Enhanced Fault Detection in Satellite Attitude Control Systems Using LSTM-Based Deep Learning and Redundant Reaction Wheels
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Reliable fault detection in satellite attitude control systems stands as a critical aspect of ensuring the safety and success of space missions. Central to these systems, reaction wheels (RWs), despite being the most frequently used actuators, present a vulnerability given their susceptibility to faults—a factor with the potential to precipitate catastrophic failures such as total satellite loss. In light of this, we introduce a fault detection methodology grounded in deep learning techniques specifically designed for satellite attitude control systems. Our proposed method utilizes a Long Short-Term Memory (LSTM) model adept at learning temporal patterns inherent to both healthy and faulty system behaviors. Incorporated into our model is a torque allocation algorithm designed to circumvent specific velocities known to induce torque disturbances, a factor known to influence LSTM performance adversely. To bolster the robustness of our fault detection technique, we also incorporated denoising autoencoders within the LSTM framework, thereby enabling the model to identify temporal patterns in healthy and faulty system behavior, even amidst the noise. The method was evaluated using cross-validation on simulated satellite data comprising 1000 time series samples and across different fault scenarios, such as stiction and resonance at varying intensities (90%, 50%, and 30%). The results confirm achieving performance metrics such as Mean Squared Error for accurate fault identification. This research underscores a stride in the evolution of fault detection and control strategies for satellite attitude control systems, holding promise to boost the reliability and efficiency of future space missions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it