A Fast Unsupervised Online Learning Algorithm to Detect Structural Damage in Time-Varying Environments

Abstract

Machine learning based health monitoring techniques for damage detection have been widely studied. Most such approaches suffer from two main problems, time-varying environmental and operating conditions, and the difficulty in acquiring training data from damaged structures. Recently, our group presented an unsupervised learning algorithm using support vector data description (SVDD) and an autoencoder to detect damage in time-varying environments without training on data from damaged structures. Though the preliminary experiments produced promising results, the algorithm was computationally expensive. This paper presents an iterative algorithm that learns the state of a structure in time-varying environments online in a computationally efficient manner. This algorithm combines the fast, incremental SVDD (FISVDD) algorithm with signal features based on wavelet packet decomposition (WPD) to create a method that is efficient and provides more accurate detection of smaller damage than the autoencoder-based method. The use of FISVDD has created the possibility of online learning and adaptive damage detection in time-varying environmental and operating conditions (EOC). The WPD-based features also have the potential to provide explainability for the learning algorithm.