Machine Learning Approaches for Predicting Flow and Consistency Retention Performance in Cementitious Mixtures with Diverse Grinding Aid Dosages and Types

Yahya Kaya, Veysel Kobya, Naz Mardani, Gulveren Tabansiz-Goc, Fatih Cavdur, Ali Mardani · 2026

Read Machine Learning Approaches for Predicting Flow and Consistency Retention Performance in Cementitious Mixtures with Diverse Grinding Aid Dosages and Types by Yahya Kaya, Veysel Kobya, Naz Mardani, Gulveren Tabansiz-Goc, Fatih Cavdur, Ali Mardani (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13567626.txt.

Description

Yahya Kaya and co-authors ask in a 2026 study whether machine learning can spare cement makers the slow bench tests of how a mix flows and stiffens. Grinding aids save energy in cement mills but can sap flow and shorten working time. Twenty-nine cements with varied aids and doses were tested for flow over time and for strength.

Four models raced the bench data. A random forest best predicted compressive strength, while a multilayer perceptron best predicted flow values. Both beat the tedium of full testing within the study's aid types. Predictive screening, the authors suggest, can shortlist mixes before the lab work starts.

Catalog record

CREATORYahya Kaya, Veysel Kobya, Naz Mardani, Gulveren Tabansiz-Goc, Fatih Cavdur, Ali Mardani
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE55 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13567626

Browse the full library · About the Tower of Babel