Machine Learning Approaches for Data-Driven Self-Diagnosis and Fault Detection in Spacecraft Systems
Ensuring the reliability and robustness of spacecraft systems remains a key challenge, particularly given the limited feasibility of continuous real-time monitoring during on-orbit operations. In the domain of Fault Detection, Isolation, and Recovery (FDIR), no universal strategy has yet emerged. Tr...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/14/7761 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839616603775303680 |
|---|---|
| author | Enrico Crotti Andrea Colagrossi |
| author_facet | Enrico Crotti Andrea Colagrossi |
| author_sort | Enrico Crotti |
| collection | DOAJ |
| description | Ensuring the reliability and robustness of spacecraft systems remains a key challenge, particularly given the limited feasibility of continuous real-time monitoring during on-orbit operations. In the domain of Fault Detection, Isolation, and Recovery (FDIR), no universal strategy has yet emerged. Traditional approaches often rely on precise, model-based methods executed onboard. This study explores data-driven alternatives for self-diagnosis and fault detection using Machine Learning techniques, focusing on spacecraft Guidance, Navigation, and Control (GNC) subsystems. A high-fidelity functional engineering simulator is employed to generate realistic datasets from typical onboard signals, including sensor and actuator outputs. Fault scenarios are defined based on potential failures in these elements, guiding the data-driven feature extraction and labeling process. Supervised learning algorithms, including Support Vector Machines (SVMs) and Artificial Neural Networks (ANNs), are implemented and benchmarked against a simple threshold-based detection method. Comparative analysis across multiple failure conditions highlights the strengths and limitations of the proposed strategies. Results indicate that Machine Learning techniques are best applied not as replacements for classical methods, but as complementary tools that enhance robustness through higher-level self-diagnostic capabilities. This synergy enables more autonomous and reliable fault management in spacecraft systems. |
| format | Article |
| id | doaj-art-e44596bafec54c5f90f2a9aa3d9f70f9 |
| institution | Matheson Library |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-e44596bafec54c5f90f2a9aa3d9f70f92025-07-25T13:12:17ZengMDPI AGApplied Sciences2076-34172025-07-011514776110.3390/app15147761Machine Learning Approaches for Data-Driven Self-Diagnosis and Fault Detection in Spacecraft SystemsEnrico Crotti0Andrea Colagrossi1Department of Aerospace Science and Technology, Politecnico di Milano, Via La Masa 34, 20156 Milan, ItalyDepartment of Aerospace Science and Technology, Politecnico di Milano, Via La Masa 34, 20156 Milan, ItalyEnsuring the reliability and robustness of spacecraft systems remains a key challenge, particularly given the limited feasibility of continuous real-time monitoring during on-orbit operations. In the domain of Fault Detection, Isolation, and Recovery (FDIR), no universal strategy has yet emerged. Traditional approaches often rely on precise, model-based methods executed onboard. This study explores data-driven alternatives for self-diagnosis and fault detection using Machine Learning techniques, focusing on spacecraft Guidance, Navigation, and Control (GNC) subsystems. A high-fidelity functional engineering simulator is employed to generate realistic datasets from typical onboard signals, including sensor and actuator outputs. Fault scenarios are defined based on potential failures in these elements, guiding the data-driven feature extraction and labeling process. Supervised learning algorithms, including Support Vector Machines (SVMs) and Artificial Neural Networks (ANNs), are implemented and benchmarked against a simple threshold-based detection method. Comparative analysis across multiple failure conditions highlights the strengths and limitations of the proposed strategies. Results indicate that Machine Learning techniques are best applied not as replacements for classical methods, but as complementary tools that enhance robustness through higher-level self-diagnostic capabilities. This synergy enables more autonomous and reliable fault management in spacecraft systems.https://www.mdpi.com/2076-3417/15/14/7761fault detection, isolation, and recovery (FDIR)spacecraft autonomyself-diagnosisartificial intelligencedata-driven methodsguidance, navigation, and control |
| spellingShingle | Enrico Crotti Andrea Colagrossi Machine Learning Approaches for Data-Driven Self-Diagnosis and Fault Detection in Spacecraft Systems Applied Sciences fault detection, isolation, and recovery (FDIR) spacecraft autonomy self-diagnosis artificial intelligence data-driven methods guidance, navigation, and control |
| title | Machine Learning Approaches for Data-Driven Self-Diagnosis and Fault Detection in Spacecraft Systems |
| title_full | Machine Learning Approaches for Data-Driven Self-Diagnosis and Fault Detection in Spacecraft Systems |
| title_fullStr | Machine Learning Approaches for Data-Driven Self-Diagnosis and Fault Detection in Spacecraft Systems |
| title_full_unstemmed | Machine Learning Approaches for Data-Driven Self-Diagnosis and Fault Detection in Spacecraft Systems |
| title_short | Machine Learning Approaches for Data-Driven Self-Diagnosis and Fault Detection in Spacecraft Systems |
| title_sort | machine learning approaches for data driven self diagnosis and fault detection in spacecraft systems |
| topic | fault detection, isolation, and recovery (FDIR) spacecraft autonomy self-diagnosis artificial intelligence data-driven methods guidance, navigation, and control |
| url | https://www.mdpi.com/2076-3417/15/14/7761 |
| work_keys_str_mv | AT enricocrotti machinelearningapproachesfordatadrivenselfdiagnosisandfaultdetectioninspacecraftsystems AT andreacolagrossi machinelearningapproachesfordatadrivenselfdiagnosisandfaultdetectioninspacecraftsystems |