Towards Agent-based Test Support Systems: An Unsupervised Environment Design Approach

2025-08-19

AI Summary

Conventional modal testing relies on static, globally optimized sensor placement strategies, neglecting feedback from environmental dynamics on historical decisions (e.g., previously deployed sensor configurations), thereby degrading testing accuracy and adaptability. Method: This paper proposes an agent-based adaptive decision-making framework that introduces, for the first time in modal testing, an underspecified partially observable Markov decision process (POMDP) formulation, integrated with a dual-curriculum reinforcement learning strategy to enable online sensing and continuous optimization of sensor configurations under dynamic frequency bands; unsupervised environmental modeling is further incorporated to enhance generalization. Contribution/Results: Evaluated on a steel cantilever beam, the method significantly improves the accuracy and robustness of modal parameter identification, demonstrating both engineering feasibility and methodological advancement over existing approaches.

Technology Category

• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)
• Search and Optimization: Mixed Discrete/Continuous Search
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Modal testing plays a critical role in structural analysis by providing essential insights into dynamic behaviour across a wide range of engineering industries. In practice, designing an effective modal test campaign involves complex experimental planning, comprising a series of interdependent decisions that significantly influence the final test outcome. Traditional approaches to test design are typically static-focusing only on global tests without accounting for evolving test campaign parameters or the impact of such changes on previously established decisions, such as sensor configurations, which have been found to significantly influence test outcomes. These rigid methodologies often compromise test accuracy and adaptability. To address these limitations, this study introduces an agent-based decision support framework for adaptive sensor placement across dynamically changing modal test environments. The framework formulates the problem using an underspecified partially observable Markov decision process, enabling the training of a generalist reinforcement learning agent through a dual-curriculum learning strategy. A detailed case study on a steel cantilever structure demonstrates the efficacy of the proposed method in optimising sensor locations across frequency segments, validating its robustness and real-world applicability in experimental settings.

Problem

• Optimizing adaptive sensor placement in modal testing
• Addressing rigid methodologies compromising test accuracy
• Enabling dynamic decision-making in experimental planning

Innovation

• Agent-based framework for adaptive sensor placement
• Unsupervised dual-curriculum reinforcement learning training
• Partially observable Markov decision process formulation