Real-Time HIL Emulation of DRM With Machine Learning Accelerated WBG Device Models
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The proliferation of artificial intelligence (AI) has opened up new avenues for the modeling of power electronics with ultra-fast transient responses, such as wide-bandgap (WBG) devices. This paper highlights the significance of ultra-fast transient device-level hardware emulation for the DC railway microgrid (DRM) in real-time. To this end, the proposed approach partitions the DRM power system by transmission line method (TLM) and employs gated recurrent unit (GRU) and electromagnetic transient (EMT) modeling techniques for system-level subsystems. Meanwhile, for WBG devices, gallium nitride (GaN) high electron mobility transistors (HEMT) and silicon carbide (SiC) insulated gate bipolar transistors (IGBT) are modeled using a novel physical feature neuron network (PFNN), which offers high flexibility with a variable time-step (as low as 1 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$ns$</tex-math></inline-formula> ), thereby improving the accuracy, efficiency and accelerating the emulation on the field-programmable gate array (FPGA). The effectiveness of the proposed approach is confirmed by comparing the emulation results with offline simulation results obtained from PSCAD/EMTDC ® for system-level and SaberRD ® for device-level transients. The proposed PFNN approach provides strong versatility, ultra-fast transient emulation capability, and significantly improved accuracy, which bodes well for the future of power electronics device-level emulation.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it