CN116973103A - Fault diagnosis method, system, medium and equipment for gear box - Google Patents
Fault diagnosis method, system, medium and equipment for gear box Download PDFInfo
- Publication number
- CN116973103A CN116973103A CN202310950433.2A CN202310950433A CN116973103A CN 116973103 A CN116973103 A CN 116973103A CN 202310950433 A CN202310950433 A CN 202310950433A CN 116973103 A CN116973103 A CN 116973103A
- Authority
- CN
- China
- Prior art keywords
- particle
- filter
- entropy
- value
- signal group
- 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
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000003745 diagnosis Methods 0.000 title claims abstract description 56
- 239000002245 particle Substances 0.000 claims abstract description 172
- 238000012545 processing Methods 0.000 claims abstract description 52
- 238000001914 filtration Methods 0.000 claims abstract description 25
- 238000001228 spectrum Methods 0.000 claims description 45
- 230000006870 function Effects 0.000 claims description 23
- 238000010606 normalization Methods 0.000 claims description 14
- 230000015556 catabolic process Effects 0.000 claims description 7
- 238000006731 degradation reaction Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 abstract description 18
- 238000010586 diagram Methods 0.000 description 11
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/028—Acoustic or vibration analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/021—Gearings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Acoustics & Sound (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The application belongs to the field of agricultural machinery, and particularly relates to a fault diagnosis method, a fault diagnosis system, a fault diagnosis medium and fault diagnosis equipment for a gearbox. The method comprises the following steps: acquiring vibration signals of a gear box, and determining the primary length of a filter, the number range of the filter, the number of particles of a particle swarm algorithm and the iteration times of the particle swarm algorithm according to the vibration signals; performing iterative processing on the vibration signal based on the primary length of the filter, the number range of the filter, the number of particles of the particle swarm algorithm and the iteration times of the particle swarm algorithm to obtain an entropy time value and a basic parameter corresponding to the entropy time value after each iteration; and performing fault diagnosis analysis processing on the signal group in the basic parameters of the particles with the minimum entropy value. The method can measure the entropy values of the filtering precision and the efficiency at the same time, adopts the particle swarm optimization algorithm to carry out self-adaptive selection on the length and the number of the filters, and has better accuracy and intelligence compared with the existing fault diagnosis method.
Description
Technical Field
The application belongs to the field of agricultural machinery, and particularly relates to a fault diagnosis method, a fault diagnosis system, a fault diagnosis medium and fault diagnosis equipment for a gearbox.
Background
Speed change gearboxes are critical components of a vehicle driveline, the operating state of which directly affects the performance and safety of the vehicle. When the speed change gear box of the vehicle breaks down, the gear shifting difficulty and the unstable acceleration are caused by light weight, the vehicle is completely out of order due to heavy weight, and the control capability of a driver and the safety of the vehicle are seriously affected. In addition, fault diagnosis of the vehicle transmission contributes to saving of maintenance cost and time. By identifying the cause of the failure in time, technicians can quickly take appropriate maintenance measures to avoid unnecessary replacement of parts and complicated maintenance procedures. Therefore, how to find early faults of the speed change gear box in time, accurately judge the fault type and take corresponding efficient maintenance measures, avoid causing larger loss and accidents, and are one of the hot spot problems of current concern.
The bearing and the gear are used as parts which are easy to fail in the speed change gear box, and the method has practical significance on how to diagnose the early failure of the bearing and the gear with high efficiency, accuracy and intelligence. Compared with the traditional fault diagnosis method, the convolution sparse filtering does not need any priori knowledge; the dominant peak will not be excessively highlighted; and under the strong noise interference, the pulse characteristics can be well restored in the time domain. However, the filtering effect of convolution sparse filtering is severely affected by the filter length and the number of filters. Improper filter parameters often cause misdiagnosis of the convolution sparse filtering method. The particle swarm algorithm is an intelligent optimization algorithm with good global optimizing capability, and is widely applied to solving the parameter selection problem. However, the key to solving the parameter self-adaptation problem of the particle swarm algorithm is that the selection of the fitness function, and when the traditional sparse indexes such as kurtosis, envelope spectrum entropy, qp-mean and the like are used as the fitness function, the overfitting phenomenon of the filter is often caused. For this purpose, the application extends on the basis of the entropy of the envelope spectrum, and proposes an entropy value. Compared with the traditional index, the entropy value can be used for measuring the filtering efficiency under different filter parameters while describing the uniformity of frequency distribution. The improved method adopting the entropy value as the parameter selection basis is not influenced by the overfitting of the filter, and the application overcomes the defects of insufficient intelligence, low efficiency and poor accuracy of the traditional method.
In view of the defect that the traditional method is insufficient in intelligence and accuracy of fault pulse detection, the application provides a gearbox fault diagnosis method based on self-adaptive convolution sparse filtering, and entropy time values are used as the basis for self-adaptively selecting optimal parameters by a particle swarm algorithm, so that the intelligence and accuracy of gearbox fault diagnosis are effectively improved.
Disclosure of Invention
The application aims to provide a fault diagnosis method, a fault diagnosis system, a fault diagnosis medium and fault diagnosis equipment for a gearbox.
The technical scheme for solving the technical problems is as follows: a fault diagnosis method of a gear box, comprising:
acquiring vibration signals of a gear box, and determining the primary length of a filter, the number range of the filter, the number of particles of a particle swarm algorithm and the iteration times of the particle swarm algorithm according to the vibration signals;
performing iterative processing on the vibration signal based on the filter preliminary length, the filter number range, the particle number of the particle swarm algorithm and the iteration times of the particle swarm algorithm to obtain an entropy value and a basic parameter corresponding to the entropy value after each iteration;
and performing fault diagnosis analysis processing on the signal group in the basic parameters of the particles with the minimum entropy value.
The beneficial effects of the application are as follows: the method can measure the entropy values of the filtering precision and the efficiency at the same time, adopts the particle swarm optimization algorithm to carry out self-adaptive selection on the length and the number of the filters, and has better accuracy and intelligence compared with the existing fault diagnosis method.
On the basis of the technical scheme, the application can be improved as follows.
Further, performing iteration processing on the vibration signal to obtain an entropy value after each iteration and specific basic parameters corresponding to the entropy value, wherein the specific parameters comprise:
the iterative processing of the vibration signal comprises the following steps:
determining the filter length and the filter number corresponding to each particle according to the filter number range and the particle number of the particle swarm algorithm;
according to a preset range, randomly assigning a length value and a number value in a filter bank determined according to the length of the filter and the number of the filters to obtain a first filter bank corresponding to each particle;
filtering the vibration signal according to any one of the first filter groups to obtain a first signal group until a first signal group corresponding to each particle is obtained;
for each signal in any one of the first signal groups 2 Norm normalization processing and combining l of all signals in the first signal group 2 Summing the results of the norm normalization processing to obtain an objective function corresponding to the first signal group until the objective function corresponding to each first signal group is obtained, and performing finite memory quasi-Newton method processing on each objective function to obtain a second filter group corresponding to each particle;
processing the vibration signal through any one of the second filters to obtain a second signal group corresponding to the particle until a second signal group corresponding to each particle is obtained, calculating the envelope spectrum entropy corresponding to each second signal group, and obtaining the time from determining the length and the number of the filters corresponding to each particle to determining the envelope spectrum entropy corresponding to each second signal;
determining an entropy value of each particle according to all the envelope spectrum entropies and the time corresponding to each particle, taking the minimum value of the entropy value as the output value of the iteration, and repeatedly carrying out iteration processing on the vibration signal according to the iteration times until the output value after each iteration is obtained, wherein the output value comprises: entropy values and basic parameters corresponding to the entropy values.
Further, the entropy value H of each particle is determined e The process of-T is:
determining the entropy value H of each particle by a first formula e -T；
The first formula is:
wherein E is emin Represents the minimum value of the entropy of the envelope spectrum in the filtered signal group, E emax And (3) representing the maximum value of the entropy of the envelope spectrum in the filtered signal group, wherein T represents time and lambda is a degradation factor.
Further, the base parameters include:
the filter length, the number of filters, and the second signal group of the particles corresponding to the entropy value.
The other technical scheme for solving the technical problems is as follows: a fault diagnosis system of a gearbox, comprising:
the acquisition module is used for: acquiring vibration signals of a gear box, and determining the primary length of a filter, the number range of the filter, the number of particles of a particle swarm algorithm and the iteration times of the particle swarm algorithm according to the vibration signals;
the iteration module is used for: performing iterative processing on the vibration signal based on the filter preliminary length, the filter number range, the particle number of the particle swarm algorithm and the iteration times of the particle swarm algorithm to obtain an entropy value and a basic parameter corresponding to the entropy value after each iteration;
the analysis module is used for: and performing fault diagnosis analysis processing on the signal group in the basic parameters of the particles with the minimum entropy value.
The beneficial effects of the application are as follows: the method can measure the entropy values of the filtering precision and the efficiency at the same time, adopts the particle swarm optimization algorithm to carry out self-adaptive selection on the length and the number of the filters, and has better accuracy and intelligence compared with the existing fault diagnosis method.
Further, performing iteration processing on the vibration signal to obtain an entropy value after each iteration and specific basic parameters corresponding to the entropy value, wherein the specific parameters comprise:
the iterative processing of the vibration signal comprises the following steps:
determining the filter length and the filter number corresponding to each particle according to the filter number range and the particle number of the particle swarm algorithm;
according to a preset range, randomly assigning a length value and a number value in a filter bank determined according to the length of the filter and the number of the filters to obtain a first filter bank corresponding to each particle;
filtering the vibration signal according to any one of the first filter groups to obtain a first signal group until a first signal group corresponding to each particle is obtained;
for each signal in any one of the first signal groups 2 Norm normalization processing and combining l of all signals in the first signal group 2 Summing the results of the norm normalization processing to obtain an objective function corresponding to the first signal group until the objective function corresponding to each first signal group is obtained, and performing finite memory quasi-Newton method processing on each objective function to obtain a second filter group corresponding to each particle;
processing the vibration signal through any one of the second filters to obtain a second signal group corresponding to the particle until a second signal group corresponding to each particle is obtained, calculating the envelope spectrum entropy corresponding to each second signal group, and obtaining the time from determining the length and the number of the filters corresponding to each particle to determining the envelope spectrum entropy corresponding to each second signal;
determining an entropy value of each particle according to all the envelope spectrum entropies and the time corresponding to each particle, taking the minimum value of the entropy value as the output value of the iteration, and repeatedly carrying out iteration processing on the vibration signal according to the iteration times until the output value after each iteration is obtained, wherein the output value comprises: entropy values and basic parameters corresponding to the entropy values.
Further, the entropy value H of each particle is determined e The process of-T is:
determining the entropy value H of each particle by a first formula e -T；
The first formula is:
wherein E is emin Represents the minimum value of the entropy of the envelope spectrum in the filtered signal group, E emax And (3) representing the maximum value of the entropy of the envelope spectrum in the filtered signal group, wherein T represents time and lambda is a degradation factor.
Further, the base parameters include:
the filter length, the number of filters, and the second signal group of the particles corresponding to the entropy value.
The other technical scheme for solving the technical problems is as follows: a storage medium having instructions stored therein which, when read by a computer, cause the computer to perform the method of any of the preceding claims.
The beneficial effects of the application are as follows: the method can measure the entropy values of the filtering precision and the efficiency at the same time, adopts the particle swarm optimization algorithm to carry out self-adaptive selection on the length and the number of the filters, and has better accuracy and intelligence compared with the existing fault diagnosis method.
The other technical scheme for solving the technical problems is as follows: an electronic device includes the storage medium and a processor executing instructions within the storage medium.
The beneficial effects of the application are as follows: the method can measure the entropy values of the filtering precision and the efficiency at the same time, adopts the particle swarm optimization algorithm to carry out self-adaptive selection on the length and the number of the filters, and has better accuracy and intelligence compared with the existing fault diagnosis method.
Drawings
FIG. 1 is a schematic flow chart of a fault diagnosis method embodiment of a gearbox according to the present application;
FIG. 2 is a structural frame diagram provided by an embodiment of a fault diagnosis system for a gearbox of the present application;
FIG. 3 is a schematic diagram of a fault diagnosis provided by an embodiment of a fault diagnosis method for a gearbox according to the present application;
FIG. 4 is a timing diagram of gear fault signals provided by an embodiment of a fault diagnosis method for a gearbox according to the present application;
FIG. 5 is a timing diagram of bearing fault signals provided by an embodiment of a fault diagnosis method for a gearbox according to the present application;
FIG. 6 is a schematic diagram of an evolutionary iteration curve provided by an embodiment of a fault diagnosis method for a gearbox of the present application;
FIG. 7 is a diagram of a filter bank spectrum provided by an embodiment of a fault diagnosis method for a gearbox according to the present application;
FIG. 8 is a time domain diagram of filtered signals provided by an embodiment of a fault diagnosis method for a gearbox according to the present application;
FIG. 9 is a filtered signal envelope spectrum provided by an embodiment of a fault diagnosis method for a gearbox of the present application;
FIG. 10 is a schematic diagram of an evolutionary iteration curve provided by an embodiment of a fault diagnosis method for a gearbox of the present application;
FIG. 11 is a diagram of a filter bank spectrum provided by an embodiment of a fault diagnosis method for a gearbox according to the present application;
FIG. 12 is a time domain diagram of filtered signals provided by an embodiment of a fault diagnosis method for a gearbox according to the present application;
fig. 13 is a schematic diagram of a filtered signal envelope spectrum provided by an embodiment of a fault diagnosis method for a gearbox according to the present application.
Detailed Description
The principles and features of the present application are described below with examples given for the purpose of illustration only and are not intended to limit the scope of the application.
As shown in fig. 1, a fault diagnosis method of a gear box includes:
acquiring vibration signals of a gear box, and determining the primary length of a filter, the number range of the filter, the number of particles of a particle swarm algorithm and the iteration times of the particle swarm algorithm according to the vibration signals;
performing iterative processing on the vibration signal based on the filter preliminary length, the filter number range, the particle number of the particle swarm algorithm and the iteration times of the particle swarm algorithm to obtain an entropy value and a basic parameter corresponding to the entropy value after each iteration;
and performing fault diagnosis analysis processing on the signal group in the basic parameters of the particles with the minimum entropy value.
In some possible embodiments, the scheme can measure the entropy values of the filtering precision and the efficiency at the same time, and adopts a particle swarm optimization algorithm to carry out self-adaptive selection on the length and the number of the filters.
As shown in fig. 3, step 1, a gear box fault vibration signal S is collected i (1≤i≤n)，S i As shown in fig. 4 and 5;
step 2, according to the rotation speed of the gear box, the gear type and the like S i Determining the preliminary length L of the filter and the number N of the filters f The optimization interval of (1) is the filter number range, the particle number M and the iteration number I; the particles are carried [ L, N ] in a particle swarm algorithm f ]The particle individual of (1) is iteratively updated by the principle of a particle swarm optimization algorithm f ]To construct a filter to achieve accurate diagnosis of gearbox faults. It should be noted that S is based on the rotational speed of the gearbox, the type of gear, etc i Determining the preliminary length L of the filter and the number N of the filters f The optimization interval of (1) is that the number of filters, the number of particles M and the number of iterations I are obtained by collecting S such as the rotation speed of a gear box, the type of gears and the like i Correspondingly searching the primary length L of the corresponding filter and the number N of the filters in a preset mapping table f The optimization interval of (1) is the filter number range, the particle number M and the iteration number I, or the preset mapping table can be different, and the preliminary length L of the filter and the filter number N can be determined directly through the experience of staff f The optimization interval of (a) is the filter number range, the particle number M and the iteration number I. It should be emphasized that the preset mapping table characterizes the preliminary lengths L and the number N of the filters corresponding to different basic information f Is a filterThe number range, the mapping relation between the number M of particles and the iteration number I.
Step 3, as shown in fig. 6 and 7, each particle obtains its own filter length and number according to the optimization interval described in step 2, and obtains its own filter length L and original vibration signal S according to its own filter length L i The concrete implementation process for constructing the Hankel matrix is as follows:
the particles acquire the filter length L according to the iterative principle of the particle swarm optimization algorithm to determine the dimension of the Hankel matrix and according to the acquired vibration signal S i (i is more than or equal to 1 and less than or equal to n) constructing a Hankel matrix, wherein the iterative principle of the particle swarm optimization algorithm is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,representing the speed of the r-th particle in the kth iteration; />Representing the filter length and number of the r-th particles in the kth iteration; l and N f Respectively representing the length and the number of the filters; v represents the particle velocity, ω, c 1 、c 2 Inertial factors, self-learning factors and social factors respectively; k represents the current iteration number; [ L, N ] f ] p_best And [ L, N ] f ] g_best The individual best positions and the group best positions of the particles are represented respectively; xi is [0,1 ]]Random numbers within.
The Hankel matrix is as follows:
step 4, the M particles in the step 3 are respectively according to the filter length L and the number N acquired by the M particles f Random assignment filter bankI.e. the first filter bank and using the filter bank +.>For the original signal S i Filtering to obtain a filtered signal set +.>I.e. the first signal group. The process is as follows: each particle randomly initializes the filter group according to the number of the filters acquired by the particle>Filtering the original signal with an initialized filter bank, i.e. +.>
Step 5, for the filtered signal groupGo through l 2 Norm normalization and normalizing the signal group l 1/2 And taking the sum of norms as an objective function, and updating the filter bank through a limited memory quasi-Newton method to obtain a second filter bank, wherein the implementation process is as follows:
first, the signal after the filter bank is initialized and filteredAnd (3) carrying out row feature normalization to realize sparsity among columns, namely sparsity exists. The line feature normalization procedure may be expressed as +.>Then, the normalized filtered signal is l 1/2 The sum of norms is the objective function, i.e. +.>Obtaining updated filter bank by finite memory quasi-Newton method>At the same time, the time T required for the operation of steps 3, 4, 5 is recorded.
Step 6, each particle uses the filter group generated in step 5For the original signal S i Filtering to obtain a filtered signal group +.>I.e. the second signal group. For the filtered signal group->Envelope demodulation is performed and the entropy of the envelope spectrum is calculated>The filtered signal group is obtained by respectively filtering original signals by each filter in the filter group; the calculation formula of the envelope spectrum entropy is as follows:
wherein E is e HX (i) is the signal S and is the envelope spectrum entropy of the signal i Is used for the envelope spectrum of the (c),
step 7, as shown in fig. 8 and 9, based on the envelope spectrum entropy described in step 6Minimum value E of (2) emin Calculating entropy values H of the particles with the running time T e -T. By comparing the entropy values H of the M particles described in step 2 e -T size, outputting entropy value H in this iteration e -Tminimum particles and corresponding filter length L, number of filters N f Filtered signal groupThe calculation formula of the entropy value is as follows:
wherein H is e -T represents the entropy value, E emin Represents the minimum value of the entropy of the envelope spectrum in the filtered signal group, E emax And (3) representing the maximum value of the entropy of the envelope spectrum in the filtered signal group, wherein T represents the running time in the step (5), and lambda is a degradation factor.
Step 8: as shown in fig. 10 and 11, the iteration number I described in steps 3-7 to 2 is repeated to output the entropy value H in the I iterations by comparison e -Tminimum particles and corresponding filter length L, number of filters N f Filtered signal group
Step 9: as shown in fig. 12 and 13, the entropy value H in I iterations e -a filtered set of signals comprised by particles of minimum TminAnd carrying out envelope demodulation on the signal with the minimum medium envelope spectrum entropy, and analyzing faults according to the information in the envelope spectrum.
Preferably, in any embodiment of the foregoing, performing an iterative process on the vibration signal to obtain an entropy value after each iteration and a basic parameter corresponding to the entropy value specifically include:
the iterative processing of the vibration signal comprises the following steps:
determining the filter length and the filter number corresponding to each particle according to the filter number range and the particle number of the particle swarm algorithm;
according to a preset range, randomly assigning a length value and a number value in a filter bank determined according to the length of the filter and the number of the filters to obtain a first filter bank corresponding to each particle;
filtering the vibration signal according to any one of the first filter groups to obtain a first signal group until a first signal group corresponding to each particle is obtained;
for each signal in any one of the first signal groups 2 Norm normalization processing and combining l of all signals in the first signal group 2 Summing the results of the norm normalization processing to obtain an objective function corresponding to the first signal group until the objective function corresponding to each first signal group is obtained, and performing finite memory quasi-Newton method processing on each objective function to obtain a second filter group corresponding to each particle;
processing the vibration signal through any one of the second filters to obtain a second signal group corresponding to the particle until a second signal group corresponding to each particle is obtained, calculating the envelope spectrum entropy corresponding to each second signal group, and obtaining the time from determining the length and the number of the filters corresponding to each particle to determining the envelope spectrum entropy corresponding to each second signal;
determining an entropy value of each particle according to all the envelope spectrum entropies and the time corresponding to each particle, taking the minimum value of the entropy value as the output value of the iteration, and repeatedly carrying out iteration processing on the vibration signal according to the iteration times until the output value after each iteration is obtained, wherein the output value comprises: entropy values and basic parameters corresponding to the entropy values.
Preferably, in any of the above embodiments, the entropy value H of each particle is determined e The process of-T is:
determining the entropy value H of each particle by a first formula e -T；
The first formula is:
wherein E is emin Represents the minimum value of the entropy of the envelope spectrum in the filtered signal group, E emax And (3) representing the maximum value of the entropy of the envelope spectrum in the filtered signal group, wherein T represents time and lambda is a degradation factor.
Preferably, in any of the above embodiments, the base parameters include:
the filter length, the number of filters, and the second signal group of the particles corresponding to the entropy value.
As shown in fig. 2, a fault diagnosis system of a gear box includes:
the acquisition module 100 is configured to: acquiring vibration signals of a gear box, and determining the primary length of a filter, the number range of the filter, the number of particles of a particle swarm algorithm and the iteration times of the particle swarm algorithm according to the vibration signals;
the iteration module 200 is used for: performing iterative processing on the vibration signal based on the filter preliminary length, the filter number range, the particle number of the particle swarm algorithm and the iteration times of the particle swarm algorithm to obtain an entropy value and a basic parameter corresponding to the entropy value after each iteration;
the analysis module 300 is configured to: and performing fault diagnosis analysis processing on the signal group in the basic parameters of the particles with the minimum entropy value.
In some possible embodiments, the scheme can measure the entropy values of the filtering precision and the efficiency at the same time, and adopts a particle swarm optimization algorithm to carry out self-adaptive selection on the length and the number of the filters.
Preferably, in any embodiment of the foregoing, performing an iterative process on the vibration signal to obtain an entropy value after each iteration and a basic parameter corresponding to the entropy value specifically include:
the iterative processing of the vibration signal comprises the following steps:
determining the filter length and the filter number corresponding to each particle according to the filter number range and the particle number of the particle swarm algorithm;
according to a preset range, randomly assigning a length value and a number value in a filter bank determined according to the length of the filter and the number of the filters to obtain a first filter bank corresponding to each particle;
filtering the vibration signal according to any one of the first filter groups to obtain a first signal group until a first signal group corresponding to each particle is obtained;
for each signal in any one of the first signal groups 2 Norm normalization processing and combining l of all signals in the first signal group 2 Summing the results of the norm normalization processing to obtain an objective function corresponding to the first signal group until the objective function corresponding to each first signal group is obtained, and performing finite memory quasi-Newton method processing on each objective function to obtain a second filter group corresponding to each particle;
processing the vibration signal through any one of the second filters to obtain a second signal group corresponding to the particle until a second signal group corresponding to each particle is obtained, calculating the envelope spectrum entropy corresponding to each second signal group, and obtaining the time from determining the length and the number of the filters corresponding to each particle to determining the envelope spectrum entropy corresponding to each second signal;
determining an entropy value of each particle according to all the envelope spectrum entropies and the time corresponding to each particle, taking the minimum value of the entropy value as the output value of the iteration, and repeatedly carrying out iteration processing on the vibration signal according to the iteration times until the output value after each iteration is obtained, wherein the output value comprises: entropy values and basic parameters corresponding to the entropy values.
Preferably, in any of the above embodiments, the entropy value H of each particle is determined e The process of-T is:
determining the entropy value H of each particle by a first formula e -T；
The first formula is:
wherein E is emin Represents the minimum value of the entropy of the envelope spectrum in the filtered signal group, E emax And (3) representing the maximum value of the entropy of the envelope spectrum in the filtered signal group, wherein T represents time and lambda is a degradation factor.
Preferably, in any of the above embodiments, the base parameters include:
the filter length, the number of filters, and the second signal group of the particles corresponding to the entropy value.
The other technical scheme for solving the technical problems is as follows: a storage medium having instructions stored therein which, when read by a computer, cause the computer to perform the method of any of the preceding claims.
In some possible embodiments, the scheme can measure the entropy values of the filtering precision and the efficiency at the same time, and adopts a particle swarm optimization algorithm to carry out self-adaptive selection on the length and the number of the filters.
The other technical scheme for solving the technical problems is as follows: an electronic device includes the storage medium and a processor executing instructions within the storage medium.
In some possible embodiments, the scheme can measure the entropy values of the filtering precision and the efficiency at the same time, and adopts a particle swarm optimization algorithm to carry out self-adaptive selection on the length and the number of the filters.
The reader will appreciate that in the description of this specification, a description of terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the method embodiments described above are merely illustrative, e.g., the division of steps is merely a logical function division, and there may be additional divisions of actual implementation, e.g., multiple steps may be combined or integrated into another step, or some features may be omitted or not performed.
The above-described method, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-only memory (ROM), a random access memory (RAM, randomAccessMemory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The present application is not limited to the above embodiments, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the present application, and these modifications and substitutions are intended to be included in the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (10)
1. A fault diagnosis method of a gear box, characterized by comprising:
acquiring vibration signals of a gear box, and determining the primary length of a filter, the number range of the filter, the number of particles of a particle swarm algorithm and the iteration times of the particle swarm algorithm according to the vibration signals;
performing iterative processing on the vibration signal based on the filter preliminary length, the filter number range, the particle number of the particle swarm algorithm and the iteration times of the particle swarm algorithm to obtain an entropy value and a basic parameter corresponding to the entropy value after each iteration;
and performing fault diagnosis analysis processing on the signal group in the basic parameters of the particles with the minimum entropy value.
2. The fault diagnosis method of a gear box according to claim 1, wherein performing iteration processing on the vibration signal to obtain an entropy value after each iteration and a basic parameter corresponding to the entropy value specifically comprises:
the iterative processing of the vibration signal comprises the following steps:
determining the filter length and the filter number corresponding to each particle according to the filter number range and the particle number of the particle swarm algorithm;
according to a preset range, randomly assigning a length value and a number value in a filter bank determined according to the length of the filter and the number of the filters to obtain a first filter bank corresponding to each particle;
filtering the vibration signal according to any one of the first filter groups to obtain a first signal group until a first signal group corresponding to each particle is obtained;
for each signal in any one of the first signal groups 2 Norm normalization processing and combining l of all signals in the first signal group 2 Summing the results of the norm normalization process to obtain the firstThe signal group corresponds to the objective function until the objective function corresponding to each first signal group is obtained, and the finite memory quasi-Newton method processing is carried out on each objective function to obtain a second filter group corresponding to each particle;
processing the vibration signal through any one of the second filters to obtain a second signal group corresponding to the particle until a second signal group corresponding to each particle is obtained, calculating the envelope spectrum entropy corresponding to each second signal group, and obtaining the time from determining the length and the number of the filters corresponding to each particle to determining the envelope spectrum entropy corresponding to each second signal;
determining an entropy value of each particle according to all the envelope spectrum entropies and the time corresponding to each particle, taking the minimum value of the entropy value as the output value of the iteration, and repeatedly carrying out iteration processing on the vibration signal according to the iteration times until the output value after each iteration is obtained, wherein the output value comprises: entropy values and basic parameters corresponding to the entropy values.
3. A fault diagnosis method for a gearbox according to claim 2, characterised in that the entropy value H of each particle is determined e The process of-T is:
determining the entropy value H of each particle by a first formula e -T；
The first formula is:
wherein E is emin Represents the minimum value of the entropy of the envelope spectrum in the filtered signal group, E emax And (3) representing the maximum value of the entropy of the envelope spectrum in the filtered signal group, wherein T represents time and lambda is a degradation factor.
4. A method of diagnosing a fault in a gearbox according to claim 2, wherein said basic parameters include:
the filter length, the number of filters, and the second signal group of the particles corresponding to the entropy value.
5. A fault diagnosis system of a gear box, characterized by comprising:
the acquisition module is used for: acquiring vibration signals of a gear box, and determining the primary length of a filter, the number range of the filter, the number of particles of a particle swarm algorithm and the iteration times of the particle swarm algorithm according to the vibration signals;
the iteration module is used for: performing iterative processing on the vibration signal based on the filter preliminary length, the filter number range, the particle number of the particle swarm algorithm and the iteration times of the particle swarm algorithm to obtain an entropy value and a basic parameter corresponding to the entropy value after each iteration;
the analysis module is used for: and performing fault diagnosis analysis processing on the signal group in the basic parameters of the particles with the minimum entropy value.
6. The fault diagnosis system of a gear box according to claim 5, wherein performing iterative processing on the vibration signal to obtain an entropy value after each iteration and a basic parameter corresponding to the entropy value specifically comprises:
the iterative processing of the vibration signal comprises the following steps:
determining the filter length and the filter number corresponding to each particle according to the filter number range and the particle number of the particle swarm algorithm;
according to a preset range, randomly assigning a length value and a number value in a filter bank determined according to the length of the filter and the number of the filters to obtain a first filter bank corresponding to each particle;
filtering the vibration signal according to any one of the first filter groups to obtain a first signal group until a first signal group corresponding to each particle is obtained;
for each signal in any one of the first signal groups 2 Norm normalizationProcess and combine l of all signals in the first signal group 2 Summing the results of the norm normalization processing to obtain an objective function corresponding to the first signal group until the objective function corresponding to each first signal group is obtained, and performing finite memory quasi-Newton method processing on each objective function to obtain a second filter group corresponding to each particle;
processing the vibration signal through any one of the second filters to obtain a second signal group corresponding to the particle until a second signal group corresponding to each particle is obtained, calculating the envelope spectrum entropy corresponding to each second signal group, and obtaining the time from determining the length and the number of the filters corresponding to each particle to determining the envelope spectrum entropy corresponding to each second signal;
determining an entropy value of each particle according to all the envelope spectrum entropies and the time corresponding to each particle, taking the minimum value of the entropy value as the output value of the iteration, and repeatedly carrying out iteration processing on the vibration signal according to the iteration times until the output value after each iteration is obtained, wherein the output value comprises: entropy values and basic parameters corresponding to the entropy values.
7. A fault diagnosis system for a gearbox according to claim 6, characterized in that the entropy value H of each particle is determined e The process of-T is:
determining the entropy value H of each particle by a first formula e -T；
The first formula is:
wherein E is emin Represents the minimum value of the entropy of the envelope spectrum in the filtered signal group, E emax And (3) representing the maximum value of the entropy of the envelope spectrum in the filtered signal group, wherein T represents time and lambda is a degradation factor.
8. A fault diagnosis system for a gearbox according to claim 6, wherein said base parameters comprise:
the filter length, the number of filters, and the second signal group of the particles corresponding to the entropy value.
9. A storage medium having stored therein instructions which, when read by a computer, cause the computer to perform the method of any of claims 1 to 4.
10. An electronic device comprising the storage medium of claim 9, a processor executing instructions within the storage medium.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310950433.2A CN116973103A (en) | 2023-07-31 | 2023-07-31 | Fault diagnosis method, system, medium and equipment for gear box |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310950433.2A CN116973103A (en) | 2023-07-31 | 2023-07-31 | Fault diagnosis method, system, medium and equipment for gear box |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116973103A true CN116973103A (en) | 2023-10-31 |
Family
ID=88472697
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310950433.2A Pending CN116973103A (en) | 2023-07-31 | 2023-07-31 | Fault diagnosis method, system, medium and equipment for gear box |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116973103A (en) |
-
2023
- 2023-07-31 CN CN202310950433.2A patent/CN116973103A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829402B (en) | GS-SVM-based bearing damage degree diagnosis method under different working conditions | |
| CN114323644B (en) | Gear box fault diagnosis and signal acquisition method and device and electronic equipment | |
| CN109374293B (en) | Gear fault diagnosis method | |
| CN107506710A (en) | A kind of rolling bearing combined failure extracting method | |
| CN108444696A (en) | A kind of gearbox fault analysis method | |
| CN111751117A (en) | Special vehicle health state assessment method and device | |
| CN110927490A (en) | Transformer winding fault diagnosis method based on IVMD (integrated virtual machine direction) permutation entropy and CWAA-SVM (continuous wave operation-support vector machine) | |
| CN113532848A (en) | Fault diagnosis system for planetary gear box | |
| CN116358871B (en) | Rolling bearing weak signal composite fault diagnosis method based on graph rolling network | |
| Jie et al. | Spectral kurtosis based on evolutionary digital filter in the application of rolling element bearing fault diagnosis | |
| CN114755017B (en) | Variable-speed bearing fault diagnosis method of cross-domain data driving unsupervised field shared network | |
| CN115031967A (en) | Fault diagnosis method and device for rolling bearing and electronic equipment | |
| CN112782614A (en) | Fault early warning method and device of converter based on multi-information fusion | |
| CN116821762A (en) | Mechanical fault diagnosis method based on multi-scale graph attention fusion network | |
| CN116973103A (en) | Fault diagnosis method, system, medium and equipment for gear box | |
| CN113378359A (en) | Method and device for evaluating oil consumption of engine and transmission efficiency of whole vehicle | |
| CN116127398B (en) | Hydraulic pump fault diagnosis method based on mechanism model and multi-source data fusion | |
| CN112202630A (en) | Network quality abnormity detection method and device based on unsupervised model | |
| CN115791159A (en) | Gear fault online real-time diagnosis method based on vibration signals | |
| CN113807431A (en) | Intelligent spindle state evaluation method and system based on multi-source information fusion | |
| CN113686577A (en) | Bearing fault diagnosis method based on rapid nonlinear sparse spectrum | |
| CN109975025B (en) | Locomotive wheel pair bearing quantitative diagnosis method based on adaptive filtering demodulation | |
| CN112380782A (en) | Rotating equipment fault prediction method based on mixed indexes and neural network | |
| CN110516659A (en) | The recognition methods of ball-screw catagen phase, device, equipment and storage medium | |
| CN113033601B (en) | DBN parameter selection method for double-rotor misalignment fault identification |
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 |