Transferring Graph Neural Networks for Soft Sensor Modeling using Process Topologies

2025-02-05

AI Summary

Soft sensor models struggle to generalize across factories and process topologies due to heterogeneous sensor configurations and variable process structures. Method: This paper proposes a topology-aware graph neural network (GNN) soft sensor framework that explicitly encodes chemical process topology—where unit operations serve as nodes, material streams as edges, and sensors as node/edge attributes—into the GNN architecture. It integrates topology embedding with transfer learning to enable cross-factory generalization under structural variability and sensor inconsistency. Results: Evaluated on an ammonia synthesis loop, the model trained on data from a single plant successfully transferred to a new facility with significantly different topology, accurately predicting product ammonia concentration. The approach overcomes the generalization bottleneck of conventional fixed-dimension models and empirically validates the feasibility and effectiveness of collaborative multi-plant modeling.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Data-driven soft sensors help in process operations by providing real-time estimates of otherwise hard- to-measure process quantities, e.g., viscosities or product concentrations. Currently, soft sensors need to be developed individually per plant. Using transfer learning, machine learning-based soft sensors could be reused and fine-tuned across plants and applications. However, transferring data-driven soft sensor models is in practice often not possible, because the fixed input structure of standard soft sensor models prohibits transfer if, e.g., the sensor information is not identical in all plants. We propose a topology-aware graph neural network approach for transfer learning of soft sensor models across multiple plants. In our method, plants are modeled as graphs: Unit operations are nodes, streams are edges, and sensors are embedded as attributes. Our approach brings two advantages for transfer learning: First, we not only include sensor data but also crucial information on the plant topology. Second, the graph neural network algorithm is flexible with respect to its sensor inputs. This allows us to model data from different plants with different sensor networks. We test the transfer learning capabilities of our modeling approach on ammonia synthesis loops with different process topologies. We build a soft sensor predicting the ammonia concentration in the product. After training on data from one process, we successfully transfer our soft sensor model to a previously unseen process with a different topology. Our approach promises to extend the data-driven soft sensors to cases to leverage data from multiple plants.

Problem

• Transferring soft sensors across different plants.
• Using graph neural networks for flexible sensor inputs.
• Modeling plant topologies to enhance transfer learning.

Innovation

• Graph Neural Networks
• Transfer Learning
• Topology-aware Modeling