Dual-indicator early damage warning framework for composite wind turbine blade: integrating acoustic emission energy drift and frequency cluster evolution
Restricted accessResearch articleFirst published online 2025
Dual-indicator early damage warning framework for composite wind turbine blade: integrating acoustic emission energy drift and frequency cluster evolution
This study presents a comprehensive acoustic emission (AE)-based structural health monitoring framework applied to a full-scale 51.5-m wind turbine blade containing an artificial cross-shaped crack. A staged crack extension procedure under variable-amplitude fatigue loading was employed to realistically simulate damage progression. Fourteen resonant AE sensors continuously monitored transient signals associated with matrix cracking, delamination, interfacial debonding, and fiber breakage. A robust multi-stage noise filtering pipeline was developed to ensure data integrity. Two physically interpretable early-warning indicators were introduced: a normalized energy drift index, tracking time-domain energy deviations, and the Jensen–Shannon distance, quantifying changes in peak-frequency cluster distributions. Results demonstrated that the dual-indicator framework reliably identifies both sustained damage progression and sudden shifts in failure mechanisms. Post-test inspections verified strong correspondence between AE-based predictions and actual crack propagation zones. This research bridges the gap between coupon-scale laboratory studies and practical, full-scale blade monitoring, providing a physically meaningful approach to early damage detection in large composite structures.
PanZZhuZGuoX, et al. Dynamic strain distribution monitoring and fatigue damage analysis on a 100 kW wind turbine blade based on field aerodynamic measurements. Meas Sci Technol2024; 36: 016117.
2.
BenzonHHMielkeARitschelTKS, et al. Acoustic emission data analytics on delamination growth in a wind turbine blade under full-scale cyclic testing. Measurement2025; 242: 115822.
3.
Samareh-MousaviSSChenXMcGuganM, et al. Monitoring fatigue delamination growth in a wind turbine blade using passive thermography and acoustic emission. Struct Health Monit2024; 23(5): 2906–2921.
4.
DuYZhouSJingX, et al. Damage detection techniques for wind turbine blades: a review. Mech Syst Signal Process2020; 141: 106445.
5.
NairACaiCS.Acoustic emission monitoring of bridges: review and case studies. Eng Struct2010; 32(6): 1704–1714.
6.
GaoPLiuJWangX, et al. Damage evaluation and failure mechanism analysis of axially compressed square concrete-filled steel tubular columns by acoustic emission techniques. Measurement2023; 217: 113132.
7.
MandalDDBentaharMEl MahiA, et al. Acoustic emission monitoring of damage modes in reinforced concrete beams by using narrow partial power bands. Sci Rep2024; 14(1): 27082.
8.
HanWHuBZhouJ, et al. Characterization of the damage mechanism in CFRP composites under mode I based on comprehensive analysis of AE signals. J Adhes Sci Technol2024; 38(18): 3461–3479.
9.
LiuPFXuDLiJ, et al. Damage mode identification of composite wind turbine blade under accelerated fatigue loads using acoustic emission and machine learning. Struct Health Monit2019; 19(4): 1092–1103.
10.
FotouhiMSuwartaPJalalvandM, et al. Detection of fibre fracture and ply fragmentation in thin-ply UD carbon/glass hybrid laminates using acoustic emission. Compos Part A Appl Sci Manuf2016; 86: 66–76.
11.
MichałSSzymonDPawełZ, et al. Damage characterisation of GFRP composites based on clustering acoustic emission events utilizing single-failure-cause tests as reference. Compos Struct2025; 351: 118596.
12.
CrivelliDGuaglianoMEatonM, et al. Localisation and identification of fatigue matrix cracking and delamination in a carbon fibre panel by acoustic emission. Compos Part B Eng2015; 74: 1–12.
13.
SikdarSLiuDKunduA.Acoustic emission data based deep learning approach for classification and detection of damage-sources in a composite panel. Compos Part B Eng2022; 228: 109450.
14.
MuirCSwaminathanBAlmansourAS, et al. Damage mechanism identification in composites via machine learning and acoustic emission. NPJ Comput Mater2021; 7(1): 95.
15.
MuirCSwaminathanBFieldsK, et al. A machine learning framework for damage mechanism identification from acoustic emissions in unidirectional SiC/SiC composites. NPJ Comput Mater2021; 7(1): 146.
16.
XuDLiuPFChenZP, et al. Achieving robust damage mode identification of adhesive composite joints for wind turbine blade using acoustic emission and machine learning. Compos Struct2020; 236: 111840.
17.
XuDLiuPFChenZP.Damage mode identification and singular signal detection of composite wind turbine blade using acoustic emission. Compos Struct2021; 255: 112954.
18.
JiaoYYangHFangM, et al. Fracture mode classification of UHPC based on deep learning and wavelet time–frequency spectrum derived from acoustic emission waveform. Struct Health Monit2025. (In Press).
19.
XuDLiuPFChenZP.A deep learning method for damage prognostics of fiber-reinforced composite laminates using acoustic emission. Eng Fract Mech2022; 259: 108139.
20.
EatonMJPullinRHolfordKM.Acoustic emission source location in composite materials using Delta T mapping. Compos Part A Appl Sci Manuf2012; 43(6): 856–863.
21.
FremmelevMALadpliPOrlowitzE, et al. Structural health monitoring of 52-meter wind turbine blade: detection of damage propagation during fatigue testing. Data Centric Eng2022; 3: e22.
22.
KimKRLeeYS.Acoustic emission source localization in plate-like structures using least-squares support vector machines with Delta T feature. J Mech Sci Technol2014; 28(8): 3013–3020.
23.
SauseMGRGribovAUnwinAR, et al. Pattern recognition approach to identify natural clusters of acoustic emission signals. Pattern Recognit Lett2012; 33(1): 17–23.
24.
TangJSouaSMaresC, et al. An experimental study of acoustic emission methodology for in service condition monitoring of wind turbine blades. Renew Energy2016; 99: 170–179.
25.
MarecAThomasJHEl GuerjoumaR.Damage characterization of polymer-based composite materials: multivariable analysis and wavelet transform for clustering acoustic emission data. Mech Syst Signal Process2008; 22(6): 1441–1464.
26.
SmolnickiMDudaSStablaP, et al. Acoustic emission with machine learning in fracture of composites: preliminary study. Arch Civ Mech Eng2023; 23(4): 254.
27.
LiuRZhangPFShenGT, et al. Acoustic emission study on damage mechanism of composite materials repaired with bi-adhesive and damage classification model. J Adhes Sci Technol2024; 38(10): 1718–1737.
28.
AliHQTabriziIEKhanRMA, et al. Microscopic analysis of failure in woven carbon fabric laminates coupled with digital image correlation and acoustic emission. Compos Struct2019; 230: 111515.
29.
NikbakhtMYousefiJHosseini-ToudeshkyH, et al. Delamination evaluation of composite laminates with different interface fiber orientations using acoustic emission features and micro visualization. Compos Part B Eng2017; 113: 185–196.
30.
CarpinteriALacidognaGPugnoN.Richter’s laws at the laboratory scale interpreted by acoustic emission. Mag Concr Res2006; 58(9): 619–625.
31.
BeattieAG. Acoustic emission non-destructive testing of structures using source location techniques. Technical Report. Albuquerque, NM, USA: Sandia National Laboratories; September 2013.
32.
LiQQiTShiL, et al. Intelligent recognition of acoustic emission signals from damage of glass fiber-reinforced plastics. Compos Adv Mater2020; 29: 2633366X20974683.
33.
ZhouWZhaoWZZhangYN, et al. Cluster analysis of acoustic emission signals and deformation measurement for delaminated glass fiber epoxy composites. Compos Struct2018; 195: 349–358.
34.
ArthurDVassilvitskiiS. K-means++: the advantages of careful seeding. In: Proceedings of the 18th annual ACM-SIAM symposium on discrete algorithms, New Orleans, LA, USA, 7–9 January 2007, pp. 1027–1035. Philadelphia, PA, USA: Society for Industrial and Applied Mathematics.
35.
LinJ.Divergence measures based on the Shannon entropy. IEEE Trans Inf Theory1991; 37(1): 145–151.
36.
EndresDMSchindelinJE.A new metric for probability distributions. IEEE Trans Inf Theory2003; 49(7): 1858–1860.
37.
SikdarSFiborekPKudelaP, et al. Effects of debonding on Lamb wave propagation in a bonded composite structure under variable temperature conditions. Smart Mater Struct2019; 28(1): 015021.
38.
XuDLiuPFLiJG, et al. Damage mode identification of adhesive composite joints under hygrothermal environment using acoustic emission and machine learning. Compos Struct2019; 211: 351–363.
39.
SikdarSMirgalPBanerjeeS, et al. Damage-induced acoustic emission source monitoring in a honeycomb sandwich composite structure. Compos Part B Eng2019; 158: 179–188.
40.
HanQXuJCarpinteriA, et al. Localization of acoustic emission sources in structural health monitoring of masonry bridge. Struct Control Health Monit2015; 22(2): 314–329.
41.
XuDLiuPFChenZP, et al. Dynamic feature evaluation on streaming acoustic emission data for adhesively bonded joints for composite wind turbine blade. Struct Health Monit2021; 21(2): 387–406.
42.
HanBHYoonDJHuhYH, et al. Damage assessment of wind turbine blade under static loading test using acoustic emission. J Intell Mater Syst Struct2013; 25(5): 621–630.
43.
ZhouWPanZBWangJ, et al. Review on acoustic emission source location, damage recognition and lifetime prediction of fiber-reinforced composites. J Mater Sci2023; 58(2): 583–607.
44.
FotouhiMHeidaryHAhmadiM, et al. Characterization of composite materials damage under quasi-static three-point bending test using wavelet and fuzzy C-means clustering. J Compos Mater2012; 46(15): 1795–1808.
45.
SaeedifarMNajafabadiMAZarouchasD, et al. Clustering of interlaminar and intralaminar damages in laminated composites under indentation loading using acoustic emission. Compos Part B Eng2018; 144: 206–219.
46.
XuDLiuPFChenZP, et al. A new quantitative acoustic emission model for damage characterization of composite laminates using original waveforms. Struct Health Monit2022; 21(5): 2276–2290.
