Multi agent system improves bridge maintenance using large language models
Multi-Modal Multi-Agent System for Bridge Operation and Maintenance based on Large Language Model
Multiagent Systems
Summary
Bridges need regular checking and fixing to keep people safe and traffic flowing. This paper presents a new computer system that uses multiple cooperating agents powered by a large language model to better manage bridge operation and maintenance tasks. The system links data from different sources, uses physics knowledge about how bridges work, and remembers past experiences to make clearer and more reliable decisions. Tests showed it schedules tasks well and explains its reasoning, helping bridge engineers work more effectively.
What this means in practice
- •For bridge maintenance teams: Coordinate varied inspection and repair tasks using an AI system that understands bridge mechanics and expert knowledge in one workflow.
- •For infrastructure monitoring services: Integrate multi-source bridge diagnostics with interpretable AI reasoning for long-term maintenance decision support.
Authors
Xiangyun Luo, Yunkai Zhang, Yong Huang, Stephen Wu, Hui Li
Abstract
Bridges are critical transportation infrastructure, and reliable operation and maintenance (O&M) is essential for traffic safety and long-term structural performance. However, bridge O&M faces key bottlenecks: no unified architecture coordinates heterogeneous resources; model inferences lack clear links to physical-mechanical laws; and experts' tacit knowledge remains difficult to formalize. This study proposes a knowledge-enhanced autonomy formalization methodology and apply it to construct the Bridge O&M Multi-Modal Multi-Agent System (BOMMA), which integrates heterogeneous diagnostic actions, physics-mechanics-informed representations, long-term memory, and structured experiential knowledge within a coordinated multi-agent workflow, enabling interpretable and traceable scheduling, analysis, and decision-making. On 3,492 multi-source instructions, the proposed method achieves scheduling recalls of 85.37% for simple and 99.40% for composite tasks, with 95.35% BERT F1-score for O&M action reasoning. Ablation studies confirm the contributions of the components in the autonomy. This study bridges general LLM reasoning and specialized bridge O&M requirements.