A transfer learning approach for chatter detection in multi-posture robot machining
Bibliographic record
Abstract
Chatter stability prediction is crucial for enhancing machining accuracy and surface quality. However, in robotic machining, variations in the frequency response function (FRF) across different robot postures result in corresponding differences in the stability lobe diagram (SLD), making accurate prediction challenging. Impact testing for each posture is costly and time-consuming. To address this, this paper introduces a transfer learning method based on deep neural networks (DNNs) that enables chatter predictions to be transferred across different postures, thereby reducing the need for large datasets and testing time. First, impact hammer testing is conducted for a specific robot posture to generate the FRF and SLD. The simulated SLD data is then used to pre-train the neural network, enabling it to learn the boundaries and patterns of binary stability classification. Subsequently, a small experimental dataset from another posture, containing only a few dozen samples, is used to fine-tune the network, adapting it for chatter prediction across different postures. Experimental validation shows that the predicted SLDs for various postures align closely with experimentally determined stability limits. The results indicate that, compared to traditional machining learning methods, the transfer learning approach significantly reduces the requirement for training data while achieving high prediction accuracy.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".