Abstract
To accurately describe the characteristics of a signal, the feature parameters in time domain and frequency domain are usually extracted for characterization. However, the total number of feature parameters in time domain and frequency domain exceeds twenty, and all of the feature parameters are used for feature extraction, which will result in a large amount of data processing. For the purpose of using fewer feature parameters to accurately reflect the characteristics of the vibration signal, a simple but effective vibration feature extraction method combining time-domain dimensional parameters (TDDP) and Mahalanobis distance (MD) is proposed, i.e., TDDP-MD. In this method, ten time-domain dimensional parameters are selected to extract fault features, and the distance evaluation technique based on Mahalanobis distance criterion function is also introduced to calculate the feature vector, which can be used to classify different failure types. Finally, the proposed method is applied to fault diagnosis of rolling element bearings, and experimental analysis results show that the proposed method can recognize different failure types accurately and effectively with only ten time-domain dimensional parameters and a small quantity of training samples.
Highlights
In this paper, we utilize time-domain dimensional parameters to represent the fault characteristics of vibration signals collected from rolling bearing
In order to better combine the feature parameters, Mahalanobis distance criterion function is introduced for failure classification of vibration signals
Each norm of the fault feature vectors is input into the Mahalanobis distance (MD) classifiers and the fault modes of rolling element bearings can be discerned. e analysis results of test signals collected from rolling element bearings prove the validity and availability of the presented method
Summary
In the system of condition monitoring and fault diagnosis, the signals which are collected from the testing equipment are usually time-domain signals. E feature extraction method combining the dimensional parameters in time domain and ED is described as follows: EDDf 1 E1. E feature extraction method combining the dimensionless parameters in time domain and ED is described as follows: EDDf 2 E2. Every time-domain dimensional parameter is first calculated to extract the fault characteristic from the vibration signals. Because each characteristic parameter of a signal contains only one value, MD can be used to compute the feature distance vector MDDf1, whose 2-norm will be used in identification of the work state of the machinery. The mean and variance of fault feature set for training samples in each state are calculated, and MD discriminant distance MDi is computed according to (16). The classification method using M1 feature extraction can be effectively utilized to identify the failure types of roller element bearings
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
