Prediction of diameter error in one-setup machining test by using machinelearning algorithms
Bibliographic record
Abstract
Abstract: To efficiently collect data for training machine learning (ML) algorithms in predicting diameter error for process planning optimization, a one-setup milling test with 27 cylinders on a workpiece implements a full factorial experiment of three factors, each with three levels. The factors are cutting parameters: width of cut, cutting speed, and feedrate. Results show that, among those three factors, cutting speed is the main contributor with the standardized effect of up to 57 to the diameter error, followed by the feedrate (standardized effect of 43). Three ML algorithms are tested to predict the diameter error: Polynomial, XGboost?eXtreme Gradient Boosting) and AdaBoost (Adaptive Boosting). Besides three cutting parameters, positions of each cylinder and the desired initial diameter are also considered as features. Taking Polynomial as a base line, and using a 5-fold cross-validation method, the mean and standard deviation of R-squared of each ML algorithm are compared. It shows that both regressors perform better than the base line (average R-squared=0.7522), the average R-squared of XGboost (0.9126) is slightly higher than the one of AdaBoost, which is 0.9015. Moreover, the standard deviation of R-squared for XGboost(0.0483) is smaller than the one of AdaBoost (0.0569), which shows a more robust performance for XGboost. By applying AdaBoost or XGBoost, more than 90% of the diameter error is explained by the six inputs (positions of each cylinder in x and y on the test workpiece, three cutting parameters and the desired initial diameter).
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 teacher head, 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".