Answers are grounded in this paper and cite their sources.
The increasing adoption of Permanent Magnet Synchronous Motors (PMSMs) across industrial automation and electric mobility creates challenges for reliable, non-invasive health monitoring. This paper presents a prototype Digital Twin diagnostic screening system that integrates multi-phase current acquisition, automated signal windowing, 68-dimensional physics-informed feature extraction, ensemble machine learning classification, symmetrical sequence decomposition, and 3D virtual asset synchronization. National Instruments TDMS recordings captured at 5.0 kHz from physical PMSMs (1.0 kW, 1.5 kW, and 3.0 kW) are segmented into 256-sample windows. A 350-estimator Random Forest classifier processes a 68-channel representation comprising time-domain statistical moments, 6-band Fast Fourier Transform (FFT) sub-band energy densities, and inter-phase cross-correlations. Symmetrical sequence components (I0, I1, I2) are extracted to monitor negative-sequence imbalance. An interactive Three.js 3D WebGL Digital Twin provides real-time spatial fault localization, displaying a localized thermal hotspot beacon on Stator Slot #4 and dispatching automated ISO 10816 prescriptive maintenance work orders. Under rigorous recording-level, zero window-leakage grouped 5-fold cross-validation, the model achieves 82.29% CV accuracy and 89.12% holdout test accuracy with 100.0% precision and recall on intercoil faults.
No takes yet. Share an insight, caveat, or question.
Kadam et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: