?About the author: A Matlab simulation developer who loves scientific research. He cultivates his mind and improves his technology simultaneously.
For code acquisition, paper reproduction and scientific research simulation cooperation, please send a private message.
Personal homepage: Matlab Research Studio
Personal credo: Investigate things to gain knowledge.
For more complete Matlab code and simulation customization content, click
Intelligent optimization algorithm Neural network prediction Radar communication Wireless sensor Power system
Signal processing Image processing Path planning Cellular automaton Drone
Content introduction
Rolling bearings are one of the common key components in industrial equipment, and their normal operation is crucial to the reliability and performance of the equipment. However, due to the harsh working environment and wear and tear of long-term operation, rolling bearings are often prone to various failures. Therefore, timely and accurate fault diagnosis is crucial to the normal operation and maintenance of equipment.
In order to achieve fault diagnosis of rolling bearings, researchers have proposed many different methods and technologies. Among them, feature extraction algorithm is a commonly used method, which can extract feature information related to faults from vibration signals collected by sensors. This article will introduce the process of a feature extraction algorithm for rolling bearing fault diagnosis.
First, we need to collect the vibration signal of the rolling bearing. Normally, we use an acceleration sensor to convert vibration signals into electrical signals, which are recorded and stored through a data acquisition system.
Next, we need to preprocess the collected vibration signals. The purpose of preprocessing is to remove noise and interference from the signal to improve the accuracy of subsequent feature extraction. Commonly used preprocessing methods include filtering, noise reduction, and detrending.
After the preprocessing is completed, we can start feature extraction. The purpose of feature extraction is to extract fault-related feature information from vibration signals for subsequent fault diagnosis and classification. Common features include time domain features, frequency domain features, wavelet packet features, etc. Selecting appropriate features is critical to the accuracy and reliability of fault diagnosis.
After feature extraction is completed, we can use machine learning or pattern recognition algorithms for fault diagnosis and classification. Common algorithms include support vector machines, neural networks, and decision trees. These algorithms can accurately identify and classify rolling bearing fault types based on the extracted feature information.
Finally, we can display the fault diagnosis results in a visual way. Through charts and reports, we can clearly understand the fault type, extent and location of rolling bearings, thereby guiding subsequent maintenance and repair work.
To sum up, the rolling bearing fault diagnosis feature extraction algorithm process includes vibration signal collection, preprocessing, feature extraction, fault diagnosis and result display. Through this process, we can achieve accurate diagnosis of rolling bearing faults and provide strong support for the normal operation and maintenance of equipment.
Rolling bearing fault diagnosis is a complex and important field with broad application prospects. Future research can further explore more efficient and accurate feature extraction algorithms and fault diagnosis technologies to improve the reliability and performance of rolling bearings and make greater contributions to the development of industrial equipment.
Part of the code
?%% Preliminary data processing of rolling bearing fault diagnosis%======================== ================================================== %%% Data import processing G3015%============================== Bearing fault diagnosis data processing============================%%%Import data% fg=fopen('G3015.txt','r'); %Open the data file in reading mode?G302m=sum(G302j) /20000; %G302m is the mean value, G302j is the result after zero-mean processing, the same belowG302f=sum((G302j-G302m).^2); %G302f is the varianceG302rms=sqrt(sum(G302j.^2)/20000); %G302rms root mean square valueG302peak=(max(G302j)-min(G302j))/2; %G302peak is the peak valueG302c= G302peak/G302rms; %G302c is the crest factorG302k=sum(G302j.^4)/((G302rms.^4)*20000); %G302k is the kurtosis CoefficientG302s=(G302rms*20000)/sum(abs(G302j)); %G302s is the waveform factorG302cl=G302peak/(sum(sqrt(abs(G302j))) )/20000).^2; %G302cl margin factorG302i=(G302peak*20000)/sum(abs(G302j)); %G302i pulse factor?G303m=sum(G303j)/20000; %G303m is the mean value, G303j is the result after zero-meaning processing, the same belowG303f=sum((G303j-G303m).^2) ; %G303f is the varianceG303rms=sqrt(sum(G303j.^2)/20000); %G303rms root mean square valueG303peak=(max(G303j)-min( G303j))/2; %G303peak is the peak valueG303c= G303peak/G303rms; %G303c is the peak factorG303k=sum(G303j.^4)/((G303rms.^ 4)*20000); %G303k is the kurtosis coefficientG303s=(G303rms*20000)/sum(abs(G303j)); %G303s is the waveform factorG303cl=G303peak /(sum(sqrt(abs(G303j)))/20000).^2; %G303cl margin factorG303i=(G303peak*20000)/sum(abs(G303j)); %G303i pulse Factor?G304m=sum(G304j)/20000; %G304m is the mean value, G304j is the result after zero-meaning processing, the same belowG304f= sum((G304j-G304m).^2); %G304f is the varianceG304rms=sqrt(sum(G304j.^2)/20000); %G304rms root mean square valueG304peak=(max(G304j)-min(G304j))/2; %G304peak is the peak valueG304c= G304peak/G304rms; %G304c is the peak factorG304k=sum( G304j.^4)/((G304rms.^4)*20000); %G304k is the kurtosis coefficientG304s=(G304rms*20000)/sum(abs(G304j)); %G304s is the waveform FactorG304cl=G304peak/(sum(sqrt(abs(G304j)))/20000).^2; %G304cl margin factorG304i=(G304peak*20000)/ sum(abs(G304j)); %G304i pulse factor?G305m=sum(G305j)/20000; %G305m is the mean value, G305j is the result of zero averaging processing, The same belowG305f=sum((G305j-G305m).^2); %G305f is the varianceG305rms=sqrt(sum(G305j.^2)/20000); % G305rms root mean square valueG305peak=(max(G305j)-min(G305j))/2; %G305peak is the peak valueG305c= G305peak/G305rms; %G305c is the peak factorG305k=sum(G305j.^4)/((G305rms.^4)*20000); %G305k is the kurtosis coefficientG305s=(G305rms*20000)/sum (abs(G305j)); %G305s is the waveform factorG305cl=G305peak/(sum(sqrt(abs(G305j)))/20000).^2; %G305cl margin factorG305i=(G305peak*20000)/sum(abs(G305j)); %G305i pulse factor?G306m=sum(G306j)/20000; %G306m is Mean value, G306j is the result after zero averaging processing, the same belowG306f=sum((G306j-G306m).^2); %G306f is the varianceG306rms=sqrt(sum (G306j.^2)/20000); %G306rms root mean square valueG306peak=(max(G306j)-min(G306j))/2; %G306peak is the peak valueG306c= G306peak/G306rms; %G306c is the crest factorG306k=sum(G306j.^4)/((G306rms.^4)*20000); %G306k is the kurtosis coefficientG306s=(G306rms*20000)/sum(abs(G306j)); %G306s is the waveform factorG306cl=G306peak/(sum(sqrt(abs(G306j)))/20000).^ 2; %G306cl margin factorG306i=(G306peak*20000)/sum(abs(G306j)); %G306i pulse factor?G307m =sum(G307j)/20000; %G307m is the mean value, G307j is the result after zero-mean processing, the same belowG307f=sum((G307j-G307m).^2); %G307f is the varianceG307rms=sqrt(sum(G307j.^2)/20000); %G307rms root mean square valueG307peak=(max(G307j)-min(G307j))/2; %G307peak is the peak valueG307c= G307peak/G307rms; %G307c is the peak factorG307k=sum(G307j.^4)/((G307rms.^4)*20000); %G307k is the kurtosis coefficientG307s=(G307rms*20000)/sum(abs(G307j)); %G307s is the waveform factorG307cl=G307peak/(sum(sqrt( abs(G307j)))/20000).^2; %G307cl margin factorG307i=(G307peak*20000)/sum(abs(G307j)); %G307i pulse factor?G308m=sum(G308j)/20000; %G308m is the mean value, G308j is the result after zero averaging processing, the same belowG308f=sum((G308j-G308m ).^2); %G308f is the varianceG308rms=sqrt(sum(G308j.^2)/20000); %G308rms root mean square valueG308peak=(max( G308j)-min(G308j))/2; %G308peak is the peak valueG308c= G308peak/G308rms; %G308c is the peak factorG308k=sum(G308j.^4)/ ((G308rms.^4)*20000); %G308k is the kurtosis coefficientG308s=(G308rms*20000)/sum(abs(G308j)); %G308s is the waveform factorG308cl=G308peak/(sum(sqrt(abs(G308j)))/20000).^2; %G308cl margin factorG308i=(G308peak*20000)/sum(abs(G308j) ); %G308i pulse factor?G309m=sum(G309j)/20000; %G309m is the mean value, G309j is the result after zero averaging processing, the same belowG309f=sum((G309j-G309m).^2); %G309f is the varianceG309rms=sqrt(sum(G309j.^2)/20000); %G309rms root mean square valueG309peak=(max(G309j)-min(G309j))/2; %G309peak is the peak valueG309c= G309peak/G309rms; %G309c is the peak factorG309k=sum(G309j.^4)/((G309rms.^4)*20000); %G309k is the kurtosis coefficientG309s=(G309rms*20000)/sum(abs(G309j)) ; %G309s is the waveform factorG309cl=G309peak/(sum(sqrt(abs(G309j)))/20000).^2; %G309cl margin factorG309i=( G309peak*20000)/sum(abs(G309j)); %G309i pulse factor?G3010m=sum(G3010j)/20000; %G3010m is the mean value, G3010j is the zero mean value The result after processing, the same belowG3010f=sum((G3010j-G3010m).^2); %G3010f is the varianceG3010rms=sqrt(sum(G3010j.^2) /20000); %G3010rms root mean square valueG3010peak=(max(G3010j)-min(G3010j))/2; %G3010peak is the peak valueG3010c= G3010peak/G3010rms; %G3010c is the crest factorG3010k=sum(G3010j.^4)/((G3010rms.^4)*20000); %G3010k is the kurtosis coefficientG3010s=(G3010rms *20000)/sum(abs(G3010j)); %G3010s is the waveform factorG3010cl=G3010peak/(sum(sqrt(abs(G3010j)))/20000).^2; %G3010cl margin FactorG3010i=(G3010peak*20000)/sum(abs(G3010j)); %G3010i pulse factor?%% Bearing Z3015 processingcode>%===================Import data and perform zero-mean processing==================== =============%%==============Read directly============ =========================================%Z3015 =textread('Z3015.txt','%f'); %Read data to generate matrixZ301=Z3015(1:1:20000); %Get the first 20000 elements of the array , that is, the first set of data, the number of sampling points is 20000Z301j=Z301-mean(Z301); %zero mean processing, %Z301j=Z301-sum(Z301)/20000?Z302=Z3015(20001:1:40000);Z302j=Z302-mean(Z302); %zero mean processing?Z303=Z3015(40001:1:60000);Z303j=Z303-mean(Z303); %Zero mean processing?Z304=Z3015(60001:1:80000);Z304j=Z304-mean(Z304); %zero mean processing??
Operation results
References
[1] Zhao Peng. Research on rolling bearing fault diagnosis system based on virtual instrument[D]. Hebei Engineering University[2023-11-02].DOI:CNKI:CDMD:2.1017.010710.
[2] Wang Liang. Research on rolling bearing fault diagnosis system based on DSP [D]. Dalian University of Technology, 2008. DOI: 10.7666/d.y1418840.