Bearing performance degradation assessment based on the rough support vector data description

Spectral kurtosis for fault detection, diagnosis and prognostics of rotating machines: A review with applications

“…For example, a monotonic degradation assessment index of rolling bearings using fuzzy support vector data description and damage severity index was given in [110]. In [111], an incremental rough support vector data description was designed based on the rough support vector description, and a new assessment indicator was also proposed. In [112], a method of prognostics for machine condition was proposed using energy based monitoring index combined with CI.…”

The Application of LCS and Information Entropy as a Novel Fusion Algorithm for Degradation Feature Extraction

“…To establish the appropriate PHM of equipment, it is first necessary to conduct the research of degradation feature extraction for prognostics [4]. The degradation experiment requires a long time and the vibration signals during the degradation are very complex [5]. However, features extracted by traditional methods [6] are normally based on the single monitoring signal.…”

Performance Degradation Assessment of Rolling Element Bearings using Improved Fuzzy Entropy

“…It requires reflecting the comprehensive performance degradation degree based on the extracted features and focuses on the vibration trend over a whole lifetime while traditional fault diagnosis only needs to be capable of identifying different types of faults. To date, many researches on the performance degradation assessment of rolling element bearings have been carried out, most of which are based on the intelligent assessment approaches, such as self-organizing map (SOM) [5]- [6], hidden Markov model (HMM) [7], support vector data description (SVDD) [8]- [10], Gaussian mixture model (GMM) [11] and logistic regression (LR) [12]. However, these proposed intelligent assessment models may all exhibit their own limitations [13]- [14].…”