CN113740064B - Rolling bearing fault type diagnosis method, device, equipment and readable storage medium - Google Patents
Rolling bearing fault type diagnosis method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN113740064B CN113740064B CN202110853108.5A CN202110853108A CN113740064B CN 113740064 B CN113740064 B CN 113740064B CN 202110853108 A CN202110853108 A CN 202110853108A CN 113740064 B CN113740064 B CN 113740064B
- Authority
- CN
- China
- Prior art keywords
- rolling bearing
- network
- layer
- convolution
- deep belief
- 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.)
- Active
Links
- 238000005096 rolling process Methods 0.000 title claims abstract description 69
- 238000003745 diagnosis Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 238000001228 spectrum Methods 0.000 claims abstract description 18
- 230000006870 function Effects 0.000 claims description 26
- 238000012549 training Methods 0.000 claims description 25
- 239000013598 vector Substances 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 18
- 238000011176 pooling Methods 0.000 claims description 13
- 230000004913 activation Effects 0.000 claims description 12
- 230000015654 memory Effects 0.000 claims description 11
- 238000012935 Averaging Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 7
- 150000001875 compounds Chemical class 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 10
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 239000000306 component Substances 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
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
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
-
- 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
- G06F17/15—Correlation function computation including computation of convolution operations
- G06F17/153—Multidimensional correlation or convolution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Acoustics & Sound (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a method, a device and equipment for diagnosing fault types of rolling bearings and a readable storage medium, wherein the method comprises the following steps: acquiring a vibration signal of a rolling bearing; converting the vibration signal of the rolling bearing into a frequency spectrum; and inputting the frequency spectrum into a pre-constructed hybrid intelligent diagnosis model, and outputting a diagnosis result of the fault type of the rolling bearing. The invention can be more suitable for the application environment with rare fault data in the actual industry.
Description
Technical Field
The invention belongs to the field of fault diagnosis, and particularly relates to a method, a device and equipment for diagnosing fault types of a rolling bearing and a readable storage medium.
Background
As a key core component of rotary mechanical equipment, the monitoring and detecting technology of the rolling bearing is very important for the reliable and stable operation of the equipment. The depth model is widely applied to the field of mechanical fault diagnosis by virtue of strong modeling and characterization capabilities of the depth model. The existing research mainly comprises basic models such as a Deep Belief Network (DBN), a deep convolutional network (CNN), a stacked self-encoder (SAE) and a Recurrent Neural Network (RNN) and the like and the variants thereof, wherein the input of the network relates to different expressions such as a vibration signal time domain, a frequency domain and a time-frequency domain. And the fault feature extraction and the health state recognition of the bearing are realized by mining the deep level features of the data through the depth model. Recent applications show that deep networks have a problem of long training time due to a large number of parameters. Researches find that the huge parameters of the depth model put high requirements on the scale and quality of training data, and a large amount of label data are needed in the training process, otherwise, under-fitting is caused, and the service performance of the model is influenced. In order to overcome the problems of large amount of data and high time cost required by deep model training, a special intelligent diagnosis model needs to be designed, and the fast learning capability of the model is improved.
Disclosure of Invention
The invention provides a method, a device, equipment and a readable storage medium for diagnosing the fault type of a rolling bearing, which aim at solving the problems in the prior art and are more suitable for the application environment with rare fault data in the actual industry.
In order to solve the technical problems, the invention is realized by the following technical scheme:
a rolling bearing fault type diagnostic method comprising:
acquiring a vibration signal of a rolling bearing;
converting the vibration signal of the rolling bearing into a frequency spectrum;
and inputting the frequency spectrum into a pre-constructed hybrid intelligent diagnosis model, and outputting a diagnosis result of the fault type of the rolling bearing.
Further, the hybrid intelligent diagnosis model is composed of a random kernel convolution network and a deep belief network;
the random core convolution network comprises c layers of one-dimensional feedforward convolution networks, the value of c is 2 or 3, and each layer of one-dimensional feedforward convolution network comprises a convolution layer and a pooling layer; after the c-layer one-dimensional feedforward convolution network, carrying out average operation on the feature outputs corresponding to all channels to obtain a feature vector of the rolling bearing;
the deep belief network consists of a Boltzmann machine with limited z layers, the value of z is 2, 3 or 4, and the deep belief network is used for processing the characteristic vector of the rolling bearing and outputting the fault type diagnosis result of the rolling bearing.
Further, assume that the input of the l-th convolutional layer of the random-core convolutional network is X l-1 The method specifically comprises the following steps:
wherein s is the data length;
the first layer of the convolution layer K l Consisting of m convolution kernels, K l ＝[k 1 ，k i …k m ]Ith convolution kernel k i ＝[k i,1 ,k i,2 …k i,t ,k i,n ]N represents the length of the convolution kernel, and t represents the t-th numerical value of the ith convolution kernel;
when convolution operation is carried out, the step size of each convolution kernel slippage is 1, when the ith volumeWhen the kernel moves by j steps, the output is
The method specifically comprises the following steps:
value k of the convolution kernel i,t Randomly generated from {0,1 }.
Further, a Leaky-ReLu function is adopted as an activation function in the convolutional layer of the random kernel convolutional network, and the Leaky-ReLu function is specifically as follows:
in the formula (I), the compound is shown in the specification,
for the input of an activation function, is>
Is the output of the activation function.
Further, the pooling layer of the random kernel convolutional network adopts a non-overlapping maximum pooling operation to process the output of the activation function, which is specifically as follows:
in the formula (I), the compound is shown in the specification,
is the output of the ith convolution kernel in the ith convolution layer.
Further, after the c-layer one-dimensional feedforward convolution network, averaging the feature outputs of different channels to obtain a feature vector of the rolling bearing specifically includes:
generating a single convolution kernel K = [ K ] 1 ,k 2 …,k t ,…k n ]Averaging the characteristic outputs corresponding to all the channels without overlapping, and averaging the convolution operation results of the same positions of all the channels to obtain the characteristic vector O = [ O ] of the rolling bearing 1 ,o 2 ,…,o p ,…o q ]Wherein:
in the formula o p Representing the p-th characteristic value in the characteristic vector of the rolling bearing, q representing the dimensionality of the characteristic vector, q outputting data by a l-th network
Is determined; u and g respectively represent the total channel number and the g channel of the network output.
Further, the deep belief network is configured to process the feature vector of the rolling bearing and output a rolling bearing fault type diagnosis result, specifically as follows:
dividing the obtained vibration signal of the rolling bearing into a training sample and a test sample;
taking the extracted training sample feature vector as the input of a deep belief network, and initializing a deep belief network parameter in a layer-by-layer greedy pre-training mode;
calculating an actual output error between a preset label of a training sample and the deep belief network, and finely adjusting an initialization parameter of the deep belief network to obtain the trained deep belief network;
and classifying the test samples by using the trained deep belief network, and outputting the diagnosis result of the fault type of the rolling bearing.
A rolling bearing fault type diagnosis device comprising:
the acquisition module is used for acquiring a vibration signal of the rolling bearing;
the conversion module is used for converting the vibration signal of the rolling bearing into a frequency spectrum;
and the result output module is used for inputting the frequency spectrum into a pre-constructed hybrid intelligent diagnosis model and outputting the diagnosis result of the fault type of the rolling bearing.
An apparatus comprising a memory, a processor and a computer program stored in said memory and executable on said processor, said processor implementing the steps of said method for diagnosing a fault type of a rolling bearing when executing said computer program.
A computer-readable storage medium, which stores a computer program that, when being executed by a processor, carries out the steps of a method of diagnosing a fault type of a rolling bearing.
Compared with the prior art, the invention at least has the following beneficial effects: according to the fault diagnosis method, the vibration signals of the rolling bearing are obtained and converted into the frequency spectrum, and the vibration signals of the rolling bearing are classified and identified by using the hybrid intelligent fault diagnosis model based on the random kernel convolution network and the deep belief network, so that the fault diagnosis result is obtained, and the fault diagnosis of the rolling bearing is realized. The hybrid intelligent diagnosis model integrates the convolution network and the deep belief network, does not learn all network layers of the deep model, only trains and adjusts parameters of the deep belief network, and can reduce the calculation complexity of the model on the premise of ensuring the recognition precision, thereby improving the training efficiency of the model. The convolutional network has the characteristic of local receptive field and weight sharing, and because in the hybrid intelligent fault diagnosis model, network parameters are generated according to certain distribution and are not adjusted in the training process, the scale of training parameters can be reduced, the quantity requirement of training data is further reduced, and the convolutional network can be more suitable for the application environment with rare fault data in the actual industry.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the description below are some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a main flow chart of a fault type diagnosis method of a rolling bearing according to the present invention;
FIG. 2 is an overall architecture of a hybrid intelligent fault diagnosis model of the present invention;
FIG. 3 is a block diagram of a random-kernel convolutional network according to the present invention;
FIG. 4 is a diagram showing the feature extraction results of each layer of the random-kernel convolutional network according to the present invention;
FIG. 5 shows different types of bearing feature results extracted by the random kernel convolution network according to the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As one embodiment of the present invention, as shown in fig. 1, a method for diagnosing a fault type of a rolling bearing specifically includes the following steps:
step 1: and acquiring a vibration signal of the rolling bearing.
And 2, step: and converting the vibration signal of the rolling bearing into a frequency spectrum.
Specifically, the invention uses Fourier transform to process the vibration signal of the rolling bearing to obtain a frequency spectrum.
And step 3: and inputting the frequency spectrum into a pre-constructed hybrid intelligent diagnosis model, and outputting a diagnosis result of the fault type of the rolling bearing.
Specifically, the hybrid intelligent diagnosis model is composed of a random kernel convolution network and a deep belief network.
In the hybrid intelligent diagnosis model, a random kernel convolution network is used as a feature extractor, the random kernel convolution network comprises c layers of one-dimensional feedforward convolution networks, the value of c is 2 or 3, and each layer of one-dimensional feedforward convolution network comprises a convolution layer and a pooling layer. In this embodiment, preferably, the random-kernel convolutional network comprises a 2-layer one-dimensional feedforward convolutional network. In this embodiment, as shown in fig. 3, the spectrum result is used as an input of the random kernel convolution network, and passes through 2 convolution layers and a pooling layer, so as to obtain a feature mapping result of each convolution layer and pooling operation.
After the c-layer one-dimensional feedforward convolutional network, averaging the feature outputs corresponding to all channels to obtain a feature vector of the rolling bearing, specifically comprising:
generating a single convolution kernel K = [ K ] 1 ,k 2 …,k t ,…k n ]Averaging the characteristic outputs corresponding to all the channels without overlapping, and averaging the convolution operation results of the same positions of all the channels to obtain the characteristic vector O = [ O ] of the rolling bearing 1 ,o 2 ,…,o p ,…o q ]Wherein:
in the formula o p Representing the p-th characteristic value in the characteristic vector of the rolling bearing, q representing the dimensionality of the characteristic vector, q outputting data by a l-th network
Determining the length s of the target; u and g respectively represent the total channel number and the g channel of the network output of the layer; k should avoid taking a zero vector.
In this embodiment, after the layer 2 convolutional network layer, averaging the feature outputs corresponding to all channels, and extracting a feature vector reflecting a local frequency band in the frequency spectrum, as shown in fig. 4, where each dimension of the feature vector corresponds to a local frequency band of the original frequency spectrum, and its physical meaning is the energy of the local frequency band, so as to finally obtain high-dimensional local features of different rolling bearing fault types as shown in fig. 5.
The method for constructing the random kernel convolution network specifically comprises the following steps:
the input of the first layer convolution layer of the assumed random core convolution network is X l-1 The method specifically comprises the following steps:
wherein s is the data length;
the first layer of the convolution layer K l Is composed of m convolution kernels, K l ＝[k 1 ，k i …k m ]Ith convolution kernel k i ＝[k i,1 ,k i,2 …k i,t ,k i,n ]N represents the length of the convolution kernel, and t represents the t-th numerical value of the ith convolution kernel;
when convolution operation is carried out, the step size of each convolution kernel slippage is 1, and when the ith convolution kernel moves by j steps, the output is
The method specifically comprises the following steps:
value k of the convolution kernel i,t Randomly generated from 0,1, frozen once generated, and not adjusted during the training phase.
As a preferred embodiment, a leak-ReLu function is used as an activation function for a convolutional layer of a random kernel convolutional network, and the leak-ReLu function is used to replace a traditional sigmoid function to avoid a phenomenon of gradient disappearance, wherein the leak-ReLu function is specifically as follows:
in the formula (I), the compound is shown in the specification,
for the input of an activation function, is>
Is the output of the activation function.
In the invention, in order to make the obtained two-dimensional random convolution characteristics have certain invariance to target translation, the pooling layer of the random kernel convolution network adopts non-overlapping maximum value pooling operation, namely, the maximum value of a specific area of 3 × 3 or 5 × 5 is selected as the output of the pooling layer, and the output of an activation function is processed, specifically as follows:
in the formula (I), the compound is shown in the specification,
is the output of the ith convolution kernel in the l convolutional layer.
In this embodiment, the convolution kernel parameters of the random kernel convolution network are generated according to 0-1 distribution, and each layer of the network performs local weighting and dimensionality reduction on the input spectrum by adopting convolution and maximum pooling operations.
In the hybrid intelligent diagnosis model, the deep belief network is composed of a z-layer limited Boltzmann machine (RBM), and the value of z is 2, 3 or 4. In the embodiment, the fault type diagnosis result of the rolling bearing is preferably output by combining a Soft-max classifier.
As a specific embodiment of the present invention, the deep belief network is configured to process a feature vector of a rolling bearing and output a diagnosis result of a fault type of the rolling bearing, and specifically includes the following steps:
dividing the obtained vibration signal of the rolling bearing into a training sample and a test sample;
taking the extracted training sample feature vector as the input of a deep belief network, and initializing a deep belief network parameter in a layer-by-layer greedy pre-training mode;
calculating an actual output error between a preset label of a training sample and the deep belief network, and finely adjusting an initialization parameter of the deep belief network to obtain the trained deep belief network; in this embodiment, the 1 st RBM is trained with input until energy balance is reached; using the output obtained by the layer 1 deep belief network learning as the input of the 2 nd RBM to continue training until the energy of the 2 nd RBM is balanced; adding a Soft-max function after the 2 nd RBM, and utilizing expected output to fine-tune network parameters to realize the training of the deep belief network; it is emphasized that only the parameters of the deep belief network and the Soft-max classifier are trained in the training stage, and the parameters of the feature extractor are not adjusted once generated so as to process all data including training samples and test samples;
and classifying the test samples by using the trained deep belief network, and outputting the diagnosis result of the fault type of the rolling bearing.
The invention relates to a fault type diagnosis device for a rolling bearing, which comprises:
the acquisition module is used for acquiring a vibration signal of the rolling bearing;
the conversion module is used for converting the vibration signal of the rolling bearing into a frequency spectrum;
and the result output module is used for inputting the frequency spectrum into a pre-constructed hybrid intelligent diagnosis model and outputting the diagnosis result of the fault type of the rolling bearing.
The present invention provides, in one embodiment, a computer device comprising a processor and a memory, the memory for storing a computer program comprising program instructions, the processor for executing the program instructions stored by the computer storage medium. The Processor may be a Central Processing Unit (CPU), or may be other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable gate array (FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc., which is a computing core and a control core of the terminal, and is specifically adapted to load and execute one or more instructions to implement a corresponding method flow or a corresponding function; the processor according to the embodiment of the invention can be used for the operation of the diagnosis method for the fault type of the rolling bearing.
In one embodiment of the present invention, a rolling bearing fault type diagnosis method, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer-readable storage medium. Based on such understanding, all or part of the flow in the method according to the above embodiments may be implemented by a computer program, which may be stored in a computer readable storage medium and used by a processor to implement the steps of the above embodiments of the method. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. Computer-readable storage media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data.
The computer storage media may be any available media or data storage device that can be accessed by a computer, including but not limited to magnetic memory (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical memory (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor memory (e.g., ROMs, EPROMs, EEPROMs, non-volatile memories (NANDFLASH), solid State Disks (SSDs)), etc.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (3)
1. A method for diagnosing a type of failure of a rolling bearing, comprising:
acquiring a vibration signal of a rolling bearing;
converting the rolling bearing vibration signal into a frequency spectrum by using Fourier transform;
inputting the frequency spectrum into a pre-constructed hybrid intelligent diagnosis model, and outputting a diagnosis result of the fault type of the rolling bearing;
the hybrid intelligent diagnosis model is composed of a random kernel convolution network and a deep belief network;
the random kernel convolutional network comprises c layers of one-dimensional feedforward convolutional networks, the value of c is 2 or 3, and each layer of one-dimensional feedforward convolutional network comprises a convolutional layer and a pooling layer; after the c-layer one-dimensional feedforward convolution network, carrying out average operation on the feature outputs corresponding to all channels to obtain a feature vector of the rolling bearing;
the deep belief network consists of a boltzmann machine with a limited z layer, the value of z is 2, 3 or 4, and the deep belief network is used for processing the characteristic vector of the rolling bearing and outputting the fault type diagnosis result of the rolling bearing;
assuming that the input of the l-th convolutional layer of the random core convolutional network is X l-1 The method specifically comprises the following steps:
wherein s is the data length;
the first layer of the convolution layer K l Consisting of m convolution kernels, K l ＝[k 1 ，k i ...k m ]Ith convolution kernel k i ＝[k i，1 ，k i， 2 ...k i，t ，k i，n ]N represents the length of the convolution kernel, and t represents the t-th numerical value of the ith convolution kernel;
when convolution operation is carried out, the step length of each convolution kernel slip is 1, and when the ith convolution kernel moves j steps, the output is
The method specifically comprises the following steps:
value k of convolution kernel i，t Randomly generated from {0,1 };
the convolutional layer of the random kernel convolutional network adopts a Leaky-ReLu function as an activation function, and the Leaky-ReLu function is specifically as follows:
in the formula (I), the compound is shown in the specification,
for the input of an activation function>
Is the output of the activation function;
the pooling layer of the random kernel convolutional network adopts non-overlapping maximum pooling operation to process the output of the activation function, which specifically comprises the following steps:
in the formula (I), the compound is shown in the specification,
is the output of the ith convolution kernel in the first convolution layer;
after the c-layer one-dimensional feedforward convolution network, averaging the feature outputs of different channels to obtain the feature vector of the rolling bearing, specifically comprising:
generating a single convolution kernel K = [ K ] 1 ，k 2 ...，k t ，...k n ]Averaging the characteristic outputs corresponding to all the channels without overlapping, and averaging the convolution operation results at the same position of all the channels to obtain the characteristic vector O = [ O ] of the rolling bearing 1 ，o 2 ，...，o p ，...o q ]Wherein:
in the formula o p Representing the p-th characteristic value in the characteristic vector of the rolling bearing, q representing the dimensionality of the characteristic vector, q outputting data by a l-th network
Determining the length s of the target; u and g respectively represent the total channel number and the g channel of the network output of the layer;
the deep belief network is used for processing the characteristic vectors of the rolling bearing and outputting the fault type diagnosis result of the rolling bearing, and the deep belief network specifically comprises the following steps:
dividing the obtained vibration signal of the rolling bearing into a training sample and a test sample;
taking the extracted training sample feature vector as the input of a deep belief network, and initializing a deep belief network parameter in a layer-by-layer greedy pre-training mode;
calculating actual output errors of a preset label of the training sample and the deep belief network, and finely adjusting initialization parameters of the deep belief network to obtain a trained deep belief network;
and classifying the test samples by using the trained deep belief network, and outputting the diagnosis result of the fault type of the rolling bearing.
2. An apparatus comprising a memory, a processor and a computer program stored in said memory and executable on said processor, characterized in that said processor implements the steps of a rolling bearing fault type diagnosis method as claimed in claim 1 when executing said computer program.
3. A computer-readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of a rolling bearing fault type diagnosis method according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110853108.5A CN113740064B (en) | 2021-07-27 | 2021-07-27 | Rolling bearing fault type diagnosis method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110853108.5A CN113740064B (en) | 2021-07-27 | 2021-07-27 | Rolling bearing fault type diagnosis method, device, equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113740064A CN113740064A (en) | 2021-12-03 |
| CN113740064B true CN113740064B (en) | 2023-03-31 |
Family
ID=78729269
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110853108.5A Active CN113740064B (en) | 2021-07-27 | 2021-07-27 | Rolling bearing fault type diagnosis method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113740064B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705525A (en) * | 2019-10-24 | 2020-01-17 | 北京建筑大学 | Method and device for diagnosing rolling bearing fault |
| CN112051062B (en) * | 2020-08-10 | 2021-07-27 | 华中科技大学 | Fault diagnosis method, device, equipment and storage medium for rolling bearing |
| CN112254964A (en) * | 2020-09-03 | 2021-01-22 | 太原理工大学 | Rolling bearing fault diagnosis method based on rapid multi-scale convolution neural network |
| CN112418175A (en) * | 2020-12-09 | 2021-02-26 | 北京信息科技大学 | Rolling bearing fault diagnosis method and system based on domain migration and storage medium |
| CN112798280B (en) * | 2021-02-05 | 2022-01-04 | 山东大学 | Rolling bearing fault diagnosis method and system |
-
2021
- 2021-07-27 CN CN202110853108.5A patent/CN113740064B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113740064A (en) | 2021-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Subspace network with shared representation learning for intelligent fault diagnosis of machine under speed transient conditions with few samples | |
| Xia et al. | Multi-stage fault diagnosis framework for rolling bearing based on OHF Elman AdaBoost-Bagging algorithm | |
| CN111275175B (en) | Neural network training method, device, image classification method, device and medium | |
| CN113281048B (en) | Rolling bearing fault diagnosis method and system based on relational knowledge distillation | |
| CN108596327B (en) | Seismic velocity spectrum artificial intelligence picking method based on deep learning | |
| Berghout et al. | A semi-supervised deep transfer learning approach for rolling-element bearing remaining useful life prediction | |
| CN112393934B (en) | Wind turbine generator fault diagnosis method based on sparse self-coding and extreme learning machine | |
| CN114169110B (en) | Motor bearing fault diagnosis method based on feature optimization and GWAA-XGboost | |
| CN108879732B (en) | Transient stability evaluation method and device for power system | |
| US11380301B2 (en) | Learning apparatus, speech recognition rank estimating apparatus, methods thereof, and program | |
| CN115374810A (en) | Fault diagnosis method and equipment based on dynamic separable convolutional neural network | |
| CN113705396A (en) | Motor fault diagnosis method, system and equipment | |
| CN112418175A (en) | Rolling bearing fault diagnosis method and system based on domain migration and storage medium | |
| CN114548199A (en) | Multi-sensor data fusion method based on deep migration network | |
| CN114609994A (en) | Fault diagnosis method and device based on multi-granularity regularization rebalance incremental learning | |
| CN115290326A (en) | Rolling bearing fault intelligent diagnosis method | |
| CN115688040A (en) | Mechanical equipment fault diagnosis method, device, equipment and readable storage medium | |
| CN117708656A (en) | Rolling bearing cross-domain fault diagnosis method for single source domain | |
| CN115392301A (en) | Converter transformer state identification method, converter transformer state identification device, converter transformer state identification equipment, converter transformer state identification medium and program product | |
| Kibrete et al. | Applications of artificial intelligence for fault diagnosis of rotating machines: A review | |
| Wang et al. | Distilling the knowledge of multiscale densely connected deep networks in mechanical intelligent diagnosis | |
| CN113740064B (en) | Rolling bearing fault type diagnosis method, device, equipment and readable storage medium | |
| CN112633362B (en) | Rotary machine self-adaptive fault diagnosis method, device, equipment and medium | |
| CN116593980B (en) | Radar target recognition model training method, radar target recognition method and device | |
| CN117975086A (en) | Method and system for classifying few-sample images based on metric element learning |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |