Noise-Aware Temporal Fusion Network for SCADA-Based Fault-State Recognition of Gas Pressure Regulators in Natural Gas Distribution Processes

Abstract

Reliable operating-state recognition of gas pressure regulators is essential for pressure stability, operational safety, and supply continuity in urban natural gas distribution networks. However, SCADA pressure–flow signals from regulating stations are often affected by non-stationary noise, impulsive disturbances, limited fault-state samples, and short-window temporal fluctuations, which reduce the reliability of data-driven recognition. To address these issues, this study proposes K2-TLNet, a noise-state-guided fault-state recognition framework for gas pressure regulation processes. The framework integrates adaptive Kalman filtering, training-only KMeans-SMOTE, parallel temporal convolutional network–long short-term memory feature extraction, and a Noise-Aware Gated Fusion mechanism. Adaptive Kalman filtering is used to generate denoised pressure–flow sequences and extract innovation-residual-based noise descriptors. These descriptors guide the fusion module to adaptively balance local transient features from the temporal convolutional network and contextual temporal features from long short-term memory. A field-SCADA-background-based semi-synthetic dataset was constructed using real operating records and mechanism-informed fault-state emulation rules. Experimental results demonstrate that K2-TLNet achieves 98.50% accuracy and 98.20% Macro-F1, while maintaining strong robustness under Gaussian and impulsive noise disturbances.