Browse Bar: Browse by Author | Browse by Category | Browse by Citation | Advanced Search
Author(s): Ganapathy, C. | Idichandy, V.G. | Mangal, L. |
Year: 1996
Citation: APPLIED OCEAN RESEARCH Volume: 18 Issue: 2-3 Pages: 137-143
Abstract: A novel scheme using artificial neural networks to automate the vibration monitoring method of detecting the occurrence and location of damage in offshore jacket platforms is presented. A multiple neural network system is adopted which enables the problem to be decomposed into smaller ones, facilitating easier solution. An adaptive resonance theory (ART) neural network is used for damage diagnosis and its advantages and limitations are investigated. A comparison between a back-propagation network and an ART network is presented. The adaptability of ART for on-line monitoring is explored for possible adaptation to monitor offshore platforms in service. The system developed is tested using data from a finite-element analysis of a scale model of a jacket platform.
Topics:
Machine Learning,
Applications:
Industrial Control,
Remote Sensing,
Models:
ART 2 / Fuzzy ART,
