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

2025-06-16

AI Summary

To address the high energy consumption and communication overhead induced by cloud-based processing in industrial edge predictive maintenance (PM), this paper proposes a lightweight multi-task learning framework based on spiking neural networks (SNNs). It is the first to jointly model operational condition regression (flow rate, pressure, rotational speed) and multi-fault classification (normal, overpressure, cavitation) using tri-axial vibration signals from progressing cavity pumps. Leveraging event-driven computation and deployment on neuromorphic hardware (Intel Loihi), the framework achieves zero false negatives (0% false negative rate) for critical faults, >97% classification accuracy, and <1% regression error. A single inference on Loihi consumes only 0.0032 J—three orders of magnitude lower than x86/ARM platforms—demonstrating the substantial energy efficiency advantage of brain-inspired computing for edge PM applications.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• Develop energy-efficient SNN for vibration-based predictive maintenance
• Enable multi-task condition monitoring on edge devices
• Reduce power consumption compared to traditional hardware

Innovation

• SNNs enable energy-efficient edge vibration analysis
• Multi-task SNN for regression and classification
• Neuromorphic hardware drastically reduces power consumption