Self-Evolving Multi-Agent Network for Industrial IoT Predictive Maintenance

2026-02-17

AI Summary

This work addresses the challenges of real-time performance, interpretability, and resource constraints in predictive maintenance for industrial IoT under dynamic operating conditions, where traditional static models exhibit poor adaptability and large language models (LLMs) are difficult to deploy. To overcome these limitations, the authors propose SEMAS—a resource-aware, self-evolving hierarchical multi-agent architecture that deploys lightweight feature extraction agents at the edge, diverse ensemble detection agents at the fog layer, and policy optimization agents in the cloud. The framework integrates proximal policy optimization (PPO), dynamic consensus voting, federated knowledge aggregation, and an LLM-based generative explanation mechanism. Evaluated on boiler and wind turbine datasets, SEMAS achieves high-accuracy, low-latency anomaly detection, significantly outperforming baseline methods. Ablation studies confirm the contribution of each component, demonstrating its suitability for real-time deployment in practical industrial environments.

Technology Category

• Machine Learning: Hardware-aware ML
• Multiagent Systems: Multiagent Learning
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Industrial IoT predictive maintenance requires systems capable of real-time anomaly detection without sacrificing interpretability or demanding excessive computational resources. Traditional approaches rely on static, offline-trained models that cannot adapt to evolving operational conditions, while LLM-based monolithic systems demand prohibitive memory and latency, rendering them impractical for on-site edge deployment. We introduce SEMAS, a self-evolving hierarchical multi-agent system that distributes specialized agents across Edge, Fog, and Cloud computational tiers. Edge agents perform lightweight feature extraction and pre-filtering; Fog agents execute diversified ensemble detection with dynamic consensus voting; and Cloud agents continuously optimize system policies via Proximal Policy Optimization (PPO) while maintaining asynchronous, non-blocking inference. The framework incorporates LLM-based response generation for explainability and federated knowledge aggregation for adaptive policy distribution. This architecture enables resource-aware specialization without sacrificing real-time performance or model interpretability. Empirical evaluation on two industrial benchmarks (Boiler Emulator and Wind Turbine) demonstrates that SEMAS achieves superior anomaly detection performance with exceptional stability under adaptation, sustains prediction accuracy across evolving operational contexts, and delivers substantial latency improvements enabling genuine real-time deployment. Ablation studies confirm that PPO-driven policy evolution, consensus voting, and federated aggregation each contribute materially to system effectiveness. These findings indicate that resource-aware, self-evolving 1multi-agent coordination is essential for production-ready industrial IoT predictive maintenance under strict latency and explainability constraints.

Problem

• Industrial IoT
• predictive maintenance
• real-time anomaly detection
• edge deployment
• model interpretability

Innovation

• Self-Evolving Multi-Agent System
• Industrial IoT Predictive Maintenance
• Hierarchical Edge-Fog-Cloud Architecture
• Proximal Policy Optimization (PPO)
• Federated Knowledge Aggregation