Real-time operational load monitoring of a composite aerostructure using FPGA-based computing system

• Autorzy: Mucha Waldemar

Identyfikatory

DOI

10.24425/bpasts.2023.148251

• Języki publikacji: EN

Abstrakty

EN

Operational load monitoring (OLM) is an industrial process related to structural health monitoring, where fatigue of the structure is tracked. Artificial intelligence methods, such as artificial neural networks (ANNs) or Gaussian processes, are utilized to improve efficiency of such processes. This paper focuses on moving such processes towards green computing by deploying and executing the algorithm on low-power consumption FPGA where high-throughput and truly parallel computations can be performed. In the following paper, the OLM process of typical aerostructure (hat-stiffened composite panel) is performed using ANN. The ANN was trained using numerically generated data, of every possible load case, to be working with sensor measurements as inputs. The trained ANN was deployed to Xilinx Artix-7 A100T FPGA of a real-time microcontroller. By executing the ANN on FPGA (where every neuron of a given layer can be processed at the same time, without limiting the number of parallel threads), computation time could be reduced by 70% as compared to standard CPU execution. Series of real-time experiments were performed that have proven the efficiency and high accuracy of the developed FPGA-based algorithm. Adjusting the ANN algorithm to FPGA requirements takes some effort, however it can lead to high performance increase. FPGA has the advantages of many more potential parallel threads than a standard CPU and much lower consumption than a GPU. This is particularly important taking into account potential embedded and remote applications, such as widely performed monitoring of airplane structures.

Słowa kluczowe

EN

operational load monitoring; FPGA; aerostructures; neural networks; artificial intelligence; structural health monitoring; green computing; real time computation

PL

monitorowanie obciążenia operacyjnego; obliczenia w czasie rzeczywistym; FPGA; konstrukcje lotnicze; sieci neuronowe; sztuczna inteligencja; monitorowanie stanu konstrukcji; zielone technologie informatyczne

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2024
• Tom: Vol. 72, nr 1
• Strony: art. no. e148251
• Opis fizyczny: Bibliogr. 67 poz., rys., tab.

Twórcy

autor

Mucha Waldemar

• Department of Computational Mechanics and Engineering, Silesian University of Technology, Konarskiego 18A, 44-100 Gliwice, Poland

• https://orcid.org/0000-0002-9724-1817

Bibliografia

• [1] F.M. Reis, P.F. da Costa Antunes, N.M. Mendes Maia, A.R. Carvalho, and P.S. de Brito André, “Structural Health Monitoring Suitable for Airborne Components Using the Speckle Pattern in Plastic Optical Fibers,” IEEE Sens. J., vol. 17, no. 15, pp. 4791–4796, 2017, doi: 10.1109/JSEN.2017.2715258.
• [2] S. Willis, “Olm: A Hands-on Approach,” in ICAF 2009, Bridging the Gap between Theory and Operational Practice, M.J. Bos, Ed., Dordrecht: Springer Netherlands, 2009, pp. 1199–1214.
• [3] N. Aldridge, P. Foote, and I. Read, “Operational Load Monitoring for Aircraft & Maritime Applications,” Strain, vol. 36, no. 3, pp. 123–126, 2000, doi: 10.1111/j.1475-1305.2000.tb01187.x.
• [4] L. Colombo, C. Sbarufatti, W. Zielinski, K. Dragan, and M. Giglio, “Numerical and experimental flight verifications of a calibration matrix approach for load monitoring and temperature reconstruction and compensation,” Aerosp. Sci. Technol., vol. 118, p. 107074, Nov. 2021, doi: 10.1016/j.ast.2021.107074.
• [5] H. Guo, G. Xiao, N. Mrad, and J. Yao, “Fiber Optic Sensors for Structural Health Monitoring of Air Platforms,” Sensors, vol. 11, no. 4, pp. 3687–3705, 2011, doi: 10.3390/s110403687.
• [6] J. Serafini, G. Bernardini, R. Porcelli, and P. Masarati, “In-flight health monitoring of helicopter blades via differential analysis,” Aerosp. Sci. Technol., vol. 88, pp. 436–443, May 2019, doi: 10.1016/j.ast.2019.03.039.
• [7] F. Terroba, M. Frövel, and R. Atienza, “Structural health and usage monitoring of an unmanned turbojet target drone,” Struct. Health Monit., vol. 18, no. 2, pp. 635–650, Mar. 2019, doi: 10.1177/1475921718764082.
• [8] L. Li, “Damage development and lifetime prediction of fiber-reinforced ceramic-matrix composites subjected to cyclic loading at 1300◦C in vacuum, inert and oxidative atmospheres,” Aerosp. Sci. Technol., vol. 86, pp. 613–629, Mar. 2019, doi: 10.1016/j.ast.2019.01.060.
• [9] F. Fang, L. Qiu, S. Yuan, and Y. Ren, “Dynamic probability modeling-based aircraft structural health monitoring framework under time-varying conditions: Validation in an in-flight test simulated on ground,” Aerosp. Sci. Technol., vol. 95, p. 105467, Dec. 2019, doi: 10.1016/j.ast.2019.105467.
• [10] S.R. Hunt and I.G. Hebden, “Validation of the Eurofighter Typhoon structural health and usage monitoring system,” Smart Mater Struct., vol. 10, no. 3. pp. 497–503, 2001. doi: 10.1088/0964-1726/10/3/311.
• [11] H. Rocha, C. Semprimoschnig, and J.P. Nunes, “Sensors for process and structural health monitoring of aerospace composites: A review,” Eng. Struct., vol. 237, p. 112231, 2021, doi: 10.1016/j.engstruct.2021.112231.
• [12] Z. Ma and X. Chen, “Fiber Bragg Gratings Sensors for Aircraft Wing Shape Measurement: Recent Applications and Technical Analysis,” Sensors, vol. 19, no. 1, p. 55, 2019, doi: 10.3390/s19010055.
• [13] M.J. Nicolas, R.W. Sullivan, and W.L. Richards, “Large Scale Applications Using FBG Sensors: Determination of In-Flight Loads and Shape of a Composite Aircraft Wing,” Aerospace, vol. 3, no. 3, p. 18, 2016, doi: 10.3390/aerospace3030018.
• [14] A. Kakei and J.A. Epaarachchi, “Use of fiber Bragg grating sensors for monitoring delamination damage propagation in glass-fiber reinforced composite structures,” Front. Optoelectron., vol. 11, no. 1, pp. 60–68, Mar. 2018, doi: 10.1007/s12200-018-0761-9.
• [15] D. Anastasopoulos, G. De Roeck, and E.P.B. Reynders, “One-year operational modal analysis of a steel bridge from high-resolution macrostrain monitoring: Influence of temperature vs. retrofitting,” Mech. Syst. Signal Process., vol. 161, p. 107951, Dec. 2021, doi: 10.1016/j.ymssp.2021.107951.
• [16] D.J. Robert, D. Chan, P. Rajeev, and J. Kodikara, “Effects of operational loads on buried water pipes using field tests,” Tunn. Undergr. Space Technol., vol. 124, p. 104463, Jun. 2022, doi: 10.1016/j.tust.2022.104463.
• [17] K. Schroeder, W. Ecke, J. Apitz, E. Lembke, and G. Lenschow, “A fibre Bragg grating sensor system monitors operational load in a wind turbine rotor blade,” Meas. Sci. Technol., vol. 17, no. 5, p. 1167, 2006.
• [18] P. Krot, P. Sliwinski, R. Zimroz, and N. Gomolla, “The identification of operational cycles in the monitoring systems of underground vehicles,” Measurement, vol. 151, p. 107111, Feb. 2020, doi: 10.1016/j.measurement.2019.107111.
• [19] M. Gordan et al., “State-of-the-art review on advancements of data mining in structural health monitoring,” Measurement, vol. 193, p. 110939, Apr. 2022, doi: 10.1016/j.measurement.2022.110939.
• [20] O. Ahmed, X. Wang, M.-V. Tran, and M.-Z. Ismadi, “Advancements in fiber-reinforced polymer composite materials damage detection methods: Towards achieving energy-efficient SHM systems,” Compos. Part B Eng., vol. 223, p. 109136, Oct. 2021, doi: 10.1016/j.compositesb.2021.109136.
• [21] S.K. Baduge et al., “Artificial intelligence and smart vision for building and construction 4.0: Machine and deep learning methods and applications,” Autom. Constr., vol. 141, p. 104440, Sep. 2022, doi: 10.1016/j.autcon.2022.104440.
• [22] D.J. Livingstone, “Artificial Neural Networks: Methods and Applications,” in Methods in Molecular Biology. Humana Press, 2011. [Online]. Available: https://books.google.pl/books?id=eVocYgEACAAJ
• [23] I. Tabian, H. Fu, and Z. Sharif Khodaei, “A Convolutional Neural Network for Impact Detection and Characterization of Complex Composite Structures,” Sensors, vol. 19, no. 22, p. 4933, 2019, doi: 10.3390/s19224933.
• [24] A.M. Damm, C. Spitzmüller, A.T.S. Raichle, A. Bühler, P. Weiß-graeber, and P. Middendorf, “Deep learning for impact detection in composite plates with sparsely integrated sensors,” Smart Mater. Struct., vol. 29, no. 12, p. 125014, Oct. 2020, doi: 10.1088/1361-665X/abb644.
• [25] K.-C. Jung and S.-H. Chang, “Advanced deep learning model-based impact characterization method for composite laminates,” Compos. Sci. Technol., vol. 207, p. 108713, May 2021, doi: 10.1016/j.compscitech.2021.108713.
• [26] A. Khan, D.-K. Ko, S.C. Lim, and H.S. Kim, “Structural vibration-based classification and prediction of delamination in smart composite laminates using deep learning neural network,” Compos. Part B Eng., vol. 161, pp. 586–594, Mar. 2019, doi: 10.1016/j.compositesb.2018.12.118.
• [27] M.-H. Yu and H.-S. Kim, “Deep-learning based damage sensing of carbon fiber/polypropylene composite via addressable conducting network,” Compos. Struct., vol. 267, p. 113871, Jul. 2021, doi: 10.1016/j.compstruct.2021.113871.
• [28] A. Datta, M.J. Augustin, N. Gupta, S.R. Viswamurthy, K.M. Gaddikeri, and R. Sundaram, “Impact Localization and Severity Estimation on Composite Structure Using Fiber Bragg Grating Sensors by Least Square Support Vector Regression,” IEEE Sens. J., vol. 19, no. 12, pp. 4463–4470, 2019, doi: 10.1109/JSEN.2019.2901453.
• [29] A. Mardanshahi, V. Nasir, S. Kazemirad, and M.M. Shokrieh, “Detection and classification of matrix cracking in laminated composites using guided wave propagation and artificial neural networks,” Compos. Struct., vol. 246, p. 112403, Aug. 2020, doi: 10.1016/j.compstruct.2020.112403.
• [30] W. Mucha, “Comparison of Machine Learning Algorithms for Structure State Prediction in Operational Load Monitoring,” Sensors, vol. 20, no. 24, p. 87, 2020, doi: 10.3390/s20247087.
• [31] W. Mucha, W. Kuś, J.C. Viana, and J.P. Nunes, “Operational Load Monitoring of a Composite Panel Using Artificial Neural Networks,” Sensors, vol. 20, no. 9, p. 2534, 2020, doi: 10.3390/s20092534.
• [32] M.J. Candon, O. Levinski, A. Altaf, R. Carrese, and P. Marzocca, “Aircraft Transonic Buffet Load Prediction using Artificial Neural Networks,” in AIAA Scitech 2019 Forum, 2019, doi: 10.2514/6.2019-0763.
• [33] D. Wada, Y. Sugimoto, H. Murayama, H. Igawa, and T. Nakamura, “Investigation of Inverse Analysis and Neural Network Approaches for Identifying Distributed Load using Distributed Strains,” Trans. Jpn. Soc. Aeronaut. SPACE Sci., vol. 62, no. 3, pp. 151–161, 2019, doi: 10.2322/tjsass.62.151.
• [34] M. Kuss and C.E. Rasmussen, “Gaussian processes in reinforcement learning,” in Advances in neural information processing systems, 2004, pp. 751–758.
• [35] G. Holmes, P. Sartor, S. Reed, P. Southern, K. Worden, and E. Cross, “Prediction of landing gear loads using machine learning techniques,” Struct. Health Monit., vol. 15, no. 5, pp. 568–582, Sep. 2016, doi: 10.1177/1475921716651809.
• [36] R. Fuentes, E. Cross, A. Halfpenny, K. Worden, and R.J. Barthorpe, “Aircraft parametric structural load monitoring using Gaussian process regression,” in 7th European Workshop on Structural Health Monitoring, EWSHM 2014 – 2nd European Conference of the Prognostics and Health Management (PHM) Society, 2014, pp. 1933–1940. [Online]. Available: https://www.scopus.com/inward/record.uri?eid=2-s2.0-84939438509&partnerID=40&md5=8609fbbf7c6af0e6ffd49784da56ac53
• [37] A. Chandani, S. Wagholikar, and O. Prakash, “A Bibliometric Analysis of Green Computing,” in Information and Communication Technology for Competitive Strategies (ICTCS 2021), A. Joshi, M. Mahmud, and R.G. Ragel, Eds., Singapore: Springer Nature Singapore, 2023, pp. 547–557.
• [38] A.O. Ojo, M. Raman, and A.G. Downe, “Toward green computing practices: A Malaysian study of green belief and attitude among Information Technology professionals,” J. Clean. Prod., vol. 224, pp. 246–255, Jul. 2019, doi: 10.1016/j.jclepro.2019.03.237.
• [39] C. Maxfield, The Design Warrior’s Guide to FPGAs: Devices, Tools and Flows. Elsevier Science, 2004. [Online]. Available: https://books.google.pl/books?id=dnuwr2xOFpUC
• [40] S. Tyurin, “Green Logic: Green LUT FPGA Concepts, Models and Evaluations,” in Green IT Engineering: Components, Networks and Systems Implementation, V. Kharchenko, Y. Kondratenko, and J. Kacprzyk, Eds., Cham: Springer International Publishing, 2017, pp. 241–261. doi: 10.1007/978-3-319-55595-9_12.
• [41] O. Yanovskaya, M. Yanovsky, and V. Kharchenko, “The concept of green Cloud infrastructure based on distributed computing and hardware accelerator within FPGA as a Service,” in Proceedings of IEEE East-West Design & Test Symposium (EWDTS 2014), 2014, pp. 1–4. doi: 10.1109/EWDTS.2014.7027089.
• [42] A. Shrivastava et al., “VLSI Implementation of Green Computing Control Unit on Zynq FPGA for Green Communication,” Wirel. Commun. Mob. Comput., vol. 2021, p. 4655400, Nov. 2021, doi: 10.1155/2021/4655400.
• [43] D. Ratter, “FPGAs on Mars,” Xcell Journal, 2004, [Online]. Available: http://dea.unsj.edu.ar/sda/FPGA_On_Mars.pdf
• [44] “FPGA processors keep Mars Rovers moving.” [Online]. Available: https://www.militaryaerospace.com/articles/2005/01/ fpga-processors-keep-mars-rovers-moving.html (Accessed: Nov. 26, 2018).
• [45] R. Wu, X. Guo, J. Du, and J. Li, “Accelerating Neural Network Inference on FPGA-Based Platforms—A Survey,” Electronics, vol. 10, no. 9, p. 1025, 2021, doi: 10.3390/electronics10091025.
• [46] V. Shymkovych, S. Telenyk, and P. Kravets, “Hardware implementation of radial-basis neural networks with Gaussian activation functions on FPGA,” Neural Comput. Appl., vol. 33, no. 15, pp. 9467–9479, Aug. 2021, doi: 10.1007/s00521-021-05706-3.
• [47] E. Chung et al., “Serving DNNs in Real Time at Datacenter Scale with Project Brainwave,” IEEE Micro, vol. 38, pp. 8–20, Mar. 2018.
• [48] J. Fowers et al., “A Configurable Cloud-Scale DNN Processor for Real-Time AI,” in Proceedings of the 45th International Symposium on Computer Architecture, 2018, Jun. 2018. [Online]. Available: https://www.microsoft.com/en-us/research/publication/a-configurable-cloud-scale-dnn-processor-for-real-time-ai/
• [49] B. Betkaoui, D.B. Thomas, and W. Luk, “Comparing performance and energy efficiency of FPGAs and GPUs for high productivity computing,” in 2010 International Conference on Field-Programmable Technology, 2010, pp. 94–101. doi: 10.1109/FPT.2010.5681761.
• [50] M. Qasaimeh, K. Denolf, J. Lo, K. Vissers, J. Zambreno, and P.H. Jones, “Comparing Energy Efficiency of CPU, GPU and FPGA Implementations for Vision Kernels,” in 2019 IEEE International Conference on Embedded Software and Systems (ICESS), 2019, pp. 1–8. doi: 10.1109/ICESS.2019.8782524.
• [51] P. Cooke, J. Fowers, G. Brown, and G. Stitt, “A Tradeoff Analysis of FPGAs, GPUs, and Multicores for Sliding-Window Applications,” ACM Trans Reconfigurable Technol Syst, vol. 8, no. 1, p. 2, Mar. 2015, doi: 10.1145/2659000.
• [52] J. Fowers, G. Brown, P. Cooke, and G. Stitt, “A Performance and Energy Comparison of FPGAs, GPUs, and Multicores for Sliding-Window Applications,” in Proc. ACM/SIGDA International Symposium on Field Programmable Gate Arrays, FPGA ’12, New York, USA, 2012, pp. 47–56. doi: 10.1145/2145694.2145704.
• [53] Y. Tang, R. Dai, and Y. Xie, “Optimization of Energy Efficiency for FPGA-Based Convolutional Neural Networks Accelerator,” J. Phys. Conf. Ser., vol. 1487, no. 1, p. 012028, Mar. 2020, doi: 10.1088/1742-6596/1487/1/012028.
• [54] E.N. |A. May 2015, “Controlling the EMI effects of air-craft avionics,” Aerospace Manufacturing and Design. [Online]. Available: https://www.aerospacemanufacturinganddesign.com/article/amd0415-aircraft-avionics-emi-effects/ (Accessed: Oct. 17, 2023).
• [55] E. Cetin et al., “Overview and Investigation of SEU Detection and Recovery Approaches for FPGA-Based Heterogeneous Systems,” in FPGAs and Parallel Architectures for Aerospace Applications: Soft Errors and Fault-Tolerant Design, F. Kastensmidt and P. Rech, Eds., Cham: Springer International Publishing, 2016, pp. 33–46. doi: 10.1007/978-3-319-14352-1_3.
• [56] S.-Y. Yuan et al., “EMI behavior of FPGA-IP measurement,” in 2022 Asia-Pacific International Symposium on Electromagnetic Compatibility (APEMC), Sep. 2022, pp. 270–272. doi: 10.1109/APEMC53576.2022.9888692.
• [57] “Aviation With FPGAs | Microchip Technology.” [On-line]. Available: https://www.microchip.com/en-us/solutions/aerospace-and-defense/aviation/fpga (Accessed: Oct. 17, 2023).
• [58] “Avionics & UAV,” AMD. [Online]. Available: https://www.xilinx.com/applications/aerospace-and-defense/avionics-uav.html (Accessed: Oct. 17, 2023).
• [59] M. Petko and T. Uhl, “Smart sensor for operational load measurement,” Trans. Inst. Meas. Control, vol. 26, no. 2, pp. 99–117, Jun. 2004, doi: 10.1191/0142331204tm111oa.
• [60] R. Grzejda, “Finite element modeling of the contact of elements preloaded with a bolt and externally loaded with any force,” J. Comput. Appl. Math., vol. 393, p. 113534, 2021, doi: 10.1016/j.cam.2021.113534.
• [61] M. Bečvář and P. Štukjunger, “Fixed-point arithmetic in FPGA,” Acta Polytech., vol. 45, no. 2, pp. 67–72, 2005.
• [62] R. Yates, “Fixed-point arithmetic: An introduction,” Digit. Signal Labs, vol. 81, no. 83, p. 198, 2009.
• [63] S. Cherubin, D. Cattaneo, M. Chiari, A. Di Bello, and G. Agosta, “TAFFO: Tuning assistant for floating to fixed point optimization,” IEEE Embed. Syst. Lett., vol. 12, no. 1, pp. 5–8, 2019.
• [64] D. Cattaneo, A. Di Bello, S. Cherubin, F. Terraneo, and G. Agosta, “Embedded operating system optimization through floating to fixed point compiler transformation,” 21st Euromicro Conference on Digital System Design (DSD), IEEE, 2018, pp. 172–176.
• [65] W. Mucha, W. Kuś, J.C. Viana, and J.P. Nunes, “Experimental Validation of Numerical Model of Composite Panel for Aerospace Structural Applications,” in Proceedings of the 26th International Conference Engineering Mechanics 2020, Czech Republic, 2020.
• [66] W. Mucha, W. Kuś, J.C. Viana, and J.P. Nunes, “Comparison of numerical and experimental strains distributions in composite panel for aerospace applications,” in Proceedings of the 6th ECCOMAS Young Investigators Conference, 7th-9th July 2021, Valencia, Spain, 2022, pp. 403–411, doi: 10.4995/YIC2021.2021.15320.
• [67] S.W. Tsai and E.M. Wu, “A General Theory of Strength for Anisotropic Materials,” J. Compos. Mater., vol. 5, no. 1, pp. 58–80, Jan. 1971, doi: 10.1177/002199837100500106.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).