Statistical Analysis of Model Attention for Battery Fault Types Based on Grad-CAM

5.5 KB of statistical results analyzing the distribution of a model's attention across different fault types using Grad-CAM. The dataset, created by Xiaofei Yin and last updated on March 17, 2026, is stored in an Excel (XLS) file and is licensed under CC-BY-4.0. It appears to be derived from experiments involving lithium battery voltage data and a 2DCNN model.

Use Cases

• Compare model attention patterns for different fault types based on the statistical analysis described.
• Validate the effectiveness of Grad-CAM for extracting key fault features in diagnostic models.
• Benchmark the performance of a 2DCNN model on processing complex signals like battery voltage data.
• Study the relationship between model attention distribution and diagnostic accuracy for lithium batteries.

Strengths

• Dataset is small (5.5 KB), facilitating quick download and inspection.
• License is clearly defined as CC-BY-4.0, permitting broad reuse with attribution.
• Last update timestamp is precisely recorded as 2026-03 17:25:31.

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

Xiaofei Yin via figshare

Collection Method

Likely generated from experimental results of a research-designed model using Grad-CAM.

Time Range

null

Freshness

Last updated 2026-03-17 17:25:31; freshness should be verified.

Geography

null