Artificial neural network and regressed beam-column connection explicit mathematical moment-rotation expressions

Steel flush endplate beam-column connections behavior is commonly described by the moment-rotation, M-φ, relationship, which characterized two essential terms; resistant moment, Mj, Rd, and initial rotational stiffness, Sj, init. A great amount of concerted effort has been invested worldwide to either experimentally or analytically describe these properties due geometrical material variations. However, methods are costly, laborious, time-consuming. Therefore, acknowledging wealth literature information, this paper formulates a set practically convenient mathematical M-φ expressions means artificial neural network (ANN) multi-linear regression (MLR) approaches utilizing MATLAB software. Differing from most existing machine learning variants, offers explicit for maximum Mmax, init, can be through simplistic insertion input parameters in terms beam depth, width, thickness flange, web, column thickness, bolt capacity. The computed Mmax init then adopted express currently defined continuous relationship. By statistical evaluation, it witnessed that mean-absolute-percentage error (MAPE) correlation coefficient (R2) both ANN MLR remarkable prediction vitality. Also, outperforms slightly model although agree closely with source data. high reliability predicting as well characterizing relationship further engineering analysis design purposes.