Advances in intelligent computing for diagnostics, prognostics, and system health management

Abstract

The guest editors have accepted 41 papers with the special issue. By diagnosis, prognostics and system health management we mean a set of activities including: fault detection, fault classification, fault prognosis, and system modeling. Informally, fault detection refers to the real-time signal processing required to know whether or not a given system is in its healthy normal operating state. Fault classification refers to determination of the type of fault an unhealthy system is suffering from and is a pattern recognition task. Fault prognosis refers to the forecast of the remaining useful life of a system and is based on dynamic modeling. In general, these activities require a sequence of operations such as data acquisition and conditioning, feature extraction, feature selection, and a final

Fault diagnosis for rolling bearing based on parameter transfer Bayesian network

“…7 How to extract weak fault features from vibration signals to diagnose and identify the early fault of bearing is one of the complex problems in bearing fault diagnosis. [8][9][10] In recent years, many new methods and techniques, such as adaptive filtering, high-order statistics, wavelet transformation, and empirical mode decomposition (EMD), have been proposed. [11][12][13] Ding et al 14 put forward a method of fault diagnosis of rolling bearing based on continuous wavelet to improve the diagnosis accuracy.…”

“…It is often submerged in the vibration signal of other moving parts and background noise, which makes it difficult to apply traditional envelope spectrum analysis to diagnose fault accurately 7 . How to extract weak fault features from vibration signals to diagnose and identify the early fault of bearing is one of the complex problems in bearing fault diagnosis 8–10 . In recent years, many new methods and techniques, such as adaptive filtering, high‐order statistics, wavelet transformation, and empirical mode decomposition (EMD), have been proposed 11–13 .…”

A New Intelligent Weak Fault Recognition Framework for Rotating Machinery

“…11,12 However, there still exist some problems, such as mode mixing, which will result in obstacles on signal decomposition and reconstruction. 12,13 Inspired from EMD, Smith et al proposed a new time-frequency signal decomposition method, namely local mean decomposition (LMD), which can adaptively decompose a given nonstationary signal into a linear combination of multiple product function (PF) components. 14 Su et al developed an early fault diagnosis method based on EMD and spectral kurtosis.…”