Comparative Analysis of Prediction Algorithms for Surface Roughness in AI-oriented Courses
Bibliographic record
Abstract
The integration of artificial intelligence (AI) into mechanical engineering curricula has garnered significant interest. A critical challenge lies in effectively incorporating AI technologies into foundational courses, which is essential for advancing the practical implementation of AI. In the field of machining, surface roughness serves as a crucial parameter for assessing the quality of manufactured components, influencing properties such as wear resistance, fatigue strength, and dimensional accuracy. Conventional empirical approaches struggle to accurately model the complex nonlinear dynamics involved in machining processes. As a result, data-driven intelligent prediction methods have emerged as a prominent area of research in this domain. This paper aims to investigate the effectiveness of machine learning algorithms in predicting surface roughness. Prediction models are developed using the Exponential Function (EF), Ridge Regression (RR), Gradient Boosting Regression (GBR), eXtreme Gradient Boosting (XGBoost), and Ensemble Learning based on a Genetic Algorithm (ELGA). Through the training and testing based on experimental data, the prediction accuracy and stability of various algorithms were evaluated and compared. The results demonstrate that the ELGA algorithm proposed in this paper further reduces prediction error by employing a unique global optimization strategy. Specifically, the root mean square error (RMSE) is 0.035, the mean absolute percentage error (MAPE) is 0.027, and the coefficient of determination (R²) reaches 0.955. Overall, ELGA outperforms individual machine learning models, significantly enhancing both the accuracy and robustness of predictive performance. This advancement provides an effective solution and a valuable reference for algorithm selection in high-precision surface roughness prediction.
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 | 0.002 | 0.003 |
| 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".