نوع مقاله : مقاله پژوهشی
نویسندگان
1 دانشگاه صنعتی خواجه نصیرالدین طوسی-دانشکده مهندسی عمران
2 شهرداری قم، قم، ایران
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
The dynamic modulus (|E*|) and phase angle (φ) are key parameters for describing the viscoelastic performance of asphalt mixtures. However, their experimental evaluation involves lengthy testing and costly laboratory procedures. To overcome these limitations, several predictive models have been introduced, among which the Witczak and Hirsch models are the most recognized. In recent years, machine learning (ML) techniques have gained attention in engineering applications due to their strong capabilities in data analysis, optimization, and prediction. This study introduces the K-Nearest Neighbors (KNN) algorithm as an ML-based method to estimate the viscoelastic behavior of asphalt mixtures. The model was trained and validated using an extensive dataset comprising bitumen characteristics, volumetric parameters, and measured values of dynamic modulus and phase angle at various temperatures and loading frequencies, totaling over 5500 data points. The results demonstrate that the proposed ML model provides high prediction accuracy and represents a promising alternative for estimating the viscoelastic properties of asphalt mixtures.
کلیدواژهها [English]
)