DOI QR코드

DOI QR Code

Development of Noise and AI-based Pavement Condition Rating Evaluation System

소음도·인공지능 기반 포장상태등급 평가시스템 개발

  • Han, Dae-Seok (Korea Institute of Civil Engineering & Building Technology) ;
  • Kim, Young-Rok (Korea Institute of Civil Engineering & Building Technology)
  • 한대석 (한국건설기술연구원 노후인프라센터, 복합재난대응연구센터) ;
  • 김영록 (한국건설기술연구원 노후인프라센터, 복합재난대응연구센터)
  • Received : 2020.11.12
  • Accepted : 2021.01.08
  • Published : 2021.01.31

Abstract

This study developed low-cost and high-efficiency pavement condition monitoring technology to produce the key information required for pavement management. A noise and artificial intelligence-based monitoring system was devised to compensate for the shortcomings of existing high-end equipment that relies on visual information and high-end sensors. From idea establishment to system development, functional definition, information flow, architecture design, and finally, on-site field evaluations were carried out. As a result, confidence in the high level of artificial intelligence evaluation was secured. In addition, hardware and software elements and well-organized guidelines on system utilization were developed. The on-site evaluation process confirmed that non-experts could easily and quickly investigate and visualized the data. The evaluation results could support the management works of road managers. Furthermore, it could improve the completeness of the technologies, such as prior discriminating techniques for external conditions that are not considered in AI learning, system simplification, and variable speed response techniques. This paper presents a new paradigm for pavement monitoring technology that has lasted since the 1960s.

본 연구에서는 도로 포장 유지관리에 필요한 핵심정보를 생산해 낼 수 있는 저비용·고효율 포장상태 모니터링 기술을 개발하고자 하였다. 특히 시각정보와 고가 센서에 의존하는 기존 장비의 단점을 보완하기 위해 소음과 인공지능 기반의 포장상태등급 평가시스템을 고안하였다. 시스템 개발을 위한 아이디어 정립부터 기능 정의, 정보흐름 및 아키텍쳐 설계 과정을 거쳤으며, 생산된 프로토타입에 대한 성능 검증과 활용 전주기에 대한 실증 평가를 수행하였다. 그 결과, 높은 수준의 인공지능 평가 신뢰도가 확보되었으며, 하드웨어와 소프트웨어적 요소 외에도 시스템 활용에 관한 짜임새 있는 가이드라인이 개발되었다. 또한 현장평가 과정을 통해 비전문가도 쉽고 빠른 조사와 분석이 가능하고, 직관적인 시각적 정보 제공을 통해 관리자의 업무 지원이 가능함도 확인하였다. 반면에 학습에 고려되지 않은 외부 조건에 대한 선행 판별 기술, 시스템 간소화, 가변 주행속도 대응 기술 등 기술의 완성도 제고도 필요함을 알 수 있었다. 본 연구를 시작으로 1960년대 이후 반세기 이상 지속되어온 포장상태 모니터링 기술의 새로운 패러다임이 제시되길 기대한다.

Keywords

References

  1. MOLIT(Ministry of Land, Infrastructure and Transport), Manual of Road Works, Report Number 11-1500000-001480-10, Ministry of Land, Infrastructure and Transport, Korea, pp.65, 2020.
  2. D. Han and M. Do, "Evaluation of Socio-Environmental Effects considering Road Service Levels for Transportation Asset Management", Journal of Testing and Evaluation, Vol. 44, No. 1, pp. 679-691, 2016. DOI: http://dx.doi.org/10.1520/JTE20140484
  3. MOLIT, The 1st Infrastructure Management Basic Plan(Government Notice MLOIT-2020-560), Ministry of Land, Infrastructure and Transport, Korea, p.41, 2020.
  4. ISO(International Organization for Standardization), Acoustics-Measurement of the Influence of Road Surfaces on Traffic Noise - Part 3: References tyres, International Organization for Standardization, Geneva, Switzerland, 2017.
  5. ISO, Acoustics-Measurement of the Influence of Road Surfaces on Traffic Noise-Part 2: The Close-proximity Method, International Organization for Standardization, Geneva, Switzerland, 2017.
  6. K. Kobayashi, M. Do and D. Han, "Estimation of Markovian Transition Probabilities for Pavement Deterioration Forecasting", KSCE Journal of Civil Engineering, Vol. 14, No. 3, pp.343-351, 2010. DOI:http://dx.doi.org/10.1007/s12205-010-0343-x
  7. D. Han and Y. R. Kim, "Improvement of Artificial Intelligence for Acoustic-based Pavement Condition Grade Evaluation", International Journal of Highway Engineering, Vol. 22. No. 6, pp.9-15, 2020. DOI:http://dx.doi.org/10.7855/IJHE.2020.22.6.009