국방 C5ISR 분야 품질문제의 빅데이터 분석 및 예측 모델에 대한 연구
A Study on the Big Data Analysis and Predictive Models for Quality Issues in Defense C5ISR
1
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
Purpose: The purpose of this study is to propose useful suggestions by analyzing the causal effect relationship between the failure rate of quality and the process variables in the C5ISR domain of the defense industry. Methods: The collected data through the in house Systems were analyzed using Big data analysis. Data analysis between quality data and A/S history data was conducted using the CRISP-DM(Cross-Industry Standard Process for Data Mining) analysis process. Results: The results of this study are as follows: After evaluating the performance of candidate models for the influence of inspection data and A/S history data, logistic regression was selected as the final model because it performed relatively well compared to the decision tree with an accuracy of 82%/67% and an AUC of 0.66/0.57. Based on this model, we estimated the coefficients using 'R', a data analysis tool, and found that a specific variable(continuous maximum discharge current time) had a statistically significant effect on the A/S quality failure rate and it was analysed that 82% of the failure rate could be predicted. Conclusion: As the first case of applying big data analysis to quality issues in the defense industry, this study confirms that it is possible to improve the market failure rates of defense products by focusing on the measured values of the main causes of failures derived through the big data analysis process, and identifies improvements, such as the number of data samples and data collection limitations, to be addressed in subsequent studies for a more reliable analysis model.
Abstract
Purpose: The purpose of this study is to propose useful suggestions by analyzing the causal effect relationship between the failure rate of quality and the process variables in the C5ISR domain of the defense industry. Methods: The collected data through the in house Systems were analyzed using Big data analysis. Data analysis between quality data and A/S history data was conducted using the CRISP-DM(Cross-Industry Standard Process for Data Mining) analysis process. Results: The results of this study are as follows: After evaluating the performance of candidate models for the influence of inspection data and A/S history data, logistic regression was selected as the final model because it performed relatively well compared to the decision tree with an accuracy of 82%/67% and an AUC of 0.66/0.57. Based on this model, we estimated the coefficients using 'R', a data analysis tool, and found that a specific variable(continuous maximum discharge current time) had a statistically significant effect on the A/S quality failure rate and it was analysed that 82% of the failure rate could be predicted. Conclusion: As the first case of applying big data analysis to quality issues in the defense industry, this study confirms that it is possible to improve the market failure rates of defense products by focusing on the measured values of the main causes of failures derived through the big data analysis process, and identifies improvements, such as the number of data samples and data collection limitations, to be addressed in subsequent studies for a more reliable analysis model.
참고문헌 (29)
- 최창현, "군수품의 고품질 확보를 위한 개발 품질보증 적용사례 연구", 품질경영학회지, 47(1), pp.151~162 (2019), 한국품질경영학회[DOI]
- Total Life Cycle Quality Assurance Plan to Guarantee Performance of Weapon System, "Defense Acquisition Program Administration(DAPA).", ~ (2011)
- Defense Acquisition Program Administration(DAPA)., "Establishment of MRA & TRA work guidelines", ~ (2012)
- Defense Acquisition Program Administration(DAPA)., "A Comprehensive Plan for the Defense quality to Settle the culture of Quality Management", ~ (2013)
- Defense Agency for Technology and Quality(DTaQ), "Reinforcement Plan of Quality Management for Development and Early-Stage Mass Production", DQS(Defense Quality Society)general meeting seminar (2018)
- Defense Agency for Technology and Quality(DTaQ), "Defense Agency for Technology and Quality 40Years", 140~141 (2021)
- Harper, Gavin, "Methods for mining HTS data", Drug Discovery Today, 11(15-16), pp.694~699 (2006)
- 전주호, "Gage R&R을 통한 KVMF 디스플레이 시험 방법 검증 및 개선 사례 연구", 국방품질연구논집(JDQS), 3(1), pp.37~45 (2021), 국방기술품질원[DOI]
- 전수연, "빅데이터 기반 군수품 품질정보 활용방안에 대한 연구", 한국산학기술학회논문지, 17(6), pp.315~325 (2016), 한국산학기술학회[DOI]
- 정동호, "데이터 마이닝을 이용한 리튬 이차전지의 전류밀도 영향인자 분석", 대한기계학회논문집 A, 38(6), pp.677~682 (2014), 대한기계학회
- Jin, H. S, "Big Data Analysis with R", pp.74~87 (2022), BOOK K
- Kang, J., "Understanding of the Overview of Quality 4.0 Using Text Mining", Journal of the Korean Society for Quality Management, pp.121~122 (2014)
- 김민준, "텍스트마이닝을 활용한 품질 4.0 연구동향 분석", 품질경영학회지, 51(3), pp.403~418 (2023), 한국품질경영학회[DOI]
- 김세용, "4차 산업혁명시대 스마트 강군 건설을 위한 국방 데이터의 전략적 활용 방안연구", 융합보안 논문지, 20(4), pp.113~123 (2020), 한국융합보안학회
- Kim, W. C., "Modern Statistics", pp.194~196 (2005), Young Ji Moonhwasa
- The future battlefield seen through AI : C5ISR, "Koo, E", 68~73, pp.Defense & Technology no. 528 (2023)
- 구지인, "시스템 통합 관점의 복합 무기체계 기술성숙도 평가 프레임워크 개선에 관한 연구", 한국국방기술학회 논문지, 5(2), pp.23~30 (2023), 사단법인 한국국방기술학회[DOI]
- Lee, C. H, "The Study on Improvement solution by the analysis TICN Project Secondary Battery Failure Case", The Korean Society for Quality Management Proceeding, 158 (2021)
- 이은지, "CSR·CSV·ESG 연구 동향 분석 - 빅데이터 분석을 중심으로 -", 품질경영학회지, 50(4), pp.751~776 (2022), 한국품질경영학회[DOI]
- 이재환, "국방획득 사업을 위한 빅데이터 활용 고찰", 한국방위산업학회지, 24(3), pp.1~12 (2017), 한국방위산업학회
- Matthew D. Chellin, "Proactive Obsolescence Management Methods For C5ISR Systems : Insight From Practitioners", Defense ARJ, 30(1), pp.24~44 (2023)
- 박성현, "적응적 배터리 팩 피막 저항 변화 감지를 통한 배터리스웰링 감지 기법", 전기전자학회논문지, 27(1), pp.85~92 (2023), 한국전기전자학회
- Park, Y. T, "Quality Management Theory", KSAM, 674~675 (2018)
- 서호진, "품질 4.0: 개념, 요소, 수준 평가와 전개 방향", 품질경영학회지, 49(4), pp.447~466 (2021), 한국품질경영학회[DOI]
- Seo, M. K., "A Sensitivity Analysis for the Google Applications Users: Exploring the Explanatory Power of OLS, Decision: Tree, and Neural Network Models with Big Data of International Trading", International Conference of Korea Trade Research Association, pp.799~825 (2019)
- Seo, S. H., "A Review of Data Quality Management Measures for Implementing Quality 4.0 in Defense", Proceedings of the Korean Society for Quality Management, pp.118~ (2022)
- Shearer C, "The CRISP-DM model : the new blueprint for data mining", J Data Warehousing, 5, pp.13~22 (2000)
- 신재영, "KPI 중심의 e-QMS 구현: 우주항공 및 방위 산업 사례 연구", 품질경영학회지, 51(1), pp.131~154 (2023), 한국품질경영학회[DOI]
- 윤근식, "ASRP자료를 이용한 155MM 추진장약 KM4A2 저장수명 추정 연구", 품질경영학회지, 42(3), pp.291~300 (2014), 한국품질경영학회[DOI]