返回Google圖書搜尋

Development of Roughness Index Model For Urban Roads Using Machine Learning Techniques and Prioritizing Using MCDM Techniques

出版	SSRN, 2022
URL	http://books.google.com.hk/books?id=I-ngzwEACAAJ&hl=&source=gbs_api

註釋It is important to first evaluate the existing flexible pavement condition to select the improvement strategy that will be utilized to improve the quality of the flexible pavement. As a result of many distinct pavement deterioration features, roughness presents itself as cracking, potholes, ravelling, patching, edge break, and rutting. Using machine learning techniques such as Artificial Neural Network (ANN) and Support Vector Machine (SVM) in MATLAB, an attempt was made to establish a relationship between road roughness and other surface distresses on an urban flexible pavement in this study. Accordingly, distress data is collected for every 100m on the selected stretch and bump integrator, which was calibrated with MERLIN is used for obtaining roughness data. A regression equation is developed with the IRI value and the distreses based on the data collected the IRI value and the distresses is created based on the data collected. MCDM techniques like VIKOR and TOPSIS are used for prioritizing the chainages along the stretch to carry out maintenance strategies.