Case Analysis in AI Practice Courses: A Comparative Study of Tool Wear Prediction Methods
Bibliographic record
Abstract
Artificial intelligence is anticipated to play a crucial role in shaping the future of education and academic research. Using a mechanical testing course as a case study, this paper illustrates how AI can be effectively integrated into engineering education by examining various AI methodologies through the application of tool wear prediction. In predictive modelling, commonly used intelligent algorithms mainly come from traditional machine learning techniques, such as support vector machines (SVM) and random forests, as well as deep learning methods like long short-term memory (LSTM) and gated recurrent units (GRU). Traditional models generally rely on manual feature extraction, which provides a degree of interpretability but often falls short in capturing the dynamic characteristics of time-series data. This study assesses the performance of several deep learning algorithms in predicting tool wear. The CNN-LSTM hybrid model consistently outperformed other models across all evaluation metrics. Specifically, compared to the GRU model, it reduced RMSE by 42.07% and MAE by 52.06%, while improving R² by 4.43%. When compared to the standalone LSTM model, the CNN-LSTM model achieved a 17.72% reduction in RMSE and a 42.25% decrease in MAE, along with a 2.97% increase in R². These results indicate that the CNN-LSTM architecture successfully combines CNN's proficiency in automatic local feature extraction with LSTM's capacity to model long-term temporal dependencies, thereby providing a highly effective and accurate method for tool wear 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 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 | 0.009 | 0.031 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".