Answers are grounded in this paper and cite their sources.
Surface roughness (Ra) is a central quality indicator in precision CNC grinding, yet it is measured offline, after machining. Predicting Ra from machine-internal spindle signals offers process-signal-based workpiece quality prediction with the potential for in-process monitoring. We argue that model selection for such soft sensors must satisfy three requirements jointly: signal, robustness beyond the training campaign, and budget on a CPU-only edge gateway, including the feature-extraction cost of classical pipelines. We evaluate feature-based classical regressors, end-to-end sequence models (1D CNN, BiGRU), and the kernel-based MultiRocket transform on the High Precision CNC-Grinding Roughness dataset (20 workpieces, two campaigns) under leave-one-workpiece-out and cross-campaign protocols with strictly fold-internal preprocessing, workpiece-level bootstrap confidence intervals, and an edge-oriented deployment benchmark that charges feature extraction to the classical path. Within the known campaigns, the best models reach an MAE of 0.17 μm (R2≈0.5), 44% below a mean-prediction baseline. Under campaign shift, no model retains practically useful accuracy and the within-distribution ranking partially inverts. We trace this to a strong campaign-level target shift (Cohen’s d=3.24) perfectly confounded with the only varying process parameter, so that within-distribution accuracy may reflect campaign identity rather than a campaign-invariant process–roughness relationship. The compact CNN is the cheapest complete pipeline (5.4 ms model path per workpiece), whereas the evaluated library-level MultiRocket implementation costs 7.0 s. Each family fails a different requirement; we give guidance on which deployment claims the data currently support.
No takes yet. Share an insight, caveat, or question.
Schneider et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: