Redfish API와 BIT 정보 융합 기반 서버류 장비 CBM+ 적용 방안 연구

원선주¹^{, *} ; 박병호¹ ; 박경덕² ; 조일훈² ; 김영선³ ; 김민³

1LIG 디펜스앤에어로스페이스 미래전장IPS연구소 선임연구원
2LIG 디펜스앤에어로스페이스 미래전장IPS연구소 수석연구원
3네모시스㈜ 신뢰성 연구팀 책임

Study on CBM+ Application for Server-Class Equipment Based on Redfish API and BIT Data Fusion

Sun-Ju Won¹^{, *} ; Byeongho Bak¹ ; Kyoung-Deok Park² ; Il-Hoon Cho² ; Young-Seon Kim³ ; Min Kim³

1Research engineer, Future Warfare Integrated Product Support R&D, LIG Defense&Aerospace
2Chief research engineer, Future Warfare Integrated Product Support R&D, LIG Defense&Aerospace
3Principal researcher, Reliability Research Group, Nemosys Co., Ltd.

Correspondence to: *Sun-Ju Won 20, Daewangpangyo-ro 851beon-gil, Sujeong-gu, Seongnam-si, Gyeonggi-do, Republic of Korea Tel: +82-31-8038-0439 E-mail: sunju.won@ligdna.com

초록

본 연구는 해군 무기체계에 적용되는 COTS 기반 랙마운트형 서버류 장비의 CBM+ 적용 방안을 제안한다. 고성능 서버는 평시 낮은 자원 사용률과 오버 프로비저닝 특성으로 인해 고장 데이터가 부족하고, 고장 직전까지 상태지표가 정상 범위에 머무를 수 있다. 이에 Redfish API 기반 하드웨어 상태정보와 체계 고유 BIT 정보를 융합하고, LSTM-autoencoder 기반 이상감지, Bayesian LSTM 기반 RUL 산출, 운용자 피드백 기반 모델 보정 절차를 제시하였다.

Abstract

This study proposes a CBM+ application framework for COTS-based rack-mounted server-class equipment in naval weapon systems. The proposed framework integrates Redfish-based hardware telemetry and system-specific BIT data and employs LSTM-AE-based anomaly detection, Bayesian LSTM-based RUL estimation, and operator-feedback-based model calibration.

Keywords:

CBM+, Redfish API, BIT, LSTM-AE, RUL, Human-in-the-Loop

키워드:

상태기반정비 플러스, 레드피시 API, 자체고장진단, 장단기 메모리 오토인코더, 잔여수명, 운용자 참여형

References

U.S. Department of Defense, DoD Instruction 5000.88: Engineering of Defense Systems, November 18, 2020.
Office of the Under Secretary of Defense for Research and Engineering, Implementing a Modular Open Systems Approach in Department of Defense Programs, 2025.
DMTF, Redfish Specification, DSP0266 Version 1.24.0, Distributed Management Task Force, 2026.
DMTF, Redfish Data Model Specification, DSP0268, Distributed Management Task Force, 2026.
DMTF, Redfish Resource and Schema Guide, DSP2046 Version 1, Distributed Management Task Force, 2026.
ISO, ISO 13374-3:2012, Condition Monitoring and Diagnostics of Machines - Data Processing, Communication and Presentation - Part 3: Communication, 2012.
Jin Eun Jeong & Gyunghyun Choi, ‘On the Study of the Establishment of Condition Based Maintenance System for Weapon Systems,’ Asia-Pacific Journal of Convergent Research Interchange, VOL. 10, NO. 6, 2024, pp. 65-83. [https://doi.org/10.47116/apjcri.2024.06.06]
Andrew K. S. Jardine, Daming Lin, & Dragan Banjevic, ‘A Review on Machinery Diagnostics and Prognostics Implementing Condition-Based Maintenance,’ Mechanical Systems and Signal Processing, VOL. 20, NO. 7, 2006, pp. 1483-1510. [https://doi.org/10.1016/j.ymssp.2005.09.012]
N. M. Vichare & M. G. Pecht, ‘Prognostics and Health Management of Electronics,’ IEEE Transactions on Components and Packaging Technologies, VOL. 29, NO. 1, 2006, pp. 222-229. [https://doi.org/10.1109/TCAPT.2006.870387]
Fei Tony Liu, Kai Ming Ting, & Zhi-Hua Zhou, ‘Isolation Forest,’ Proceedings of the 8th IEEE International Conference on Data Mining, Pisa, Italy, December 2008, pp. 413-422. [https://doi.org/10.1109/ICDM.2008.17]
Pankaj Malhotra, Anusha Ramakrishnan, Gaurangi Anand, Lovekesh Vig, Puneet Agarwal, & Gautam Shroff, ‘LSTM-Based Encoder-Decoder for Multi-Sensor Anomaly Detection,’ arXiv:1607.00148, , 2016.
Pankaj Malhotra, Vishnu TV, Anusha Ramakrishnan, Gaurangi Anand, Lovekesh Vig, Puneet Agarwal, & Gautam Shroff, ‘Multi-Sensor Prognostics using an Unsupervised Health Index Based on LSTM Encoder-Decoder,’ arXiv:1608.06154, , 2016.
Thamo Sutharssan, Stoyan Stoyanov, Chris Bailey, & Chunyan Yin, ‘Prognostic and Health Management for Engineering Systems: A Review of the Data-Driven Approach and Algorithms,’ The Journal of Engineering, VOL. 2015, NO. 7, 2015. [https://doi.org/10.1049/joe.2014.0303]
Yarin Gal & Zoubin Ghahramani, ‘Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning,’ in Proceedings of the 33rd International Conference on Machine Learning, 2016, pp. 1050-1059.
James Bergstra & Yoshua Bengio, ‘Random Search for Hyper-Parameter Optimization,’ Journal of Machine Learning Research, VOL. 13, 2012, pp. 281-305.
Jasper Snoek, Hugo Larochelle, & Ryan P. Adams, ‘Practical Bayesian Optimization of Machine Learning Algorithms,’ Advances in Neural Information Processing Systems 25, 2012.
Office of the Secretary of Defense, Condition Based Maintenance Plus DoD Guidebook, U.S. Department of Defense, 2008.
Yong Kim, Daewoong Kim, & Dohyeon Jeong, ‘Feasibility and Foundational Elements of CBM+ Technology Application in Weapon Systems,’ Journal of Advances in Military Studies, VOL. 7, NO. 2, 2024, pp. 29-54. [https://doi.org/10.37944/jams.v7i2.243]
Jong-Moon Rhee, Dong-Ju Jeon, Yonggeun Kim, & So-Jung Kim, ‘The Operational Availability Improvement Based on PMS & CBM+ Strategy,’ Journal of the Korea Academia-Industrial Cooperation Society, VOL. 25, NO. 6, 2024, pp. 246-252. [https://doi.org/10.5762/KAIS.2024.25.6.246]
Younho Lee, Seongmok Kim, Ji-Won Kim, Jae-Woo Jung, Jung-Won Park, & Yong Soo Kim, ‘A Study on Method for Applying CBM+ in Missile for Effective Health Management,’ Journal of the KIMST, VOL. 27, NO. 2, 2024, pp. 294-303. [https://doi.org/10.9766/KIMST.2024.27.2.294]