Research of Automobile Engine Fault Diagnosis Based on Wavelet Packet

2012 ◽  
Vol 472-475 ◽  
pp. 795-798
Author(s):  
Min Yong Tong
Keyword(s):  
Fault Diagnosis ◽  
Frequency Band ◽  
Signal Analysis ◽  
Energy Analysis ◽  
Wavelet Packet ◽  
Automobile Engine ◽  
Band Energy ◽  
Diagnosis Method ◽  
S Model ◽  
Frequency Band Energy

A diagnosis method using wavelet packet, frequency band energy analysis and neural network was presented for the automobile engine fault diagnosis. Fault signal of automobile engine was decomposed at different frequency band by wavelet packet. According to the change of frequency band energy, fault frequency band of the automobile engine was found. Fault diagnosis knowledge is described by means of applying T-S model. Results from the experimental signal analysis show that the proposed method is effective in diagnosing the automobile engine faults.

Application of Wavelet Packet Energy Spectrum in Micro Motor Fault Diagnosis

2013 ◽  
Vol 726-731 ◽  
pp. 3159-3162
Author(s):  
Sheng Yi Chen ◽  
Gui Tang Wang ◽  
Shou Lei Sun ◽  
Qiang Zhou
Keyword(s):  
Fault Diagnosis ◽  
Energy Spectrum ◽  
Frequency Band ◽  
Wavelet Packet ◽  
Reconstruction Algorithm ◽  
Mechanical Equipment ◽  
Vibration Signals ◽  
Band Energy ◽  
Status Information ◽  
Frequency Band Energy

To diagnosis vibration signals of micro motor in several different fault types a method based on wavelet packet energy spectrum is presented, the energy on each Sub-frequency band, which are Calculated by Wavelet packet decomposition and reconstruction algorithm, are used to normalization process.Under both circumstances of normal working and unmoral working of mechanical equipment,there exist evident differences among the Sub-frequency band energy after the decomposition of wavelet packet, which energy contains a wealth of micro motor running status information and the eigenvectors is structured by the Sub-frequency band energy spectrum can establish energy and Fault mapping relationship.The preliminary experimental results show that it is effective to use the wavelet packet-energy spectrum in micro motor fault diagnosis .

scholarly journals Researching Coal and Rock Character Recognition Based on Wavelet Packet Frequency Band Energy

2014 ◽  
Vol 6 (1) ◽  
pp. 1793-1797 ◽  
Author(s):  
Guanghui Xue ◽  
Xinying Zhao ◽  
Ermeng Liu ◽  
Weijian Ding ◽  
Baohua Hu
Keyword(s):  
Frequency Band ◽  
Character Recognition ◽  
Wavelet Packet ◽  
Band Energy ◽  
Frequency Band Energy

Fault Diagnosis of Automobile Rear Axle Based on Wavelet Packet and Support Vector Machine

2011 ◽  
Vol 211-212 ◽  
pp. 1021-1026 ◽  
Author(s):  
Yong Chen ◽  
Bao Qiang Wang ◽  
Jin Yao
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Frequency Band ◽  
Rear Axle ◽  
Wavelet Packet ◽  
Support Vector ◽  
Svm Classifier ◽  
Failure State ◽  
Diagnosis Method ◽  
Specific Frequency

This paper presents a fault diagnosis method of automobile rear axle based on wavelet packet analysis (WPA) and support vector machine (SVM) classifier. By Fourier transformation we find out the frequency band that can mostly reflect the rear axle failure state and use wavelet packet to decompose and reconstruct the vibration signals of rear axle, then extract each band’s energy and the variance, standard deviation, skewness, kurtosis of the specific frequency band to constitute a feature vector. We use the feature vectors which are come from some pieces of normal and abnormal samples to train support vector machine classifier for obtaining the best classification，at the same time, discuss the optimization of SVM parameters. Application shows that the method is effective in real time fault diagnosis for the automobile rear axle and has a strong anti-interference ability in different working conditions.

scholarly journals A Diagnosis Method for the Compound Fault of Gearboxes Based on Multi-Feature and BP-AdaBoost

Symmetry ◽  
2020 ◽  
Vol 12 (3) ◽  
pp. 461 ◽  
Author(s):  
Yangyang Zhang ◽  
Yunxian Jia ◽  
Weiyi Wu ◽  
Zhonghua Cheng ◽  
Xiaobo Su ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Time Domain ◽  
Failure Modes ◽  
Wavelet Packet ◽  
Rotating Machinery ◽  
Adaboost Algorithm ◽  
Feature Parameters ◽  
Reconstructed Signal ◽  
Diagnosis Method ◽  
Frequency Band Energy

Gearbox is an important structure of rotating machinery, and the accurate fault diagnosis of gearboxes is of great significance for ensuring efficient and safe operation of rotating machinery. Aiming at the problem that there is little common compound fault data of gearboxes, and there is a lack of an effective diagnosis method, a gearbox fault simulation experiment platform is set up, and a diagnosis method for the compound fault of gearboxes based on multi-feature and BP-AdaBoost is proposed. Firstly, the vibration signals of six typical states of gearbox are obtained, and the original signals are decomposed by empirical mode decomposition and reconstruct the new signal to achieve the purpose of noise reduction. Then, perform the time domain analysis and wavelet packet analysis on the reconstructed signal, extract three time domain feature parameters with higher sensitivity, and combine them with eight frequency band energy feature parameters obtained by wavelet packet decomposition to form the gearbox state feature vector. Finally, AdaBoost algorithm and BP neural network are used to build the BP-AdaBoost strong classifier model, and feature vectors are input into the model for training and verification. The results show that the proposed method can effectively identify the gearbox failure modes, and has higher accuracy than the traditional fault diagnosis methods, and has certain reference significance and engineering application value.

scholarly journals The Analysis of Hand Movement Distinction Based on Relative Frequency Band Energy Method

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Yanyan Zhang ◽  
Gang Wang ◽  
Chaolin Teng ◽  
Zhongjiang Sun ◽  
Jue Wang
Keyword(s):  
Frequency Band ◽  
Classification Accuracy ◽  
Relative Frequency ◽  
Wavelet Packet ◽  
Support Vector ◽  
Wavelet Packet Decomposition ◽  
Band Energy ◽  
Frequency Band Energy ◽  
Semg Signals

For the purpose of successfully developing a prosthetic control system, many attempts have been made to improve the classification accuracy of surface electromyographic (SEMG) signals. Nevertheless, the effective feature extraction is still a paramount challenge for the classification of SEMG signals. The relative frequency band energy (RFBE) method based on wavelet packet decomposition was proposed for the prosthetic pattern recognition of multichannel SEMG signals. Firstly, the wavelet packet energy of SEMG signals in each subspace was calculated by using wavelet packet decomposition and the RFBE of each frequency band was obtained by the wavelet packet energy. Then, the principal component analysis (PCA) and the Davies-Bouldin (DB) index were used to perform the feature selection. Lastly, the support vector machine (SVM) was applied for the classification of SEMG signals. Our results demonstrated that the RFBE approach was suitable for identifying different types of forearm movements. By comparing with other classification methods, the proposed method achieved higher classification accuracy in terms of the classification of SEMG signals.

Fault Diagnosis Method of Time Domain and Time-Frequency Domain Based on Information Fusion

2013 ◽  
Vol 300-301 ◽  
pp. 635-639 ◽  
Author(s):  
Jiang Zhao ◽  
Jiao Wang ◽  
Meng Shang
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Information Fusion ◽  
Time Domain ◽  
Wavelet Packet ◽  
Network Information ◽  
Time Frequency ◽  
Index Data ◽  
Diagnosis Method ◽  
Frequency Band Energy

On account of the problem that traditional pipe leakage diagnosis method is not highly accuracy .this paper come up with a method that based on pipe leakage diagnosis method of neural network information fusion. Giving the stress wave time domain feature extraction index data algorithm and wavelet packet extraction each the frequency band energy algorithm, by comparing with these results of the pressure wave time domain feature index data, time-frequency extraction energy values and fault diagnosis of both information fusion ,which show the neural network information fusion method that is used for pipe leakage diagnosis that is feasible and effective.

Frequency Band Energy Statistics Method and the Applications in Monitoring the Work Conditions for Mechanical Equipments

2010 ◽  
Vol 29-32 ◽  
pp. 78-83
Author(s):  
Yun Long Yuan ◽  
Chao Yong Yuan ◽  
Chao Zhen Yang
Keyword(s):  
Fault Diagnosis ◽  
Energy Distribution ◽  
Frequency Band ◽  
Present Method ◽  
Vibration Signal ◽  
Work Conditions ◽  
Current Work ◽  
Vibration Signals ◽  
Band Energy ◽  
Frequency Band Energy

A new manner, named frequency band energy statistics method, has been proposed for the analysis of the spectra from the vibration signals. The recorded vibration signals were first divided into multi-segments. Then each segment was calculated via the FFT transformation and 1/3 octave spectrum to obtained the characteristics of energy distribution, by making the histogram maps of the obtained features of the frequency energies. Consequently, we can monitor the work conditions and fault diagnosis for the mechanical equipments by the compared analysis of the corresponding histogram maps of equipments with normal and abnormal work conditions. The results show that present method exhibits a very strong sensitivity to the changes of vibration signal, leading to the fine detection of the minor changes form the equipment work conditions. Current work might provide a novel and facile method for definitely monitoring the work conditions and fault diagnosis of the mechanical equipments.

Sign in / Sign up

Export Citation Format

Share Document