CN115758083A - Motor bearing fault diagnosis method based on time domain and time-frequency domain fusion - Google Patents
Motor bearing fault diagnosis method based on time domain and time-frequency domain fusion Download PDFInfo
- Publication number
- CN115758083A CN115758083A CN202211406979.3A CN202211406979A CN115758083A CN 115758083 A CN115758083 A CN 115758083A CN 202211406979 A CN202211406979 A CN 202211406979A CN 115758083 A CN115758083 A CN 115758083A
- Authority
- CN
- China
- Prior art keywords
- fault
- time
- frequency domain
- early warning
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention relates to the field of motor bearing fault diagnosis methods, and discloses a motor bearing fault diagnosis method based on time domain and time-frequency domain fusion, which comprises the following steps: carrying out data acquisition and processing on the time domain index and the time-frequency domain index of the rolling bearing by using a vibration signal acquisition device; performing VMD decomposition on the time-frequency domain indexes to obtain optimal parameters, calculating the kurtosis of each IMF component after VMD decomposition, and reconstructing a vibration signal; performing SVD (singular value decomposition) to obtain a singular value matrix according to each IMF component reconstruction matrix, and selecting the largest singular value of each IMF component to form a fault characteristic vector; fusing the extracted time domain indexes and the characteristic vector of the VMD-SVD to form a composite characteristic vector of multi-dimensional information; and inputting the composite feature vector into a support vector machine for training and testing, and finally realizing the judgment and diagnosis of the fault type. The invention provides an algorithm for integrating time domain indexes and VMD-SVD decomposition characteristics on a time-frequency domain, and the accuracy of fault diagnosis of a rolling bearing of a motor is improved.
Description
Technical Field
The invention belongs to the field of motor bearing fault diagnosis methods, and particularly relates to a motor bearing fault diagnosis method based on time domain and time-frequency domain fusion.
Background
The power plant in China has various types of motors, and the motors play important roles in water supply, lubrication, water drainage and the like in the power plant. However, after the motor runs for a long time, a series of problems that parts of unit equipment are aged, information is difficult to collect, faults are difficult to find in time and the like exist, certain potential safety hazards are generated due to the problems, and the rolling bearing is used as the most applied and most vulnerable part in the water pump, so that the stable running of the motor is influenced, and the stable running of a generator set is also influenced.
Like other fault diagnosis systems, the fault diagnosis of the rolling bearing realizes fault diagnosis by analyzing and processing signals generated by the rolling bearing, and the fault diagnosis process comprises the parts of signal acquisition, feature extraction and fault identification. The fault diagnosis of the rolling bearing adopts the following four methods according to different principles:
(1) Temperature diagnostic method
In the fault diagnosis of the rolling bearing, a temperature diagnosis method is applied earliest, mainly monitors the temperature of the bearing and judges whether the bearing has a fault according to the temperature change condition of the bearing, but the temperature diagnosis method is greatly influenced by the external environment and can only be used as an auxiliary diagnosis method.
(2) Acoustic diagnostic method
The method needs experienced engineers to monitor noise at random and judge faults according to noise changes, but the method has the defects that specific parts of the bearing with faults cannot be obtained, and acoustic signals are easily influenced by the structure, the position and the like of the bearing.
(3) Oil film resistance diagnostic method
An oil film resistance diagnosis method which diagnoses by a resistance value of an oil film generated in a rolling bearing, when the rolling bearing is out of order, an oil film layer between them is broken to cause a change in the resistance value, and then diagnoses whether the bearing is out of order based on the change in the resistance value. This method has good results in the face of bearing failure caused by wear and corrosion, but the technical method has high requirements on bearing sealing and cannot be widely applied in practice at present.
(4) Vibration signal diagnostic method
The method comprises the steps of firstly collecting vibration signals of the bearing, then extracting fault characteristics of the signals through a series of analysis methods, and finally diagnosing. A series of fault diagnosis systems for rolling bearings which are currently on the market are based on the principle of vibration. The invention also provides a diagnosis method based on the vibration signal on the basis of the vibration signal, and the fault diagnosis of the rolling bearing is realized.
The current mainstream method is to use a pattern recognition algorithm to carry out intelligent diagnosis on the rolling bearing, and fault pattern recognition can be divided into two categories according to the difference of recognition principles, wherein the first category is supervised pattern recognition, and the common categories comprise a support vector machine, a neural network, deep learning and the like. The principle of the classifiers is to construct a classification model through learning, firstly, a known sample is learned to form a specific mathematical classification model, and the mathematical classification model can identify and judge an unknown sample; the second category is unsupervised pattern recognition, which is completely different from supervised pattern recognition, does not need to learn and train samples in advance and then carry out pattern recognition, carries out pattern recognition by finding out the similarity existing between input samples, and is a common unsupervised pattern recognition fuzzy clustering method. The Yaohika et al successfully applies the K-means clustering identification method to fault diagnosis of the rolling bearing, the method successfully solves the problem of local solution in a clustering algorithm by utilizing simulated annealing, and then the fault signal of the rolling bearing is acquired by constructing a fault experiment for diagnosis, and the experiment shows that the method has good effect. The fuzzy clustering method is also used for carrying out mode identification on bearing faults for Ding et al, the model identification method carries out EMD decomposition on vibration signals generated when a rolling bearing runs from vibration signals, corresponding modal components are generated after EMD decomposition, approximate entropies of various modes are input into FCM clustering as features for classification and identification, and good identification rate proves the feasibility of the method. The neural network is more and more widely applied to fault diagnosis of the rolling bearing, and the core idea is to simulate the human brain neuron network to construct a mathematical classification model which is obtained by machine learning on the basis of empirical knowledge learning. Zhang Qing et al proposed a BP neural network-based diagnostic method, which first decomposes a bearing vibration signal into a series of modal components through EEMD, then takes the approximate entropy of each modal component as a feature, then trains a feature sample by using the BP neural network, diagnoses and identifies a fault signal after the training is finished, and the experimental result verifies the effectiveness of the method.
The support vector machine is a classifier based on statistics, and the basic principle is to find the optimal hyperplane that can distinguish different types of data samples. Compared with a neural network, the support vector machine has the advantages that the support vector machine is particularly suitable for small sample classification, the problems like overfitting and underfitting of the neural network are not caused, a fault diagnosis method combining time domain features with the support vector machine is proposed by Zhang Pepeng, and experiments prove that the method is effective. Wangjindong et al proposed a fault diagnosis method based on EMD and support vector machine, firstly using EMD to decompose the bearing original signal, using the information entropy of each modal component as the parameter input of the support vector machine to train, and analyzing the method by test samples to have certain effectiveness.
The above method has the following disadvantages:
the temperature diagnosis method is greatly influenced by the external environment and can only be used as an auxiliary diagnosis method; the acoustic diagnosis method has the defects that the specific position of the bearing with the fault cannot be obtained, and the acoustic emission signal is easily influenced by the structure, the position and the like of the bearing; the oil film resistance diagnostic method has high requirements on bearing sealing, and cannot be widely applied to practice at present; the fault recognition rate of the EMD method is not high.
Disclosure of Invention
The invention aims to provide a motor bearing fault diagnosis method based on time domain and time-frequency domain fusion, and aims to solve the technical problem of low accuracy of the existing fault diagnosis method.
In order to solve the technical problems, the specific technical scheme of the invention is as follows:
in some embodiments of the present application, a method for diagnosing a fault of a motor bearing based on time domain and time-frequency domain fusion is provided, which includes the following steps:
s1, carrying out data acquisition and processing on time domain indexes and time-frequency domain indexes of a rolling bearing by using a vibration signal acquisition device;
s2, setting VMD decomposition parameters, carrying out VMD decomposition on the time-frequency domain indexes in the set parameter range to obtain optimal parameters, calculating the kurtosis of each IMF component after VMD decomposition, and reconstructing a vibration signal;
s3, according to the IMF component reconstruction matrix, carrying out SVD to obtain a singular value matrix, and selecting the singular value with the largest IMF component to form a fault feature vector;
s4, fusing the extracted time domain indexes and the characteristic vectors extracted by the VMD-SVD decomposition to form a composite characteristic vector of multi-dimensional information;
and S5, inputting the composite feature vector into a support vector machine for training and testing, and finally realizing the judgment and diagnosis of the fault type.
Preferably, in an embodiment of the above method for diagnosing a fault of a motor bearing based on fusion of time domain and time-frequency domain, the time domain index in step S1 includes: kurtosis, peak factor, impulse factor, and margin factor.
Preferably, in an embodiment of the above method for diagnosing a fault of a motor bearing based on time domain and time-frequency domain fusion, the specific process of step S2 is as follows:
s21, carrying out parameter initialization on the time-frequency domain indexes through a PSO optimization algorithm;
s22, decomposing the filtered vibration signal into a plurality of modal components by utilizing a VMD decomposition algorithm, and calculating a kurtosis coefficient value of each mode;
s23, setting the current iteration times to be not N and the preset maximum iteration times to be N; judging whether the current iteration number N is greater than or equal to a preset maximum iteration number N, if so, entering a step S24, otherwise, enabling N = N +1, and returning to the step S22;
s24, storing the optimal parameters, performing VMD decomposition on the optimal parameters, decomposing the optimal parameters into a plurality of modal components, calculating the kurtosis coefficient value of each modal component, and selecting the modal component corresponding to the maximum kurtosis coefficient value to perform signal synthesis;
s25, after filtering processing is carried out on the synthesized signal obtained in the step S24, envelope demodulation is carried out to generate an envelope spectrum;
and S26, analyzing according to the envelope spectrum obtained in the step S25 and extracting a fault feature vector.
Preferably, in an embodiment of the above method for diagnosing a motor bearing fault based on time domain and time-frequency domain fusion, the parameters in step S2 are a secondary penalty factor α and a number K of modal components.
Preferably, in an embodiment of the motor bearing fault diagnosis method based on time domain and time-frequency domain fusion, the method further includes: and determining the working state of the motor bearing according to the acquired vibration signal, and then carrying out different adjustments according to different working states.
Preferably, in an embodiment of the above method for diagnosing a fault of a motor bearing based on time domain and time-frequency domain fusion, the determining a working state of the motor bearing according to the collected vibration signal specifically includes: comparing the collected vibration signal with a preset vibration signal, determining the current working state of the motor bearing based on the comparison result, and transmitting the working state to a fault management terminal; wherein the working state comprises a normal state and a fault state; when the working state is normal, the adjustment is not carried out; when the working state is a fault, the current fault level needs to be judged according to the number of the faults, and the early warning processing is carried out at the same time, and the fault type comprises the following steps: inner ring failure, outer ring failure, and rolling element failure.
Preferably, in an embodiment of the motor bearing fault diagnosis method based on time domain and time-frequency domain fusion, the determining, according to the number of faults occurring, a current fault level and performing early warning processing specifically include:
presetting a preset fault state degree matrix A0, and setting A0= (A1, A2, A3), wherein A1 is a first preset fault state degree, A2 is a second preset fault state degree, and H3 is a third preset fault state degree, wherein A1 is more than A2 and less than A3;
presetting a preset early warning level matrix B0, and setting B0= (B1, B2 and B3), wherein B1 is a first preset early warning level, B2 is a second preset early warning level, B3 is a third preset early warning level, and B1 is greater than B2 and is greater than B3; setting an early warning grade G according to the relation between the leakage degree H and each preset leakage degree: when A is less than A1, selecting the first preset early warning level B1 as an early warning level B; when A1 is not less than A and is less than A2, selecting the second preset early warning grade B2 as an early warning grade B; and when A2 is not less than A and is less than A3, selecting the third preset early warning grade B3 as an early warning grade B.
Through the technical scheme, compared with the prior art, the invention has the beneficial effects that:
according to the scheme, a vibration signal collector based on ZYNQ is designed to realize the collection and processing of vibration data of the rolling bearing; the PL end is designed to comprise a signal conditioning circuit, an AD acquisition and control circuit, FIR digital filtering, system clock frequency and the like, and the PS end is designed to finish data storage, ethernet data transmission and the like. The design selects an acceleration sensor to collect rolling bearing vibration signals at different measuring points, the rolling bearing vibration signals are transmitted to a PC (personal computer) end through an Ethernet after being preprocessed, and the PC end carries out fault identification on the running state of a unit rolling bearing;
according to the scheme, the bearing vibration signals are decomposed by utilizing Variational Modal Decomposition (VMD), the method has a solid theoretical basis and strong robustness, is suitable for processing nonlinear and non-stationary signals such as the rolling bearing vibration signals, can self-adaptively select two important parameters of decomposition layer number k and punishment factors of the VMD according to signal characteristics, then completes the decomposition of the signals, and finally verifies the effectiveness of the method by utilizing fault simulation signals of the rolling bearing;
according to the method, fault diagnosis of the rolling bearing is realized by using a support vector machine algorithm, the characteristic values extracted by VMD-SVD decomposition and the indexes in the time domain are fused to form a composite characteristic matrix of multi-dimensional information, the characteristics are input into the support vector machine for training, and in order to show the application effect of the method, the method is used for carrying out diagnosis test on the bearing fault data collected in an experiment, so that a good diagnosis effect is obtained, and the effectiveness of the method is verified.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of feature extraction provided by an embodiment of the present invention;
fig. 2 is a flow chart of parameter adaptive VMD feature extraction according to an embodiment of the present invention;
FIG. 3 is a diagram of a recognition result of a time-domain feature fusion SVM-VMD feature sample in an SVM provided by the embodiment of the present invention
FIG. 4 is a diagram of the recognition result of a time-domain feature sample in an SVM;
FIG. 5 is a diagram of the recognition result of a time-domain feature fusion SVM-EMD feature sample in an SVM.
Detailed Description
The following detailed description of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention, but are not intended to limit the scope of the invention.
In the description of the present application, it is to be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience in describing the present application and simplifying the description, but do not indicate or imply that the referred device or element must have a particular orientation, be constructed in a particular orientation, and be operated, and thus should not be construed as limiting the present application.
The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, the meaning of "a plurality" is two or more unless otherwise specified.
In the description of the present application, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art.
For a better understanding of the objects, structure and function of the invention, reference should be made to the following detailed description taken in conjunction with the accompanying drawings.
Referring to fig. 1-2, according to some embodiments of the present application, in some embodiments of the present application, a method for diagnosing a fault of a motor bearing based on time domain and time-frequency domain fusion is provided, which includes the following steps:
s1, carrying out data acquisition and processing on time domain indexes and time-frequency domain indexes of a rolling bearing by using a vibration signal acquisition device;
s2, setting VMD decomposition parameters, carrying out VMD decomposition on the time-frequency domain indexes in the set parameter range to obtain optimal parameters, calculating the kurtosis of each IMF component after VMD decomposition, and reconstructing a vibration signal;
s3, performing SVD (singular value decomposition) to obtain a singular value matrix according to the IMF component reconstruction matrix, and selecting the largest singular value of each IMF component to form a fault characteristic vector;
s4, fusing the extracted time domain indexes and the characteristic vectors extracted by the VMD-SVD decomposition to form a composite characteristic vector of multi-dimensional information;
and S5, inputting the composite feature vector into a support vector machine for training and testing, and finally realizing the judgment and diagnosis of the fault type.
Specifically, the vibration signal collector includes: the system comprises a plurality of acceleration sensors, a plurality of signal regulators, an AD acquisition card, a PL terminal, a PS terminal and a PC terminal; the interface of the acceleration sensor, the signal conditioner and the AD acquisition card are sequentially connected; the vibration electric signal acquisition module is used for amplifying and filtering the acquired vibration electric signal, converting the vibration electric signal into a digital signal and transmitting the digital signal to the acquisition control module; the PL terminal is a logic terminal and comprises: the system comprises a plurality of FIFD buffers, an FIR filtering module, an acquisition control module, an internet memory and an expansion MIO pin; storing and transmitting the collected data by receiving; the PS end is a processing end, completes data storage, transmits the data to the PC end, and displays the data through the PC end.
Through above-mentioned technical scheme, the technical effect that this application can reach lies in:
the invention realizes the acquisition and processing of vibration data of a rolling bearing based on a ZYNQ vibration signal acquisition device, designs a signal conditioning circuit, an AD acquisition and control circuit, FIR digital filtering, system clock frequency and the like at a PL end, and completes data storage, ethernet data transmission and the like at a PS end; the design selects an acceleration sensor to collect rolling bearing vibration signals at different measuring points, the rolling bearing vibration signals are transmitted to a PC (personal computer) end through an Ethernet after being preprocessed, and the PC end carries out fault identification on the running state of a unit rolling bearing;
the time domain index and the VMD-SVD decomposition characteristics in the time-frequency domain are fused, and experimental data verification shows that the method improves the classification precision.
In another preferred embodiment of the present application, referring to fig. 2, the specific process of step S2 is as follows:
s21, carrying out parameter initialization on the time-frequency domain indexes through a PSO optimization algorithm;
s22, decomposing the filtered vibration signal into a plurality of modal components by utilizing a VMD decomposition algorithm, and calculating a kurtosis coefficient value of each mode;
s23, setting the current iteration times to be not N and the preset maximum iteration times to be N; judging whether the current iteration number N is greater than or equal to a preset maximum iteration number N, if so, entering a step S24, otherwise, enabling N = N +1, and returning to the step S22;
s24, storing the optimal parameters, performing VMD decomposition on the optimal parameters, decomposing the optimal parameters into a plurality of modal components, calculating the kurtosis coefficient value of each modal component, and selecting the modal component corresponding to the maximum kurtosis coefficient value to perform signal synthesis;
s25, after filtering processing is carried out on the synthesized signal obtained in the step S24, envelope demodulation is carried out to generate an envelope spectrum;
and S26, analyzing according to the envelope spectrum obtained in the step S25 and extracting a fault feature vector.
Specifically, the parameters in step S2 include a secondary penalty factor α and the number of modal components.
Through above-mentioned technical scheme, the technical effect that this application can reach lies in:
the VMD algorithm is adopted to decompose the short-circuit protection current signal of the converter valve, and compared with the EMD and the improved algorithm thereof in the traditional non-stable signal processing method, the method has a solid theoretical foundation and has a better decomposition effect;
the method combines the VMD and the SVM, and further improves the accuracy of the fault diagnosis of the rolling bearing of the motor by means of the good dividing capability of the VMD algorithm on the similar frequency components and the learning and training capability of the SVM.
In another preferred embodiment of the present application, the method further comprises: and determining the working state of the motor bearing according to the acquired vibration signal, and then carrying out different adjustments according to different working states.
Specifically, the determining the working state of the motor bearing according to the collected vibration signal specifically comprises: comparing the collected vibration signal with a preset vibration signal, determining the current working state of the motor bearing based on a comparison result, and transmitting the working state to a fault management terminal; wherein the working state comprises a normal state and a fault state; when the working state is normal, the adjustment is not carried out; when the working state is a fault, the current fault level needs to be judged according to the number of the faults and the early warning treatment is carried out at the same time, and the fault type comprises: inner ring failure, outer ring failure, and rolling element failure.
Specifically, judging the current fault level according to the number of faults and simultaneously performing early warning treatment specifically comprises:
presetting a preset fault state degree matrix A0, and setting A0= (A1, A2, A3), wherein A1 is a first preset fault state degree, A2 is a second preset fault state degree, and H3 is a third preset fault state degree, wherein A1 is more than A2 and less than A3;
presetting a preset early warning level matrix B0, and setting B0= (B1, B2 and B3), wherein B1 is a first preset early warning level, B2 is a second preset early warning level, B3 is a third preset early warning level, and B1 is greater than B2 and is greater than B3; setting an early warning grade G according to the relationship between the leakage degree H and each preset leakage degree: when A is smaller than A1, selecting the first preset early warning grade B1 as an early warning grade B; when A1 is not less than A and is less than A2, selecting the second preset early warning grade B2 as an early warning grade B; and when A2 is not less than A and is less than A3, selecting the third preset early warning grade B3 as an early warning grade B.
Through above-mentioned technical scheme, the technical effect that this application can reach lies in:
different early warning levels can be selected according to different fault degrees by presetting the fault state degree matrix and the early warning levels, so that the fault can be conveniently adjusted.
The technical effect of the invention is further illustrated below by means of several examples:
the fault diagnosis experimental result based on the SVM is as follows:
example 1:
and (3) measuring a characteristic sample formed by fusing the time domain index of the sample and the SVD-VMD characteristic, inputting the test sample into a trained SVM classification model for diagnosis, and as shown in figure 3, only recognizing the result of the time domain characteristic sample in the SVM by 96%.
Comparative example 1:
and (3) testing a sample time-sharing domain feature sample (kurtosis, peak factor, pulse factor and margin factor), and inputting the test sample into a trained SVM classification model for diagnosis, wherein as can be seen from fig. 4, only the time domain feature sample identifies the result in the SVM by 89%.
Comparative example 2:
and (3) measuring a characteristic sample obtained by fusing the time domain index of the sample and the SVD-EMD characteristic, and inputting the test sample into a trained SVM classification model for diagnosis, wherein as shown in FIG. 5, only 92% of the result of the time domain characteristic sample is recognized in the SVM.
From the above, it can be seen that: the time domain index and the VMD-SVD decomposition characteristics in the time-frequency domain are fused, and experimental data verification shows that the recognition result is 96%, and the classification precision is greatly improved.
In the invention:
the Variational Modal Decomposition (VMD) is a signal adaptive decomposition method proposed by Dragonomirskisky and Zosso of the university of California in the 2014, and as an improved empirical mode decomposition method, the VMD has a solid mathematical theory basis, and the noise robustness and the signal separation performance are greatly improved. However, VMD decomposition parameters such as the number of modal components and modal component frequency bandwidth control parameters have a significant influence on the decomposition result.
Support Vector Machines (SVMs) are a class of generalized linear classifiers (generalized linear classifiers) that binary classify data in a supervised learning (supersupervisory) manner, and their decision boundaries are maximum edge-distance hyperplanes (maximum-margin) for solving learning samples. Training and testing are carried out by adopting an SVM integrated classifier, a primary learner is obtained by training an initial data set, and the output of the primary learner is used as a sample input characteristic to generate a new training set for training a secondary learner; an SVM classifier is selected as a primary learner, a secondary learner adopts an AdaBoost multi-classification integrated learning algorithm based on learning, an individual SVM classifier generated circularly each time is integrated by adopting a weighted majority voting method to obtain a new strong classifier, and a trained classification model is used for fault classification of the rolling bearing so as to obtain remarkable improvement of classification precision.
Empirical Mode Decomposition (EMD) is an important component of hilbert-yellow transform, a new method for processing non-stationary signals, proposed by doctor norden. The time-frequency analysis method based on EMD is suitable for analyzing nonlinear and non-stationary signals and linear and stationary signals, and better reflects the physical significance of the signals than other time-frequency analysis methods.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: although the present invention has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (7)
1. A motor bearing fault diagnosis method based on time domain and time-frequency domain fusion is characterized by comprising the following steps:
s1, carrying out data acquisition and processing on time domain indexes and time-frequency domain indexes of a rolling bearing by using a vibration signal acquisition device;
s2, setting VMD decomposition parameters, carrying out VMD decomposition on the time-frequency domain indexes in the set parameter range to obtain optimal parameters, calculating the kurtosis of each IMF component after VMD decomposition, and reconstructing a vibration signal;
s3, according to the IMF component reconstruction matrix, carrying out SVD to obtain a singular value matrix, and selecting the singular value with the largest IMF component to form a fault feature vector;
s4, fusing the extracted time domain indexes and the characteristic vectors extracted by the VMD-SVD decomposition to form a composite characteristic vector of multi-dimensional information;
and S5, inputting the composite feature vector into a support vector machine for training and testing, and finally realizing the judgment and diagnosis of the fault type.
2. The method for diagnosing the fault of the motor bearing based on the fusion of the time domain and the time-frequency domain according to claim 1, wherein the time domain index in the step S1 comprises the following steps: kurtosis, peak factor, impulse factor, and margin factor.
3. The method for diagnosing the fault of the motor bearing based on the fusion of the time domain and the time-frequency domain as claimed in claim 1, wherein the specific process of the step S2 is as follows:
s21, carrying out parameter initialization on the time-frequency domain indexes through a PSO optimization algorithm;
s22, decomposing the filtered vibration signal into a plurality of modal components by utilizing a VMD decomposition algorithm, and calculating a kurtosis coefficient value of each mode;
s23, setting the current iteration times to be not N and the preset maximum iteration times to be N; judging whether the current iteration number N is greater than or equal to a preset maximum iteration number N, if so, entering a step S24, otherwise, enabling N = N +1, and returning to the step S22;
s24, storing the optimal parameters, performing VMD decomposition on the optimal parameters, decomposing the optimal parameters into a plurality of modal components, calculating the kurtosis coefficient value of each modal component, and selecting the modal component corresponding to the maximum kurtosis coefficient value to perform signal synthesis;
s25, after filtering processing is carried out on the synthesized signal obtained in the step S24, envelope demodulation is carried out to generate an envelope spectrum;
and S26, analyzing according to the envelope spectrum obtained in the step S25 and extracting a fault feature vector.
4. The method for diagnosing the fault of the motor bearing based on the fusion of the time domain and the time-frequency domain as claimed in claim 3, wherein the parameters in the step S2 are a secondary penalty factor α and a number K of modal components.
5. The method for diagnosing the fault of the motor bearing based on the fusion of the time domain and the time-frequency domain as claimed in claim 1, wherein the method further comprises the following steps: and determining the working state of the motor bearing according to the acquired vibration signal, and then carrying out different adjustments according to different working states.
6. The method for diagnosing the fault of the motor bearing based on the fusion of the time domain and the time-frequency domain according to claim 5, wherein the determining of the working state of the motor bearing according to the collected vibration signal specifically comprises: comparing the collected vibration signal with a preset vibration signal, determining the current working state of the motor bearing based on a comparison result, and transmitting the working state to a fault management terminal; wherein the working state comprises a normal state and a fault state; when the working state is normal, the adjustment is not carried out; when the working state is a fault, the current fault level needs to be judged according to the number of the faults, and the early warning processing is carried out at the same time, and the fault type comprises the following steps: inner ring failure, outer ring failure, and rolling element failure.
7. The method for diagnosing the fault of the motor bearing based on the fusion of the time domain and the time-frequency domain as claimed in claim 6, wherein the step of judging the current fault level according to the number of the faults and performing early warning processing at the same time specifically comprises the steps of:
presetting a preset fault state degree matrix A0, and setting A0= (A1, A2, A3), wherein A1 is a first preset fault state degree, A2 is a second preset fault state degree, and H3 is a third preset fault state degree, wherein A1 is more than A2 and less than A3;
presetting a preset early warning level matrix B0, and setting B0= (B1, B2 and B3), wherein B1 is a first preset early warning level, B2 is a second preset early warning level, B3 is a third preset early warning level, and B1 is greater than B2 and is greater than B3; setting an early warning grade G according to the relation between the leakage degree H and each preset leakage degree: when A is smaller than A1, selecting the first preset early warning grade B1 as an early warning grade B; when A1 is more than or equal to A and less than A2, selecting the second preset early warning level B2 as an early warning level B; and when A2 is not less than A and is less than A3, selecting the third preset early warning grade B3 as an early warning grade B.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211406979.3A CN115758083A (en) | 2022-11-10 | 2022-11-10 | Motor bearing fault diagnosis method based on time domain and time-frequency domain fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211406979.3A CN115758083A (en) | 2022-11-10 | 2022-11-10 | Motor bearing fault diagnosis method based on time domain and time-frequency domain fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115758083A true CN115758083A (en) | 2023-03-07 |
Family
ID=85369163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211406979.3A Pending CN115758083A (en) | 2022-11-10 | 2022-11-10 | Motor bearing fault diagnosis method based on time domain and time-frequency domain fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115758083A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116150677A (en) * | 2023-04-19 | 2023-05-23 | 国家石油天然气管网集团有限公司 | Support vector machine-based oil transfer pump fault early warning method and system |
| CN117705448A (en) * | 2024-02-05 | 2024-03-15 | 南京凯奥思数据技术有限公司 | Bearing fault degradation trend threshold early warning method and system based on fusion of moving average and 3 sigma criterion |
-
2022
- 2022-11-10 CN CN202211406979.3A patent/CN115758083A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116150677A (en) * | 2023-04-19 | 2023-05-23 | 国家石油天然气管网集团有限公司 | Support vector machine-based oil transfer pump fault early warning method and system |
| CN117705448A (en) * | 2024-02-05 | 2024-03-15 | 南京凯奥思数据技术有限公司 | Bearing fault degradation trend threshold early warning method and system based on fusion of moving average and 3 sigma criterion |
| CN117705448B (en) * | 2024-02-05 | 2024-05-07 | 南京凯奥思数据技术有限公司 | Bearing fault degradation trend threshold early warning method and system based on fusion of moving average and 3 sigma criterion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Principi et al. | Unsupervised electric motor fault detection by using deep autoencoders | |
| Wu et al. | A hybrid classification autoencoder for semi-supervised fault diagnosis in rotating machinery | |
| Zhang et al. | Semi-supervised bearing fault diagnosis and classification using variational autoencoder-based deep generative models | |
| Li et al. | Degradation alignment in remaining useful life prediction using deep cycle-consistent learning | |
| CN106682814B (en) | Wind turbine generator fault intelligent diagnosis method based on fault knowledge base | |
| Shan et al. | A multisensor data fusion method for ball screw fault diagnosis based on convolutional neural network with selected channels | |
| CN111914883B (en) | Spindle bearing state evaluation method and device based on deep fusion network | |
| CN115758083A (en) | Motor bearing fault diagnosis method based on time domain and time-frequency domain fusion | |
| CN111353482A (en) | LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method | |
| Xue et al. | Feature extraction using hierarchical dispersion entropy for rolling bearing fault diagnosis | |
| Ren et al. | A systematic review on imbalanced learning methods in intelligent fault diagnosis | |
| CN107320115B (en) | Self-adaptive mental fatigue assessment device and method | |
| CN105275833A (en) | CEEMD (Complementary Empirical Mode Decomposition)-STFT (Short-Time Fourier Transform) time-frequency information entropy and multi-SVM (Support Vector Machine) based fault diagnosis method for centrifugal pump | |
| CN105139070A (en) | Fatigue driving evaluation method based on artificial nerve network and evidence theory | |
| CN111504635B (en) | Planetary gear fault diagnosis method based on differential evolution probability neural network | |
| Yuan et al. | A multiscale feature learning scheme based on deep learning for industrial process monitoring and fault diagnosis | |
| CN111459144A (en) | Airplane flight control system fault prediction method based on deep cycle neural network | |
| CN111397902A (en) | Rolling bearing fault diagnosis method based on feature alignment convolutional neural network | |
| Lu et al. | Joint training of a predictor network and a generative adversarial network for time series forecasting: A case study of bearing prognostics | |
| CN110705694A (en) | Electric larceny monitoring method facing edge data center based on feature extraction | |
| Zhao et al. | A novel deep fuzzy clustering neural network model and its application in rolling bearing fault recognition | |
| Zhang et al. | A novel intelligent method for bearing fault diagnosis based on Hermitian scale-energy spectrum | |
| CN115877205A (en) | Intelligent fault diagnosis system and method for servo motor | |
| CN115496108A (en) | Fault monitoring method and system based on manifold learning and big data analysis | |
| Lu et al. | Early fault warning and identification in condition monitoring of bearing via wavelet packet decomposition coupled with graph |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |