# Spiking Neural Networks for Low-Power Vibration-Based Predictive Maintenance

arXiv: https://arxiv.org/abs/2506.13416 · HTML: https://mlsanity.com/paper/2506.13416/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 35 references that are in the map.
- First posted on arXiv 16 Jun 2025.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Training Spiking Neural Networks Using Lessons From Deep Learning](https://mlsanity.com/paper/2109.12894/) (2021)
- [Benchmarking Keyword Spotting Efficiency on Neuromorphic Hardware](https://mlsanity.com/paper/1812.01739/) (2018)
- [Online Detection of Vibration Anomalies Using Balanced Spiking Neural Networks](https://mlsanity.com/paper/2106.00687/) (2021)
- [Low-Power Vibration-Based Predictive Maintenance for Industry 4.0 using Neural Networks: A Survey](https://mlsanity.com/paper/2408.00516/) (2024)
- [A PyTorch-Compatible Spike Encoding Framework for Energy-Efficient Neuromorphic Applications](https://mlsanity.com/paper/2504.11026/) (2025)

## Built on by (most cited first, 1 of 1)

- [Neuromorphic Parameter Estimation for Power Converter Health Monitoring Using Spiking Neural Networks](https://mlsanity.com/paper/2604.15714/) (2026)

## Abstract (arXiv)

Advancements in Industrial Internet of Things (IIoT) sensors enable sophisticated Predictive Maintenance (PM) with high temporal resolution. For cost-efficient solutions, vibration-based condition monitoring is especially of interest. However, analyzing high-resolution vibration data via traditional cloud approaches incurs significant energy and communication costs, hindering battery-powered edge deployments. This necessitates shifting intelligence to the sensor edge. Due to their event-driven nature, Spiking Neural Networks (SNNs) offer a promising pathway toward energy-efficient on-device processing. This paper investigates a recurrent SNN for simultaneous regression (flow, pressure, pump speed) and multi-label classification (normal, overpressure, cavitation) for an industrial progressing cavity pump (PCP) using 3-axis vibration data. Furthermore, we provide energy consumption estimates comparing the SNN approach on conventional (x86, ARM) and neuromorphic (Loihi) hardware platforms. Results demonstrate high classification accuracy (>97%) with zero False Negative Rates for critical Overpressure and Cavitation faults. Smoothed regression outputs achieve Mean Relative Percentage Errors below 1% for flow and pump speed, approaching industrial sensor standards, although pressure prediction requires further refinement. Energy estimates indicate significant power savings, with the Loihi consumption (0.0032 J/inf) being up to 3 orders of magnitude less compared to the estimated x86 CPU (11.3 J/inf) and ARM CPU (1.18 J/inf) execution. Our findings underscore the potential of SNNs for multi-task PM directly on resource-constrained edge devices, enabling scalable and energy-efficient industrial monitoring solutions.