scholarly journals Gear Fault Diagnosis Based on Kurtosis Criterion VMD and SOM Neural Network

2019 ◽  
Vol 9 (24) ◽  
pp. 5424 ◽  
Author(s):  
Dongming Xiao ◽  
Jiakai Ding ◽  
Xuejun Li ◽  
Liangpei Huang
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Characteristic Curve ◽  
Vibration Signal ◽  
Good Effect ◽  
Feature Vectors ◽  
Gear Fault ◽  
Diagnosis Method ◽  
Som Neural Network ◽  
Gear Fault Diagnosis

A gear fault diagnosis method based on kurtosis criterion variational mode decomposition (VMD) and self-organizing map (SOM) neural network is proposed. Firstly, the VMD algorithm is used to decompose the gear vibration signal, and the instantaneous frequency mean is calculated as the evaluation index, and the characteristic curve is drawn to screen out the most relevant intrinsic mode functions (IMFs) of the original vibration signal. Then, the number of VMD decompositions is determined, and the kurtosis value of IMFs are extracted to form the feature vectors. Then, the kurtosis value feature vectors of IMFs are normalized to form the kurtosis value normalized vectors. Finally, the normalized vectors of kurtosis value are input into SOM neural network to realize gear fault diagnosis. When the number of training times of SOM neural network is 100, the gear fault category is accurately classified by SOM neural network. The results show that when the training times of SOM neural network is 100 times, the gear fault diagnosis method, based on the kurtosis criterion VMD and SOM neural network is 100%, which indicates that the new method has a good effect on gear fault diagnosis.

scholarly journals Gear Fault Diagnosis Based on VMD Sample Entropy and Discrete Hopfield Neural Network

2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Jiakai Ding ◽  
Dongming Xiao ◽  
Liangpei Huang ◽  
Xuejun Li
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Empirical Mode Decomposition ◽  
Hopfield Neural Network ◽  
Sample Entropy ◽  
Feature Vectors ◽  
Mode Decomposition ◽  
Gear Fault ◽  
Diagnosis Method ◽  
Gear Fault Diagnosis

The gear fault signal has some defects such as nonstationary nonlinearity. In order to increase the operating life of the gear, the gear operation is monitored. A gear fault diagnosis method based on variational mode decomposition (VMD) sample entropy and discrete Hopfield neural network (DHNN) is proposed. Firstly, the optimal VMD decomposition number is selected by the instantaneous frequency mean value. Then, the sample entropy value of each intrinsic mode function (IMF) is extracted to form the gear feature vectors. The gear feature vectors are coded and used as the memory prototype and memory starting point of DHNN, respectively. Finally, the coding vector is input into DHNN to realize fault pattern recognition. The newly defined coding rules have a significant impact on the accuracy of gear fault diagnosis. Driven by self-associative memory, the coding of gear fault is accurately classified by DHNN. The superiority of the VMD-DHNN method in gear fault diagnosis is verified by comparing with an advanced signal processing algorithm. The results show that the accuracy based on VMD sample entropy and DHNN is 91.67% of the gear fault diagnosis method. The experimental results show that the VMD method is better than the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and empirical mode decomposition (EMD), and the effect of it in the diagnosis of gear fault diagnosis is emphasized.

Gear Fault Diagnosis Methods Based on EMD and HMM

2013 ◽  
Vol 333-335 ◽  
pp. 1684-1687
Author(s):  
Bin Wu ◽  
Song He Zhang ◽  
Yue Gang Luo ◽  
Shan Ping Yu
Keyword(s):  
Fault Diagnosis ◽  
Vibration Signal ◽  
Modulation Amplitude ◽  
Double Frequency ◽  
Gear Mesh ◽  
Gear Fault ◽  
Diagnosis Method ◽  
Modulation Signal ◽  
Gear Fault Diagnosis ◽  
Modulation Sideband

Due to the feature and the forms of motion of the gears, the vibration signal of the gear is mainly the frequency modulation, amplitude modulation, or hybrid modulation signal corresponding to the gear-mesh frequency and its double frequency signal. When faults arise on the gears, the number and shape of the modulation sideband will be changed. The structures and forms of the FM composition differ according to the type of faults. According to the above mentioned characteristic, this essay raises a method to disassemble the gear vibrate signal, points out the formulas to build up characteristic vector, on that basis, the essay raised a gear fault diagnosis method based on EMD and Hidden Markov Model (HMM), this method can identify the working condition of the normal gears, snaggletooth gears, and pitting gears.

Research on the Fault Diagnosis Technology of Diesel Engine Based on the Instantaneous Speed

2009 ◽  
Vol 413-414 ◽  
pp. 547-552 ◽  
Author(s):  
Yi Hu ◽  
Rui Ping Zhou ◽  
Jian Guo Yang
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Diesel Engine ◽  
Vibration Amplitude ◽  
Good Effect ◽  
Cylinder Pressure ◽  
Angular Vibration ◽  
Diagnosis Method ◽  
Som Neural Network ◽  
Instantaneous Speed

The instantaneous speed signals of diesel contain lots of information about machine states, which is useful for fault diagnosis of diesel engine. Mixed fault diagnosis method of diesel engine based on the instantaneous speed has been proposed, which combines with the lower order angular vibration amplitude and SOM neural network to diagnose the cylinder pressure fault, then extracts three feature parameters of instantaneous speed to locate the fault cylinder. The method can detect the cylinder pressure fault accurately in diesel engine and locate the fault cylinder. The experimental confirmation shows that it has good effect on fault diagnosis of diesel engine.

Gear Fault Diagnosis Method Based on the Integration of Empirical Mode Decomposition and Cepstrum Analysis

2013 ◽  
Vol 310 ◽  
pp. 328-333 ◽  
Author(s):  
Bing Luo ◽  
Wen Tong Yang ◽  
Zhi Feng Liu ◽  
Yong Sheng Zhao ◽  
Li Gang Cai
Keyword(s):  
Fault Diagnosis ◽  
Empirical Mode Decomposition ◽  
Vibration Signal ◽  
Mechanical Transmission ◽  
Intrinsic Mode Functions ◽  
Cepstrum Analysis ◽  
Mode Decomposition ◽  
Gear Fault ◽  
Diagnosis Method ◽  
Gear Fault Diagnosis

Gear is the most common mechanical transmission equipment. Therefore, gear fault diagnosis is of much significance. In this article, a gear fault diagnosis method based on the integration of empirical mode decomposition and cepstrum is proposed by introducing empirical mode decomposition and cepstrum into gear fault analysis. Firstly EMD is used to decompose the gear vibration signal finite number of intrinsic mode functions and a residual error item. To do gear fault diagnosis, cepstrum analysis is carried upon those intrinsic mode functions to extract feature information from the vibration signal. The results of the study on simulated and experimental signals show that this method is better than the cepstrum method and it can precisely locate the site of gear failure.

New Gear Fault Diagnosis Method Based on MODWPT and Neural Network for Feature Extraction and Classification

2019 ◽  
Vol 49 (2) ◽  
pp. 20190107 ◽  
Author(s):  
Adel Afia ◽  
Chemseddine Rahmoune ◽  
Djamel Benazzouz ◽  
Boualem Merainani ◽  
Semcheddine Fedala
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Fault Diagnosis ◽  
Gear Fault ◽  
Diagnosis Method ◽  
Gear Fault Diagnosis

Gear Fault Diagnosis Method of Intelligence Based on Genetic Algorithm to Optimize the BP Neural Network

2013 ◽  
Vol 756-759 ◽  
pp. 3674-3679 ◽  
Author(s):  
Jie Fang
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Fault Diagnosis ◽  
Bp Neural Network ◽  
Vibration Signal ◽  
Linear Mapping ◽  
Gear Fault ◽  
Gear Fault Diagnosis ◽  
Signal Processing Methods ◽  
Bp Neural Network Model

The work of the gear transmission is very complex, and its failure in the form and features tend to show non-linear mapping. Fault signal is often submerged in conventional vibration signal and noise, it is not easy using traditional signal processing methods to extract fault features which in a difficult to gear fault diagnosis. This paper based on the genetic algorithm to optimize the structure of the BP neural network model for the intelligent diagnosis system which is used in gear fault diagnosis.The experimental results show that this method can be effectively used for the diagnosis and identification of the gears common fault type.

Research on Roller Bearing with Fault Diagnosis Method Based on EMD and BP Neural Network

2014 ◽  
Vol 1014 ◽  
pp. 501-504 ◽  
Author(s):  
Shu Guo ◽  
You Cai Xu ◽  
Xin Shi Li ◽  
Ran Tao ◽  
Kun Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Bp Neural Network ◽  
Roller Bearing ◽  
Vibration Signal ◽  
Classification Performance ◽  
Outer Race ◽  
Mode Decomposition ◽  
Diagnosis Method ◽  
Main Fault

In order to discover the fault with roller bearing in time, a new fault diagnosis method based on Empirical mode decomposition (EMD) and BP neural network is put forward in the paper. First, we get the fault signal through experiments. Then we use EMD to decompose the vibration signal into a series of single signals. We can extract main fault information from the single signals. The kurtosis coefficient of the single signals forms a feature vector which is used as the input data of the BP neural network. The trained BP neural network can be used for fault identification. Through analyzing, BP neural network can distinguish the fault into normal state, inner race fault, outer race fault. The results show that this method can gain very stable classification performance and good computational efficiency.

Sign in / Sign up

Export Citation Format

Share Document