디지털 유지관리를 위한 데이터 기반 교량 신축이음 유간 평가
Evaluation of Data-based Expansion Joint-gap for Digital Maintenance
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
신축이음 장치는 교량 상부구조의 신축량을 수용할 목적으로 설치되며 공용중 충분한 유간을 확보하여야 한다. 안전점검 및 정밀안전진단 수행 시 유간부족 및 유간과다에 대한 손상을 명시하고 있으나, 유간에 따른 교량의 이상 거동을 판별하기 위한 기준이 미흡하다. 본연구에서는 동일 신축이음부의 유간 데이터를 지속적으로 추적하여 데이터 기반의 유지관리 방안을 제시하였다. 689개소의 신축이음 장치에서 계절별 영향을 고려하여 총 2,756개의 유간 데이터를 수집하였다. 동일 위치에서 4개 이상의 데이터를 통해 신축거동을 분석할 수 있는 유간변화 평가 방안을 마련하였으며, 신축거동에 영향을 미치는 인자를 분류하고 딥러닝과 설명 가능한 AI를 통해 각 인자의 영향도를 분석하였다. 유간 평가 그래프를 통해 교량 상부구조의 이상 거동을 협착 및 기능 고장으로 분류하였다. 이론적 거동을 보이고 있다하더라도 협착 가능성이나타날 수 있는 사례 및 하절기 협착 가능성이 매우 높게 나타난 사례가 도출되었다. 협착 가능성은 낮으나 교량 상부구조에 기능상 문제점이발생했을 가능성이 높은 사례와 시공오류에 따라 신축이음 장치가 재시공된 사례도 도출되었다. 딥러닝 및 설명 가능한 AI를 통한 영향인자 분석은 기존의 신축유간 계산식 및 교량 설계에 따른 결과로 설명 가능하여 신뢰 가능한 수준으로 판단되어 추후 모델의 개선을 통해 유지관리를위한 가이드를 제시할 수 있을 것이라 판단된다.
Abstract
The expansion joint is installed to offset the expansion of the superstructure and must ensure sufficient gap during its service life. In detailed guideline of safety inspection and precise safety diagnosis for bridge, damage due to lack or excessive gap is specified, but there are insufficient standards for determining the abnormal behavior of superstructures. In this study, a data-based maintenance was proposed by continuously monitoring the expansion-gap data of the same expansion joint. A total of 2,756 data were collected from 689 expansion joint, taking into account the effects of season. We have developed a method to evaluate changes in the expansion joint-gap that can analyze the thermal movement through four or more data at the same location, and classified the factors that affect the superstructure behavior and analyze the influence of each factor through deep learning and explainable artificial intelligence(AI). Abnormal behavior of the superstructure was classified into narrowing and functional failure through the expansion joint-gap evaluation graph. The influence factor analysis using deep learning and explainable AI is considered to be reliable because the results can be explained by the existing expansion gap calculation formula and bridge design.
참고문헌 (14)
- Ministry of Land, Infrastructure and Transport, "KCS 24 40 10 Expansion Joint", Korea Road Association, 1~6 (2023)
- Detailed Guidelines for the Safety and Maintenance of Facilities (Part of Safety Inspection and Precise Safety Diagnosis for Bridge), "Ministry of Land, Infrastructure and Transport", Korea Authority of Land & Infrastructure Safety, 1~18 (2023)
- Research of Proper Construction and Management for Bridge Expansion Joints, "Korea Expressway Corporation Research Institute", Korea Expressway Corporation Research Institute, 1~202 (2020)
- Choi, J. W., "A Case Study on the Maintenance of Bridge that Abutment and Deck are Jammed", Proceedings of Korea Institute for Structural Maintenance and Inspection, pp.210~ (2022), Korea Institute for Structural Maintenance and Inspection
- Jung, H. J., "Correlation Analysis between Damage of Expansion Joints and Response of Deck in RC Slab Bridges", Journal of Korea Institute for Structural Maintenance and Inspection, 25(6), pp.245~253 (2021)
- Choi, H. H., "Empirical analysis of Influencing Factors using Bridge Expansion Joint-gap Data", Proceedings of Korea Institute for Structural Maintenance and Inspection, pp.161~162 (2020), Korea Institute for Structural Maintenance and Inspection
- Hornik, K., "Multilayer Feedforward Networks Universal Approximators", Neural Networks, 2(5), pp.359~366 (1989), Elsevier
- Maintenance strategy for bridge expansion joint gap variation, "Korea Expressway Corporation Research Institute", Korea Expressway Corporation Research Institute, 1~51 (2024)
- Park, J. H., "A Suggestion on Bridge Maintenance by Evaluating Expansion Joint-gap", Proceedings of Korea Institute for Structural Maintenance and Inspection (2024), Korea Institute for Structural Maintenance and Inspection
- Glorot, X., "Understanding the difficulty of training deep feedforward neural networks", Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS), Proceedings of Machine Learning Research, pp.249~256 (2010)
- Štrumbelj, E, "An Efficient Explanation of Individual Classifications using Game Theory", Journal of Machine Learning Research, 11, pp.1~18 (2010)
- Lundberg, S. M., "A Unified Approach to Interpreting Model Predictions", 31st Conference on Neural Information Processing Systems (NIPS 2017), pp.4768~4777 (2017)
- Song, Y. J., "Analysis of load-bearing capacity factors of textilereinforced mortar using multilayer perceptron and explainable artificial intelligence", Construction and Building Materials, 363, pp.129560~ (2023), Elsevier
- Neyman, J., "On the Two Different Aspects of the Representative Method: The Method of Stratified Sampling and the Method of Purposive Selection", Journal of the Royal Statistical Society, 97(4), pp.558~625 (1934), Oxford University Press