scholarly journals Compound Fault Diagnosis of Stator Interturn Short Circuit and Air Gap Eccentricity Based on Random Forest and XGBoost

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Rui Tian ◽  
Fuyang Chen ◽  
Shiyi Dong
Keyword(s):  
Fault Diagnosis ◽  
Random Forest ◽  
High Speed ◽  
Wavelet Packet ◽  
Short Circuit ◽  
Principal Component ◽  
Air Gap ◽  
Fault Features ◽  
Diagnosis Method ◽  
Pca Method

Taking the traction motor of CRH2 high-speed train as the research object, this paper proposes a diagnosis method based on random forest and XGBoost for the compound fault resulting from stator interturn short circuit and air gap eccentricity. First, the U-phase and V-phase currents are used as fault diagnosis signal and then the Savitzky–Golay filtering method is used for the noise deduction from the signal. Second, the wavelet packet decomposition is used to extract the composite fault features and then the high-dimensional features are optimized by the principal component analysis (PCA) method. Finally, the random forest and XGBoost are combined to detect composite faults. Using the experimental data of CRH2 semiphysical simulation platform, the diagnosis of different fault modes is completed, and the high diagnosis accuracy is achieved, which verifies the validity of this method.

ON-LINE PERFORMANCE ASSESSMENT AND FAULT DIAGNOSIS OF MECHANICAL SYSTEMS

2015 ◽  
Vol 39 (3) ◽  
pp. 705-715 ◽  
Author(s):  
Shang-Liang Chen ◽  
Yin-Ting Cheng ◽  
Hsien-Cheng Liu ◽  
Yun-Yao Chen
Keyword(s):  
Fault Diagnosis ◽  
Performance Assessment ◽  
Mechanical System ◽  
High Speed ◽  
Mechanical Performance ◽  
Wavelet Packet ◽  
Principal Component ◽  
Spindle Motor ◽  
Diagnostic Model ◽  
On Line

This study integrates sensors, signal capture equipment, industrial computers and machinery health check-up software to develop an On-line Performance Assessment and Fault Diagnosis of Mechanical System, helping engineers predict mechanical conditions. Physical quantities captured by the sensors is utilized to process physical signals, and the Wavelet Packet Energy method is used for the feature extraction of non-stationary signals in coordination with the Principal Component Analysis for feature selection. This study establishes On-line Performance Assessment and Fault Diagnosis of Mechanical System based on Discriminant Analysis which is able to immediately determine the mechanical performance. When abnormal mechanical conditions occur, Bayesian Network will be activated to construct error diagnostic model and determine possible causes of error or malfunction of the machinery. Finally, the system is applied to the fan motor, high-speed spindle motor and AC motor of the machine tool. Experimental results show that the theory can effectively diagnose mechanical performance remarkable with an accuracy rate of 92.50% or higher.

scholarly journals Research on Fault Diagnosis Based on SVM

2013 ◽  
Vol 341-342 ◽  
pp. 843-846
Author(s):  
Wan Ling Li ◽  
Zhen Sheng Wang ◽  
Da Quan Deng ◽  
Jun Tang
Keyword(s):  
Fault Diagnosis ◽  
Extraction Method ◽  
Wavelet Packet ◽  
Electron System ◽  
Wavelet Packet Transform ◽  
Feature Extraction Method ◽  
System A ◽  
Fault Features ◽  
Diagnosis Method ◽  
Circuit Output

In order to improve the fault diagnosis precision of electron system, a method based on wavelet packet transform and SVM was proposed. Fault diagnosis method based on SVM was researched on in this paper because of the complexity of electron system, difficulty of fault diagnosis method and special advantages of SVM. Wavelet packet transform is used to extract fault features from the signal of the circuit output voltage. The specific feature extraction method is introduced. Improved QPSO algorithm was proposed to improve the training speed and class precision of SVM. At last the method mentioned above was applied to a circuit. The result showed that this method was very good.

Aeroengine Rub-Impact Fault Diagnosis Based on Wavelet Packet Transform and the Local Discriminate Bases

2012 ◽  
Vol 226-228 ◽  
pp. 740-744 ◽  
Author(s):  
Ya Hui Wu ◽  
Meng Xiao Shan ◽  
Yu Ning Qian ◽  
Xin Liang Li ◽  
Ru Qiang Yan
Keyword(s):  
Fault Diagnosis ◽  
High Speed ◽  
High Performance ◽  
Wavelet Packet ◽  
Integrated Approach ◽  
Wavelet Packet Transform ◽  
Fault Classification ◽  
Time Frequency ◽  
Diagnosis Method ◽  
Optimal Set

With the development of aeroengine towards the direction of high speed and high performance, the clearance between rotor and stator in aerongine is reduced so that the possibility of rub-impact fault is increased. Since rub-impact signals often exhibits non-stationarity, an integrated approach, which combines the wavelet packet transform (WPT) with local discriminate bases (LDB), is presented in this study to diagnose the rub-impact faults. Specifically, the LDB algorithm is used to select an optimal set of orthogonal time-frequency subspaces resulted from WPT, which have the best discriminatory information for aeroengine rub-impact fault classification. Then the desired parameters generated by the LDB vectors were taken as input to a Bayes classifier for identifying rub-impact faults. Experimental results from the aeroengine vibration signals show that the fault diagnosis method can classify working conditions and fault patterns effectively.

Fault Diagnosis Method of Offset Printer Feeding Mechanism Based on Kernel Principal Component Analysis and K-Means Clustering

2015 ◽  
Vol 731 ◽  
pp. 395-400 ◽  
Author(s):  
Qian Qian Xu ◽  
Hai Yan Zhang ◽  
He Ping Hou ◽  
Zhuo Fei Xu
Keyword(s):  
Principal Component Analysis ◽  
Fault Diagnosis ◽  
High Speed ◽  
Large Scale ◽  
Principal Component ◽  
Component Analysis ◽  
Fault Detection And Diagnosis ◽  
Kernel Principal Component Analysis ◽  
Diagnosis Method ◽  
Detection And Diagnosis

The printing machine is a sort of large-scale equipment characterized by high speed and precision. A fault diagnosis method based on kernel principal component analysis (KPCA) and K-means clustering is developed to classify the types of feeding fault. The multidimensional and nonlinear data of printed image could be reduced by KPCA to make up the deficiency of the traditional K-means clustering method. In this paper, it is experimentally verified that the classification accuracy of the combined method is higher than the traditional clustering analysis method in feeding fault detection and diagnosis. This method provides a shortcut for the determination of fault sources and realizes multi-faults diagnosis of printing machinery efficiently

Vibration Fault Diagnosis Method Based on Compositive Characteristics of Rotor Vibration and Stator Current

2007 ◽  
Author(s):  
Shuting Wan ◽  
Yonggang Li
Keyword(s):  
Fault Diagnosis ◽  
Short Circuit ◽  
Air Gap ◽  
Vibration Characteristics ◽  
Rotor Vibration ◽  
Stator Current ◽  
Dynamic Eccentricity ◽  
Diagnosis Method ◽  
Current Characteristics ◽  
Rotor Winding

Rotor vibration characteristics are first analyzed, when the rotor winding inter-turn short circuit fault, the air-gap dynamic eccentricity fault, the air-gap static eccentricity fault and the imbalance fault occurs. Next, the generator stator current characteristics on the faults also were analyzed, the results show that the faults can’t be diagnosed based only on rotor vibration characteristics or stator current characteristics. But considering the differences of compositive characteristics of the rotor vibration and stator current caused by different rotor faults, a new method of generator vibration fault diagnosis, based on compositive characteristics, is developed. Finally, the rotor vibration and stator current of a type SDF-9 generator is measured in the laboratory to verify the theoretical analysis presented above.

A Novel Method for Fault Diagnosis Based on PCA Enhanced by Wavelet Denoising

2013 ◽  
Vol 756-759 ◽  
pp. 3450-3454
Author(s):  
Feng Qiao ◽  
Hao Ming Zhao ◽  
Feng Zhang ◽  
Qing Ma
Keyword(s):  
Fault Diagnosis ◽  
Principal Component ◽  
Original Data ◽  
Wavelet Denoising ◽  
Fault Detection And Diagnosis ◽  
Simulation Studies ◽  
Diagnosis Method ◽  
Pca Method ◽  
Novel Method ◽  
Detection And Diagnosis

There are some disadvantages for fault detection and diagnosis with traditional Principal Component Analysis (PCA) method because of its shortcomings. It is, in this paper, presented a novel fault diagnosis method based on conventional PCA enhanced by wavelet denoising. The proposed method employs wavelet denoising to deal with the signals, which can reserve enough information of original data, and then establishes PCA model. Based on SPE and T2 statistics, abnormal situation can be detected. And the location of the fault can be recognized via contribution plots. At last, the simulation studies with Matlab are carried out to verify the correctness and effectiveness of the proposed method, the advantages of the proposed method over the conventional PCA also are shown in the simulation.

An Integrated Fault Diagnosis Method Based on the ICA-SVM

2015 ◽  
Vol 740 ◽  
pp. 523-526
Author(s):  
Zhen Ping Ji ◽  
Xiao Jie Zhang
Keyword(s):  
Fault Diagnosis ◽  
Diagnostic Yield ◽  
Principal Component ◽  
Component Analysis ◽  
Support Vector ◽  
Level Control ◽  
Monitoring Model ◽  
Diagnosis Method ◽  
Pca Method ◽  
Tank Water

For sets of measurements does not follow a Gaussian distribution, the conventional principal component analysis (PCA) method has the disadvantage of low diagnostic yield. An integrated fault diagnosing method based on the independent component analysis (ICA) and support vector machine (SVM) was proposed. The observed data is preprocessed and feature extracted by ICA and a monitoring model was developed. When the fault is detected, SVM is adopted to classifying and diagnosing the type of faults. It is applied for fault diagnosing in the Three-Tank water level control system. The simulation results show that the fault diagnosis rates of this method is 99.8%, which can effectively detect and diagnose the fault.

Comparative study on the use of acoustic emission and vibration analyses for the bearing fault diagnosis of high-speed trains

2021 ◽  
pp. 147592172110360
Author(s):  
Dongming Hou ◽  
Hongyuan Qi ◽  
Honglin Luo ◽  
Cuiping Wang ◽  
Jiangtian Yang
Keyword(s):  
Acoustic Emission ◽  
Fault Diagnosis ◽  
High Speed ◽  
High Speed Train ◽  
Signal Attenuation ◽  
Transmission Path ◽  
Bearing Fault Diagnosis ◽  
Operation Conditions ◽  
Fault Features ◽  
High Speed Trains

A wheel set bearing is an important supporting component of a high-speed train. Its quality and performance directly determine the overall safety of the train. Therefore, monitoring a wheel set bearing’s conditions for an early fault diagnosis is vital to ensure the safe operation of high-speed trains. However, the collected signals are often contaminated by environmental noise, transmission path, and signal attenuation because of the complexity of high-speed train systems and poor operation conditions, making it difficult to extract the early fault features of the wheel set bearing accurately. Vibration monitoring is most widely used for bearing fault diagnosis, with the acoustic emission (AE) technology emerging as a powerful tool. This article reports a comparison between vibration and AE technology in terms of their applicability for diagnosing naturally degraded wheel set bearings. In addition, a novel fault diagnosis method based on the optimized maximum second-order cyclostationarity blind deconvolution (CYCBD) and chirp Z-transform (CZT) is proposed to diagnose early composite fault defects in a wheel set bearing. The optimization CYCBD is adopted to enhance the fault-induced impact response and eliminate the interference of environmental noise, transmission path, and signal attenuation. CZT is used to improve the frequency resolution and match the fault features accurately under a limited data length condition. Moreover, the efficiency of the proposed method is verified by the simulated bearing signal and the real datasets. The results show that the proposed method is effective in the detection of wheel set bearing faults compared with the minimum entropy deconvolution (MED) and maximum correlated kurtosis deconvolution (MCKD) methods. This research is also the first to compare the effectiveness of applying AE and vibration technologies to diagnose a naturally degraded high-speed train bearing, particularly close to actual line operation conditions.

An Adaptive Multi-Sensor Fault Diagnosis Method for High-Speed Train Traction Converters

2020 ◽  
pp. 1-1
Author(s):  
Honghui Dong ◽  
Fuzhao Chen ◽  
zhipeng wang ◽  
Limin Jia ◽  
Yong Qin ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
High Speed ◽  
High Speed Train ◽  
Sensor Fault ◽  
Diagnosis Method
Sign in / Sign up

Export Citation Format

Share Document