aiqbench analysis
This research advances the frontier of Edge AI by demonstrating how Hardware-Aware Neural Architecture Search (HW-NAS) can deploy high-accuracy fault diagnosis directly onto low-memory sensor dies without requiring expensive GPUs. By optimizing models for extreme micro-budgets, BearingNAS proves that shifting intelligence into the sensor package is a viable path toward scalable industrial IoT applications.
BearingNAS: Obtaining In-Sensor Intelligent Fault Diagnosis Systems for Bearings Using a Laptop
arXiv:2607.18287v1 Announce Type: cross Abstract: This paper introduces BearingNAS, a Hardware-Aware Neural Architecture Search (HW-NAS) framework designed to shift the intelligence directly onto the sensor die via in-sensor processing. BearingNAS frames the search as a constrained optimization problem targeting extreme micro-budgets (4 to 8 kiB of RAM and 16 to 32 kiB of Flash). To eliminate the reliance on expensive discrete GPUs, we propose a lightweight, derivative-free search strategy paired with a single data-flow search space that leverages a decaying kernel growth formulation to prevent parameter explosion. We evaluate our framework on the Case Western Reserve University (CWRU) bearing benchmark, optimizing architectures for three STMicroelectronics targets: two commodity microcontrollers and the LSM6DSO16IS Intelligent Sensor Processing Unit (ISPU). Running entirely on a laptop CPU, the search converges in less than an hour. The resulting best in-sensor architecture achieves a highly competitive diagnostic accuracy of 99.50\% on the ISPU. These results demonstrate the viability of shifting the machine learning workload inside the sensor package, enabling low-cost, production-scale bearing fault diagnosis.
Abstract:This paper introduces BearingNAS, a Hardware-Aware Neural Architecture Search (HW-NAS) framework designed to shift the intelligence directly onto the sensor die via in-sensor processing. BearingNAS frames the search as a constrained optimization problem targeting extreme micro-budgets (4 to 8 kiB of RAM and 16 to 32 kiB of Flash). To eliminate the reliance on expensive discrete GPUs, we propose a lightweight, derivative-free search strategy paired with a single data-flow search space that leverages a decaying kernel growth formulation to prevent parameter explosion. We evaluate our framework on the Case Western Reserve University (CWRU) bearing benchmark, optimizing architectures for three STMicroelectronics targets: two commodity microcontrollers and the LSM6DSO16IS Intelligent Sensor Processing Unit (ISPU). Running entirely on a laptop CPU, the search converges in less than an hour. The resulting best in-sensor architecture achieves a highly competitive diagnostic accuracy of 99.50\% on the ISPU. These results demonstrate the viability of shifting the machine learning workload inside the sensor package, enabling low-cost, production-scale bearing fault diagnosis.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2607.18287 [cs.LG]
(or arXiv:2607.18287v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2607.18287 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 258 words
Related coverage
News
Quantum Computing Report · Jun 7, 2026
Deconfusing Corrigibility
AI Alignment Forum · Oct 17, 2026
Physically Verifiable Evidence and LLM-Based Reporting for Bearing Fault Diagnosis
arXiv · Jul 28, 2026
A Reliable Fault Diagnosis Method Based on Belief Rule Base Consider Robustness Analysis
arXiv · Jun 10, 2026