Statistical Results by Gearbox Failure Severity from Vibration Experiments

Experimental data from a study proposing a dynamic principal component analysis methodology for detecting progressive failures in spur gearboxes. The dataset covers combinations of load, speed, and failure severity, validated using vibration signals segmented and characterized with time and frequency domain indicators. It was authored by Antonio Pérez-Torres and last updated on 2026-05-18.

Use Cases

• Training failure detection models based on vibration signal condition indicators mentioned in the description
• Benchmarking multivariate statistical process control methods based on Hotelling’s T² statistic and squared prediction error
• Analyzing the relationship between operational parameters (load, speed) and failure progression based on the experimental design

Strengths

• File size is 9.5 KB, indicating a focused and manageable dataset.
• License is CC-BY-4.0, permitting open sharing and modification.
• Dataset is empirically validated using an experimental setup covering load, speed, and failure severity combinations.

Limitations

• Row count is unknown, which may limit suitability assessment.
• 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

Empirical validation using an experimental dataset, as described.

Freshness

Last updated 2026-05-18 17:46:32; freshness should be verified.