Development of an IRMO-BPNN Based Single Pile Ultimate Axial Bearing Capacity Prediction Model

The ultimate axial bearing capacity (UABC) of a single pile is an important parameter in design. BP neural network (BPNN) has strong nonlinear mapping ability and can effectively predict the UABC pile. However, frequent immersion unstable search results with local vibration leads BPNN to less usable solution. weights biases model are optimized using improved radial movement optimization (IRMO) algorithm this study, new method named IRMO-BP (IRMO-BPNN) proposed IRMO-BPNN was developed from database 196 static load test (SLT) samples, hyper-parameter analysis carried out determine optimal number hidden nodes, population size, iterations. prediction accuracy stability verified by comparing it GA-based ANN model, ANFIS-GMDH-PSO RBFANN model. show that accurately improves situation easy fall into values its unstable. significant advantages over other models.