# BearingNAS: Obtaining In-Sensor Intelligent Fault Diagnosis Systems for Bearings Using a Laptop

arXiv: https://arxiv.org/abs/2607.18287 · HTML: https://mlsanity.com/paper/2607.18287/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 32 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Builds on (most cited first, 7 of 7)

- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [A Comprehensive Survey on Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2101.09336/) (2021)
- [A novel time-frequency Transformer based on self-attention mechanism and its application in fault diagnosis of rolling bearings](https://mlsanity.com/paper/2104.09079/) (2021)
- [Searching Neural Architectures for Sensor Nodes on IoT Gateways](https://mlsanity.com/paper/2505.23939/) (2025)
- [An affordable hardware-aware neural architecture search for deploying convolutional neural networks on ultra-low-power computing platforms](https://mlsanity.com/paper/2606.16290/) (2026)
- [Leveraging systems' non-linearity to tackle the scarcity of data in the design of Intelligent Fault Diagnosis Systems](https://mlsanity.com/paper/2606.20323/) (2026)

## Abstract (arXiv)

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.