Find in Library

Estimating the remaining useful life (RUL) of components is a crucial task to enhance reliability, safety, productivity, and to reduce maintenance cost. In general, predicting the RUL of a component includes constructing a health indicator (<inline-formula><math display="inline"><semantics><mrow><mi>H</mi><mi>I</mi></mrow></semantics></math></inline-formula>) to infer the current condition of the component, and modelling the degradation process in order to estimate the future behavior. Although many signal processing and data-driven methods have been proposed to construct the <inline-formula><math display="inline"><semantics><mrow><mi>H</mi><mi>I</mi></mrow></semantics></math></inline-formula>, most of the existing methods are based on manual feature extraction techniques and require the prior knowledge of experts, or rely on a large amount of failure data. Therefore, in this study, a new data-driven method based on the convolutional autoencoder (CAE) is presented to construct the <inline-formula><math display="inline"><semantics><mrow><mi>H</mi><mi>I</mi></mrow></semantics></math></inline-formula>. For this purpose, the continuous wavelet transform (CWT) technique was used to convert the raw acquired vibrational signals into a two-dimensional image; then, the CAE model was trained by the healthy operation dataset. Finally, the Mahalanobis distance (<i>MD</i>) between the healthy and failure stages was measured as the <inline-formula><math display="inline"><semantics><mrow><mi>H</mi><mi>I</mi></mrow></semantics></math></inline-formula>. The proposed method was tested on a benchmark bearing dataset and compared with several other traditional <inline-formula><math display="inline"><semantics><mrow><mi>H</mi><mi>I</mi></mrow></semantics></math></inline-formula> construction models. Experimental results indicate that the constructed <inline-formula><math display="inline"><semantics><mrow><mi>H</mi><mi>I</mi></mrow></semantics></math></inline-formula> exhibited a monotonically increasing degradation trend and had good performance in terms of detecting incipient faults.