Cerchar Abrasivity Index Results for Weakly Cemented Sandstones

Cerchar abrasivity index tests on weakly cemented sandstones in western China show the dry state increases the CAI by 19.23% compared to the water-saturated state. The dataset contains training results for an improved fuzzy stochastic RBF neural network model predicting rock abrasivity. It was authored by Yafeng Yao and uploaded to figshare in April 2026.

Use Cases

• Train neural networks to predict Cerchar Abrasivity Index (CAI) using input features like hardness, wave velocity, porosity, and equivalent quartz content.
• Compare model performance metrics such as MSE, MAE, and R-squared between improved RBF, MLR, SVR, and traditional RBF models.
• Analyze the relationship between rock physical state (dry, water-saturated, mud-saturated) and the resulting Cerchar Abrasivity Ratio (CAR).
• Validate predictive models where the improved RBF's error for rock abrasivity rate is less than 5% compared to actual measurements.

Strengths

• Model predictions achieve a high coefficient of determination (R²) of 0.967.
• The improved RBF model reduced MSE by up to 65.7% and MAE by up to 47.4% compared to baseline models.

Limitations

• Dataset size is only 9.5 KB, indicating a very limited number of samples or model training records.
• Data is geographically specific to weakly cemented sandstones from western China, limiting generalizability.
• Specific row count and column details are unknown.

Provenance

Source

figshare, authored by Yafeng Yao.

Collection Method

Results from Cerchar abrasivity tests and training of an improved fuzzy stochastic RBF neural network model.

Time Range

null

Freshness

Last updated in April 2026.

Geography

Weakly cemented sandstones from western China.