DSPR: Dual-Stream Physics-Residual Networks for Trustworthy Industrial Time Series Forecasting

2026-04-08

AI Summary

Industrial time-series forecasting under non-stationary operating conditions faces dual challenges of prediction accuracy and physical plausibility, as existing data-driven methods struggle to model state-dependent interaction structures and transmission delays. This work proposes a dual-stream neural architecture: a primary stream captures univariate statistical dynamics, while an auxiliary stream adaptively estimates transmission delays via a learnable windowing mechanism and incorporates physical priors to guide dynamic graph learning of time-varying interactions. This design explicitly decouples statistical patterns from physical constraints at the architectural level, enhancing model interpretability and trustworthiness. Evaluated on four industrial benchmarks, the method achieves state-of-the-art performance with over 99% average conservation accuracy and a total variation ratio of 97.2%, demonstrating robust applicability to autonomous control systems in long-term deployment.

Abstract

Accurate forecasting of industrial time series requires balancing predictive accuracy with physical plausibility under non-stationary operating conditions. Existing data-driven models often achieve strong statistical performance but struggle to respect regime-dependent interaction structures and transport delays inherent in real-world systems. To address this challenge, we propose DSPR (Dual-Stream Physics-Residual Networks), a forecasting framework that explicitly decouples stable temporal patterns from regime-dependent residual dynamics. The first stream models the statistical temporal evolution of individual variables. The second stream focuses on residual dynamics through two key mechanisms: an Adaptive Window module that estimates flow-dependent transport delays, and a Physics-Guided Dynamic Graph that incorporates physical priors to learn time-varying interaction structures while suppressing spurious correlations. Experiments on four industrial benchmarks spanning heterogeneous regimes demonstrate that DSPR consistently improves forecasting accuracy and robustness under regime shifts while maintaining strong physical plausibility. It achieves state-of-the-art predictive performance, with Mean Conservation Accuracy exceeding 99% and Total Variation Ratio reaching up to 97.2%. Beyond forecasting, the learned interaction structures and adaptive lags provide interpretable insights that are consistent with known domain mechanisms, such as flow-dependent transport delays and wind-to-power scaling behaviors. These results suggest that architectural decoupling with physics-consistent inductive biases offers an effective path toward trustworthy industrial time-series forecasting. Furthermore, DSPR's demonstrated robust performance in long-term industrial deployment bridges the gap between advanced forecasting models and trustworthy autonomous control systems.

Problem

• industrial time series forecasting
• physical plausibility
• regime-dependent dynamics
• transport delays
• non-stationary conditions

Innovation

• Dual-Stream Architecture
• Physics-Guided Dynamic Graph
• Adaptive Window
• Regime-Dependent Dynamics
• Physical Plausibility