Abstract
Mooring line breakage of a moored offshore Floating Production Storage and Offloading (FPSO) platform results in an increased load on the remaining lines, worsening their degradation rates. Furthermore, a line break causes the FPSO to change its motions and move away from the desired location. In addition, platform motions differ depending on its draft and environmental conditions, making it difficult to detect mooring line failure. In this paper, we propose a system based on machine learning called Neural Motion Estimator (NeMo) composed of (i) a multilayer perceptron network capable of forecasting the horizontal motions of a FPSO with 18 mooring lines under 14 draft configurations, from ballasted (8 meters) to full load (21 meters), and (ii) a multinomial logistic regression classifier that provides the associated probability of failure for each line group in the mooring system. The results of several tests show that NeMo was able to identify the occurrence of line breakage in all draft configurations with a minimum percentage of false classification.