insider brief
- WISER and Fraunhofer ITWM investigated the use of quantum machine learning for anomaly detection in industrial production systems.
- The collaboration evaluated quantum neural networks for tasks such as air pressure leak detection and rotating machinery failure analysis using industrial sensor data.
- This study investigated how short-term quantum AI methods can support predictive maintenance and process optimization in industrial environments.
Press Release — At the core of this collaboration, we considered how new quantum computing techniques can be supported. Anomaly detection in manufacturingis a critical task for identifying faults in complex production systems. These approaches analyze sensor data from industrial equipment to detect anomalies early, aiming to reduce downtime, improve quality control, and increase overall efficiency. The research focuses on practical scenarios such as identifying air pressure leaks and detecting faults in rotating machinery, and shows how quantum-enhanced models can complement existing data-driven solutions in industry.
Based on this application perspective, the team conducted a systematic evaluation. quantum neural network (QNN), a class of machine learning models designed for short-term quantum hardware. Results show that QNN can achieve competitive performance, including 87.77% accuracy in air pressure leak detection and strong ROC-AUC performance on NASA bearing failure dataset. This study further analyzes key design choices such as data encoding strategies and highlights binary versus exponential encoding as an effective trade-off between model expressiveness and trainability. Complete technical details are available in the corresponding arXiv publication.
»Quantum neural networks (QNNs) have the potential to integrate quantum principles into machine learning. However, significant gaps exist in understanding the practical limitations of QNNs in terms of trainability and approximation capabilities. Our work provides a roadmap for choosing analyzes that balance expressive power on both synthetic and real-world datasets while using a limited number of qubits to address noise issues. ” said Vardaan Sahgal of WISER.
Introducing quantum machine learning into industrial practice
Data-driven methodologies, including quantum-inspired and quantum-native approaches, offer new opportunities for predictive maintenance and process optimization across sectors such as aerospace, automotive, energy, and industrial automation.
“This research demonstrates how quantum machine learning can be applied to real-world industrial problems today, while also highlighting the potential to improve the quality of decision support in complex production environments as quantum hardware continues to evolve,” said Dr. Pascal Halffmann from Fraunhofer ITWM.
This partnership reflects WISER’s mission to accelerate applied innovation by connecting emerging technologies with real-world challenges through Solution Launchpads. This collaboration, combined with Fraunhofer ITWM’s expertise in industrial mathematics, provides a structured pathway to evaluate early-stage quantum technologies and translate them into relevant industrial use cases.
