Residual life prediction method of multi-source sensing linear degradation equipment based on BP neural network
Bibliographic record
Abstract
With increasing complexity in modern equipment systems, single-source degradation signals are often insufficient to characterize system health, posing significant challenges for accurate remaining useful life (RUL) prediction. This paper proposes a method for RUL prediction of equipment with linear degradation patterns using a backpropagation (BP) neural network integrated with multi-source sensing data. Composite health indicator (CHI) is constructed by a BP neural network with multi-source linear degradation signals. A one-dimensional linear Wiener process is adopted to model performance degradation, with its parameters estimated via maximum likelihood estimation. To enhance prediction accuracy and stability, the BP network is optimized using the NSGA-II algorithm, ensuring that the evolution of CHI aligns with the degradation model. Based on this matching, online RUL prediction is achieved for complex systems under multi-source monitoring. The proposed method is validated using 100 data sets of the F001 single-failure-mode engine from the C-MAPSS benchmark. Performance is evaluated through four metrics: average prediction score (0.56), accuracy (95%), mean squared error (25.81), and coefficient of determination (0.9920). Comparative analysis confirms the method’s superior performance and reliability in predicting RUL under linear degradation scenarios with complex sensor environments.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 source (direct Gemma or distilled Codex), 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".