Quantum

Predictive Maintenance at the Edge: An Embedded Anomaly Detection Pipeline Trained with Quantum Optimization

Read full article at source ↗

Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 02/11/2026, 05:13:25 UTC.

Briefings

A new predictive maintenance pipeline detects bearing anomalies using vibration signals, adapted for edge deployment on low-cost microcontrollers. The system uses a one-class support vector machine (OCSVM) trained via variational quantum optimization, specifically employing variational quantum eigensolver (VQE) for feature selection and Pauli-correlation encoding (PCE) for classification. Initial small-scale tests on a simulator using the Paderborn bearing dataset showed VQE found the optimal feature selection in 36% of runs with Adam optimizer, while PCE selected better support vectors than chance until a classical local search equalized the results.

Key points

• The pipeline uses a one-class support vector machine (OCSVM) trained via variational quantum optimization to detect bearing anomalies in vibration signals.
• VQE found the optimal feature selection in 36% of runs with Adam optimizer on the Paderborn bearing dataset simulator.

Context

This research presents an embedded anomaly detection pipeline for predictive maintenance, adapted for deployment on low-cost microcontrollers. The method combines quantum optimization techniques with classical machine learning to optimize feature selection and classification for edge devices.

Limitations

Initial results were obtained from small-scale simulator tests using the Paderborn bearing dataset. Results are preliminary and may not reflect real-world performance on diverse hardware or operational conditions.

Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 02/11/2026, 06:15:34 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.

View archived briefing on IPFS
bafybeiab4bjg5qssq32kme6r4ogdjsqs42zbrzduqc3c7rs6hxu4qpptru