A physics-enhanced multi-modal fused neural network for predicting contamination length interval in pipeline

TL;DR

This paper introduces a physics-enhanced multi-modal neural network that integrates scientific principles and feature correlations to accurately predict contamination length intervals in pipelines, outperforming existing methods.

Contribution

The study proposes a novel neural network model that combines physical knowledge with multi-modal feature fusion for improved contamination prediction.

Findings

Outperforms state-of-the-art techniques in contamination length prediction.

Reduces root mean squared relative errors by over 30%.

Both feature fusion and physical principles are essential for model accuracy.

Abstract

During the operation of a multi-product pipeline, an accurate and effective prediction of contamination length interval is the central key to guiding the cutting plan formulation and improving the economic effect. However, the existing methods focus on extracting implicit principles and insufficient feature correlations in a data-driven pattern but overlook the potential knowledge in the scientific theory of contamination development, may cause practically useless results. Consequently, in this study, the holistic feature correlations and physical knowledge are extracted and integrated into the neural network to propose a physics-enhanced adaptive multi-modal fused neural network (PE-AMFNN) for contamination length interval prediction. In PE-AMFNN, a multi-modal adaptive feature fusion module is created to establish a comprehensive feature space with quantified feature importance, thus capturing sufficient feature correlations. Subsequently, a mechanism-coupled customized neural network is designed to incorporate the explicit scientific principle into the forward and backward propagation. Besides, a physics-embedded loss function, which introduces interval differences and interval correlation constraints, is established to unearth the latent physical knowledge in contamination development and force the model to draw physically unreasonable results. Validation on the real-world cases implies that the proposed model outperforms the start-of-art techniques and latest achievements, with Root Mean Squared Relative Errors reduced by 31% and 36% in lower and upper limit prediction. Furthermore, the sensitivity analysis of model modules suggests that both the multi-modal feature fusion and the physical principle are crucial for model improvements