Open AccessAutomatic Classification of Coarse Aggregate Particle Size Based on Light Gradient Boost Machine
Author(s) -
Lili Pei,
Tao Yu,
Ruichi Ma,
Wei Li,
Xin Hao
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/693/1/012040
Subject(s) - aggregate (composite) , computer science , artificial intelligence , pattern recognition (psychology) , contextual image classification , particle (ecology) , image (mathematics) , materials science , geology , composite material , oceanography
Aggregate plays an important role in the performance of asphalt mixture. In order to complete the intelligent online monitoring of asphalt aggregate quality, an automatic classification algorithm for coarse aggregate particle size based on LightGBM classification algorithm is proposed. Firstly, OpenCV is used to extract the two-dimensional morphological features of coarse aggregates, and then the correlation between these features and the classification of aggregates is analyzed. Finally, the accurate classification of coarse aggregate particles is achieved through grid search and cross-validation optimization model. The results show that the average classification precision of coarse aggregate can reach 84.7%. Compared with the classification method based only on image processing technology, the precision is increased by about 20%, and the efficiency of classification is greatly improved.