CN113673468A - Conveyor fault diagnosis method and system, electronic equipment and storage medium - Google Patents
Conveyor fault diagnosis method and system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113673468A CN113673468A CN202111004068.3A CN202111004068A CN113673468A CN 113673468 A CN113673468 A CN 113673468A CN 202111004068 A CN202111004068 A CN 202111004068A CN 113673468 A CN113673468 A CN 113673468A
- Authority
- CN
- China
- Prior art keywords
- fault
- conveyor
- vibration signal
- eigenmode
- signal
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000003860 storage Methods 0.000 title claims abstract description 11
- 239000013598 vector Substances 0.000 claims abstract description 36
- 238000000354 decomposition reaction Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 13
- 238000005070 sampling Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000013519 translation Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 5
- 238000007689 inspection Methods 0.000 description 3
- 238000009529 body temperature measurement Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 206010000369 Accident Diseases 0.000 description 1
- 108010076504 Protein Sorting Signals Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Mathematics (AREA)
- Evolutionary Biology (AREA)
- Mathematical Optimization (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Signal Processing (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention relates to a method, a system, an electronic device and a computer readable storage medium for diagnosing faults of a conveyor, wherein the method comprises the following steps: acquiring a vibration signal of a conveyor, and generating a plurality of eigenmode components according to the vibration signal; acquiring an energy entropy value of each eigenmode component, and acquiring a feature vector according to the energy entropy value; inputting the characteristic vector into a well-trained SVM classifier, acquiring a vibration signal type, and determining the fault state of the conveyor according to the vibration signal type. The conveyor fault diagnosis method provided by the invention improves the efficiency of conveyor fault diagnosis and the accuracy of early fault diagnosis.
Description
Technical Field
The present invention relates to the field of fault diagnosis technologies, and in particular, to a method and a system for diagnosing a fault of a conveyor, an electronic device, and a computer-readable storage medium.
Background
The conveyor is used as the main equipment for transporting bulk cargo materials at present, and is widely applied to the industrial fields of ports, mines, power stations, metallurgy, chemical industry, coal and the like. In particular, a belt conveyor is used as a central link in the transportation field, and once a fault occurs, a large amount of materials are accumulated, the whole transportation system is directly stopped, and a large amount of economic loss is caused. The carrier roller and the roller are used as important rotating equipment of the belt conveyor, the generated faults account for about 50% of the total faults of the belt conveyor, and the caused equipment downtime accounts for about 45% of the total downtime.
The idlers, which are the main load-bearing components of the belt conveyor, are widely distributed on the belt conveyor, and account for about 30% of the total weight of the belt conveyor and about 35% of the total manufacturing cost of the belt conveyor. For analyzing accidents of the belt conveyor, the temperature rise of the carrier roller caused by the failure of the carrier roller is one of the main reasons of the fire accidents of the belt conveyor. Most of the existing methods for detecting faults of belt conveyors are manual inspection, which puts high requirements on fault identification capability of inspectors. And early faults of the carrier roller and the roller are difficult to detect by an inspection worker. These make the diagnosis efficiency of workman's inspection low and early fault diagnosis rate of accuracy is low.
Disclosure of Invention
In view of the above, it is desirable to provide a method, a system, an electronic device and a computer readable storage medium for diagnosing a fault of a conveyor, which solve the problems of low diagnosis efficiency and low accuracy of early fault diagnosis in the prior art.
In order to solve the above problems, the present invention provides a method for diagnosing a failure of a conveyor, including:
acquiring a vibration signal of a conveyor, and generating a plurality of eigenmode components according to the vibration signal;
acquiring an energy entropy value of each eigenmode component, and acquiring a feature vector according to the energy entropy value;
inputting the characteristic vector into a well-trained SVM classifier, acquiring a vibration signal type, and determining the fault state of the conveyor according to the vibration signal type.
Further, generating a plurality of eigenmode components according to the vibration signal specifically includes: and deconvolving by utilizing the maximum correlation kurtosis to obtain an optimal filter coefficient, filtering the vibration signal by using the optimal filter coefficient to obtain a filtered vibration signal, and performing modal decomposition on the filtered vibration signal to obtain a plurality of intrinsic modal components.
Further, the obtaining an optimal filter coefficient by deconvolution of the maximum correlation kurtosis specifically includes: determining a shift correlation kurtosis equation, deriving the shift correlation kurtosis equation, enabling a derivative to be 0, obtaining an iterative solution, carrying out iterative solution according to an initial filter coefficient and the iterative solution until an iterative error is smaller than a set value, and obtaining an optimal filter coefficient; the shift correlation kurtosis equation is
Wherein CKM(T) is the shift correlation kurtosis, xnThe amplitude of the nth sampling point of the vibration signal is represented, N represents the sampling number of the input signal, T represents the period of the fault signal, and M is the number of signal translation periods.
Further, performing modal decomposition on the filtered vibration signal to obtain a plurality of intrinsic modal components, which specifically includes:
adding different white noises with the amplitude mean value of 0 and the standard deviation of a constant into the filtered vibration signals for multiple times, respectively carrying out empirical mode decomposition on the vibration signals added with the white noises to respectively obtain a plurality of intrinsic mode components, and carrying out addition average operation on the corresponding intrinsic mode components to obtain the intrinsic mode components after the white noises are eliminated so as to obtain a plurality of intrinsic mode components.
Further, acquiring an energy entropy value of each eigenmode component, and obtaining a feature vector according to the energy entropy value, specifically including: calculating the energy value of each eigenmode component, acquiring the energy entropy value of each eigenmode component according to the energy value and an energy entropy value formula, and forming all the energy entropy values into a feature vector; the energy entropy formulaIs composed ofWherein p isi=Ei/E,EiIs the energy value of the ith eigenmode component, and E is the sum of the energy values of all the eigenmode components.
Further, the conveyor fault diagnosis method further comprises the step of training the SVM classifier by using the feature vectors corresponding to the vibration signals, so as to obtain the SVM classifier capable of identifying the vibration signals of the normal type, the slight type, the normal type and the serious type, and the SVM classifier is used as the SVM classifier with complete training.
Further, determining a fault state of the conveyor according to the type of the vibration signal specifically comprises: determining the conveyor to be in a corresponding fault state by taking the vibration signal as a normal fault, a slight fault, a general fault or a serious fault; or acquiring the temperature of the conveyor roller, and determining the fault state of the conveyor according to the temperature and the type of the vibration signal.
The invention also provides a fault diagnosis system of the conveyor, which comprises an eigenmode component acquisition module, a characteristic vector acquisition module and a fault state determination module;
the eigenmode component acquisition module is used for acquiring a vibration signal of the conveyor and generating a plurality of eigenmode components according to the vibration signal;
the characteristic vector acquisition module is used for acquiring an energy entropy value of each eigenmode component and obtaining a characteristic vector according to the energy entropy value;
and the fault state determination module is used for inputting the characteristic vector into a completely trained SVM classifier, acquiring the type of a vibration signal and determining the fault state of the conveyor according to the type of the vibration signal.
The invention also provides an electronic device, which comprises a memory and a processor, wherein the memory is stored with a computer program, and when the computer program is executed by the processor, the conveyor fault diagnosis method in any technical scheme is realized.
The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for diagnosing a conveyor failure according to any one of the above aspects.
The beneficial effects of adopting the above embodiment are: generating a plurality of intrinsic mode components by obtaining vibration signals of a conveyor, obtaining an energy entropy value of each intrinsic mode component, obtaining a feature vector according to the energy entropy value, inputting the feature vector into a well-trained SVM classifier to obtain a vibration signal type, and determining the fault state of the conveyor according to the vibration signal type; the efficiency of conveyer fault diagnosis and early fault diagnosis rate of accuracy have been improved.
Drawings
Fig. 1 is a schematic flow chart of an embodiment of a method for diagnosing a fault of a conveyor according to the present invention;
FIG. 2 is a schematic diagram of an SVM classifier according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a conveyor fault diagnosis system provided by an embodiment of the invention;
FIG. 4 is a schematic diagram of the operation of a conveyor fault diagnosis system provided by an embodiment of the invention;
fig. 5 is a schematic view of a mounting position of a signal acquisition device on a carrier roller according to an embodiment of the present invention;
FIG. 6 is a schematic view of a mounting position of a signal acquisition device on a roller according to an embodiment of the present invention;
fig. 7 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
The embodiment of the invention provides a fault diagnosis method for a conveyor, which has a flow schematic diagram, and as shown in fig. 1, the method comprises the following steps:
step S1, obtaining a vibration signal of the conveyor, and generating a plurality of eigenmode components according to the vibration signal;
s2, acquiring an energy entropy value of each eigenmode component, and obtaining a feature vector according to the energy entropy value;
and step S3, inputting the feature vectors into a fully trained SVM classifier, acquiring vibration signal types, and determining the fault state of the conveyor according to the vibration signal types.
As a preferred embodiment, generating a plurality of eigenmode components according to the vibration signal specifically includes: and deconvolving by utilizing the maximum correlation kurtosis to obtain an optimal filter coefficient, filtering the vibration signal by using the optimal filter coefficient to obtain a filtered vibration signal, and performing modal decomposition on the filtered vibration signal to obtain a plurality of intrinsic modal components.
It should be noted that the vibration signal collected from the conveyor by the sensor contains a large amount of noise information, and the noise directly affects the result of the fault diagnosis of the conveyor, so that the noise reduction processing should be performed on the original signal before the signal fault diagnosis.
As a preferred embodiment, the deconvolving with the maximum correlation kurtosis to obtain the optimal filter coefficient specifically includes: determining a shift correlation kurtosis equation, deriving the shift correlation kurtosis equation, enabling a derivative to be 0, obtaining an iterative solution, carrying out iterative solution according to an initial filter coefficient and the iterative solution until an iterative error is smaller than a set value, and obtaining an optimal filter coefficient; the shift correlation kurtosis equation is
Wherein CKM(T) is the shift correlation kurtosis, xnThe amplitude of the nth sampling point of the vibration signal is represented, N represents the sampling number of the input signal, T represents the period of the fault signal, and M is the number of signal translation periods.
It should be noted that the kurtosis value of a signal represents the proportion of a fault impact signal in the signal to a certain extent, the larger the kurtosis value is, the larger the fault impact component of the signal is, and the maximum correlation kurtosis deconvolution denoising is to utilize this point to find a group of filter coefficients to make the kurtosis of the signal filtered by the filter be the maximum value, so as to achieve the purposes of enhancing the fault signal and attenuating the noise signal.
In one embodiment, the vibration signal is x (t), and the equation for shift correlation kurtosis is defined as M
Wherein x isnThe amplitude of the nth sampling point of the vibration signal is represented, N represents the sampling number of the input signal, T represents the period of the fault signal, M is the signal translation period number, also called the shift number, and in the specific implementation, M is 7.
The maximum of the computational expressions can be solved by derivation, by CKM(T) taking the derivative of f and making the derivative equal to 0, an iterative solution can be obtained:
in the formula (I), the compound is shown in the specification,
x in the matrixiRepresenting an input signalMiddle ith value, yjRepresenting the output signalThe jth value.
Setting initial filter coefficients The length is set to L; the initial coefficient is substituted into the following formula to obtain
And substituting the result in the formula (3) into the result in the formula (2) for iterative solution, wherein in the first iteration,is composed ofAnd stopping the calculation until the iteration error is smaller than a set value, and otherwise, continuing the iteration. When the iteration is completed, the optimal filter coefficient f is calculated.
And filtering the original input vibration signal by using the obtained optimal filter coefficient f, namely performing convolution operation on the input signal and the filter coefficient, and then obtaining a filtered signal y (t).
As a preferred embodiment, performing modal decomposition on the filtered vibration signal to obtain a plurality of eigenmode components, specifically including:
adding different white noises with the amplitude mean value of 0 and the standard deviation of a constant into the filtered vibration signals for multiple times, respectively carrying out empirical mode decomposition on the vibration signals added with the white noises to respectively obtain a plurality of intrinsic mode components, and carrying out addition average operation on the corresponding intrinsic mode components to obtain the intrinsic mode components after the white noises are eliminated so as to obtain a plurality of intrinsic mode components.
It should be noted that empirical mode decomposition may decompose a complex signal into a plurality of eigenmode functions, and each decomposed eigenmode function component includes features of different time scales of an initial signal. The signal obtained by empirical mode decomposition has a higher signal-to-noise ratio, but the problem of modal aliasing is easily generated by empirical mode decomposition, and the collective empirical mode decomposition has better anti-modal aliasing capability than the empirical mode decomposition, so that the intrinsic modal component can be obtained by using the collective empirical mode decomposition in specific implementation.
In one embodiment, white noise n with a constant standard deviation and an average amplitude of 0 is added to the filtered signal y (t)i(t) (the standard deviation value is generally 0.1-0.4 times of the standard deviation of the input signal), obtaining a white noise-added signal,
yi(t)=y(t)+ni(t) (4)
wherein, yi(t) is the signal of the ith noise addition;
for yi(t) respectively carrying out empirical mode decomposition to obtain a plurality of intrinsic mode components bij(t) with a remainder, bijAnd (t) represents the j-th intrinsic mode component obtained by decomposing the ith noise adding.
Repeating the above total M times, because the mean value of the uncorrelated random signal sequences is 0, performing the addition average operation on the corresponding eigen-mode components (i.e. performing the addition average operation on the jth eigen-mode component obtained each time), so as to eliminate the influence of the white noise added for many times on the eigen-mode components, and the obtained eigen-mode components are:
wherein, bjAnd (t) represents the jth intrinsic mode component obtained by performing ensemble empirical mode decomposition on the filtered signal, and the energy and fault information of the vibration signal are mainly concentrated in a plurality of intrinsic mode components obtained by initial decomposition, so the first n intrinsic mode components can be taken as information sources for fault diagnosis.
As a preferred embodiment, acquiring an energy entropy value of each eigenmode component, and obtaining a feature vector according to the energy entropy value specifically includes: calculating the energy value of each eigenmode component, acquiring the energy entropy value of each eigenmode component according to the energy value and an energy entropy value formula, and forming all the energy entropy values into a feature vector; the energy entropy value formula isWherein p isi=Ei/E,EiIs the energy value of the ith eigenmode component, and E is the sum of the energy values of all the eigenmode components.
It should be noted that, when the signal includes different faults, the energy distribution of each eigenmode component of the signal may change correspondingly, and specifically, on the basis of the ensemble empirical mode decomposition, the corresponding energy entropy is obtained by calculating the energy distribution of each eigenmode component.
In one embodiment, the energy value of each eigenmode component is first calculated, denoted as E1,E2,…,EnThe sum of the energy values of the n eigenmode components is denoted as E, and the energy entropy of the ensemble mode decomposition of the filtered signal can be defined by the following formula:
wherein p isi=Eiand/E represents the ratio of the energy of the ith eigenmode component to the total energy.
As a preferred embodiment, the method for diagnosing the fault of the conveyor further includes training an SVM classifier by using a feature vector corresponding to the vibration signal, acquiring the SVM classifier capable of recognizing four types of vibration signals, namely normal, light fault, general fault and serious fault, and using the SVM classifier as a fully trained SVM classifier.
It should be noted that the energy entropy of the signal can be used to determine the type of the fault of the conveyor, but there is not enough suitable quantization index for the degree of the fault to measure, so that the embodiment of the present invention chooses to construct the energy eigenvector T ═ p1,p2,…pn]The fault degree is used as an index for measuring the fault degree, and the fault degree is input into an SVM classifier for classification.
The SVM classifier is developed from a method for obtaining an optimal classification vector under linear separable conditions. The principle schematic diagram of the SVM classifier is shown in fig. 2, there are two types of samples in fig. 2, H1 and H2 are straight lines passing through the sample data closest to H (classification line) in each type of sample and parallel to H, and the distance between the two is called classification interval. The optimal classification means that the classification line not only can correctly separate the two types of samples, but also can maximize the classification interval as much as possible. The classification line equation is ω × x + b ═ 0.
However, the classification directly using the classification line equation is only suitable for the sample data which can be linearly divided on the plane, and in the specific implementation, the input feature vector is linearly inseparable, so the feature vector is firstly mapped into the high-dimensional space through the kernel function, and then the optimal hyperplane is searched in the high-dimensional space to classify the feature vector.
In a specific embodiment, the classifier for performing fault diagnosis is a multi-class classifier for classifying remaining classes, in this embodiment, signals are required to be classified into four types in total, namely normal, slight fault, general fault and serious fault, the normal is regarded as a positive class, the remaining three classes are regarded as negative classes, a hyperplane function is calculated by using a two-class SVM classifier to separate the positive class from the negative class, then the slight fault is regarded as a positive class, the remaining two classes are regarded as negative classes, a new hyperplane function is calculated to separate the two classes, and the like, so that a multi-fault classifier capable of separating the four types can be trained.
As a preferred embodiment, determining the fault state of the conveyor according to the type of the vibration signal specifically includes: determining the conveyor to be in a corresponding fault state by taking the vibration signal as a normal fault, a slight fault, a general fault or a serious fault; or acquiring the temperature of the conveyor, and determining the fault state of the conveyor according to the temperature and the type of the vibration signal.
In one embodiment, the conveyor (idlers and roller bearings) may be determined to be in a corresponding fault condition for the type of normal, light fault, general fault, or critical fault with the vibration signal.
In another embodiment, the temperature of the conveyor can be acquired through a temperature sensor (temperature vibration sensor), and after fault classification of vibration signals is completed, two indexes of the vibration signals and the temperature signals are combined to carry out fault diagnosis on carrier rollers and roller bearings of the conveyor. The temperature signals can be subjected to threshold division, and the maximum value of the temperature signals can be divided into four types according to the actual situation of the field environment, namely normal, slight fault, general fault and serious fault. For example, the device is set to be normal when the maximum value of the temperature signal is below 30 ℃; when the maximum value of the temperature signal is 30-40 ℃, the equipment is slightly failed; when the maximum value of the temperature signal is 40-50 ℃, the equipment is in general failure; when the maximum value of the temperature signal is above 50 ℃, the device is severely malfunctioning. When the vibration signal and the temperature signal show serious faults, the operation of the belt conveyor is directly stopped, and an alarm is given. When the vibration signal and the temperature signal are displayed normally, the conveyor normally runs; in other cases, if the fault states determined by the vibration signal and the temperature signal are consistent, the fault state is subject to any one state, and if the fault states are inconsistent, the more serious fault state is subject to the standard.
If the finally determined fault state is a serious fault, directly stopping the operation of the conveyor and giving an alarm; if the finally determined fault state is a normal state, the conveyor normally operates; and if the finally determined fault state is other states, early warning is carried out.
The embodiment of the invention provides a conveyor fault diagnosis system, which has a schematic structural diagram, as shown in fig. 3, wherein the coefficient comprises an eigenmode component acquisition module 01, a feature vector acquisition module 02 and a fault state determination module 03;
the eigenmode component obtaining module 01 is configured to obtain a vibration signal of the conveyor, and generate a plurality of eigenmode components according to the vibration signal;
the eigenvector obtaining module 02 is configured to obtain an energy entropy value of each eigenmode component, and obtain an eigenvector according to the energy entropy value;
the fault state determination module 03 is configured to input the feature vector into a fully trained SVM classifier, acquire a vibration signal type, and determine a fault state of the conveyor according to the vibration signal type.
In a specific embodiment, as shown in fig. 4, fig. 4 includes a frame 1, a belt conveyor 2 mounted on the frame 1, a signal acquisition device 3 connected to the belt conveyor 2, a signal processing device 4 connected to the signal acquisition device 3, and a control device 5 connected to the signal processing device 4. A schematic diagram of the mounting position of the signal acquisition device on the carrier roller is shown in fig. 5; the schematic diagram of the installation position of the signal acquisition device on the roller is shown in fig. 6.
The conveyor comprises a driving roller, a driven roller, a carrier roller, a driving motor and a frequency converter, wherein the driving roller and the driven roller are respectively installed at two ends of a rack, the driving motor is installed inside the driving roller, and the frequency converter is connected with the driving motor.
The signal acquisition device is arranged on the carrier roller bracket, the driving roller and the driven roller bearing support. The signal processing device can be a computer, the computer is connected with the temperature vibration sensor through the USB data line, a signal processing module is installed in the computer, and the signal processing module is used for processing and analyzing signals collected by the signal collecting device. The control device can be a PLC control device, the control device is installed on the driving motor, and the control device is connected with the signal processing device to control the starting, stopping and alarming of the driving motor.
The eigenmode component acquisition module comprises a signal acquisition device 3; the signal acquisition device 3 comprises a vibration signal sensor for acquiring a vibration signal of the conveyor 2. The signal processing device 4 comprises a feature vector acquisition module and a fault state determination module. The signal processing device 4 is used for analyzing and processing the acquired signals so as to determine the fault state of the conveyor; the control device 5 is used for controlling the starting, stopping and alarming of the belt conveyor.
The signal acquisition device can comprise a temperature sensor and a vibration sensor, and can be a temperature vibration sensor, the vibration sensor adopted by the embodiment can measure vibration signals of three axial directions of a measured object, the vibration measurement range is 0-50mm/s, the measurement frequency range is 10-1600 Hz, the temperature measurement range is-40-150 ℃, and the temperature measurement precision is +/-0.5 ℃; the signals collected by the sensor are transmitted to a signal processing device for processing.
An electronic device according to an embodiment of the present invention is configured in a block diagram, as shown in fig. 7, the electronic device includes a memory 20 and a processor 10, the memory 20 stores a computer program 30, and when the computer program 30 is executed by the processor 10, the method for diagnosing a conveyor fault according to any one of the above embodiments is implemented.
An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the computer program implements the method for diagnosing the fault of the conveyor according to any one of the above embodiments.
The invention discloses a conveyor fault diagnosis method, a conveyor fault diagnosis system, electronic equipment and a computer readable storage medium.A plurality of eigenmode components are generated by obtaining a vibration signal of a conveyor, an energy entropy value of each eigenmode component is obtained, a feature vector is obtained according to the energy entropy value, the feature vector is input into a well-trained SVM classifier to obtain a vibration signal type, and a conveyor fault state is determined according to the vibration signal type; the automatic diagnosis of the fault of the conveyor is realized, and the efficiency of the fault diagnosis of the conveyor and the early fault diagnosis accuracy are improved; according to the technical scheme, the fault state of the conveyor is judged through the collected vibration signals and temperature signals, and different feedbacks are made to the belt conveyor through different fault states, so that technical support is provided for automatic operation and continuous safe operation of the conveyor.
Those skilled in the art will appreciate that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program, which is stored in a computer readable storage medium, to instruct related hardware. The computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (10)
1. A conveyor fault diagnosis method, characterized by comprising:
acquiring a vibration signal of a conveyor, and generating a plurality of eigenmode components according to the vibration signal;
acquiring an energy entropy value of each eigenmode component, and acquiring a feature vector according to the energy entropy value;
inputting the characteristic vector into a well-trained SVM classifier, acquiring a vibration signal type, and determining the fault state of the conveyor according to the vibration signal type.
2. The method according to claim 1, wherein generating a plurality of eigenmode components from the vibration signal specifically comprises: and deconvolving by utilizing the maximum correlation kurtosis to obtain an optimal filter coefficient, filtering the vibration signal by using the optimal filter coefficient to obtain a filtered vibration signal, and performing modal decomposition on the filtered vibration signal to obtain a plurality of intrinsic modal components.
3. The method according to claim 2, wherein said deconvolving with a maximum correlation kurtosis to obtain optimal filter coefficients comprises: determining a shift correlation kurtosis equation, deriving the shift correlation kurtosis equation, enabling a derivative to be 0, obtaining an iterative solution, carrying out iterative solution according to an initial filter coefficient and the iterative solution until an iterative error is smaller than a set value, and obtaining an optimal filter coefficient; the shift correlation kurtosis equation is
Wherein CKM(T) is the shift correlation kurtosis, xnThe amplitude of the nth sampling point of the vibration signal is represented, N represents the sampling number of the input signal, T represents the period of the fault signal, and M is the number of signal translation periods.
4. The method according to claim 2, wherein performing modal decomposition on the filtered vibration signal to obtain a plurality of eigenmode components specifically includes:
adding different white noises with the amplitude mean value of 0 and the standard deviation of a constant into the filtered vibration signals for multiple times, respectively carrying out empirical mode decomposition on the vibration signals added with the white noises to respectively obtain a plurality of intrinsic mode components, and carrying out addition average operation on the corresponding intrinsic mode components to obtain the intrinsic mode components after the white noises are eliminated so as to obtain a plurality of intrinsic mode components.
5. The method according to claim 1, wherein obtaining an energy entropy value of each eigenmode component and obtaining a feature vector according to the energy entropy value specifically includes: calculating an energy value, root, of each eigenmode componentAcquiring an energy entropy value of each eigenmode component according to the energy value and an energy entropy value formula, and forming a feature vector by all the energy entropy values; the energy entropy value formula isWherein p isi=Ei/E,EiIs the energy value of the ith eigenmode component, and E is the sum of the energy values of all the eigenmode components.
6. The method for diagnosing the fault of the conveyor according to claim 1, further comprising the step of training an SVM classifier by using the feature vector corresponding to the vibration signal to obtain the SVM classifier capable of recognizing four types of vibration signals, namely normal, light fault, general fault and serious fault, and using the SVM classifier as a well-trained SVM classifier.
7. The method for diagnosing the fault of the conveyor according to claim 6, wherein determining the fault state of the conveyor according to the type of the vibration signal specifically comprises: determining the conveyor to be in a corresponding fault state by taking the vibration signal as a normal fault, a slight fault, a general fault or a serious fault; or acquiring the temperature of the conveyor roller, and determining the fault state of the conveyor according to the temperature and the type of the vibration signal.
8. A fault diagnosis system of a conveyor is characterized by comprising an eigenmode component acquisition module, a characteristic vector acquisition module and a fault state determination module;
the eigenmode component acquisition module is used for acquiring a vibration signal of the conveyor and generating a plurality of eigenmode components according to the vibration signal;
the characteristic vector acquisition module is used for acquiring an energy entropy value of each eigenmode component and obtaining a characteristic vector according to the energy entropy value;
and the fault state determination module is used for inputting the characteristic vector into a completely trained SVM classifier, acquiring the type of a vibration signal and determining the fault state of the conveyor according to the type of the vibration signal.
9. An electronic device comprising a memory and a processor, the memory having stored thereon a computer program that, when executed by the processor, implements the conveyor fault diagnosis method according to any one of claims 1 to 7.
10. A computer-readable storage medium on which a computer program is stored, the computer program, when executed by a processor, implementing the conveyor fault diagnosis method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111004068.3A CN113673468A (en) | 2021-08-30 | 2021-08-30 | Conveyor fault diagnosis method and system, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111004068.3A CN113673468A (en) | 2021-08-30 | 2021-08-30 | Conveyor fault diagnosis method and system, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113673468A true CN113673468A (en) | 2021-11-19 |
Family
ID=78547573
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111004068.3A Pending CN113673468A (en) | 2021-08-30 | 2021-08-30 | Conveyor fault diagnosis method and system, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113673468A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115510901A (en) * | 2022-09-20 | 2022-12-23 | 煤炭科学技术研究院有限公司 | Fault identification method and device for carrier roller of belt conveyor |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109033719A (en) * | 2018-09-12 | 2018-12-18 | 温州大学苍南研究院 | A kind of wind turbine Method for Bearing Fault Diagnosis |
CN109404285A (en) * | 2018-09-13 | 2019-03-01 | 温州大学 | The algorithm enhancing self-adaptive band-pass filter method that leapfrogs is shuffled in a kind of improvement of screw compressor fault diagnosis |
CN110146294A (en) * | 2019-04-23 | 2019-08-20 | 莆田学院 | A kind of wind-driven generator vibrating failure diagnosis method and storage medium |
CN111444988A (en) * | 2020-05-11 | 2020-07-24 | 北华大学 | Rolling bearing fault diagnosis system |
CN112686096A (en) * | 2020-12-03 | 2021-04-20 | 昆明理工大学 | Rolling bearing fault diagnosis method based on multi-scale diffusion entropy and VPMCD |
-
2021
- 2021-08-30 CN CN202111004068.3A patent/CN113673468A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109033719A (en) * | 2018-09-12 | 2018-12-18 | 温州大学苍南研究院 | A kind of wind turbine Method for Bearing Fault Diagnosis |
CN109404285A (en) * | 2018-09-13 | 2019-03-01 | 温州大学 | The algorithm enhancing self-adaptive band-pass filter method that leapfrogs is shuffled in a kind of improvement of screw compressor fault diagnosis |
CN110146294A (en) * | 2019-04-23 | 2019-08-20 | 莆田学院 | A kind of wind-driven generator vibrating failure diagnosis method and storage medium |
CN111444988A (en) * | 2020-05-11 | 2020-07-24 | 北华大学 | Rolling bearing fault diagnosis system |
CN112686096A (en) * | 2020-12-03 | 2021-04-20 | 昆明理工大学 | Rolling bearing fault diagnosis method based on multi-scale diffusion entropy and VPMCD |
Non-Patent Citations (2)
Title |
---|
周建中 等: "《水电机组故障诊断及状态趋势预测理论与方法》", 30 November 2020, 华中科技大学出版社, pages: 34 - 35 * |
王志坚: "《齿轮箱复合故障诊断方法研究》", 31 August 2017, 兵器工业出版社, pages: 84 - 93 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115510901A (en) * | 2022-09-20 | 2022-12-23 | 煤炭科学技术研究院有限公司 | Fault identification method and device for carrier roller of belt conveyor |
CN115510901B (en) * | 2022-09-20 | 2024-04-30 | 煤炭科学技术研究院有限公司 | Fault identification method and device for carrier roller of belt conveyor |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Jiao et al. | A multivariate encoder information based convolutional neural network for intelligent fault diagnosis of planetary gearboxes | |
CN111830408B (en) | Motor fault diagnosis system and method based on edge calculation and deep learning | |
CN112906644B (en) | Mechanical fault intelligent diagnosis method based on deep migration learning | |
CN109186813A (en) | A kind of temperature sensor self-checking unit and method | |
EP1416348A1 (en) | Methodology for temporal fault event isolation and identification | |
JP2016062258A (en) | Detection device, detection method, and program | |
Gültekin et al. | Multisensory data fusion-based deep learning approach for fault diagnosis of an industrial autonomous transfer vehicle | |
CN108956111B (en) | Abnormal state detection method and detection system for mechanical part | |
Niu et al. | Remaining useful life prediction of machining tools by 1D-CNN LSTM network | |
Meng et al. | Research on rolling bearing fault diagnosis method based on ARMA and optimized MOMEDA | |
CN113673468A (en) | Conveyor fault diagnosis method and system, electronic equipment and storage medium | |
CN114563150A (en) | Bridge health online detection module generation method, detection method, tool box and device | |
CN116805061B (en) | Leakage event judging method based on optical fiber sensing | |
Son et al. | Deep learning-based anomaly detection to classify inaccurate data and damaged condition of a cable-stayed bridge | |
CN115855463A (en) | Rotary mechanical equipment fault detection method and device | |
CN111855219A (en) | Diesel engine lubricating oil entering security parameter prediction method based on grey theory | |
CN114414023A (en) | Sensor abnormality diagnosis method and device, and storage medium | |
CN113405590A (en) | Device, system and method for testing states of key components of railway vehicle | |
Wu et al. | Semi-supervised fault diagnosis of wheelset bearings in high-speed trains using autocorrelation and improved flow Gaussian mixture model | |
Prakash et al. | Evaluating and optimizing analytic signals | |
Marseguerra | Early detection of gradual concept drifts by text categorization and Support Vector Machine techniques: The TRIO algorithm | |
CN112541524A (en) | BP-Adaboost multi-source information motor fault diagnosis method based on attention mechanism improvement | |
CN117609703B (en) | Complex equipment health management method and system integrating multi-source heterogeneous information | |
Prasetyo et al. | Vibration Analysis for Damage Classification of Finish Good Conveyor Machine Using Neural Network | |
Cho et al. | A rul estimation system from clustered run-to-failure degradation signals |
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 |