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

TL;DR

SEMAS is a hierarchical multi-agent system for industrial IoT predictive maintenance that adapts in real-time, balancing accuracy, interpretability, and resource constraints across Edge, Fog, and Cloud layers.

Contribution

The paper introduces SEMAS, a novel self-evolving multi-agent framework that integrates LLM-based explainability, federated learning, and dynamic policy optimization for industrial IoT maintenance.

Findings

Achieves superior anomaly detection accuracy on industrial benchmarks.

Maintains stable performance under operational changes.

Reduces latency enabling real-time deployment.

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.