J. Lee & C. E. Kang (1992). Analysis of the excess MSE of the individual tap LMS ( ITLMS ) equalizer. The Journal of Korean Institute of Communications and Information Sciences, 17(3), 232-239.
  12. K. T. Kim & J. Y. Choi. (2020). Deep Neural Networks Learning based on Multiple Loss Functions for Both Person and Vehicles Re-Identification. Journal of Korea Multimedia Society, 23(8), 891-902.
  13. J. H. Kim. (2009). A Study on the Estimation Methodology for the Stand-by Energy Savings of Televisions Using Learning Curves and Diffusion Models. The transactions of The Korean Institute of Electrical Engineers, 58(2), 239-241.
  14. S. H. Kim, S. J. Oh, G. Y. Geun, Y. G. Jung & M. S. Kang. (2017). Influence on overfitting and reliability due to change in training data. The International journal of advanced culture technology, 5(2), 82-89.
  15. Y. J. Yoon, M. G. Kim & J. S. Lee (2012). Calculation of Measurement Error and RMSE about Total-station Using Precise Baseline. Journal of the Korean Cadastre Information Association, 14(2), 99-106.