首页|Civil Engineering Department Researchers Add New Data to Research in Machine Lea rning (Comparative Analysis of Shear Strength Prediction Models for Reinforced C oncrete Slab-Column Connections)
Civil Engineering Department Researchers Add New Data to Research in Machine Lea rning (Comparative Analysis of Shear Strength Prediction Models for Reinforced C oncrete Slab-Column Connections)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on ar tificial intelligence. According to news originating from the Civil Engineering Department by NewsRx editors, the research stated, "This research focuses on a c omprehensive comparative analysis of shear strength prediction in slab-column co nnections, integrating machine learning, design codes, and finite element analys is (FEA)." Our news journalists obtained a quote from the research from Civil Engineering D epartment: "The existing empirical models lack the influencing parameters that d ecrease their prediction accuracy. In this paper, current design codes of Americ an Concrete Institute 318-19 (ACI 318-19) and Eurocode 2 (EC2), as well as innov ative approaches like the compressive force path method and machine learning mod els are employed to predict the punching shear strength using a comprehensive da tabase of 610 samples. The database consists of seven key parameters including s lab depth (ds), column dimension (cs), shear span ratio (av/d), yield strength o f longitudinal steel (fy), longitudinal reinforcement ratio (rl), ultimate load- carrying capacity (Vu), and concrete compressive strength (fc). Compared with th e design codes and other machine learning models, the particle swarm optimizatio n-based feedforward neural network (PSOFNN) performed the best predictions. PSOF NN predicted the punching shear of flat slab with maximum accuracy with R2 value of 99.37% and least MSE and MAE values of 0.0275% a nd 1.214%, respectively. The findings of the study are validated th rough FEA of slabs to confirm experimental results and machine learning predicti ons that showed excellent agreement with PSOFNN predictions."
NETL
NSTL
