TimoDS: A comprehensive and synthetically generated dataset of Timoshenko steel beams with general elastic supports and responses to elementary unit load cases

TimoDS is a synthetically generated dataset of 60,000 Timoshenko steel beam instances with general elastic supports, intended as a training and benchmarking resource for machine learning applications in structural engineering. Each instance corresponds to a fully defined linear static beam problem characterized by a beam length, a European steel cross-section from the IPE, HEA or HEB profile families, and twelve elastic support stiffness parameters spanning the full continuum from free to quasi-clamped boundary conditions. Six elementary unit load cases are provided independently for each instance, enabling the reconstruction of responses to arbitrary loading distributions via superposition. The dataset is distributed as two CSV files: input_data_TimoDS.csv (sampling parameters) and beam_results_TimoDS.csv (structural responses). The data generation pipeline is available at https://github.com/yourusername/TimoDS_pipeline.