Intelligent Maintenance and Monitoring in Industrial Systems

The field of industrial maintenance and monitoring is moving towards more intelligent and autonomous systems. Researchers are exploring the use of large language models, collaborative frameworks, and hybrid reasoning approaches to improve the accuracy and efficiency of maintenance tasks. These approaches aim to address the challenges of limited domain adaptability, insufficient real-time performance, and high integration complexity. Notably, some papers have proposed innovative solutions for fault diagnosis, condition monitoring, and predictive control in wastewater treatment plants and other industrial settings.

Some particularly noteworthy papers include: The paper on Towards Next-Generation Intelligent Maintenance, which proposes a collaborative fusion of large and small models for enhancing industrial maintenance. The paper on Hybrid Reasoning for Perception, Explanation, and Autonomous Action in Manufacturing, which introduces a vision-language-action model framework for industrial control. The paper on Feature Engineering for Agents, which proposes a cognitive architecture for ML monitoring that applies feature engineering principles to agents based on Large Language Models.

Sources

Towards Next-Generation Intelligent Maintenance: Collaborative Fusion of Large and Small Models

Applying XAI based unsupervised knowledge discovering for Operation modes in a WWTP. A real case: AQUAVALL WWTP

MLOps with Microservices: A Case Study on the Maritime Domain

A Metrics-Oriented Architectural Model to Characterize Complexity on Machine Learning-Enabled Systems

Hybrid Reasoning for Perception, Explanation, and Autonomous Action in Manufacturing

Linguistic Ordered Weighted Averaging based deep learning pooling for fault diagnosis in a wastewater treatment plant

Agent-based Condition Monitoring Assistance with Multimodal Industrial Database Retrieval Augmented Generation

Feature Engineering for Agents: An Adaptive Cognitive Architecture for Interpretable ML Monitoring

TrioXpert: An automated incident management framework for microservice system

Chat-of-Thought: Collaborative Multi-Agent System for Generating Domain Specific Information

Predictive control of wastewater treatment plants as energy-autonomous water resource recovery facilities

Data Driven Diagnosis for Large Cyber-Physical-Systems with Minimal Prior Information

From Tea Leaves to System Maps: Context-awareness in Monitoring Operational Machine Learning Models

A Robust Optimization Framework for Flexible Industrial Energy Scheduling: Application to a Cement Plant with Market Participation

Built with on top of