The paper presents a fast, accurate and simple systematic approach for online condition monitoring and severity identification of ball bearings. This approach utilizes compact 1D convolutional neural networks (CNNs) to identify, quantify, and localize bearing damage. The proposed approach is verified experimentally under several single and multiple damage scenarios. The experimental results demonstrated that the proposed approach can achieve a high level of accuracy for damage detection, localization and quantification. Besides its real-time processing ability and superior robustness against the high-level noise presence, the compact and minimally-trained 1D CNNs in the core of the proposed approach can handle new damage scenarios with utmost accuracy.

This study presentes a new nonparametric structural damage detection algorithm that integrates self-organizing maps with a pattern-recognition neural network to quantify and locate structural damage. In this algorithm, self-organizing maps are used to extract a number of damage indices from the ambient vibration response of the monitored structure. The presented study is unique because it demonstrates the development of a nonparametric vibration-based damage detection algorithm that utilizes self-organizing maps to extract meaningful damage indices from ambient vibration signals in the time domain. The ability of the algorithm to identify damage was demonstrated analytically using a finite-element model of a hot-rolled steel grid structure. The algorithm successfully located the structural damage under several damage cases, including damage resulting from local stiffness loss in members and damage resulting from changes in boundary conditions. A sensitivity study was also conducted to evaluate the...