논문 상세보기
pp.13-24
PURPOSES : For most local governments, including that of Gangwon-do, the establishment of an organized pavement management system is insufficient, resulting in problems such as inefficient distribution and use of maintenance budgets for deteriorated road pavements. In this study, we aimed to contribute to the establishment of a more reasonable road maintenance strategy by developing a model for predicting the annual international roughness index (IRI) change for national highway asphalt pavements in Gangwon-do based on big data analysis.
METHODS : Data on independent and dependent variables used for model development were collected. The collected data were subjected to exploratory data analysis (EDA) and data preprocessing. Independent variable candidates were selected to reduce multicollinearity through correlation analysis and specific conditions. A final model was selected, and sensitivity analysis was performed.
RESULTS : The final model that predicts annual IRI change uses independent variables such as annual temperature range, minimum temperature, freeze-thaw days, IRI, surface distress (SD), and freezing days. The sensitivity analysis confirmed that the annual IRI change was affected in the order of annual temperature range, minimum temperature, freeze-thaw days, IRI, SD, and freezing days.
CONCLUSIONS : Road maintenance can be performed rationally by predicting future pavement conditions using the model developed in this study. The accuracy of the prediction model can be improved if additional data, such as material properties and pavement thickness, are obtained in future studies.
1. 서론
1.1. 연구배경
1.2. 연구목적 및 방법
2. 데이터 수집 및 탐색적 데이터 분석
2.1. 공용성 데이터
2.2. 영향인자 데이터
3. 데이터 전처리 및 변수 후보군 선정
3.1. 데이터 전처리
3.2. 상관성 분석을 통한 변수 선정
4. 예측모형 개발
4.1. 후보모형 개발
4.2. 최종모형 선정 및 분석
5. 결론
REFERENCES
