Damage detection for offshore structures using long and short-term memory networks and random decrement technique

A damage detection method is presented which combines the random decrement technique (RDT) with long and short-term memory (LSTM) networks. The uses measured vibration response of offshore structures subjected to excitation able locate assess accuracy, even in noisy conditions. applicability proposed RDT-LSTM verified through a numerical example laboratory tests. consists jacket platform wave excitation. simulated cases encompass single multiple locations not only on whole segments but also local elements (one-fifth segment) structure, minor (1%–5%) severity, different noise levels. RDT applied first process data, then carried out using LSTM. After example, tests model under loading produced by shaking table. Minor major damages their combination at are discussed. Both simulation test show that has an outstanding performance structural detection.