A Text-Based Knowledge-Embedded Soft Sensing Modeling Approach for General Industrial Process Tasks Based on Large Language Model

2025-01-09

AI Summary

Industrial soft sensors face challenges including task-specific design, unimodal data reliance, poor performance under small-sample conditions, and difficulty in integrating heterogeneous domain knowledge. To address these issues, this paper proposes a Large Language Model (LLM)-based universal knowledge-embedded soft sensing framework. Methodologically, it introduces a novel auxiliary variable sequence encoder and a two-stage adaptive fine-tuning strategy—enabling, for the first time, multimodal co-modeling of natural language text and industrial process data. The framework integrates Parameter-Efficient Fine-Tuning (PEFT), autoregressive time-series modeling, and Adapter-based transfer learning. Evaluated on rotor thermal deformation prediction in an air preheater, the approach achieves significant performance gains over conventional Data-Driven Soft Sensors (DDSS) under limited training data, demonstrating superior generalization capability, cross-task transferability, and effective knowledge enhancement.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Data-driven soft sensors (DDSS) have become mainstream methods for predicting key performance indicators in process industries. However, DDSS development requires complex and costly customized designs tailored to various tasks during the modeling process. Moreover, DDSS are constrained to a single structured data modality, limiting their ability to incorporate additional contextual knowledge. Furthermore, DDSSs' limited representation learning leads to weak predictive performance with scarce data. To address these challenges, we propose a general framework named LLM-TKESS (large language model for text-based knowledge-embedded soft sensing), harnessing the powerful general problem-solving capabilities, cross-modal knowledge transfer abilities, and few-shot capabilities of LLM for enhanced soft sensing modeling. Specifically, an auxiliary variable series encoder (AVS Encoder) is proposed to unleash LLM's potential for capturing temporal relationships within series and spatial semantic relationships among auxiliary variables. Then, we propose a two-stage fine-tuning alignment strategy: in the first stage, employing parameter-efficient fine-tuning through autoregressive training adjusts LLM to rapidly accommodate process variable data, resulting in a soft sensing foundation model (SSFM). Subsequently, by training adapters, we adapt the SSFM to various downstream tasks without modifying its architecture. Then, we propose two text-based knowledge-embedded soft sensors, integrating new natural language modalities to overcome the limitations of pure structured data models. Furthermore, benefiting from LLM's pre-existing world knowledge, our model demonstrates outstanding predictive capabilities in small sample conditions. Using the thermal deformation of air preheater rotor as a case study, we validate through extensive experiments that LLM-TKESS exhibits outstanding performance.

Problem

• Data-Driven Soft Sensors
• Industrial Applications
• Predictive Performance

Innovation

• LLM-TKESS
• Knowledge Fusion
• Two-step Fine-tuning