What question did this study set out to answer?

The aim is to develop and evaluate advanced stall warning techniques using pressure measurements in compressors.

May 9, 2026Journal of Turbomachinery

Advanced Compressor Stall Warning Using Cross-Correlation and Deep Learning Based Approaches

View Full Paper

Ask AI

Bookmark

Authors

MEMario EckChina Aerodynamics Research and Development Center ETErgin TüzünerChina Aerodynamics Research and Development Center RERobin EckerChina Aerodynamics Research and Development Center

Discussion

Member takes

Implication

Randomized trial evaluates cross-correlation and deep learning methods for stall warning in compressors, suggesting robust performance even under varying conditions.

Key Points

The aim is to develop and evaluate advanced stall warning techniques using pressure measurements in compressors.
Applied three methods: cross-correlation technique, Convolutional Neural Network, and autoencoder.
Methods were validated using independent datasets from two axial compressors with distinct stall characteristics.
Techniques assessed for robustness under varying signal-to-noise conditions.
Deep-learning approaches provide precise warnings at about 5% stall margin.
Cross-correlation method triggers at a similar level only when the compressor is free of pre-stall instabilities.
All methods show strong applicability for reliable stall warning without manual threshold tuning.

Cite This Study

Eck et al. (2026) studied this question.

synapsesocial.com/papers/69fed0e2b9154b0b8287806d https://doi.org/10.1115/1.4071890

View Full Paper

Ask AI

Bookmark

May 9, 2026Journal of Turbomachinery

Advanced Compressor Stall Warning Using Cross-Correlation and Deep Learning Based Approaches

View Full Paper

Ask AI

Bookmark

Authors

MEMario EckChina Aerodynamics Research and Development Center ETErgin TüzünerChina Aerodynamics Research and Development Center RERobin EckerChina Aerodynamics Research and Development Center

Discussion

Member takes

Implication

Randomized trial evaluates cross-correlation and deep learning methods for stall warning in compressors, suggesting robust performance even under varying conditions.

Key Points

The aim is to develop and evaluate advanced stall warning techniques using pressure measurements in compressors.
Applied three methods: cross-correlation technique, Convolutional Neural Network, and autoencoder.
Methods were validated using independent datasets from two axial compressors with distinct stall characteristics.
Techniques assessed for robustness under varying signal-to-noise conditions.
Deep-learning approaches provide precise warnings at about 5% stall margin.
Cross-correlation method triggers at a similar level only when the compressor is free of pre-stall instabilities.
All methods show strong applicability for reliable stall warning without manual threshold tuning.

Cite This Study

Eck et al. (2026) studied this question.

synapsesocial.com/papers/69fed0e2b9154b0b8287806d https://doi.org/10.1115/1.4071890

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark