What does this research mean for the field?

Symbolic Regression combined with active learning effectively models immersion mill performance in data-sparse environments, revealing an unexpectedly weak relationship between final particle size and impeller speed or media content compared to classic vertical stirred mills. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The central aim is to evaluate various machine learning models for predicting immersion mill performance and energy consumption.

June 13, 2026ParticuologyOpen Access

Prediction of immersion mill performance and energy use via machine learning

View Full Paper

Ask AI

Bookmark

The central aim is to evaluate various machine learning models for predicting immersion mill performance and energy consumption.
Compared three machine learning models: Random Forest Regression, Gradient Boosted Trees, and Symbolic Regression.
Utilized active learning strategies on a limited dataset of 15 batches.
Assessed models based on their performance, interpretability, and usability in data-sparse environments.
Symbolic Regression models were found to be the most effective based on performance on unseen data.
The relationship between final particle size and factors like impeller speed is weaker than expected for this mill design.
Predictive models developed can optimize immersion milling while addressing changes in particle size distribution.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Comparative assessment finds symbolic regression most effective for predicting immersion mill performance and energy use.

Cite This Study

Weston et al. (2026) studied this question.

synapsesocial.com/papers/6a2cf3b4faef96ed7f05632b https://doi.org/10.1016/j.partic.2026.05.023

View Full Paper

Ask AI

Bookmark

Prediction of immersion mill performance and energy use via machine learning

Key Points

Discussion

Implication

Cite This Study

Prediction of immersion mill performance and energy use via machine learning

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider