Baseline-free Damage Detection and Localization on Composite Structures with Unsupervised Kolmogorov-Arnold Autoencoder and Guided Waves

2025-08-01

AI Summary

To address the reliance on baseline models, manual feature engineering, and insufficient localization accuracy in structural health monitoring (SHM) of advanced composite materials, this paper proposes an unsupervised, end-to-end framework for damage detection and localization. Methodologically, it introduces, for the first time, a Kolmogorov–Arnold network (KAN) embedded within an autoencoder architecture to enable automatic, data-driven feature learning from guided-wave signals; this is integrated with an enhanced probabilistic elliptical imaging algorithm—based on MRAPID—to generate high-resolution damage probability maps. The framework operates without baseline models or prior damage data and supports multi-damage identification and precise spatial localization. Validation on both simulated wind turbine blade data and experimental composite plate measurements demonstrates significantly higher localization accuracy than conventional methods, along with strong robustness and cross-condition generalizability.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Multi-modal Vision
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Structural health monitoring (SHM) ensures the safety and longevity of structures such as aerospace equipment and wind power installations. Developing a simple, highly flexible, and scalable SHM method that does not depend on baseline models is significant for ensuring the operational integrity of advanced composite structures. In this regard, a hybrid baseline-free damage detection and localization framework incorporating an unsupervised Kolmogorov-Arnold autoencoder (KAE) and modified probabilistic elliptical imaging algorithm (MRAPID) is proposed for damage detection and localization in composite structures. Specifically, KAE was used to process the guided wave signals (GW) without any prior feature extraction process. The KAE continuously learns and adapts to the baseline model of each structure, learning from the response characteristics of its undamaged state. Then, the predictions from KAE are processed, combined with the MRAPID to generate a damage probability map. The performance of the proposed method for damage detection and localization was verified using the simulated damage data obtained on wind turbine blades and the actual damage data obtained on composite flat plates. The results show that the proposed method can effectively detect and localize damage and can achieve multiple damage localization. In addition, the method outperforms classical damage detection algorithms and state-of-the-art baseline-free damage detection and localization methods in terms of damage localization accuracy.

Problem

• Detects damage in composite structures without baseline models
• Localizes damage using unsupervised learning and guided waves
• Improves accuracy over traditional baseline-free methods

Innovation

• Unsupervised Kolmogorov-Arnold autoencoder for signal processing
• Modified probabilistic elliptical imaging algorithm for localization
• Baseline-free framework combining KAE and MRAPID methods