해군 함정용 지능형 장비상태 감시체계 구현 방안

장준영^*

해군사관학교 기계시스템공학 교관

Implementation of Intelligent Equipment-Condition Monitoring System for Naval Vessels

Joon-Young Jang^*

Instructor, Dept. of Mechanical Systems Engineering, Republic of Korea Naval Academy

Correspondence to: *Joon-Young Jang Tel: +82-55-907-5390 E-mail: na05jjy@navy.ac.kr

초록

본 논문은 병력 감소와 무기체계 첨단화에 대응하여 해군 함정의 가동률을 높이고 정비 인력을 절감하기 위한 ‘지능형 장비상태 감시체계’를 제안한다. 다중 센서 데이터(음향·진동)와 인공지능을 결합하여 탐지·식별·조치·평가의 4단계 프레임워크를 정립하였으며, 특히 비지도학습 기반의 이상 탐지와 RAG 기반 LLM을 활용한 실시간 교범 가이드 제공을 통합하였다. 본 체계는 군 인력 운용의 효율화와 상태기반정비(CBM+) 고도화를 가능케 하며, 향후 전 군으로 확장 적용되어 국방 자산의 신뢰성을 극대화하는 데 기여할 것이다.

Abstract

This paper proposes an intelligent equipment-condition monitoring system to maximize naval-vessel availability and reduce maintenance personnel amid military downsizing. By integrating multisensor data (acoustic and vibration) with artificial intelligence, this study establishes a four-stage framework comprising detection, identification, action, and evaluation. The system seamlessly combines unsupervised anomaly detection with an LLM and RAG pipeline to deliver real-time, manual-based maintenance guidelines. This approach optimizes military human resources and advances data-driven preventive maintenance (CBM+) with broad applicability across other branches.

Keywords:

Condition-Based Maintenance, Artificial Intelligence, Naval Vessel, Condition Monitoring System, CBM+ methodology

키워드:

상태기반정비, 인공지능, 해군 함정, 상태 감시체계, 상태기반정비 방법론

References

한국국방연구원, 국방 환경 변화에 따른 무기체계 유지보수 인력 최적화 방안, KIDA 연구보고서, 2024.
통계청, 인구절벽에 따른 군 병력 자원 수급 전망 보고서, 2023.
해군기술연구소, 함정 기관실 승조원 근무 환경 및 직무 피로도 조사 분석, 해군기술연구소 기술보고서, 2023.
Alan V. Oppenheim & Ronald W. Schafer, Discrete-Time Signal Processing (3rd ed.), Pearson, 2010.
Robert Bond Randall, Vibration-based Condition Monitoring: Industrial, Automotive and Aerospace Applications, John Wiley & Sons, 2021. [https://doi.org/10.1002/9781119477631]
R. Keith Mobley, An Introduction to Predictive Maintenance, Elsevier, 2002. [https://doi.org/10.1016/B978-075067531-4/50006-3]
한국PHM학회, 상태기반정비(CBM+) 가이드북 및 산업 적용 표준, 2023.
방위사업청, 데이터 기반의 국방 무기체계 CBM+ 발전 방향, 방위사업청 정책연구보고서, 2023.
Michael Pecht, Prognostics and Health Management of Electronics, John Wiley & Sons, 2008. [https://doi.org/10.1002/9780470385845]
윤병동, 황태완, 조수호, 이동기, 나규민, ‘인공지능을 이용한 공학시스템 상태진단 및 예지,’ 기계저널, 제57권 제3호, 2017, pp. 38-41.
국방기술품질원, 국방 PHM 기술 동향 및 군수 혁신 연계 방안, 국방기술품질원 조사분석보고서, 2024.
Youngdoo Choi, Mingyu Jeon, Dongjin Kim, & Sera Kim, ‘A Study on the Elemental System Analysis for Applying Condition-Based Maintenance to Naval Ship Propulsion Systems,’ Journal of the KNST, VOL. 8, NO. 4, 2025, pp. 908-915. [https://doi.org/10.31818/JKNST.2025.12.8.4.908]
Naval Surface Warfare Center (NSWC), Integrated Condition Assessment System (ICAS) Fleet Operational Evaluation Report, NSWC Technical Report, 2018.
US Navy, Enterprise Remote Monitoring (eRM) Architecture Design and Cloud Migration Strategy, Naval Sea Systems Command (NAVSEA), 2021.
Government Accountability Office (GAO), Military Readiness: Opportunities Exist to Improve Option and Cost Efficiency Through Predictive Maintenance, GAO-23-10524, 2023.
Department of Defense (DoD), Condition Based Maintenance Plus (CBM+) Guidebook, US Department of Defense, 2022.
국방부, 국방운영 효율화를 위한 AI 기반 군수혁신 마스터플랜, 국방부 정책서, 2024.
국방부, 국방전력발전업무훈령(국방부훈령 제2866호, 2024년 2월 2일 개정), 대한민국 국방부, 2024.
한국항공우주산업(KAI), 수리온(KUH-1) 헬기 HUMS 데이터 분석을 통한 구성품 수명 예측 성과 보고서, KAI 기술논문집, 2020.
해군기술연구소, 광개토-Ⅲ급 구축함 ICAS 운용 데이터를 통한 선제적 정비 효과 검증, 해군기술보고서, 2022.
국방기술진흥연구소(KRIT), 무기체계 CBM+ 특화연구센터 연구 성과 요약서, 2025.
김주영, ‘한화시스템, CBMS 국산화…‘수출 주력품목으로 자리 잡을 것’,’ 연합뉴스TV, 2025.01.24. https://www.yonhapnewstv.co.kr/news/AKR20250124095146136, (accessed 2026.07.01.)
한화시스템, 함정 상태기반정비체계(CBMS) 핵심 기술 개발 및 해군 전력화 방안, 방위산업부품장비대전 발표논문집, 2023.
Jae-Soon Shim, Hyeong-Min Lee, & Chan-Yeong Park, 'Design of CBM Algorithm for Naval On-Board Equipment,' Journal of the Korean Society of Industry Convergence, VOL. 27, NO. 5, 2024, pp. 1243-1251.
Jae-Soon Shim, Chan-Yeong Park, Hun-Seok Lee, & Jin-Seok Oh, ‘Design of Regression Model for Abnormal Diagnosis of Naval Propulsion System,’ Journal of the Korea Institute of Information and Communication Engineering, VOL. 27, NO. 8, 2023, pp. 941-950. [https://doi.org/10.6109/jkiice.2023.27.8.941]
Sang-Guk Lee, Sun-Ki Lee, Do-Hwan Lee, & Sung-Keun Park, ‘A Study on Damage Evaluation of Bearings for Rotating Machinery in Power Plant Using Ultrasonic Wave,’ Transactions of the KSME A, VOL. 32, NO. 7, 2008, pp. 583-589. [https://doi.org/10.3795/KSME-A.2008.32.7.583]
Hyunseok Choi, Junu Oh, & Hong Seok Kim, ‘Early Detection of Bearing Failure Used in Power Plant Based on Ultrasound,’ in proceedings of KSME Annual Meeting 2022, November 2022, pp. 2725-2726.
Dong-Hyun Kim, Seung-Eon Yoo, Byung-Jun Lee, Kyung-Tae Kim, & Hee-Yong Youn, ‘Data Preprocessing for Efficient Machine Learning,’ in proceedings of the Korean Society of Computer and Information Winter Conference, VOL. 27, NO. 1, January 2019, pp. 49-50.
Kyung-Won Kang & Kyeong-Min Lee, ‘CNN-Based Automatic Machine Fault Diagnosis Method Using Spectrogram Images,’ The Journal of Korea Institute of Convergence Signal Processing, VOL. 21, NO. 3, 2020, pp. 121-126.
Youngjun Kim & Seok-pil Lee, ‘An Abnormalities Detection Model of a Machine Using Spectrogram,’ The Transactions of the Korean Institute of Electrical Engineers, VOL. 71, NO. 9, 2022, pp. 1274-1279. [https://doi.org/10.5370/KIEE.2022.71.9.1274]
Hyo Jin Lee & Yoonsuh Jung, ‘Comparison of Deep Learning-Based Autoencoders for Recommender Systems,’ The Korean Journal of Applied Statistics, VOL. 34, NO. 3, 2021, pp. 329-345.
Junwoo Jung, Daesik Kim, & Jaemin Baek, ‘Detection of Combustion Instability of Gas Turbine Combustor Using Convolutional Autoencoder Model,’ Journal of the Korean Society of Combustion, VOL. 28, NO. 3, 2023, pp. 11-19. [https://doi.org/10.15231/jksc.2023.28.3.011]
Jong Pil Yun, Min Su Kim, Gyogwon Koo, & Woosang Shin, ‘Fault Diagnosis and Analysis Based on Transfer Learning and Vibration Signals,’ IEMEK Journal of Embedded Systems and Applications, VOL. 14, NO. 6, 2019, pp. 287-294.
Yeo Chan Yoon & Soo Kyun Kim, ‘Trends and Prospects of Retrieval-Augmented Generation (RAG) for Generative AI,’ The Journal of Korean Association of Computer Education, VOL. 28, NO. 2, 2025, pp. 69-80. [https://doi.org/10.32431/kace.2025.28.2.007]
Cheonsu Jeong, ‘Generative AI Service Implementation Using LLM Application Architecture: Based on RAG Model and LangChain Framework,’ Journal of Intelligence and Information Systems, VOL. 29, NO. 4, 2023, pp. 129-164.
Yun-Jin Jang, Sung-Gwan Seo, Gi-Seung Lee, & HoiJin Yoon, ‘Development of a Long-Term Memory-Based Chatbot System Using Vector Database,’ Journal of Artificial Intelligence Convergence Technology, VOL. 4, NO. 4, 2024, pp. 125-130.
이종구, ‘다중회귀분석방법을 이용한 디바이스 수명예측에 관한 연구,’ 광운대학교 대학원 석사학위논문, 1996.
International Organization for Standardization, Condition Monitoring and Diagnostics of Machines — Prognostics — Part 1: General Guidelines, ISO 13381-1:2015, 2015.