A Novel Damage Identification Method for Steel Catenary Risers Based on a Novel CNN-GRU Model Optimized by PSO

• Published in: Journal of marine science and engineering Vol. 11; no. 1; p. 200
• Main Authors: Liu, Zhongyan, Mei, Jiangtao, Wang, Deguo, Guo, Yanbao, Wu, Lei
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.01.2023
• Subjects: Acceleration; Artificial intelligence; Artificial neural networks; Bending stresses; Big Data; Catenaries; Catenary; Connecting; convolutional neural network; Damage detection; damage identification; Deep learning; gated recurrent unit; Geospatial data; Heuristic; hyperparameters; Identification; Identification methods; Mathematical optimization; Metal fatigue; Methods; Neural networks; Offshore; Offshore platforms; Optimization algorithms; Parameter identification; Particle swarm optimization; Risers; Spatial data; Steel; steel catenary riser; Steel pipes; Steel structures; Submarine pipelines; Time series; Underwater pipelines; Underwater structures; Work platforms

As a new type of riser connecting offshore platforms and submarine pipelines, steel catenary risers (SCRs) are generally subject to waves and currents for a long time, thus it is significant to fully evaluate the SCR structure’s safety. Aiming at the damage identification of the SCR, the acceleratio...