Experimental investigation and machine learning-based prediction of brittleness index in heavyweight cement slurries
Bibliographic record
Abstract
In engineering design, the brittleness index (BI) seems to play a significant role in material selection, failure forecasting, and service performance. Determining BI is traditionally a laborious, expensive, and highly experimental process. This study gives a full framework that combines experimental tests with machine learning methods to model the brittleness behavior of the heavy-weight cement slurries. The study is based on different experimental tests, such as Split Hopkinson pressure bar Test, Uniaxial Compressive Strength Test, Brazilian Test and etc. on mechanical and physical properties of ten different slurry formulations and a dataset of 250 experimental observations from these formulations, each with 14 independent input parameters. Fourteen machine learning models were created, and their accuracy and dependability were statistically compared, and a new Equation has been developed for estimating the BI based on the test results. Gaussian process regression and support vector regression were the two most accurate models based on interaction with each of the models; when using the full set of input variables, their R 2 values ranged from 0.93 to 0.97. When variable selections were applied to the final models, the number of features taken into consideration was lowered to eight, which resulted in further accuracy improvements and R 2 values ranging from 0.940 to 0.990. Even though every factor affected the BI, EP had the biggest impact; the main goal of some additives was to lessen brittleness. By using more sophisticated machine learning algorithms, this research provides a new method for predicting business intelligence, which lowers the time and expense required and improves decision-making.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".