Physics-Informed Machine Learning Modeling and Inferencer-in-the-Loop Based Real-Time Digital-Twin Emulation for a Maglev Transportation System
Bibliographic record
Abstract
In response to the increasing demands for efficient, sustainable, and high-speed transportation systems, magnetic levitation (Maglev) train technology has garnered significant attention due to its frictionless operation, high efficiency, low maintenance and environmental benefits. However, accurately capturing the complex interactions among electrical, mechanical, and disparate electromagnetic components remains a significant modeling challenge. This paper introduces a physics-informed machine learning (PIML)-based modeling framework specifically designed for Maglev systems, enhanced by real-time digital-twin emulation implemented on a Xilinx UltraScale+ VCU118 FPGA platform. The proposed physics-informed partitioned neural network (PIPNN) leverages physical principles within its architecture, providing superior predictive accuracy, interpretability, and computational efficiency compared to conventional electromagnetic transient (EMT) methods and traditional neural network models. Comprehensive emulations validate the PIPNN's capability to emulate Maglev system dynamics in real-time with a prediction error consistently below 5%, highlighting errors as low as 2% for specific subsystem variables. Additionally, the hybrid offline-online training strategy and the real-time inferencer-in-the-loop (IIL) digital-twin framework enhance the model's adaptability and robustness under varying operational conditions, demonstrating significant potential for practical deployment in advanced transportation systems.
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 | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".