Sequence-based modeling of deep learning with LSTM and GRU networks for structural damage detection of floating offshore wind turbine blades

Abstract This paper proposes and tests a sequence-based modeling of deep learning (DL) for structural damage detection of floating offshore wind turbine (FOWT) blades using Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural networks. The complete framework was developed with four different designs of deep networks using unidirectional or bidirectional layers of LSTM and GRU networks. These neural networks, specifically developed to learn long-term and short-term dependencies within sequential information such as time-series data, are successfully trained with the sensor signals of damaged FOWT. The sensor data were simulated due to the limited availability of field data from damaged FOWTs using multiple computational methods previously validated with experimental tests. The simulations accounted for the damage scenarios with various intensities, locations, and damage shapes, totaling 1,320 damage scenarios. Both the presence of damage and its location were detected up to an accuracy of 94.8% using the best performing model of the selected network when tested for independent signals. The K-fold cross-validation accuracy of the selected network is estimated to be 91.7 %. The presence of damage itself was detected with an accuracy of 99.9% based on the cross-validation regardless of the damage location. Structural damage detection using deep learning is not restricted by the assumptions of the systems or the environmental conditions as the networks learn the system directly from the data. The framework can be applied to various types of civil and offshore structures. Furthermore, the sequence-based modeling enables engineers to harness the vast amounts of digital information to improve the safety of structures.

[1]  Aleksandar Pavic,et al.  Modal Testing of Tamar Suspension Bridge , 2006 .

[2]  Raimund Rolfes,et al.  Damage and ice detection on wind turbine rotor blades using a three-tier modular structural health monitoring framework , 2018 .

[3]  Jürgen Schmidhuber,et al.  Learning to forget: continual prediction with LSTM , 1999 .

[4]  Hoon Sohn,et al.  Crack detection technique for operating wind turbine blades using Vibro-Acoustic Modulation , 2014 .

[5]  Mahmoud El-Kafafy,et al.  Monitoring Changes in the Soil and Foundation Characteristics of an Offshore Wind Turbine Using Automated Operational Modal Analysis , 2013 .

[6]  Jason Jonkman,et al.  New Developments for the NWTC's FAST Aeroelastic HAWT Simulator: Preprint , 2004 .

[7]  Daoyi Chen,et al.  Developments in semi-submersible floating foundations supporting wind turbines: A comprehensive review , 2016 .

[8]  M. Hand,et al.  2013 Cost of Wind Energy Review , 2015 .

[9]  Peng Qian,et al.  Integrated data-driven model-based approach to condition monitoring of the wind turbine gearbox , 2017 .

[10]  Roham Rafiee,et al.  Simulation of fatigue failure in a full composite wind turbine blade , 2006 .

[11]  Hamid Reza Karimi,et al.  Data-driven design of robust fault detection system for wind turbines , 2014 .

[12]  A. Goupee,et al.  Experimental Comparison of an Annular Floating Offshore Wind Turbine Hull Against Past Model Test Data , 2020 .

[13]  John Langford,et al.  Beating the hold-out: bounds for K-fold and progressive cross-validation , 1999, COLT '99.

[14]  Zijun Zhang,et al.  Wind Turbine Blade Breakage Monitoring With Deep Autoencoders , 2018, IEEE Transactions on Smart Grid.

[15]  M. Stone Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[16]  R. Dwight,et al.  Data-driven turbulence modeling for wind turbine wakes under neutral conditions , 2020, Journal of Physics: Conference Series.

[17]  Wout Weijtjens,et al.  CLASSIFYING RESONANT FREQUENCIES AND DAMPING VALUES OF AN OFFSHORE WIND TURBINE ON A MONOPILE FOUNDATION FOR DIFFERENT OPERATIONAL CONDITIONS , 2014 .

[18]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[19]  Maurizio Collu,et al.  Operational Modal Analysis of a Spar-Type Floating Platform Using Frequency Domain Decomposition Method , 2016 .

[20]  Thomas G. Dietterich Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms , 1998, Neural Computation.

[21]  M.H. Hassoun,et al.  Fundamentals of Artificial Neural Networks , 1996, Proceedings of the IEEE.

[22]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[23]  Wenjing Hu,et al.  Anomaly detection and fault analysis of wind turbine components based on deep learning network , 2018, Renewable Energy.

[24]  Ruqiang Yan,et al.  Learning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks , 2017, Sensors.

[25]  G. Bir,et al.  User's Guide to BModes (Software for Computing Rotating Beam-Coupled Modes) , 2005 .

[26]  I. Johnstone,et al.  Ideal spatial adaptation by wavelet shrinkage , 1994 .

[27]  Özal Yildirim,et al.  A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification , 2018, Comput. Biol. Medicine.

[28]  Zhiyong Cui,et al.  Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction , 2018, ArXiv.

[29]  Manu Thomas,et al.  Automatic ECG arrhythmia classification using dual tree complex wavelet based features , 2015 .

[30]  Jason Jonkman,et al.  Validation of a FAST semi-submersible floating wind turbine numerical model with DeepCwind test data , 2013 .

[31]  Sung-Hoon Ahn,et al.  Condition monitoring and fault detection of wind turbines and related algorithms: A review , 2009 .

[32]  Carlo Rainieri,et al.  Operational Modal Analysis of Civil Engineering Structures: An Introduction and Guide for Applications , 2014 .

[33]  Filipe Magalhães,et al.  Operational modal analysis for testing and monitoring of bridges and special structures , 2010 .

[34]  Yoshua Bengio,et al.  No Unbiased Estimator of the Variance of K-Fold Cross-Validation , 2003, J. Mach. Learn. Res..

[35]  Christof Devriendt,et al.  Experimental and computational damping estimation of an offshore wind turbine on a monopile foundation , 2013 .

[37]  Moo-Hyun Kim,et al.  Structural health monitoring of towers and blades for floating offshore wind turbines using operational modal analysis and modal properties with numerical-sensor signals , 2019, Ocean Engineering.

[38]  Jerome P. Lynch,et al.  Three-Tier Modular Structural Health Monitoring Framework Using Environmental and Operational Condition Clustering for Data Normalization: Validation on an Operational Wind Turbine System , 2016, Proceedings of the IEEE.

[39]  Joel P. Conte,et al.  Dynamic Testing of Alfred Zampa Memorial Bridge , 2008 .

[40]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[41]  W. Kempton,et al.  Pricing offshore wind power , 2011 .

[42]  J. N. Newman,et al.  THE COMPUTATION OF SECOND-ORDER WAVE LOADS , 1991 .

[43]  Jonathan Raymond White Operational monitoring of horizontal axis wind turbines with inertial measurements , 2010 .

[44]  Seymour Geisser,et al.  The Predictive Sample Reuse Method with Applications , 1975 .

[45]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[46]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[47]  Mijin Choi,et al.  On damage diagnosis for a wind turbine blade using pattern recognition , 2014 .

[48]  Jason Jonkman,et al.  Investigation of a FAST-OrcaFlex Coupling Module for Integrating Turbine and Mooring Dynamics of Offshore Floating Wind Turbines: Preprint , 2011 .

[49]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[50]  S. Geisser A predictive approach to the random effect model , 1974 .

[51]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[52]  J. Jonkman,et al.  Definition of a 5-MW Reference Wind Turbine for Offshore System Development , 2009 .

[53]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[54]  U. Rajendra Acharya,et al.  ECG beat classification using PCA, LDA, ICA and Discrete Wavelet Transform , 2013, Biomed. Signal Process. Control..

[55]  Beom-Seon Jang,et al.  Fatigue analysis of floating wind turbine support structure applying modified stress transfer function by artificial neural network , 2018 .

[56]  Dmitri Tcherniak,et al.  Applicability Limits of Operational Modal Analysis to Operational Wind Turbines , 2011 .

[57]  Eleni Chatzi,et al.  A Data-Driven Diagnostic Framework for Wind Turbine Structures: A Holistic Approach , 2017, Sensors.

[58]  Santanu Sahoo,et al.  Multiresolution wavelet transform based feature extraction and ECG classification to detect cardiac abnormalities , 2017 .