Papers by Keyword: Fault Recognition

Paper TitlePage

Authors: Wen Bin Zhang, Yan Ping Su, Yan Jie Zhou, Ya Song Pu
Abstract: In this paper, a novel method to recognize gear fault pattern was approached based on multi-scale morphological undecimated wavelet decomposition, sample entropy and grey incidence. Firstly, multi-scale morphological undecimated wavelet decomposition was developed based on the characteristic of impulse feature extraction in difference morphological filter. And it was used to process different gear fault signals in five levels. Secondly, the sample entropy of each level was calculated. Finally, the sample entropy was served as the feature vectors and the grey incidence of different gear vibration signals was calculated to identify the fault pattern and condition. Practical example shows the efficiency of the proposed recognition method. It is suitable for on-line monitoring and fault diagnosis of gear.
369
Authors: Wen Bin Zhang, Yan Ping Su, Jie Min, Yan Jie Zhou
Abstract: In this paper, a novel method to recognize rotor fault pattern was proposed based on rank-order morphological filter, harmonic window decomposition, sample entropy and grey incidence. At first, the line structure element was selected for rank-order morphological filter to denoise the original signal. Then, the six feature frequency bands which contain the typical fault information were extracted by harmonic window decomposition that needs not decomposition; and sample entropy of each band was calculated. Finally, these sample entropies could serve as the feature vectors, the grey incidence of different rotor vibration signals was calculated to identify the fault pattern and condition. Practical results show that this method can be used in fault diagnosis of rotating machinery effectively.
1705
Authors: Mei Wang, Jing Wu
Abstract: When a fault appeared in a power cable transmission line, the transient current with high frequencies would be produced in the system. Three independent mode components could be obtained by applying the phase mode transformation to the transient current. For different types of the faults, the three independent mode components have different features. Based on wavelet energy spectrum of mode components, a method for cable fault recognition is developed in this paper. First, the fault current is decomposed by using Karenbaue transformation matrix. Then, wavelet transformation is uses to obtain the coefficients of the high frequency components which reflect the original signal high frequency energy. Finally, based on the wavelet energy spectrum method and the detailed coefficient manipulation, the equivalent norms of the mode components are obtained. Compared with the traditional fault recognition method, the new method depends less on zero mode component in two-phase short to ground state, and it can recognize the fault class in the cases of different fault positions, different fault path resistances and different inception angles.
834
Authors: Jing Jiang, Zhi Nong Li
Abstract: A new bearing fault recognition method based on volterra series and HMM is proposed. In the proposed method, first the feature vectors are extracted from amplitude demodulated signals obtained from normal, ball, inner and outer faulty bearings. The feature vectors are based on the volterra series of the vibration signals, which is obtained by the subspace method. Then these feature vectors are input to each fault’s HMM to be recognized. The result of experiment shows that the proposed method is very effective. The proposed method is tested with the experiment data sampled from drive end ball bearing of an induction motor driven mechanical system.
561
Authors: Wen Bin Zhang, Yan Ping Su, Yan Jie Zhou, Jie Min
Abstract: In this paper, a novel method to recognize gear fault pattern was approached based on harmonic wavelet package (HWP), sample entropy and grey incidence. At first, the line structure element was selected for rank-order morphological filter to denoise the original signal. Secondly, different gear fault signals were decomposed into eight frequency bands by harmonic wavelet package in three levels; and sample entropy of each band was calculated. Finally, these sample entropies could serve as the feature vectors, the grey incidence of different gear vibration signals was calculated to identify the fault pattern and condition. Practical results show that this method can be used in gear fault diagnosis effectively.
1397
Authors: Wen Bin Zhang, Yan Ping Su, Ya Song Pu, Yan Jie Zhou
Abstract: In this paper, a novel comprehensive fault identification approach was proposed based on the harmonic window decomposition (HWD) frequency band energy extraction and grey relation degree. Firstly, in order to eliminate the influence of noises, the line structure element was selected for morphological filter to denoise the original signal. Secondly, due to the energy of vibration signal will change in different frequency bands when fault occurs, therefore, the six feature frequency bands which contain the typical fault information were extracted by harmonic window decomposition that need not decomposition; and the energy distribution of each band could be calculated. Finally, these energy distributions could serve as the feature vectors, the grey relation degree of different vibration signals was calculated to identify the fault pattern and condition. Practical results show that this method can identify rotor fault patterns effectively.
373
Authors: Mei Wang, Xiao Wei Li
Abstract: Power cables are increasingly popular in daily life and industrial production. The long-term use will make various cable faults. To reduce the losses caused by the faults, the cable faults should be recognized correctly and timely. In this paper, we developed an improved particle swarm optimization and support vector machine (IPSO-SVM) algorithm to recognize the power cable faults. The algorithm used the improved PSO to optimize the SVM kernel function parameter and the penalty parameter simultaneously. Two advantages were illustrated by the simulation experiments. The first one is the recognition accuracy which was increased from 81.8% to 90.9%; the second advantage is the SVM training time which decreased from 0.0247 second to 0.0202 second.
830
Authors: Jun Liu, Lin Li, Qing Tao Long
Abstract: Using the principle of wavelet transform in the aspect of signal singularity detection analyzes and detects the electric power system fault signal. Then we extract signal feature near the fault moment and sent the feature vectors into the neural network. The simulation results fully prove the effectiveness and superiority of combining wavelet transform and neural network in electric power system fault recognition.
255
Authors: Lan Yun Li, Zhuan Zhao Yang, Zhi He
Abstract: In practical centrifugal compressor fault diagnosis, it is very difficult to improve the fault recognition rate, especially when the sample sizes are small. To solve this problem, a new fault recognition method based on fuzzy gray relational grade was proposed. Firstly, according to fuzzy set theory, the fuzzy relation coefficient (FRC), fuzzy relation degree (FRD) and fuzzy relative weights (FRW) of all fault features were calculated. Secondly, the gray system theory was used to obtain the gray relational coefficients (GRC). Thirdly, by combining FRW and GRC, two fuzzy gray relation grades (FGRG) were presented, which is the Hamming distance-based fuzzy gray relation grade (HD-FGRG) and the Euclidean distance-based fuzzy gray relation grade (ED-FGRG), respectively. Finally, the fault recognition results were obtained by using the max membership degree principle. The centrifugal compressor fault diagnosis results show that the ED-FGRG method is more effective and accurate than traditional gray relational analysis (T-GRA) method, the weighted gray relational analysis (W-GRA) method, and the entropy weight-based gray relational analysis (EW-GRA) method and the HD-FGRG method.
71
Authors: Lan Yun Li, Zhuan Zhao Yang, Xiao Li, Zhi He
Abstract: A new fault recognition method for centrifugal compressor was proposed by using entropy weight-based gray relational analysis (EW-GRA). Firstly, the weight values of all fault features were calculated objectively by the entropy method to avoid the influence of subjective factors. Secondly, an improved local gray relational coefficient (LGRC) formula with weight measures was designed to reflect the contributions of different fault features. Thirdly, according to the relationship between similarity degree and Euclidean distance, the local gray relational distances (LGRD), the global gray relational distances (GGRD) and the global gray relational grades (GGRG) were calculated, and consequently, the fault recognition result was obtained by using the max membership degree principle. Finally, the engineering practicability and validity of the EW-GRA method was demonstrated by a centrifugal compressor fault diagnosis example, and the results show that the EW-GRA method is more effective and accurate than the traditional gray relational analysis (T-GRA) method and the weighted gray relational analysis (W-GRA) method.
685
Showing 1 to 10 of 13 Paper Titles