1. Vibration-Response-Only Structural Health Monitoring for Offshore Wind Turbine Jacket Foundations via Convolutional Neural Networks
- Author
-
Christian Tutivén, Bryan Puruncajas, Yolanda Vidal, Universitat Politècnica de Catalunya. Doctorat en Automàtica, Robòtica i Visió, Universitat Politècnica de Catalunya. Departament de Matemàtiques, and Universitat Politècnica de Catalunya. CoDAlab - Control, Modelització, Identificació i Aplicacions
- Subjects
Computer science ,020209 energy ,convolutional neural network ,02 engineering and technology ,lcsh:Chemical technology ,Biochemistry ,Convolutional neural network ,Turbine ,Article ,Analytical Chemistry ,damage detection ,damage identification ,0202 electrical engineering, electronic engineering, information engineering ,Parcs eòlics marins ,lcsh:TP1-1185 ,Electrical and Electronic Engineering ,Instrumentation ,signal-to-image conversion ,structural health monitoring ,Condition monitoring ,Wind turbines -- Aerodynamics ,Matemàtiques i estadística [Àrees temàtiques de la UPC] ,jacket ,021001 nanoscience & nanotechnology ,Atomic and Molecular Physics, and Optics ,Offshore wind power plants ,offshore wind turbine foundation ,Identification (information) ,Offshore wind power ,Test set ,Structural health monitoring ,Aerogeneradors -- Aerodinàmica ,0210 nano-technology ,Marine engineering - Abstract
This work deals with structural health monitoring for jacket-type foundations of offshore wind turbines. In particular, a vibration-response-only methodology is proposed based on accelerometer data and deep convolutional neural networks. The main contribution of this article is twofold: (i) a signal-to-image conversion of the accelerometer data into gray scale multichannel images with as many channels as the number of sensors in the condition monitoring system, and (ii) a data augmentation strategy to diminish the test set error of the deep convolutional neural network used to classify the images. The performance of the proposed method is analyzed using real measurements from a steel jacket-type offshore wind turbine laboratory experiment undergoing different damage scenarios. The results, with a classification accuracy over 99%, demonstrate that the stated methodology is promising to be utilized for damage detection and identification in jacket-type support structures.
- Published
- 2020