Systematic Literature Review Data on AI for Gearbox Fault Detection

A 300.4 KB bibliometric dataset in RDATA format, last updated May 17, 2026. It contains processed data from a systematic literature review on using sensor signals and AI for gearbox fault severity classification. The dataset was prepared by Antonio Pérez-Torres and includes bibliometric data from Web of Science and Scopus, cleaned and analyzed with R scripts.

Use Cases

• Conducting bibliometric analysis based on cleaned Web of Science and Scopus data.
• Reproducing or extending the systematic review process using the provided R scripts.
• Analyzing research trends in AI-driven fault detection for mechanical systems based on the information extraction matrix.

Strengths

• Data is cleaned and ready for analysis, as indicated by the description.
• Includes R scripts for bibliometrix, facilitating reproducibility.
• Follows PRISMA 2020 guidelines, suggesting a structured review methodology.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset's 300.4 KB size indicates a very limited scope, likely containing only processed metadata and analysis scripts.

Provenance

Source

Web of Science and Scopus bibliometric data.

Collection Method

Systematic literature review following PRISMA 2020, with data cleaned and analyzed using R and the bibliometrix package.

Freshness

Last updated 2026-05-17 04:02:50; freshness should be verified.