Application of Artificial Neural Networks to a Model of a Helicopter Rotor Blade for Damage Identification in Realistic Load Conditions
Abstract
:1. Introduction
2. The Description and Modeling of the Blade Root
2.1. Blade Root Description
2.2. Finite Element Model
- -
- Blade root: Representing the component to be monitored. Its meshing strategy was presented in the previous subsection;
- -
- Blade: Representing the part of the blade from the end of the blade root up to approximately half of the whole blade. The blade was modeled using C3D8I-type elements having a characteristic length of 5 mm;
- -
- Tabs: These elements were bonded to the blade and were needed to transfer the load to the blade root. Tabs were modeled with C3D10-type elements having a characteristic length of 10 mm;
- -
- Bearing: A metallic element, which was representative of the connection of the blade to the hub; the connection was implemented by three bolts passing through the holes of the blade root. The bearing was modeled with C3D8R-type elements having a characteristic length of 2.5 mm;
- -
- Pitch arm: A metallic element that was bonded to the blade root and allows the introduction of loads to rotate the blade around a pitch axis. The pitch arm was modeled with C3D10-type elements having a characteristic length equal to 5.5 mm.
2.3. Loading Scenario
- -
- CF: centrifugal force, which was applied to the tabs;
- -
- PL: force acting on the pitch link, which counterbalances the pitching moment;
- -
- LAT: lateral load, which was applied by the lag damper connected to the blade;
- -
- CB1 and CB2: in-plane bending loads, introduced through the bearing and through the tabs, respectively;
- -
- BB1 and BB2: out-of-plane bending loads, introduced through the bearing and through the tabs, respectively.
2.4. Model Validation
3. The Damage Detection Algorithm and Virtual SHMS Description
3.1. Virtual SHMS for Strain Acquisition
3.2. Damage Detection Algorithms
3.3. Virtual Dataset Creation and Training
4. Results
4.1. Example of Damage Identification
- Output of ANN 2 for the pristine blade root = 0.26;
- Output of ANN 2 for the damaged blade root = 0.99.
4.2. Load Identification
4.3. Anomaly Detection
4.4. Damage Assessment and Localization
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Bottasso, L.M.; Sala, G.; Bettini, P.; Tagliabue, P.; Corbani, F.; Platini, E.; Guerra, A.; Anelli, A. Rugged Fiber Optics Monitoring System for Helicopter Rotor Blades. In Proceedings of the 44th European Rotorcraft Forum (ERF 2018), Delft, The Netherlands, 19–20 September 2018; pp. 965–980. [Google Scholar]
- Hassan, M.H. A mini review on manufacturing defects and performance assessments of complex shape prepreg-based composites. Int. J. Adv. Manuf. Technol. 2021, 115, 3393–3408. [Google Scholar] [CrossRef]
- Hallander, P.; Akermo, M.; Mattei, C.; Petersson, M.; Nyman, T. An experimental study of mechanisms behind wrinkle development during forming of composite laminates. Compos. Part A 2013, 50, 54–64. [Google Scholar] [CrossRef]
- Yerramalli, C.S.; Miebach, T.; Chandraseker, K.; Quek, S.C. Fiber waviness induced knockdowns in composite materials used in wind turbine blades. In Proceedings of the European Wind Energy Conference and Exhibition, Warsaw, Poland, 20–23 April 2010. [Google Scholar]
- Bloom, L.D.; Wang, J.; Potter, K.D. Damage progression and defect sensitivity: An experimental study of representative wrinkles in tension. Compos. Part B 2013, 45, 449–458. [Google Scholar] [CrossRef]
- Hakim, I.; Laquai, R.; Walter, D.; Mueller, B.; Graja, P.; Meyendorf, N.; Donaldson, S. The effect of manufacturing conditions on discontinuity population and fatigue fracture behavior in carbon/epoxy composites. AIP Conf. Proc. 2017, 1806, 090017. [Google Scholar]
- Suhot, M.A.; Chambers, A.E. The effect of voids on the flexural fatigue performance of unidirectional carbon fibre composites. In Proceedings of the 16th International Conference on Composite Materials, Kyoto, Japan, 8 July 2007. [Google Scholar]
- Lightfoot, J.S.; Wisnom, M.R.; Potter, K. A new mechanism for the formation of ply wrinkles due to shear between plies. Compos. Part A 2013, 49, 139–147. [Google Scholar] [CrossRef]
- Boisse, P.; Hamila, N.; Vidal-Sallé, E.; Dumont, F. Simulation of wrinkling during textile composite forming. Influence of tensile, in-plane shear and bending stiffness. Compos. Sci. Technol. 2011, 71, 683–692. [Google Scholar] [CrossRef]
- Mujahid, Y.; Sallih, N.; Abdullah, M.Z.; Mustapha, M. Effects of processing parameters for vacuum-bag-only method on void content and mechanical properties of laminated composites. Polym. Compos. 2021, 42, 567–582. [Google Scholar] [CrossRef]
- Grunenfelder, L.K.; Nutt, S.R. Void formation in composite prepregs–Effect of dissolved moisture. Compos. Sci. Technol. 2010, 70, 2304–2309. [Google Scholar] [CrossRef]
- Zhang, T.; Meng, J.; Pan, Q.; Sun, B. The influence of adhesive porosity on composite joints. Compos. Commun. 2019, 15, 87–91. [Google Scholar] [CrossRef]
- Lamberti, M.; Maurel-Pantel, A.; Lebon, F. Mechanical Performance of Adhesive Connections in Structural Applications. Materials 2023, 16, 7066. [Google Scholar] [CrossRef]
- Malinowski, P.H.; Wandowski, T.; Ostachowicz, W.M.; Christopoulos, A.; Koulalis, I.; Kitsianos, K.; Kanterakis, G.; Ecault, R.; Stoessel, R.; Segur, D.; et al. Study of CFRP adhesive bonds influenced by manufacturing-related contaminations. In Proceedings of the Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018, Denver, CO, USA, 5–8 March 2018; Volume 10598, pp. 56–68. [Google Scholar]
- Moutsompegka, E.; Tserpes, K.I.; Polydoropoulou, P.; Tornow, C.; Schlag, M.; Brune, K.; Mayer, B.; Pantelakis, S. Experimental study of the effect of pre-bond contamination with de-icing fluid and ageing on the fracture toughness of composite bonded joints. Fatigue Fract. Eng. Mater. Struct. 2017, 40, 1581–1591. [Google Scholar] [CrossRef]
- Markatos, D.N.; Tserpes, K.I.; Rau, E.; Markus, S.; Ehrhart, B.; Pantelakis, S. The effects of manufacturing- induced and in-service related bonding quality reduction on the mode-I fracture toughness of composite bonded joints for aeronautical use. Compos. Part B 2013, 45, 556–564. [Google Scholar] [CrossRef]
- Solodov, I.; Ségur, D.; Kreutzbruck, M. Evaluation of bonding quality in CFRP composite laminates by measurements of local vibration nonlinearity. In Proceedings of the Meetings on Acoustics, Santa Fe, NM, USA, 9–13 July 2018; Volume 34. No. 1. [Google Scholar]
- Yılmaz, B.; Jasiūnienė, E. Advanced ultrasonic NDT for weak bond detection in composite-adhesive bonded structures. Int. J. Adhes. Adhes. 2020, 102, 102675. [Google Scholar] [CrossRef]
- Wang, B.; Zhong, S.; Lee, T.L.; Fancey, K.S.; Mi, J. Non-destructive testing and evaluation of composite materials/structures: A state-of-the-art review. Adv. Mech. Eng. 2020, 12, 1687814020913761. [Google Scholar] [CrossRef]
- Gholizadeh, S. A review of non-destructive testing methods of composite materials. Procedia Struct. Integr. 2016, 1, 50–57. [Google Scholar] [CrossRef]
- Jolly, M.R.; Prabhakar, A.; Sturzu, B.; Hollstein, K.; Singh, R.; Thomas, S.; Foote, P.; Shaw, A. Review of non-destructive testing (NDT) techniques and their applicability to thick walled composites. Procedia CIRP 2015, 38, 129–136. [Google Scholar] [CrossRef]
- Boller, C. Ways and options for aircraft structural health management. Smart Mater. Struct. 2001, 10, 432. [Google Scholar] [CrossRef]
- Speckmann, H.; Henrich, R. Structural health monitoring (SHM)–overview on technologies under development. In Proceedings of the 16th World Conference on NDT, Montreal, QC, Canada, 30 August–3 September 2004; Volume 1. [Google Scholar]
- Rocha, H.; Semprimoschnig, C.; Nunes, J.P. Sensors for process and structural health monitoring of aerospace composites: A review. Eng. Struct. 2021, 237, 112231. [Google Scholar] [CrossRef]
- Dong, T.; Kim, N.H. Cost-effectiveness of structural health monitoring in fuselage maintenance of the civil aviation industry. Aerospace 2018, 5, 87. [Google Scholar] [CrossRef]
- Takeda, N.; Okabe, Y.; Kuwahara, J.; Kojima, S.; Ogisu, T. Development of smart composite structures with small-diameter fiber Bragg grating sensors for damage detection: Quantitative evaluation of delamination length in CFRP laminates using Lamb wave sensing. Compos. Sci. Technol. 2005, 65, 2575–2587. [Google Scholar] [CrossRef]
- Ghiasvand, S.; Airoldi, A.; Bettini, P.; Mirani, C. Analysis of residual stresses and interface damage propagation in hybrid composite/metallic elements monitored through optical fiber sensors. Aerosp. Sci. Technol. 2022, 129, 107373. [Google Scholar] [CrossRef]
- Huang, S.; Zhang, J.; Ke, Y.; Gu, B.; Sun, B. In-situ monitoring of carbon fiber/epoxy composite with FBG sensors under curing and thermal cycling conditions. Compos. Commun. 2024, 47, 101875. [Google Scholar] [CrossRef]
- Goossens, S.; De Pauw, B.; Geernaert, T.; Salmanpour, M.S.; Khodaei, Z.S.; Karachalios, E.; Saenz-Castillo, D.; Thienpont, H.; Berghmans, F. Aerospace-grade surface mounted optical fibre strain sensor for structural health monitoring on composite structures evaluated against in-flight conditions. Smart Mater. Struct. 2019, 28, 065008. [Google Scholar] [CrossRef]
- Mieloszyk, M.; Skarbek, L.; Krawczuk, M.; Ostachowicz, W.; Zak, A. Application of fibre Bragg grating sensors for structural health monitoring of an adaptive wing. Smart Mater. Struct. 2011, 20, 125014. [Google Scholar] [CrossRef]
- Di Sante, R. Fibre optic sensors for structural health monitoring of aircraft composite structures: Recent advances and applications. Sensors 2015, 15, 18666–18713. [Google Scholar] [CrossRef]
- Loutas, T.H.; Charlaftis, P.; Airoldi, A.; Bettini, P.; Koimtzoglou, C.; Kostopoulos, V. Reliability of strain monitoring of composite structures via the use of optical fiber ribbon tapes for structural health monitoring purposes. Compos. Struct. 2015, 134, 762–771. [Google Scholar] [CrossRef]
- Sala, G.; Di Landro, L.; Airoldi, A.; Bettini, P. Fibre optics health monitoring for aeronautical applications. Meccanica 2015, 50, 2547–2567. [Google Scholar] [CrossRef]
- Gardner, P.; Fuentes, R.; Dervilis, N.; Mineo, C.; Pierce, S.G.; Cross, E.J.; Worden, K. Machine learning at the interface of structural health monitoring and non-destructive evaluation. Philos. Trans. R. Soc. A 2020, 378, 20190581. [Google Scholar] [CrossRef]
- Azad, M.M.; Kim, S.; Cheon, Y.B.; Kim, H.S. Intelligent structural health monitoring of composite structures using machine learning, deep learning, and transfer learning: A review. Adv. Compos. Mater. 2024, 33, 162–188. [Google Scholar] [CrossRef]
- Fakih, M.A.; Chiachío, M.; Chiachío, J.; Mustapha, S. A Bayesian approach for damage assessment in welded structures using Lamb-wave surrogate models and minimal sensing. NDT E Int. 2022, 128, 102626. [Google Scholar] [CrossRef]
- Sbarufatti, C.; Manes, A.; Giglio, M. Sensor network optimization for damage detection on aluminium stiffened helicopter panels. In COUPLED IV: Proceedings of the IV International Conference on Computational Methods for Coupled Problems in Science and Engineering, Kos, Greece, 20–22 June 2011; CIMNE: Barcelona, Spain, 2011; pp. 1294–1305. [Google Scholar]
- Sbarufatti, C.; Manes, A.; Giglio, M. Performance optimization of a diagnostic system based upon a simulated strain field for fatigue damage characterization. Mech. Syst. Signal Process. 2013, 40, 667–690. [Google Scholar] [CrossRef]
- Alvarez-Montoya, J.; Torres-Arredondo, M.; Sierra-Pérez, J. Gaussian process modeling for damage detection in composite aerospace structures by using discrete strain measurements. In Proceedings of the 7th Asia-Pacific Workshop on Structural Health Monitoring, APWSHM 2018, Hong Kong, China, 12–15 November 2018; pp. 710–718. [Google Scholar]
- Sierra-Pérez, J.; Torres-Arredondo, M.A.; Alvarez-Montoya, J. Damage detection methodology under variable load conditions based on strain field pattern recognition using FBGs, nonlinear principal component analysis, and clustering techniques. Smart Mater. Struct. 2017, 27, 015002. [Google Scholar] [CrossRef]
- Alvarez-Montoya, J.; Carvajal-Castrillón, A.; Sierra-Pérez, J. In-flight and wireless damage detection in a UAV composite wing using fiber optic sensors and strain field pattern recognition. Mech. Syst. Signal Process. 2020, 136, 106526. [Google Scholar] [CrossRef]
- Lin, M.; Guo, S.; He, S.; Li, W.; Yang, D. Structure health monitoring of a composite wing based on flight load and strain data using deep learning method. Compos. Struct. 2022, 286, 115305. [Google Scholar] [CrossRef]
- Dassault Systemes Simulia Corporation. Abaqus Analysis User Manual Version 6.14; Dassault Systemes Simulia Corporation: Johnston, RI, USA, 2022. [Google Scholar]
- Turon, A.; Davila, C.G.; Camanho, P.P.; Costa, J. An engineering solution for mesh size effects in the simulation of delamination using cohesive zone models. Eng. Fract. Mech. 2007, 74, 1665–1682. [Google Scholar] [CrossRef]
- Rytter, A. Vibrational Based Inspection of Civil Engineering Structures. Ph.D. Thesis, Department of Building Technology and Structural Engineering, Aalborg University, Aalborg Øst, Denmark, 1993. [Google Scholar]
- Wang, H.; Xiang, P.; Jiang, L. Strain transfer theory of industrialized optical fiber-based sensors in civil engineering: A review on measurement accuracy, design and calibration. Sens. Actuators A Phys. 2019, 285, 414–426. [Google Scholar] [CrossRef]
- Wang, H.P.; Xiang, P.; Li, X. Theoretical analysis on strain transfer error of FBG sensors attached on steel structures subjected to fatigue load. Strain 2016, 52, 522–530. [Google Scholar] [CrossRef]
- Zhang, M.; Sun, Q.; Wang, Z.; Li, X.; Liu, H.; Liu, D. A large capacity sensing network with identical weak fiber Bragg gratings multiplexing. Opt. Commun. 2012, 285, 3082–3087. [Google Scholar] [CrossRef]
- Airoldi, A.; Marelli, L.; Bettini, P.; Sala, G.; Apicella, A. Strain field reconstruction on composite spars based on the identification of equivalent load conditions. In Proceedings of the SPIE—The International Society for Optical Engineering, San Diego, CA, USA, 6–10 August 2017; Volume 10168. [Google Scholar] [CrossRef]
- Annis, C. Department of Defense Handbook: Nondestructive Evaluation System Reliability Assessment; MIL-HDBK-1823; United States Department of Defense: Arlington, VA, USA, 2007.
A | B | C | D | E | F | G | H | I | L |
---|---|---|---|---|---|---|---|---|---|
1,2,3 | 1,2,3 | 2,3 | 1,2,3 | 1,2,3 | 1,2,3 | 2,3 | 2,3,4 | 1,2,3 | 1,2,3 |
CF | BB1 | CB1 | LAT | PL | BB2 | CB2 |
---|---|---|---|---|---|---|
122.27 | 1 | 7.5 | 12.2 | 3.3 | 1 | −7.66 |
Strain Gauge Code | Nonlinear Implicit Model | Linear Model |
---|---|---|
Difference % 100 × (Test Values − FEM Strain Values)/Test Value S7 | Difference % 100 × (Test Values − FEM Strain Values)/Test Value S7 | |
S1 | −26.27 | 13.77 |
S2 | −1.67 | 15.95 |
S3 | −3.08 | −4.82 |
S4 | −2.05 | −11.70 |
S5 | 0.17 | −8.47 |
S6 | 12.2 | 27.42 |
S7 | 10.46 | 39.62 |
S8 | −14.03 | 21.46 |
S9 | 3.33 | 6.23 |
S10 | −4.38 | 10.99 |
S11 | 20.46 | 16.83 |
S12 | 5.28 | 20.99 |
S13 | 8.93 | 31.04 |
S14 | −1.19 | 13.88 |
ANN Name | Type | Node Number per Layer | Number of Hidden Layers | Training Function | Dataset Partition [Training/Validation/Test] | Activation Function | Input | Target |
---|---|---|---|---|---|---|---|---|
ANN 1 | Regression | 10 | 3 | Levenberg–Marquardt backpropagation | [70/15/15] | Hyperbolic tangent sigmoid | Strain at sensing points | Load components |
ANN 2 | Pattern recognition | 10 | 3 | Levenberg–Marquardt backpropagation | [70/15/15] | Hyperbolic tangent sigmoid | Damage indexes at sensing points | Blade’s state of integrity (0 = pristine, 1 = damaged) |
ANN 3 | Regression | 10 | 2 | Levenberg–Marquardt backpropagation | [70/15/15] | Hyperbolic tangent sigmoid | Damage indexes at sensing points | Damage position and damage size |
Algorithm Version | Load Identification Methodology |
---|---|
Version #1 | ANN trained only on blade in pristine conditions |
Version #2 | ANN trained on blade both in pristine and damaged conditions |
Version #3 | Solution of inverse problem finding load set {P} using Equation (3) |
CF | BB1 | CB1 | LAT | PL | BB2 | CB2 | |
---|---|---|---|---|---|---|---|
Applied load set | 149.34 | 1.00 | 8.27 | 12.71 | 3.33 | 1.00 | −8.33 |
Identified load set Pristine blade root | 149.30 | 1.00 | 8.30 | 12.79 | 3.38 | 1.01 | −8.36 |
Identified load set Damaged blade root | 149.41 | 1.04 | 8.31 | 12.73 | 3.48 | 1.04 | −8.39 |
Damage Size (mm) | Curvilinear Coordinate % | Cross Section Coordinate % | |
---|---|---|---|
Real values | 30 | 33.33 | 49.95 |
Predicted from the algorithm | 21.46 | 30.95 | 44.75 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ballarin, P.; Sala, G.; Macchi, M.; Roda, I.; Baldi, A.; Airoldi, A. Application of Artificial Neural Networks to a Model of a Helicopter Rotor Blade for Damage Identification in Realistic Load Conditions. Sensors 2024, 24, 5411. https://doi.org/10.3390/s24165411
Ballarin P, Sala G, Macchi M, Roda I, Baldi A, Airoldi A. Application of Artificial Neural Networks to a Model of a Helicopter Rotor Blade for Damage Identification in Realistic Load Conditions. Sensors. 2024; 24(16):5411. https://doi.org/10.3390/s24165411
Chicago/Turabian StyleBallarin, Pietro, Giuseppe Sala, Marco Macchi, Irene Roda, Andrea Baldi, and Alessandro Airoldi. 2024. "Application of Artificial Neural Networks to a Model of a Helicopter Rotor Blade for Damage Identification in Realistic Load Conditions" Sensors 24, no. 16: 5411. https://doi.org/10.3390/s24165411