RUL Prediction Performance Comparison Under Sensor Fault Conditions

A comparison of Remaining Useful Life prediction performance between a proposed framework and representative deep learning models under sensor fault conditions. The dataset was authored by Dongdong Tang and last updated on 2026-04-29. Performance is evaluated using RMSE, the standard C-MAPSS scoring function, and statistical significance.

Use Cases

• Benchmarking new RUL prediction algorithms against established deep learning models based on the described performance metrics.
• Analyzing the impact of sensor fault conditions on prognostic model accuracy based on the described experimental setup.
• Evaluating the statistical significance of performance differences between prognostic frameworks based on the described analysis.

Strengths

• Dataset is small at 5.5 KB, enabling quick download and inspection.
• Released under a permissive CC-BY-4.0 license, allowing for broad reuse and modification.
• Performance evaluation includes multiple metrics: RMSE, C-MAPSS scoring, and statistical significance.

Limitations

• Row count is unknown, which may limit suitability assessment for large-scale training.
• Column-level documentation is absent; field semantics must be inferred after download.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

figshare

Collection Method

Likely contains results from computational experiments comparing prognostic models.

Freshness

Last updated 2026-04-29 17:37:18; freshness should be verified.