Assessment Method for Rolling Bearing Performance Degradation Using TESPAR and GMM
1
Citation
12
Reference
10
Related Paper
Citation Trend
Abstract:
Rolling bearing performance degradation assessment has been receiving much attention for which itscrucial role to realize CBM(condition-based maintenance).This paper proposed a novel bearing performance degradation method based on TESPAR(Time Encoded Signal Processing and Recognition)and GMM(Gauss Mixture Model). TESPAR is used to extracted features which constitute A-matrix. GMM is utilized to approximate the density distribution of singular values decomposed by A-matrix. TENLLP(Time-Encoded Negative Log Likelihood Probability) serves as a fault severity which can display the similarity of the singular values between normal samples and fault samples as quantificational. Results of its application to bearing fatigue test show that this performance degradation assessment can detect the incipient rolling bearing fault and be sensitive to the change of fault.Keywords:
Degradation
Similarity (geometry)
Matrix (chemical analysis)
SIGNAL (programming language)
An experimental self-starting hydrodynamic gas bearing was designed, built, and tested. This bearing operates on the principle that the bearing is started and stopped hydrostatically by means of an air supply which is generated by the bearing itself. For this purpose, a portion of the self-starting bearing is executed as a herringbone grooved bearing, which performs as a pump, charging a reservoir during hydrodynamic operation of the bearing. The reservoir air supply generated by the herringbone bearing is used for hydrostatic operation of the bearing during starts and stops. Starting and stopping of the experimental bearing was demonstrated using the air supply generated by the herringbone bearing. An equation was derived for the mass flow rate of the herringbone bearing pump.
Hydrostatic equilibrium
Fluid bearing
Air bearing
Cite
Citations (0)
Background: One of the critical factors affecting the life of bearings is the bearing temperature during operation, so the temperature is an important parameter to detect the running state of the bearing. The abnormal increase in bearing temperature can reflect problems such as bearing damage, lack of lubricating oil, and installation errors. With the continuous improvement of rotating machinery equipment operating speed, load level and equipment processing accuracy requirements, there is an urgent need to detect and analyze the temperature rise of bearings. Objective: By analyzing recent representative patents for bearing temperature detection, we summarize the characteristics and problems of current bearing temperature detection devices and provide a reference for the future development of bearing temperature detection devices Methods: This article traces the recent representative patents related to bearing temperature detection method and device structure. Results: Through the investigation of a large number of patents of bearing temperature detection devices, the main existing problems in the system and structure of bearing temperature detection are concluded and analyzed, and the development of bearing temperature detection is discussed in the future. Conclusion: The bearing temperature measuring device is significant for analyzing bearing heating and detecting the running state of the bearing. The current research results need further development and improvement. With the development of automated detection technology, bearing temperature measurement is also evolving towards intelligence and dynamics. It is foreseeable that more related patents on bearing temperature detection will be invented.
Cite
Citations (2)
Finite mixture models can be interpreted as a model representing heterogeneous subpopulations within the whole population. However, more care is needed when associating a mixture component with a cluster, because a mixture model may fit more components than the number of clusters. Modal merging via the mean shift algorithm can help identify such multicomponent clusters. So far, most of the related works are focused on the Gaussian finite mixture. As the non‐Gaussian finite mixture models are gaining attention, the need to address the component‐cluster correspondence issue in these mixture models grows. Thus, we introduce a mode merging method via the mean shift for the finite mixture of t ‐distributions and its parsimonious variants. It can be framed as an expectation–maximization algorithm and enjoys similar theoretical properties as the mean shift for the Gaussian finite mixture. The performance of our method is demonstrated via simulated and real data experiments, where it shows a competitive performance against some of the existing methods.
Component (thermodynamics)
Mode (computer interface)
Cite
Citations (1)
Development and status of domestic bearing fault diagnosis were expounded.Introduces the types of fault bearing and vibration character.Also introduces principium and application of methods of the bearing fault diagnosis.At last,advances the way of development of bearing fault diagnosis.
Cite
Citations (0)
Aiming at the problem of rolling bearing fault diagnosis, a fault diagnosis method of rolling bearing is proposed based on analytical mode decomposition (AMD) and LabVIEW. For the fault feature frequency of rolling bearing is predictable, the AMD method can be used to extract the signal in the frequency band of fault characteristic frequency in rolling bearing signal, and seek frequency spectrum of vibration signal. If the spectrum contains fault characteristic frequency, then the rolling bearing fault can be diagnosed by vibration signal. A rolling bearing fault diagnosis system is developed based on LabVIEW and AMD, and the application of AMD algorithm is realized. The validity of the method is proved by the analysis of actual fault signal of rolling bearing.
SIGNAL (programming language)
Frequency band
Feature (linguistics)
Cite
Citations (0)
Applying fault diagnosis procedure for roller bearing can recognize the fault signals in time,which can reduce the related accidents. The fault diagnosis method of roller bearing was introduced in this paper,and the development and trend of vibration analysis were mainly presented. Meanwhile the main existing problems in fault diagnosis of roller bearing were discussed in the end.
Roller bearing
Cite
Citations (0)
Gaussian mixture models (GMM) have been widely applied in speaker recognition system (SRS); it is the baseline speaker modeling approach. A GMM is composed of a joint probability distribution function (PDF) described by the weighted sum of several multivariate Gaussian PDFs, each multivariate Gaussian PDF is termed as a Mixture Component, The Mixture Component Number (N) is fixed at the classical method in the beginning of training phase in this case all speakers have a GMM model with the identical mixture number exp (16, 64, 128). To enhance effectiveness of speaker recognition system based on GMM we propose in this article a new technique used training GMM algorithm to calculate the best number mixture component for each speaker model. Results show that the new method can improve the performance compared with the basic GMM.
Component (thermodynamics)
Cite
Citations (8)
Mixture models are frequently employed in astronomical studies to model observed data and interpret results. Gaussian mixture model (GMM) is probably the most widely used one due to its simplicity. To illustrate, GMM had been applied to the pulsar data set in a previous study and discovered six clusters. On the other hand, there are more sophisticated mixture models e.g. Dirichlet process Gaussian mixture model (DPGMM). It is a Bayesian non-parametric model such that it includes prior distributions for model parameters and automatically explores the optimum number of clusters in a data set, in contrast to GMM. In this study, we repeated the application of GMM, and also tested DPGMM as a first time on a larger pulsar data set. It is revealed that there are six clusters in the data set as presented in the former study, according to both GMM and DPGMM. However, the estimated parameters of both models differ from each other. We, then, compared the clustering performance of models with respect to silhouette coefficients. Accordingly, it is observed that DPGMM exhibits better clustering performance. As a further analysis, we compared the classification performance of models. Apparently, DPGMM performs, once again, better than GMM in discriminating selected pulsar families.
Data set
Cite
Citations (1)
This document presents fault diagnosis method of rolling bearing based on blind source separation. The algorithm based on fast ICA is improved to separate fault signals according to the rolling bearing’s fault characteristics. Through the experiment it is shown that the algorithm can separate the signals collected from rolling bearing and gearbox effectively, which can provide a new method for fault diagnosis and signal processing of machinery equipment.
SIGNAL (programming language)
Cite
Citations (4)
Rolling bearing is one of the most commonly used components in rotating machinery. It is easy to be damaged which can cause mechanical fault. Thus, it is significance to study fault diagnosis technology on rolling bearing. This paper presents a Deep Boltzmann Machines (DBM) model to identify the fault condition of rolling bearing. A data set with seven fault patterns is collected to evaluate the performance of DBM for rolling bearing fault diagnosis, which is based on the health condition of a rotating mechanical system. The features of time domain, frequency domain and time-frequency domain are extracted as input parameters for the DBM model. The results showed that the accuracy presented by the DBM model is highly reliable and applicable in fault diagnosis of rolling bearing.
Cite
Citations (21)