A Systematic Review of Intelligent Agents, Language Models, and Recurrent Neural Networks in Industrial Maintenance: Driving Value Creation for the Mining Sector
Open Access
- 1 January 2025
- journal article
- review article
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 2025 (1)
Abstract
This PRISMA 2020–compliant systematic review examines how intelligent agents, large language models (LLMs), and recurrent neural networks (RNNs) can be combined for industrial maintenance, with a sector‐specific focus on mining. Scopus and Web of Science (2018–2025) were searched using replicable queries, and a dual text‐representation pipeline (TF–IDF with bi/trigrams and sentence‐transformer embeddings) was applied. Model selection scanned k over a predefined grid with internal indices (Silhouette, Davies–Bouldin, and Calinski–Harabasz), and robustness was assessed through multiseed stability, bootstrap consensus, representation‐sensitivity checks, and a control run with HDBSCAN. Study quality and risk of bias were appraised with an AI‐and‐control–oriented matrix (ACE‐QA). Two macroclusters emerged. The first centers on distributed control, consensus and formation, fault tolerance, observers, and learning‐based designs (fuzzy/neural/RL), including finite/predefined‐time and event/dynamic event–triggered mechanisms. The second addresses secure and resilient cooperation under cyber threats (DoS, deception, and FDIA), integrating observer‐based estimation and communication‐efficient protocols. Cross‐cutting findings indicate that event‐triggered updates reduce bandwidth and compute requirements, while robust estimation and fault‐tolerant control improve availability under harsh conditions and intermittent networks—typical in mining. A maturity map suggests high technical readiness and growing adoption for RNN‐based sensing analytics, advancing readiness but emerging adoption for multiagent coordination, and early adoption of LLMs for text‐grounded maintenance intelligence. Evidence gaps persist in replicability, cross‐site transfer, uncertainty reporting, and mining‐grade validation at the edge. A design agenda is outlined that prioritizes digital‐twin stress testing, edge‐first evaluation of agent coordination, secure‐by‐design pipelines (authenticated/encrypted messaging and adversarial testing), and shift‐aware validation. In sum, a hybrid stack—RNNs for perception, LLMs for knowledge grounding, and agents for coordinated action—offers a practical route to reliable, secure, and communication‐efficient predictive maintenance in Mining 4.0.Keywords
Funding Information
- Pontificia Universidad Católica de Valparaíso (039.706/2025)
This publication has 111 references indexed in Scilit:
- Optimized backstepping‐based finite‐time containment control for nonlinear multi‐agent systems with prescribed performanceOptimal Control Applications and Methods, 2024
- Leader‐following consensus of nonlinear singular switched multi‐agent systems via sliding mode controlAsian Journal of Control, 2024
- XGBoost based residual life prediction in the presence of human error in maintenanceNeural Computing and Applications, 2022
- Distributed robust fault-tolerant consensus control for a class of nonlinear multi-agent systems with intermittent communicationsApplied Mathematics and Computation, 2021
- Event-based secure consensus of muti-agent systems under asynchronous DoS attacksApplied Mathematics and Computation, 2021
- Stochastic faulty estimator-based non-fragile tracking controller for multi-agent systems with communication delayApplied Mathematics and Computation, 2021
- Modeling a predictive maintenance management architecture to meet industry 4.0 requirements: A case studySystems Engineering, 2020
- Distributed bipartite finite-time event-triggered output consensus for heterogeneous linear multi-agent systems under directed signed communication topologyApplied Mathematics and Computation, 2020
- Learning from positive and unlabeled data: a surveyMachine Learning, 2020
- A novel optimal bipartite consensus control scheme for unknown multi-agent systems via model-free reinforcement learningApplied Mathematics and Computation, 2020