Using Big Data and Machine Learning to Improve Aircraft Reliability and Safety
Bibliographic record
Abstract
The evolution of aircraft systems monitoring technology has made it possible to acquire increasing amounts of data. The big volume of available information has helped aerospace companies to increase the reliability and availability of their products and to improve the safety of aircraft, flight crew and passengers. In the event of system failures, the high complexity of the new aircraft systems, combined with the large amount of data provided by them, make the management of risk assessments a more complex activity and make the decision- making process more accurate but challenging. This process may lead to excessive conservatism when evaluating risk levels, which may in turn impact operation costs and production costs; increase the flight crew’s workload due to possibility to add more work to their normal tasks to deal with systems failures; or, conversely, lead to an underestimation of the criticality of the risk, thus exposing aircraft occupants to an unacceptable level of risk.Logical Analysis of Data (LAD) makes it possible for input signals variables or condition indicators of different physical components to be combined and compared in multiple scenarios, in a process known as pattern recognition and interpretation of physical condition. This paper addresses the potential for machine learning and pattern generation and interpretation to support reliability and safety in the aerospace industry. It examines a set of three scenarios from industry practice: in the first two, Machine Learning (ML) is used as a supporting tool for reducing costs, and improving reliability and safety, respectively. In the final scenario, ML is embedded in the system architecture to highlight the challenges of the use of ML in association with the current design assurance levels for software and real-time risk assessment. The paper ultimately aims to lay the groundwork for a better decision-making process, supporting quantitative and qualitative assessment of the level of risk in an aircraft system.
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.
How this classification was reachedexpand
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 | 0.005 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".