Laminar Burning Velocities for 3,320 Oxygenated Fuel Measurements

An artificial neural network model and dataset for predicting laminar burning velocities of oxygenated fuels. The dataset contains 3,320 experimental measurements for fuels including alcohols, ethers, aldehydes, ketones, esters, and hydrocarbons. The model was developed by Abdul Gani Abdul Jameel and published on figshare in May 2026.

Use Cases

• Predicting laminar burning velocity based on molecular functional groups and thermophysical parameters mentioned in the description
• Benchmarking linear regression models against a neural network framework for fuel property prediction
• Screening potential oxygenated fuels for reactivity and emission characteristics
• Developing and validating combustion simulation models with experimental data

Strengths

• Dataset of 3,320 experimental measurements for model training and validation
• Model achieved a high overall correlation coefficient (R=0.9827) and low RMSE (approx. 0.02 m/s)
• Input space combines structural descriptors and thermophysical parameters, capturing multiple influences on flame propagation

Limitations

• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment
• Data may reflect experimental bias inherent to the source studies aggregated in the dataset

Provenance

Source

Abdul Gani Abdul Jameel

Collection Method

Aggregated experimental measurements, likely from literature, used to train an artificial neural network model.

Freshness

Last updated 2026-05-24 03:06:10; freshness should be verified