Edge Computing in Space: Design of an FPGA Architecture for Thermal Anomaly Detection based on a Machine Learning Approach

MOREIRA, Carmen MISA; SHNEIDER, Carl; HEIN, Andreas

doi:10.1016/j.asr.2025.01.003

Article (Scientific journals)

Edge Computing in Space: Design of an FPGA Architecture for Thermal Anomaly Detection based on a Machine Learning Approach

MOREIRA, Carmen MISA; SHNEIDER, Carl; HEIN, Andreas

2025 • In Advances in Space Research

Peer Reviewed verified by ORBi

Permalink
https://hdl.handle.net/10993/63645

DOI
10.1016/j.asr.2025.01.003

Files (1)Send to Details Statistics Bibliography Similar publications

Files

Full Text

1-s2.0-S027311772500002X-main.pdf

Author preprint (4.01 MB)

Download

All documents in ORBilu are protected by a user license.

Send to

RIS BibTex APA Chicago Permalink X Linkedin

Details

Keywords :

Edge computing; SVMs; FPGA; Machine Learning; Anomaly Detection

Abstract :

[en] The extensive range of sensors, devices, and instrumentation on onboard space systems generates a substantial volume of data intended for transmission to the ground. However, the downlink data rate is inherently constrained by transmitting power and ground station access. Edge computing aims to reduce the latency and bandwidth within a downlink by processing the data as close as possible to where it has been generated, by placing the processing hardware close to the data source. In this paper, we apply edge computing to a payload for thermal anomaly detection, developed at the University of Luxembourg. The payload encompasses a series of Forward-Looking Infrared (FLIR) high-resolution Long-Wavelength Infrared (LWIR) micro-thermal cameras as an edge-sensing component to generate the thermal images. A Field-Programmable Gate Array (FPGA) acts as an edge-computing system for processing thermal images and heat distribution profiles, using a Support Vector Machine (SVM) algorithm to detect anomalies.

Disciplines :

Space science, astronomy & astrophysics

Author, co-author :

MOREIRA, Carmen MISA

SHNEIDER, Carl ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SPASYS

HEIN, Andreas ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SPASYS

External co-authors :

yes

Language :

English

Title :

Edge Computing in Space: Design of an FPGA Architecture for Thermal Anomaly Detection based on a Machine Learning Approach

Publication date :

January 2025

Journal title :

Advances in Space Research

ISSN :

0273-1177

eISSN :

1879-1948

Publisher :

Elsevier BV

Peer reviewed :

Peer Reviewed verified by ORBi

Additional URL :

https://api.elsevier.com/content/article/PII:S027311772500002X?httpAccept=text/xml

Available on ORBilu :

since 14 January 2025

Statistics

Number of views

110 (7 by Unilu)

Number of downloads

225 (4 by Unilu)

More statistics

Scopus citations^®

Scopus citations^®
without self-citations

OpenCitations

OpenAlex citations

Bibliography

Ackerman, S., Farchi, E., Raz, O. et al., 2022. Detection of data drift and outliers affecting machine learning model performance over time. URL: https://arxiv.org/abs/2012.09258. arXiv:2012.09258.
Ackerman, S., Raz, O., Zalmanovici, M. et al., 2021. Automatically detecting data drift in machine learning classifiers. URL: https://arxiv.org/abs/2111.05672. arXiv:2111.05672.
Al-Rababah, K., Mustaffa, M.R., Doraisamy, S.C., et al. Hybrid discrete wavelet transform and histogram of oriented gradients for feature extraction and classification of breast dynamic thermogram sequences. 2021 Fifth International Conference on Information Retrieval and Knowledge Management (CAMP), 2021, 31–35, 10.1109/CAMP51653.2021.9498028.
Babuscia, A., Corbin, B., Knapp, M., et al. Inflatable antenna for cubesats: motivation for development and antenna design. Acta Astronaut. 91 (2013), 322–332.
Bottou, L., 2010. Large-scale machine learning with stochastic gradient descent. In: Y. Lechevallier, & G. Saporta (Eds.), Proceedings of COMPSTAT’2010 (pp. 177–186). Heidelberg: Physica-Verlag HD.
Bottou, L., Lin, C.-J., 2007. Support vector machine solvers, pp. 301–320. doi:10.7551/mitpress/7496.003.0003.
Bouwmeester, J., Guo, J., Survey of worldwide pico-and nanosatellite missions, distributions and subsystem technology. Acta Astronaut. 67:7–8 (2010), 854–862.
Bratvold, T., 2022. Near real-time hyperspectral image classification for in-orbit decissionmaking hypso-1. NTNU.
Buttazzoni, G., Comisso, M., Cuttin, A., et al. Reconfigurable phased antenna array for extending cubesat operations to ka-band: Design and feasibility. Acta Astronaut. 137 (2017), 114–121.
Cervantes, J., Li, X., Yu, W. et al., 2008. Support vector machine classification for large data sets via minimum enclosing ball clustering. Neurocomputing, 71(4), 611–619. URL: https://www.sciencedirect.com/science/article/pii/S0925231207002962. doi: 10.1016/j.neucom.2007.07.028. Neural Networks: Algorithms and Applications 50 Years of Artificial Intelligence: a Neuronal Approach.
Chang, C.-C., Lin, C.-J., 2007. Libsvm: A library for support vector machines. ACM Trans. Intell. Syst. Technol., 2.
Chen, J., Pi, D., Wu, Z., et al. Imbalanced satellite telemetry data anomaly detection model based on bayesian lstm. Acta Astronaut. 180 (2021), 232–242.
Colin, A., Ruppel, E., Lucia, B., A reconfigurable energy storage architecture for energy-harvesting devices. ASPLOS ’18, 2018, Association for Computing Machinery, New York, NY, USA, 767–781, 10.1145/3173162.3173210.
Dalal, N., Triggs, B., 2005. Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05) (pp. 886–893 vol. 1). volume 1. doi:10.1109/CVPR.2005.177.
Denby, B., Lucia, B., Orbital edge computing: Nanosatellite constellations as a new class of computer system. In Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems, 2020, Association for Computing Machinery, New York, NY, USA, 939–954, 10.1145/3373376.3378473.
Ergen, T., Kozat, S.S., 2020. A novel distributed anomaly detection algorithm based on support vector machines. Digital Signal Processing, 99, 102657. URL: https://www.sciencedirect.com/science/article/pii/S1051200420300026. doi: 10.1016/j.dsp.2020.102657.
Giuffrida, G., Fanucci, L., Meoni, G., et al. The F-sat-1 mission: The first on-board deep neural network demonstrator for satellite earth observation. IEEE Trans. Geosci. Remote Sens. 60 (2022), 1–14, 10.1109/TGRS.2021.3125567.
Heller, K.A., Svore, K.M., Keromytis, A.D. et al., 2003. One class support vector machines for detecting anomalous windows registry accesses.
Ibrahim, S.K., Ahmed, A., Zeidan, M.A.E., et al. Machine learning methods for spacecraft telemetry mining. IEEE Trans. Aerospace Electron. Syst. 55:4 (2018), 1816–1827.
Jayaraman, V., Chandrasekhar, M., Rao, U., 1997. Managing the natural disasters from space technology inputs. Acta Astronaut., 40(2), 291–325. URL: https://www.sciencedirect.com/science/article/pii/S009457659700101X. Enlarging The Scope of Space Applications.
Kacker, S., Meredith, A., Cahoy, K. et al., 2022. Machine learning image processing algorithms onboard ops-sat.
Keerthi, S.S., Lin, C.-J., Asymptotic behaviors of support vector machines with Gaussian Kernel. Neural Comput. 15:7 (2003), 1667–1689, 10.1162/089976603321891855.
Labrèche, G., Evans, D., Marszk, D., et al. Ops-sat spacecraft autonomy with tensorflow lite, unsupervised learning, and online machine learning. In 2022 IEEE Aerospace Conference (AERO), 2022, 1–17, 10.1109/AERO53065.2022.9843402.
Laib dit Leksir, Y., Mansour, M., Moussaoui, A., 2018. Localization of thermal anomalies in electrical equipment using infrared thermography and support vector machine. Infrared Phys. Technol., 89, 120–128. URL: https://www.sciencedirect.com/science/article/pii/S1350449517306631. doi: 10.1016/j.infrared.2017.12.015.
Lakshminarayanan, V., Sriraam, N., 2014. The effect of temperature on the reliability of electronic components. (pp. 1–6). doi:10.1109/CONECCT.2014.6740182.
scikit learn ( ). Support Vector Machines.
Li, Q., Wang, S., Ma, X., et al. Service coverage for satellite edge computing. IEEE Internet of Things J. 9:1 (2021), 695–705.
Li, Y., Su, G., Simplified histograms of oriented gradient features extraction algorithm for the hardware implementation. In 2015 International Conference on Computers, Communications, and Systems (ICCCS), 2015, 192–195, 10.1109/CCOMS.2015.7562899.
Manning, C.D., Raghavan, P., Schütze, H., Introduction to Information Retrieval. 2008, Cambridge University Press, Cambridge, UK.
Mateo-Garcia, G., Veitch-Michaelis, J., Smith, L., et al. Towards global flood mapping onboard low cost satellites with machine learning. Scient. Rep., 11, 2021, 10.1038/s41598-021-86650-z.
Meoni, G., Märtens, M., Derksen, D., et al. The ops-sat case: A data-centric competition for onboard satellite image classification. Astrodynamics. 2024, 1–22, 10.1007/s42064-023-0196-y.
Nalepa, J., Myller, M., Andrzejewski, J., et al. Evaluating algorithms for anomaly detection in satellite telemetry data. Acta Astronaut. 198 (2022), 689–701.
Santoni, F., Piergentili, F., Donati, S., et al. An innovative deployable solar panel system for cubesats. Acta Astronaut. 95 (2014), 210–217.
Selva, D., Krejci, D., A survey and assessment of the capabilities of cubesats for earth observation. Acta Astronaut. 74 (2012), 50–68.
Shakarami, A., Ghobaei-Arani, M., Shahidinejad, A., A survey on the computation offloading approaches in mobile edge computing: A machine learning-based perspective. Computer Networks, 182, 2020, 107496.
Systems, F. (2018). LWIR Micro Thermal Camera Module Lepton Datasheet. https://www.mouser.es/datasheet/2/227/Lepton3_3_5_Data_Sheet-2580086.pdf.
Tsang, I.W., Kwok, J.T., Cheung, P.-M., Core vector machines: Fast svm training on very large data sets. J. Mach. Learn. Res. 6:13 (2005), 363–392 URL: http://jmlr.org/papers/v6/tsang05a.html.
Vapnik, V.N., The nature of statistical learning theory. In Statistics for Engineering and Information Science, 2000.
Yang, J., Wang, W., Lin, G., et al. Infrared thermal imaging-based crack detection using deep learning. IEEE Access 7 (2019), 182060–182077, 10.1109/ACCESS.2019.2958264.
Zhang, S., Wang, P., Wan, Y., et al. V/ka-band leo high-throughput satellite and integrated satellite–terrestrial network experiment system: First two years flight results. Acta Astronaut. 201 (2022), 533–553.
Zhu, X., Support vector machines. CS769 Spring 2010 Advanced Natural Language Processing, 2010.