نوع مقاله : علمی - پژوهشی
نویسندگان
1 دانشجوی دکتری، دانشگاه صنعتی نوشیروانی بابل، ایران
2 استاد، دانشگاه صنعتی نوشیروانی بابل، ایران
3 استاد، دانشگاه صنعتی نوشیروانی بابل، بابل، ایران
4 دانشیار ، دانشگاه مازندران، بابلسر، ایران
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
In recent decades, construction of massive structures has increased around the world. These structures which are built for different purposes, should have a useful life-time. Therefore, composite structures can increase the construction costs and useful life of such structures. Therefore, CFDST members can practically increase the efficiency of composite structures. Since the diameter and thickness of the outer tube have the greatest impact on determining the bearing capacity of CFDST columns, this study investigated four different values of D/t for the outer tube including 86, 85.8, 45.6 and 44. Two types of concrete were used to fill CFDST samples including C10 and C20. Besides, a comprehensive formula for estimating the bearing capacity of CFDST columns using artificial intelligence methods is proposed. The results showed that CFDST columns with lower Do / to value have higher load capacity and with increasing Do / to, it is observed that the ductility decreases. As a comparison between the filled concretes in CFDST samples of C10 and C20 grades, the stress-strain curves have shown that with increasing compressive strength, the bearing capacity for CFDST columns increased by about 6%. In the modeling section, the R2 for artificial neural network (ANN), support vector machines (SVM) and model tree (M5-MT) in the testing stage were determined to be 0.95, 0.96 and 0.97, respectively. Accordingly, the M5-MT method in the testing stage, had a better performance than other proposed methods for estimating the bearing capacity of CFDST columns. Comparison of traditional equations and AI models in estimating the bearing capacity of CFDST columns show that the formula presented by M5-MT with an average value of 1.01 and a standard deviation of 0.19 It has performed better in modeling the bearing capacity of CFDST columns than other intelligent models and traditional relationships.
کلیدواژهها [English]