Deep learning improves fault diagnosis in industrial fluid transport
Physical-Variable-Informed Deep Learning for Robust Diagnosis in Industrial Fluid Transport Systems
Machine LearningArtificial Intelligence
Summary
Industrial systems that move fluids use many different sensors to check if something is wrong, but these sensors can be tricky because they report data at different speeds and detail levels. The authors developed a deep learning method called PhyNet that uses known physical conditions to help understand sensor signals better without needing exact timing matches. This makes it easier to spot problems even when data is complicated or unclear. They tested PhyNet on several real and public datasets and found it worked better than other methods.
What this means in practice
- •For industrial maintenance teams: Improve detection of faults in fluid transport systems even when sensor data comes from different kinds and timings of measurements.
- •For pipeline monitoring operators: Enhance reliability of diagnosing issues like cavitation by integrating physical state information with sensor signals for better alert accuracy.
Authors
Yu Sha, Junqi Tao, Dixin Zhou, Horst Stoecker, Domagoj Vnucec, Andreas Widl, Kai Zhou
Abstract
Industrial fluid transport systems are monitored through heterogeneous sensing streams, but robust fault diagnosis remains difficult because response signals vary with operating conditions and differ from physical variables in sampling rate, observation duration and data granularity. To address these challenges, we propose a physical-variable-informed deep learning framework (PhyNet) for robust fault diagnosis under real-world sampling heterogeneity. PhyNet treats physical variables as global operating constraints and response signals as local diagnostic evidence. Its physical-to-response cross-attention mechanism connects sequence-level physical-variable tokens with a learnable global response token, enabling interaction without strict temporal alignment. Across four benchmarks, including three real-world cavitation datasets and one public two-phase-flow dataset, PhyNet achieves the best performance across all evaluated metrics. Class-wise analyses, together with attention and masking analyses, show improved discrimination of ambiguous states and indicate that physical variables meaningfully constrain local response interpretation. These findings demonstrate a deployment-oriented approach to robust diagnosis in heterogeneous industrial environments.