Mục đích của nghiên cứu này là sử dụng hệ thống suy luận thần kinh mờ thích ứng (ANFIS) kết hợp thuật toán giải thuật di truyền (GA) để dự đoán độ kim lún và điểm hóa mềm của nhựa đường biến tính GO. | Journal of Science and Transport Technology University of Transport Technology Artificial intelligence approach to predict the penetration and softening point of graphene oxide modified asphalt Hoang Thi Huong Giang Nguyen Hoang Long Le Thanh Hai Le Nho Thien Vu The Thuan 1Universityof Transport Technology No 54 Trieu Khuc Thanh Xuan Hanoi 100000 Vietnam Article info Abstract Penetration and softening point are the two most important criteria Type of article for classifying asphalt grades according to penetration. The determination of Original research paper these two parameters of modified asphalt graphene oxide GO by experimental method encountered certain difficulties due to the high cost of Corresponding author GO and long experimental time. The purpose of this study is to use the E-mail address adaptive neuro-fuzzy inference system ANFIS combined with the genetic gianghth @ algorithm GA to predict the penetration and softening point of GO modified asphalt. Two datasets including the penetration dataset 122 samples Received softening point dataset 130 samples collected from 12 different studies with 9 November 29 2021 input parameters are used to construct and test the data digital simulation Accepted tool. In addition the study uses a 10-fold cross-validation technique along with December 17 2021 statistical criteria such as correlation coefficient R and root of mean square Published error RMSE to evaluate the performance of the models. The research results December 28 2021 show that for the penetration dataset the ANFIS-GA model has RMSE mm R the ANFIS model has RMSE mm R . For the softening point dataset the ANFIS-GA model has RMSE oC R the ANFIS model has RMSE oC R . This shows that both ANFIS-GA and ANFIS models have good predictive performance and high accuracy. With smaller RMSE and higher R in both datasets the ANFIS-GA model is evaluated to be better than ANFIS. This model can completely
