Damage and Nonlinearity Effects on Stress Wave Propagation in Planar Frame Structures: A Machine Learning Classification Approach Based on Stress Wave Amplitude Solution

The paper presents a machine-learning approach for the classification of damage and nonlinearity in frame structures based on stress wave amplitude features. It uses a model-based method to extract equivalent stress wave amplitudes in the damaged structure. In the wave-based approach, structural elements are viewed as Timoshenko waveguides through which longitudinal and flexural waves transmit and refract at path discontinuities such as joints, changes in material properties, or cross-section geometry. Damage and nonlinearity introduce additional discontinuities in the structure, causing stress waves to refract and alter the response. The type of damage is identified by introducing the structural response to high-dimensional classifiers, including artificial and convolutional neural networks.

Experimental data from a three-story laboratory structure is used and imposed on a wave-based frame model. For the method to be output-only, stress wave amplitudes are normalized to the base excitation using the frequency response function.

The results show that the accuracy of the convolutional neural network with stress wave features reaches 98% while it is only 74% using accelerations as features.

The findings showed that damage identification based on features extracted from wave propagation in structures provides more helpful information for the classification of deep learning algorithms.