KANS: Knowledge Discovery Graph Attention Network for Soft Sensing in Multivariate Industrial Processes

2025-01-02

AI Summary

In industrial multivariate processes, critical process variables are often difficult to measure online, and existing soft sensor models struggle to capture complex nonlinear and dynamic interdependencies among variables. Method: This paper proposes an end-to-end soft sensor modeling framework that does not require predefined graph topologies. It innovatively integrates unsupervised graph structure learning with interpretable knowledge discovery: adaptive adjacency graphs are constructed via cosine similarity among sensor embeddings, and dynamic variable relationships are modeled using a parallelized graph attention network. The framework further enables process-driven identification of key sensor combinations. Contribution/Results: Evaluated on multiple real-world industrial datasets, the method significantly outperforms state-of-the-art soft sensors in prediction accuracy. Crucially, the identified high-correlation sensor combinations exhibit clear physical interpretability and engineering verifiability, enhancing both model transparency and operational utility.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Soft sensing of hard-to-measure variables is often crucial in industrial processes. Current practices rely heavily on conventional modeling techniques that show success in improving accuracy. However, they overlook the non-linear nature, dynamics characteristics, and non-Euclidean dependencies between complex process variables. To tackle these challenges, we present a framework known as a Knowledge discovery graph Attention Network for effective Soft sensing (KANS). Unlike the existing deep learning soft sensor models, KANS can discover the intrinsic correlations and irregular relationships between the multivariate industrial processes without a predefined topology. First, an unsupervised graph structure learning method is introduced, incorporating the cosine similarity between different sensor embedding to capture the correlations between sensors. Next, we present a graph attention-based representation learning that can compute the multivariate data parallelly to enhance the model in learning complex sensor nodes and edges. To fully explore KANS, knowledge discovery analysis has also been conducted to demonstrate the interpretability of the model. Experimental results demonstrate that KANS significantly outperforms all the baselines and state-of-the-art methods in soft sensing performance. Furthermore, the analysis shows that KANS can find sensors closely related to different process variables without domain knowledge, significantly improving soft sensing accuracy.

Problem

• Complex Industrial Processes
• Soft Sensing Technology
• Variable Relationships

Innovation

• KANS framework
• Graph Attention Network
• Unsupervised Learning