PulseAugur
EN
LIVE 09:18:21

MIMONet uses neural operators for virtual sensing in inaccessible systems

Researchers have developed MIMONet, a novel operator-based virtual sensing framework designed for real-time monitoring of inaccessible or unmeasurable parameters in safety-critical systems, such as nuclear-grade thermal-fluid systems. This approach utilizes neural operators to infer internal fields from sparse boundary measurements, distinguishing itself from traditional estimation methods. Evaluated on complex scenarios including pressurized water reactor subchannels and heat exchangers, MIMONet demonstrated high accuracy with less than 5% relative errors and achieved sub-millisecond inference times on NVIDIA H200 hardware, even under significant sensor noise. AI

IMPACT This research advances the use of neural operators for real-time monitoring in critical infrastructure, potentially improving safety and efficiency where physical sensors are not feasible.

RANK_REASON The cluster contains an academic paper detailing a new AI-based method (MIMONet) for virtual sensing, published on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Kazuma Kobayashi, Farid Ahmed, Jaewan Park, Subhankar Sarkar, Souvik Chakraborty, Syed Bahauddin Alam ·

    Virtual Sensing to Enable Real-Time Monitoring of Inaccessible Locations & Unmeasurable Parameters

    arXiv:2412.00107v2 Announce Type: replace-cross Abstract: Real-time monitoring of safety-critical interior states remains an open problem in energy systems where physical instrumentation is infeasible. Existing approaches rely on explicit governing equations, finite-dimensional s…