Floating Offshore Wind Turbines (FOWT) are currently facing the challenge of high cost of energy. Mooring lines holding the FOWTs in the deep sea are usually exposed to harsh and dynamic wind and wave loadings, which are responsible for damage among mooring lines. The physical sensors deployed for online monitoring ultimately increase the cost of energy. This study proposes a data-driven LSTM-ANN method to classify the amount of damage among mooring lines. The Long Short-Term Memory (LSTM) network identifies patterns in platform time history responses, which the Artificial Neural Network (ANN) then uses to classify the damage levels. Due to the lack of real data, the model is trained on simulated data from the 5MW-OC4 semisubmersible model available in NREL’s OpenFast. The model achieved a classification accuracy of 90%, demonstrating its ability to learn the behaviour of platforms with mooring damage. This approach provides a cost-effective online monitoring solution and enhances the reliability and safety of FOWTs by enabling timely maintenance and reducing downtime.