Optimal Transport Image Representation and Deep Covariance Alignment (CORAL) for Control Valve Stiction Detection
2026-07-24 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the problem of detecting control valve stiction, which causes issues in industrial process control. They propose a new method that converts control signals into images and uses a neural network trained to recognize patterns that work well both on simulated and real industrial data. By combining an image technique called optimal transport with a domain adaptation method called Deep CORAL, their approach better handles differences between simulated and real data. Their method performed well in tests, accurately identifying stiction in industrial loops more reliably than previous hand-crafted methods.
control valve stictionoptimal transportDeep CORALdomain adaptationconvolutional neural networkcross-entropy lossfeature extractorcontrol looposcillationsstiction detection
Authors
Seshu K. Damarla
Abstract
Control valve stiction is a common cause of unwanted oscillations and poor control-loop performance in industrial processes. Data-driven methods can automatically detect stiction, but models trained purely on simulated data often struggle to generalize to real industrial control loops due to domain shift. To bridge this gap, this work propose a novel stiction detection methodology that combines optimal transport (OT) imaging technique with deep correlation alignment (Deep CORAL) algorithm. Closed loop signals: controller output and process variable are converted into two-dimensional OT images. These images capture the dynamic behaviour of control loops. The proposed methodology includes a convolutional neural network (CNN) encoder (or feature extractor) trained to learn domain-invariant representations by optimizing a combined objective: a cross-entropy loss on labeled simulation data and a Deep CORAL (covariance-alignment) loss between simulation data and unlabeled target-domain industrial data. Downstream classifiers trained on the domain-invariant target features were evaluated on an independent test set of 20 benchmark loops from industrial stiction data benchmark. The proposed methodology successfully diagnosed 18 out of the 20 loops and achieved100% recall across all 13 stiction cases, an accuracy of 90.00% and an F1-score of 92.86%. Compared to standard baseline approach (hand-crafted features-based method), the proposed methodology significantly mitigates domain shift, providing robust, highly reliable stiction detection for real-world industrial control loops.