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

Rebin Saleh; Khanh Pham Dinh; Balázs Villányi; Truong-Son Hy

cs.MAFeb 17, 2026

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

Authors: Rebin Saleh, Khanh Pham Dinh, Balázs Villányi, Truong-Son Hy

Organizations: Department of Electronics Technology, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Műegyetem rkp. 3, H-1111 Budapest, Hungary · DataScienceWorld.Kan, Hanoi, Vietnam · Department of Computer Science, The University of Alabama at Birmingham, 1720 University Blvd, Birmingham, AL 35294 USA

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.

Figures & tables

Fig. 1: High-level self-evolving hierarchical MAS architecture for IIoT predictive maintenance.

Fig. 2: Detailed agent-level architecture showing all subagents, communication protocols, and feedback loops.

Characteristic	Specification
Dataset Size
Total samples	10,000 operational cycles
Training set	8,000 samples (80%)
Test set	2,000 samples (20%)
Sampling strategy	Stratified by anomaly class
Feature Space

TABLE I: Boiler Emulator dataset characteristics and configuration.

Characteristic	Specification
Dataset Size
Total samples	500 records (after balancing from 1000+)
Training set	400 samples (80%)
Test set	100 samples (20%)
Feature Space
Total dimensions	42 features

TABLE II: Wind Turbine IIoT dataset characteristics and configuration.

System	Dataset	F1	Precision	Recall	ROC-AUC	$\Delta$ F1	Latency (ms)
Baseline1	Boiler	0.4871	0.3225	0.9949	0.4099	0.0000	1923.0
Baseline2	Boiler	0.4489	0.3140	0.7911	0.3969	-0.0550	1594.3
SEMAS	Boiler	0.4873	0.3737	0.7114	0.6118	-0.0239	1.22
Baseline1	Wind Turbine	0.9440	0.9219	0.9672	0.3705	0.0000	455.9
Baseline2	Wind Turbine	0.9349	0.9205	0.9508	0.2634	+0.0606	286.2
SEMAS	Wind Turbine	0.9571	0.9371	0.9781	0.7583	-0.0166	0.30

TABLE III: Performance comparison across datasets

Fig. 3: Comprehensive performance comparison across all systems and metrics. SEMAS achieves superior F1-scores (Boiler: 0.4873, Wind Turbine: 0.9571), highest ROC-AUC values (0.6118 and 0.7583), and dramatically lower latency (1.22ms and 0.30ms) compared to Baseline1 (1923ms and 456ms) and Baseline2 (1594ms and 286ms). The multi-metric visualization demonstrates SEMAS’s dual advantage in both accuracy and computational efficiency.

Fig. 4: F1-score evolution across iterations for Baseline1, Baseline2, and SEMAS on both datasets. SEMAS demonstrates stable convergence and positive learning on challenging data.

Parameter	It. 1	It. 2	It. 3	Change
F1-Score	0.5031	0.4795	0.4792	-4.7%
Contamination ( $\rho$ )	0.3200	0.3100	0.3300	+3.1%
Consensus threshold ( $\tau$ )	0.7327	0.8000	0.8000	+9.2%
Weight $w_{1}$ (B1)	0.4243	0.4290	0.4333	+2.1%
Weight $w_{2}$ (B2)	0.5757	0.5710	0.5667	-1.6%

TABLE IV: SEMAS policy parameter evolution on Boiler dataset across three iterations, with corresponding F1-scores.

System	Boiler (ms)	Wind (ms)	Memory (GB)
Baseline1	1923.0	455.9	2.1 (est.)
Baseline2	1594.3	286.2	2.4 (est.)
SEMAS	1.22	0.30	3.8 (est.)

TABLE V: Computational efficiency comparison (averages across all iterations).

Configuration	F1	Impact	Prec.	Op. Acc.
SEMAS (Full)	0.4956	Baseline	0.3712	82%
w/o PPO optimization	0.4782	-3.5%	0.3501	81%
w/o consensus voting	0.4634	-6.5%	0.3045	79%
w/o federated aggregation	0.4856	-2.0%	0.3614	80%
w/o LLM response	0.4956	+0% (F1)	0.3712	41%

TABLE VI: Ablation study on Boiler dataset: per-component contributions to accuracy and operator acceptance. The last row reports an orthogonal trust metric rather than detection accuracy.

Dataset	Comparison	$\Delta$ F1	$t$	$p$	Interpretation
Boiler	SEMAS vs. BL1	+0.0002	0.08	0.94	Not significant
Boiler	SEMAS vs. BL2	+0.0384	4.21	<0.001	Highly significant
Wind Turbine	SEMAS vs. BL1	+0.0131	2.76	<0.01	Significant
Wind Turbine	SEMAS vs. BL2	+0.0222	3.12	<0.005	Highly significant

TABLE VII: Paired

t

-tests comparing SEMAS against baselines. Significance threshold:

p<0.05

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Parameter	Value	Justification	Valid Range
Contamination ( $\rho$ )	0.32	Matches Boiler anomaly prevalence (36.8%)	[0.25, 0.35]
Window size ( $W$ )	100 ts	10 seconds at 10Hz sampling rate	[50, 200]
Initial $w_{1},w_{2}$	0.42, 0.58	Equal weighting; PPO learns optimal split	[0.3, 0.7]
PPO clip ratio ( $\epsilon$ )	0.2	Standard RL literature value	[0.1, 0.3]

Appendix

TABLE VIII: TABLE VIII Hyperparameter justification and sensitivity analysis.

Model	Hyperparam.	Value
Isol. Forest	Est. ( $n_{\text{trees}}$ )	200
	Contam. ( $\rho_{0}$ )	0.32
	Max samples/tree	256
	Rand. seed	42
	Training	Unsupervised
One-Class SVM	Kernel	RBF

Appendix

TABLE IX: Training configuration for anomaly detection models.

Component	Parameter	Value/Spec.
RUL Model	Arch.	LSTM [64,32,32,1] (ReLU)
	Input	$(X_{t-10:t},\text{RUL}_{t})$
	Batch	32
	Epochs	10 (conv. obs.)
	Opt.	Adam ( $\alpha=10^{-3}$ )
	Loss	MAE

Appendix

TABLE X: Training configuration for RUL prediction and PPO policy optimization.

Explore similar work

Plan First, Judge Later, Run Better: A DMAIC-Inspired Agentic System for Industrial Anomaly Detection
Jun 3, 2026Yongzi Yu, Ao Li, Le Wang +4Multi-Agent LLM Systems LLM Agent Orchestration
1The Hong Kong University of Science and Technology (Guangzhou) · 2The Hong Kong University of Science and Technology · 3Shanghai University of Finance and Economics +2
MsFormer: Enabling Robust Predictive Maintenance Services for Industrial Devices
Mar 24, 2026Jiahui Zhou, Dan Li, Ruibing Jin +5Predictive Maintenance RUL Estimation
School of Software Engineering, Sun Yat-Sen University, China · Agency for Science, Technology and Research (A*STAR), Singapore · School of the Art Institute of Chicago, Chicago +1
Seamless Deployment of Machine Learning Inference at the Far Edge: An Empirical AWS IoT Greengrass Architecture for Industrial Predictive Maintenance
Oct 10, 2026Prince Kwabena Appiah Boadu, Jeffery Baafi Kyei, Enoch Kofi Koranteng +1Edge Inference Edge-Cloud Computing
Department of Computer Engineering, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana

Jun 3, 2026J/K move · Enter open · S save

Plan First, Judge Later, Run Better: A DMAIC-Inspired Agentic System for Industrial Anomaly Detection

Yongzi Yu, Ao Li, Le Wang, Ziyue Li+3

1The Hong Kong University of Science and Technology (Guangzhou) · 2The Hong Kong University of Science and Technology · 3Shanghai University of Finance and Economics+2

Multi-Agent LLM Systems LLM Agent Orchestration Industrial Anomaly Detection LLM Agent Planning

Open paper AskPDF arXiv

Large language model (LLM) agents have shown promise in automating complex data-analysis workflows, but their reliable deployment remains challenging in high-stakes industrial scenarios. Industrial anomaly detection (IAD) is essential for manufacturing quality, safety, and efficiency, yet existing LLM-based IAD agents mainly focus on execution while under-exploiting strategy formulation. Consequently, they struggle to handle heterogeneous modalities in a unified and cost-effective manner. Inspired by the DMAIC quality-management framework, we propose DMAIC-IAD (DMAIC-inspired Agentic Industrial Anomaly Detection), a "Plan First, Judge Later" multi-agent system that aligns LLM agents with structured industrial problem-solving. DMAIC-IAD distills heterogeneous references into standardized operating procedures (SOPs) before strategy generation, and introduces a pre-trained execution-free judge model to rank candidate strategies without costly runtime trials. Extensive experiments across four modalities show that DMAIC-IAD improves average detection performance over applicable agentic baselines by 37.76%.

Abstract

Explore similar work

Plan First, Judge Later, Run Better: A DMAIC-Inspired Agentic System for Industrial Anomaly Detection

MsFormer: Enabling Robust Predictive Maintenance Services for Industrial Devices

Seamless Deployment of Machine Learning Inference at the Far Edge: An Empirical AWS IoT Greengrass Architecture for Industrial Predictive Maintenance