Recent advances in time–frequency analysis methods for machinery fault diagnosis: A review with application examples

Abstract Nonstationary signal analysis is one of the main topics in the field of machinery fault diagnosis. Time–frequency analysis can identify the signal frequency components, reveals their time variant features, and is an effective tool to extract machinery health information contained in nonstationary signals. Various time–frequency analysis methods have been proposed and applied to machinery fault diagnosis. These include linear and bilinear time–frequency representations (e.g., wavelet transform, Cohen and affine class distributions), adaptive parametric time–frequency analysis (based on atomic decomposition and time–frequency auto-regressive moving average models), adaptive non-parametric time–frequency analysis (e.g., Hilbert–Huang transform, local mean decomposition, and energy separation), and time varying higher order spectra. This paper presents a systematic review of over 20 major such methods reported in more than 100 representative articles published since 1990. Their fundamental principles, advantages and disadvantages, and applications to fault diagnosis of machinery have been examined. Some examples have also been provided to illustrate their performance.