AI-Assisted Design of a Compact Voltage Monitoring System with a Millisecond-Delayed Fault Detection Circuit
Bibliographic record
Abstract
Voltage monitoring systems (VMS) with delayed fault detection (DFD) are critical for ensuring safe operation of voltage-sensitive integrated circuits. Traditional design approaches for such analog systems are manual, requiring time-consuming repetitive interactions with simulators. While artificial intelligence (AI)-assisted design methods have emerged, they focus on the design of isolated circuits and do not show their coordinated performance in a full system. This paper introduces an AI-driven approach for the design of a VMS-DFD implemented in a 180 nm silicon-on-insulator (SOI) process. The proposed approach generated hundreds of specification-compliant solutions for the critical circuits in the VMS-DFD, namely a hysteric comparator, an op-amp-based reference voltage circuit, and a delay element, in a fraction of the time needed by the traditional approach. For the delay element, 100 valid solutions targeting a 1 ms delay were generated in 2.17 hours, compared to five weeks required for a single manual solution. The most area-efficient design yielded an 84% area reduction in the delay element resulting in a 22% system-level area saving. The AI-Assisted design of the comparator and op-amp required only 2.4 and 6 hours, respectively. The resulting circuits were integrated into a full VMS-DFD, demonstrating stable system performance across process, voltage, and temperature (PVT) corners, achieving better delay-voltage sensitivity (2.37 ms/V vs. 3.39 ms/V) and comparable temperature sensitivity (0.116 ms/°C vs. 0.097 ms/°C) relative to a system with manually designed circuits.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".