CN112611563B - Method and device for determining target fault information - Google Patents
Method and device for determining target fault information Download PDFInfo
- Publication number
- CN112611563B CN112611563B CN202011388672.6A CN202011388672A CN112611563B CN 112611563 B CN112611563 B CN 112611563B CN 202011388672 A CN202011388672 A CN 202011388672A CN 112611563 B CN112611563 B CN 112611563B
- Authority
- CN
- China
- Prior art keywords
- target
- vibration signal
- structural
- neural network
- fault information
- 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
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The application relates to a method and a device for determining target fault information, wherein the method comprises the following steps: in the running process of the target equipment, acquiring reference structural parameters and reference vibration signal data of a rolling component, wherein the rolling component is a component included in the target equipment; target fault information of the rolling element is determined from the reference structural parameters and the reference vibration signal data. The method and the device solve the technical problem of poor timeliness and accuracy of fault diagnosis of the rolling parts.
Description
Technical Field
The present disclosure relates to the field of computers, and in particular, to a method and apparatus for determining target fault information.
Background
With the rapid development of mechanical equipment, people have more severe requirements on the reliability, safety and stability of the mechanical equipment in the whole life cycle of production and use, however, most of the mechanical equipment often works in severe environments and has complex alternation, high rotating speed and large load, so that the bearing is extremely easy to fail, the mechanical equipment is finally invalid, part of the mechanical equipment is difficult to maintain afterwards, the production progress is influenced even if the maintenance is carried out, the casualties of production are caused by heavy weight, and the like, and therefore, the monitoring of the performance of the bearing by adopting a monitoring means is extremely important.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The application provides a method and a device for determining target fault information, which at least solve the technical problems of poor timeliness and accuracy of fault diagnosis of rolling parts in the related technology.
According to an aspect of the embodiments of the present application, there is provided a method for determining target fault information, including: in the running process of target equipment, acquiring reference structural parameters and reference vibration signal data of a rolling component, wherein the rolling component is a component included in the target equipment; and determining target fault information of the rolling component according to the reference structural parameters and the reference vibration signal data.
Optionally, determining the target fault information of the rolling component from the reference structural parameter and the reference vibration signal data includes: generating target structural features corresponding to the reference structural parameters and target vibration signal features corresponding to the reference vibration signal data through a feature generation model; and determining target fault information of the rolling component according to the target structural characteristics and the target vibration signal characteristics.
Optionally, generating the target structural feature corresponding to the reference structural parameter by the feature generation model, and the target vibration signal feature corresponding to the reference vibration signal data includes: generating target structural features corresponding to the reference structural parameters through a BP residual neural network model; and generating target vibration signal characteristics corresponding to the reference vibration signal data through a depth residual convolution neural network model.
Optionally, generating the target structural feature corresponding to the reference structural parameter by the BP residual neural network model includes: normalizing the reference structure parameters to obtain processed target structure parameters; and generating the target structural feature corresponding to the target structural parameter through the BP residual neural network model.
Optionally, generating the target vibration signal feature corresponding to the reference vibration signal data by the depth residual convolutional neural network model includes: decomposing the reference vibration signal data according to an empirical mode decomposition processing method to obtain decomposed target vibration signal data; and generating the target vibration signal characteristics corresponding to the target vibration signal data through the depth residual convolution neural network model.
Optionally, determining the target fault information of the rolling component from the target structural feature and the target vibration signal feature includes: combining the target structural feature and the target vibration signal feature to obtain a rolling component feature set; generating the target fault information corresponding to the rolling component feature set through a fault diagnosis model.
Optionally, generating the target fault information corresponding to the rolling component feature set by the fault diagnosis model includes performing the following operations with the fault diagnosis model to generate the target fault information: performing target calculation on the rolling component feature set to determine a probability value of the rolling component determined as each of the preset fault information included in a plurality of preset fault information; and determining the preset fault information corresponding to the maximum probability value in the probability values as the target fault information.
Optionally, before generating the target structural feature corresponding to the reference structural parameter and the target vibration signal feature corresponding to the reference vibration signal data by the feature generation model, the method further includes: acquiring a historical rolling part data set of the target equipment in historical operation, wherein the historical rolling part data set comprises structural parameters, vibration signals, structural characteristics, vibration signal characteristics and fault diagnosis information of the rolling part; training an initial BP residual neural network model, an initial depth residual convolution neural network model and an initial fault diagnosis model according to the historical rolling part data set; and ending training to obtain the BP residual error neural network model, the depth residual error convolutional neural network model and the fault diagnosis model under the condition that a first loss function value corresponding to the initial BP residual error neural network model, a second loss function value corresponding to the initial depth residual error convolutional neural network model and a third loss function value corresponding to the initial fault diagnosis model meet target conditions.
According to another aspect of the embodiments of the present application, there is also provided a device for determining target fault information, including: the first acquisition module is used for acquiring reference structural parameters and reference vibration signal data of a rolling component in the operation process of target equipment, wherein the rolling component is a component included by the target equipment; and the determining module is used for determining target fault information of the rolling part according to the reference structural parameters and the reference vibration signal data.
According to another aspect of the embodiments of the present application, there is also provided a storage medium including a stored program that when executed performs the above-described method.
According to another aspect of the embodiments of the present application, there is also provided an electronic device including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor executing the method described above by the computer program.
In the embodiment of the application, the reference structural parameters and the reference vibration signal data of the rolling component are acquired in the running process of the target equipment, wherein the rolling component is the component included in the target equipment; according to the mode of determining the target fault information of the rolling part according to the reference structural parameters and the reference vibration signal data, different vibration signals are generated by different rolling parts during normal operation, and fault diagnosis is carried out according to the acquired reference structural parameters and the reference vibration signal data of the rolling part of the target equipment in the operation process, so that the target fault information of the rolling part can be determined when the target equipment is still in the working state, the purpose of timely maintaining the fault rolling part when the fault of the rolling part is not serious or before loss is caused is achieved, the technical effects of improving the timeliness and the accuracy of the fault diagnosis of the rolling part are achieved, and the technical problems of poor timeliness and the poor accuracy of the fault diagnosis of the rolling part are further solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, and it will be obvious to a person skilled in the art that other drawings can be obtained from these drawings without inventive effort.
FIG. 1 is a schematic diagram of a hardware environment of a method of determining target fault information according to an embodiment of the present application;
FIG. 2 is a flow chart of an alternative method of determining target fault information according to an embodiment of the present application;
FIG. 3 is a flow chart of an alternative fault diagnosis according to an embodiment of the present application;
FIG. 4 is an alternative bearing failure diagnosis model framework diagram according to an embodiment of the present application;
FIG. 5 is a schematic diagram of an alternative target fault information determination device according to an embodiment of the present application;
fig. 6 is a block diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
According to an aspect of the embodiments of the present application, a method embodiment for determining target fault information is provided.
Alternatively, in the present embodiment, the above-described determination method of the target failure information may be applied to a hardware environment constituted by the terminal 101 and the server 103 as shown in fig. 1. Fig. 1 is a schematic diagram of a hardware environment of a method for determining objective fault information according to an embodiment of the present application, as shown in fig. 1, where a server 103 is connected to a terminal 101 through a network, and may be used to provide services for the terminal or a client installed on the terminal, and a database may be set on the server or independent of the server, and used to provide data storage services for the server 103, where the network includes, but is not limited to: the terminal 101 is not limited to a PC, a mobile phone, a tablet computer, or the like. The method for determining the target fault information in the embodiment of the present application may be performed by the server 103, may be performed by the terminal 101, or may be performed by both the server 103 and the terminal 101. The method for determining the target fault information by the terminal 101 according to the embodiment of the present application may be performed by a client installed thereon.
FIG. 2 is a flowchart of an alternative method of determining target fault information according to an embodiment of the present application, as shown in FIG. 2, the method may include the steps of:
step S202, acquiring reference structural parameters and reference vibration signal data of a rolling component in the running process of target equipment, wherein the rolling component is a component included in the target equipment;
and step S204, determining target fault information of the rolling part according to the reference structural parameters and the reference vibration signal data.
Through the steps S202 to S204, different vibration signals are generated by different rolling elements during normal operation, and by acquiring the reference structural parameters and the reference vibration signal data of the rolling elements of the target equipment during operation and performing fault diagnosis according to the acquired reference structural parameters and the reference vibration signal data of the rolling elements, the target fault information of the rolling elements can be determined when the target equipment is still in an operating state, the purpose of timely maintaining the faulty rolling elements when the faults of the rolling elements are not serious or before loss is caused is achieved, the technical effects of improving the timeliness and the accuracy of the fault diagnosis of the rolling elements are achieved, and the technical problems of poor timeliness and accuracy of the fault diagnosis of the rolling elements are further solved.
In the solution provided in step S202, the rolling elements may include, but are not limited to, various types of bearings, such as: deep groove ball bearings, self-aligning ball bearings, thrust ball bearings, and the like.
Alternatively, in the present embodiment, the reference structural parameters may include, but are not limited to, size parameters, weight parameters, and position parameters between the respective members constituting the rolling member, and the like.
Alternatively, in the present embodiment, the reference vibration signal data is an original vibration signal detected during the operation of the target device.
In the technical solution provided in step S204, the target failure information may be information reflecting the degree of damage of the rolling bearing or information reflecting the degree of damage of each member constituting the rolling bearing.
As an alternative embodiment, determining the target fault information of the rolling component from the reference structural parameter and the reference vibration signal data comprises:
s11, generating target structural features corresponding to the reference structural parameters and target vibration signal features corresponding to the reference vibration signal data through a feature generation model;
and S12, determining target fault information of the rolling part according to the target structural characteristics and the target vibration signal characteristics.
Alternatively, in the present embodiment, the feature generation model may be, but is not limited to, a trained neural network model, for example, by constructing a BP (Back Propagation) residual neural network model and extracting respective target structural features from the model, by constructing a deep convolution residual neural network model and extracting respective target vibration signal features from the model.
Through the steps, the target structural characteristics and the target vibration signal characteristics of the rolling component are extracted through the constructed characteristic generation model, and the target fault information is determined according to the target structural characteristics and the target vibration signal characteristics, so that the accuracy of determining the target fault information is improved.
As an alternative embodiment, generating the target structural feature corresponding to the reference structural parameter by the feature generation model, and the target vibration signal feature corresponding to the reference vibration signal data includes:
s21, generating target structural features corresponding to the reference structural parameters through a BP residual neural network model;
and S22, generating target vibration signal characteristics corresponding to the reference vibration signal data through a depth residual convolution neural network model.
Alternatively, in the present embodiment, the target structural feature may be, but is not limited to being, extracted from each layer in the BP residual neural network model, and the target vibration signal feature may be, but is not limited to being, extracted from each layer in the depth residual convolutional neural network model.
As an alternative embodiment, generating the target structural feature corresponding to the reference structural parameter by the BP residual neural network model includes:
s31, carrying out normalization processing on the reference structure parameters to obtain processed target structure parameters;
s32, generating the target structural feature corresponding to the target structural parameter through the BP residual neural network model.
Alternatively, in this embodiment, the normalization may include, but is not limited to, a Z-score (Z-score) processing method, a Sigmoid function method, and the like, where different reference structure parameters may have different orders of magnitude, and in order to eliminate the dimensional influence between the parameters, the reference structure parameters may be normalized to have comparability between the parameters.
Through the steps, the reference structural parameters of the rolling component obtained from the target equipment are normalized, so that the dimensional influence among different parameters is eliminated, and the efficiency of generating the target structural features by the neural network model is improved.
As an alternative embodiment, generating the target vibration signal feature corresponding to the reference vibration signal data by the depth residual convolutional neural network model includes:
s41, decomposing the reference vibration signal data according to an empirical mode decomposition processing method to obtain decomposed target vibration signal data;
and S42, generating the target vibration signal characteristics corresponding to the target vibration signal data through the depth residual convolution neural network model.
Alternatively, in the present embodiment, the reference vibration signal data is vibration signal data extracted during the operation of the target device, which belongs to aliasing signal data, and thus it is necessary to decompose the reference vibration signal data to obtain a decomposed stationary component signal, i.e., target vibration signal data.
Through the steps, the acquired reference vibration signal data is decomposed by adopting an empirical mode decomposition method, so that the separation of vibration aliasing signals is realized, and the accuracy of extracting the characteristics of the target vibration signals is improved.
As an alternative embodiment, determining the target fault information of the rolling component from the target structural feature and the target vibration signal feature comprises:
S51, combining the target structural feature and the target vibration signal feature to obtain a rolling part feature set;
and S52, generating the target fault information corresponding to the rolling component feature set through a fault diagnosis model.
Alternatively, in the present embodiment, the rolling element feature set includes all the extracted target structural features and the target vibration signal features, and the order of the respective features in the rolling element feature set may be, but is not limited to, randomly set, for example, three extracted target structural features, a1, a2, a3, two extracted target vibration signal features, b1, b2, respectively, and the extracted features are combined to obtain a combined rolling element feature set { a1, a2, a3, b1, b2}, where the set includes five features.
Alternatively, in the present embodiment, the fault diagnosis model may be, but is not limited to, a neural network model trained in advance, and the target fault information corresponding to the feature set is output by inputting the feature set of the rolling member.
As an alternative embodiment, generating the target fault information corresponding to the rolling component feature set by the fault diagnosis model includes performing the following operations with the fault diagnosis model to generate the target fault information:
S61, performing target calculation on the characteristic set of the rolling part to determine a probability value of each preset fault information included in a plurality of preset fault information of the rolling part;
and S62, determining the preset fault information corresponding to the maximum probability value in the probability values as the target fault information.
Alternatively, in this embodiment, the target calculating method may, but is not limited to, calculate the probability value of the fault information according to the Softmax regression model method, determine that the fault information is the corresponding fault information according to the combined rolling component feature set, so as to obtain the target fault information, for example, the preset fault information has A, B, C, D types of fault information, and determine that the target fault information is the D fault information by calculating the probability values of the various types of fault information according to the rolling component feature set, which are a=0.1, b=0.3, c=0.1, and d=0.5, respectively.
Through the steps, the probability value of each fault information in the plurality of preset fault information is determined according to the rolling part characteristic set, and the preset fault information with the maximum probability value is determined as the target fault information, so that the accuracy of the determined target fault information is improved.
As an alternative embodiment, before generating the target structural feature corresponding to the reference structural parameter and the target vibration signal feature corresponding to the reference vibration signal data by the feature generation model, the method further includes:
s71, acquiring a historical rolling part data set of the target equipment in historical operation, wherein the historical rolling part data set comprises structural parameters, vibration signals, structural characteristics, vibration signal characteristics and fault diagnosis information of the rolling part;
s72, training an initial BP residual neural network model, an initial depth residual convolutional neural network model and an initial fault diagnosis model according to the historical rolling part data set;
and S73, finishing training to obtain the BP residual neural network model, the depth residual convolutional neural network model and the fault diagnosis model when the first loss function value corresponding to the initial BP residual neural network model, the second loss function value corresponding to the initial depth residual convolutional neural network model and the third loss function value corresponding to the initial fault diagnosis model meet target conditions.
Optionally, in this embodiment, by calculating the Loss function value of each neural network model in training, determining whether the training of the initial neural network model needs to be stopped according to the Loss function value of each model, for example, setting the model training frequency to 100 times, and during each training, there is a total Loss function value Loss, where the total Loss function value Loss is the first Loss function value L corresponding to the initial BP residual neural network model bp Second loss function value L corresponding to initial depth convolution residual neural network model conv Third corresponding to initial failure diagnosis modelLoss function value L clf And calculating a Loss function value Loss when training each time, wherein the smaller the Loss function value Loss is, the better the model convergence effect is proved, and when the Loss function is smaller than a set value (such as 5, 4.5, 4 and the like), the trained model is proved to meet the convergence requirement, and the model training is completed.
Optionally, in this embodiment, in order to prevent the problem of gradient disappearance or gradient explosion caused by excessive layers of the neural network in the neural network training process, a method of residual identity shortcuts may be but not limited to be adopted, because the neural network model is trained by adjusting parameters in the model, how many layers of networks have parameters of how many layers, for example, when five layers of networks are trained by gradient descent finally, the parameters are r1×r2×r3+r4×r5, if the layers are too many, r1×r2×r3× 3 … ×rn will occur, at this time, if all the parameters r=0.1, the value is almost 0 to update, and when the residual is added, the last multiplication is not the form of r1+r2+r3+r … +rn, thereby solving the problem of gradient disappearance and gradient explosion.
FIG. 3 is a flow chart of an alternative fault diagnosis for fault diagnosis of bearings within an apparatus, as shown in FIG. 3, according to an embodiment of the present application:
step S301, obtaining bearing structure parameters of a bearing component to be tested of the target device.
In step S302, since the structural parameters acquired on the target device have different orders of magnitude, in order to eliminate the dimensional influence between the parameters, standardized preprocessing needs to be performed on the acquired bearing structural data so that the parameters have comparability, and the data preprocessing method can adopt a Z-score data preprocessing method, so that the preprocessed parameters conform to the standard normal distribution.
Step S303, inputting the bearing structure parameters subjected to data preprocessing into a trained deep neural network model, wherein the deep neural network model can be a BP residual neural network model, so that corresponding target structure characteristics can be extracted from the model.
In step S304, a bearing vibration signal of the target device during operation is obtained, where the bearing vibration signal may be detected by a sensor installed in the target device.
In step S305, since the bearing vibration signal belongs to an aliasing signal, it is necessary to perform signal decomposition on the bearing vibration signal acquired from the target device, so as to acquire a stationary component signal of the rolling bearing vibration signal, and the signal decomposition method may be, but is not limited to, an empirical mode decomposition method.
And step S306, inputting the decomposed bearing vibration signals into a trained convolutional neural network model, so that corresponding target vibration signal characteristics can be extracted from the model.
In step S307, the target structural features and the target structural signal features of the rolling bearing can be obtained by extracting the essential features in the deep neural network model and the convolutional neural network model.
And step 308, generating target fault information of the bearing according to the obtained target structural characteristics and the target vibration signal characteristics and the fault diagnosis model.
FIG. 4 is an alternative bearing fault diagnosis model framework diagram for diagnosing fault information of a bearing, wherein the obtained structural features of the bearing are subjected to data preprocessing to eliminate dimension effects caused by different orders of magnitude, processed structural parameters are input into a BP residual neural network model, and the structural features of the bearing are extracted from layers of the BP residual neural network as shown in FIG. 4; decomposing the obtained bearing vibration signal characteristics through an empirical mode decomposition method, so as to obtain a plurality of stable vibration signal components, inputting each decomposed vibration signal component into a convolution residual neural network model, and extracting bearing vibration signal characteristics from each layer of the convolution residual neural network model; and combining the bearing structural features and the bearing vibration features extracted from the neural network model to obtain combined bearing essential features, and performing fault diagnosis on the obtained bearing essential features by using a fault diagnosis model to further generate fault information corresponding to the bearing.
It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.
From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing an electronic device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method described in the embodiments of the present application.
According to another aspect of the embodiments of the present application, there is also provided a target fault information determining apparatus for implementing the above-mentioned target fault information determining method. Fig. 5 is a schematic diagram of an alternative target fault information determining apparatus according to an embodiment of the present application, as shown in fig. 5, the apparatus may include:
a first obtaining module 52, configured to obtain, during operation of a target device, a reference structural parameter of a rolling component and reference vibration signal data, where the rolling component is a component included in the target device;
a determination module 54 for determining target fault information for the rolling component based on the reference structural parameters and the reference vibration signal data.
It should be noted that, the first obtaining module 52 in this embodiment may be used to perform step S202 in the embodiment of the present application, and the determining module 54 in this embodiment may be used to perform step S204 in the embodiment of the present application.
It should be noted that the above modules are the same as examples and application scenarios implemented by the corresponding steps, but are not limited to what is disclosed in the above embodiments. It should be noted that the above modules may be implemented in software or hardware as a part of the apparatus in the hardware environment shown in fig. 1.
By the aid of the module, the technical problem that timeliness and accuracy of fault diagnosis of the rolling parts are poor can be solved, and further the technical effect of improving timeliness and accuracy of fault diagnosis of the rolling parts is achieved.
As an alternative embodiment, the determining module includes: a generating unit for generating a target structural feature corresponding to the reference structural parameter and a target vibration signal feature corresponding to the reference vibration signal data through a feature generation model; and the determining unit is used for determining target fault information of the rolling component according to the target structural characteristics and the target vibration signal characteristics.
As an alternative embodiment, the generating unit is configured to: generating target structural features corresponding to the reference structural parameters through a BP residual neural network model; and generating target vibration signal characteristics corresponding to the reference vibration signal data through a depth residual convolution neural network model.
As an alternative embodiment, the generating unit is configured to: normalizing the reference structure parameters to obtain processed target structure parameters; and generating the target structural feature corresponding to the target structural parameter through the BP residual neural network model.
As an alternative embodiment, the generating unit is configured to: decomposing the reference vibration signal data according to an empirical mode decomposition processing method to obtain decomposed target vibration signal data; and generating the target vibration signal characteristics corresponding to the target vibration signal data through the depth residual convolution neural network model.
As an alternative embodiment, the determining unit is configured to: combining the target structural feature and the target vibration signal feature to obtain a rolling component feature set; generating the target fault information corresponding to the rolling component feature set through a fault diagnosis model.
As an alternative embodiment, the determining unit is configured to generate the target fault information by using the fault diagnosis model by: performing target calculation on the rolling component feature set to determine a probability value of the rolling component determined as each of the preset fault information included in a plurality of preset fault information; and determining the preset fault information corresponding to the maximum probability value in the probability values as the target fault information.
As an alternative embodiment, the apparatus further comprises: a second obtaining module, configured to generate, by using the feature generation model, the target structural feature corresponding to the reference structural parameter, and obtain, before the target vibration signal feature corresponding to the reference vibration signal data, a historical rolling component data set of the target device in a historical operation, where the historical rolling component data set includes structural parameters, vibration signals, structural features, vibration signal features, and fault diagnosis information of the rolling component; the training module is used for training an initial BP residual neural network model, an initial depth residual convolutional neural network model and an initial fault diagnosis model according to the historical rolling part data set; the processing module is used for ending training to obtain the BP residual error neural network model, the depth residual error convolutional neural network model and the fault diagnosis model under the condition that a first loss function value corresponding to the initial BP residual error neural network model, a second loss function value corresponding to the initial depth residual error convolutional neural network model and a third loss function value corresponding to the initial fault diagnosis model meet target conditions.
It should be noted that the above modules are the same as examples and application scenarios implemented by the corresponding steps, but are not limited to what is disclosed in the above embodiments. It should be noted that the above modules may be implemented in software or in hardware as part of the apparatus shown in fig. 1, where the hardware environment includes a network environment.
According to another aspect of the embodiments of the present application, there is also provided an electronic device for implementing the method for determining target fault information described above.
Fig. 6 is a block diagram of an electronic device according to an embodiment of the present application, as shown in fig. 6, the electronic device may include: one or more (only one is shown in the figure) processors 601, memory 603, and transmission means 605, which may also include input output devices 607, as shown in fig. 6.
The memory 603 may be configured to store software programs and modules, such as program instructions/modules corresponding to the method and apparatus for determining target fault information in the embodiments of the present application, and the processor 601 executes the software programs and modules stored in the memory 603, thereby performing various functional applications and data processing, that is, implementing the method for determining target fault information described above. Memory 603 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory. In some examples, the memory 603 may further include memory remotely located with respect to the processor 601, which may be connected to the electronic device through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 605 is used to receive or transmit data via a network, and may also be used for data transmission between the processor and the memory. Specific examples of the network described above may include wired networks and wireless networks. In one example, the transmission device 605 includes a network adapter (Network Interface Controller, NIC) that may be connected to other network devices and routers via a network cable to communicate with the internet or a local area network. In one example, the transmission device 605 is a Radio Frequency (RF) module that is configured to communicate wirelessly with the internet.
In particular, the memory 603 is used to store applications.
The processor 601 may call an application program stored in the memory 603 through the transmission means 605 to perform the steps of: in the running process of target equipment, acquiring reference structural parameters and reference vibration signal data of a rolling component, wherein the rolling component is a component included in the target equipment; and determining target fault information of the rolling component according to the reference structural parameters and the reference vibration signal data.
By adopting the embodiment of the application, the scheme of the method and the device for determining the target fault information is provided. Different vibration signals are generated by different rolling parts during normal operation, and fault diagnosis is carried out according to the obtained reference structural parameters and reference vibration signal data of the rolling parts of the target equipment in the operation process, so that the target fault information of the rolling parts can be determined when the target equipment is still in the working state, the purpose of maintaining the faulty rolling parts in time when the fault of the rolling parts is not serious or before loss is caused is achieved, the technical effects of improving the timeliness and the accuracy of the fault diagnosis of the rolling parts are achieved, and the technical problems of poor timeliness and the accuracy of the fault diagnosis of the rolling parts are solved.
Alternatively, specific examples in this embodiment may refer to examples described in the foregoing embodiments, and this embodiment is not described herein.
It will be appreciated by those skilled in the art that the structure shown in fig. 6 is merely illustrative, and the electronic device may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a palmtop computer, a mobile internet device (Mobile Internet Devices, MID), a PAD, etc. Fig. 6 is not limited to the structure of the electronic device. For example, the electronic device may also include more or fewer components (e.g., network interfaces, display devices, etc.) than shown in FIG. 6, or have a different configuration than shown in FIG. 6.
Those of ordinary skill in the art will appreciate that all or a portion of the steps in the various methods of the above embodiments may be performed by a program for instructing an electronic device to execute in conjunction with hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: flash disk, read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), magnetic or optical disk, and the like.
Embodiments of the present application also provide a storage medium. Alternatively, in the present embodiment, the above-described storage medium may be used for program code for executing the determination method of the target failure information.
Alternatively, in this embodiment, the storage medium may be located on at least one network device of the plurality of network devices in the network shown in the above embodiment.
Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: in the running process of target equipment, acquiring reference structural parameters and reference vibration signal data of a rolling component, wherein the rolling component is a component included in the target equipment; and determining target fault information of the rolling component according to the reference structural parameters and the reference vibration signal data.
Alternatively, specific examples in this embodiment may refer to examples described in the foregoing embodiments, and this embodiment is not described herein.
Alternatively, in the present embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.
The integrated units in the above embodiments may be stored in the above-described computer-readable storage medium if implemented in the form of software functional units and sold or used as separate products. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions to cause one or more computer devices (which may be personal computers, servers or network devices, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application.
In the foregoing embodiments of the present application, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.
In several embodiments provided in the present application, it should be understood that the disclosed client may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of the units, such as the division of the units, is merely a logical function division, and may be implemented in another manner, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application and are intended to be comprehended within the scope of the present application.
Claims (9)
1. A method for determining target fault information, comprising:
in the running process of target equipment, acquiring reference structural parameters and reference vibration signal data of a rolling component, wherein the rolling component is a component included in the target equipment;
determining target fault information of the rolling component according to the reference structural parameter and the reference vibration signal data;
the determining the target fault information for the rolling component from the reference structural parameter and the reference vibration signal data includes: generating target structural features corresponding to the reference structural parameters and target vibration signal features corresponding to the reference vibration signal data through a feature generation model; determining target fault information of the rolling component according to the target structural characteristics and the target vibration signal characteristics;
The generating, by the feature generation model, the target structural feature corresponding to the reference structural parameter, and the target vibration signal feature corresponding to the reference vibration signal data includes: generating target structural features corresponding to the reference structural parameters through a BP residual neural network model; and generating target vibration signal characteristics corresponding to the reference vibration signal data through a depth residual convolution neural network model.
2. The method of claim 1, wherein generating the target structural feature corresponding to the reference structural parameter by the BP residual neural network model comprises:
normalizing the reference structure parameters to obtain processed target structure parameters;
and generating the target structural feature corresponding to the target structural parameter through the BP residual neural network model.
3. The method of claim 1, wherein generating the target vibration signal features corresponding to the reference vibration signal data by the depth residual convolutional neural network model comprises:
decomposing the reference vibration signal data according to an empirical mode decomposition processing method to obtain decomposed target vibration signal data;
And generating the target vibration signal characteristics corresponding to the target vibration signal data through the depth residual convolution neural network model.
4. The method of claim 1, wherein determining the target fault information for the rolling component based on the target structural feature and the target vibration signal feature comprises:
combining the target structural feature and the target vibration signal feature to obtain a rolling component feature set;
generating the target fault information corresponding to the rolling component feature set through a fault diagnosis model.
5. The method of claim 4, wherein generating, by the fault diagnosis model, the target fault information corresponding to the rolling component feature set comprises using the fault diagnosis model to:
performing target calculation on the rolling component feature set to determine a probability value of the rolling component determined as each of the preset fault information included in a plurality of preset fault information;
and determining the preset fault information corresponding to the maximum probability value in the probability values as the target fault information.
6. The method of claim 5, wherein prior to generating the target structural feature corresponding to the reference structural parameter and the target vibration signal feature corresponding to the reference vibration signal data by the feature generation model, the method further comprises:
acquiring a historical rolling part data set of the target equipment in historical operation, wherein the historical rolling part data set comprises structural parameters, vibration signals, structural characteristics, vibration signal characteristics and fault diagnosis information of the rolling part;
training an initial BP residual neural network model, an initial depth residual convolution neural network model and an initial fault diagnosis model according to the historical rolling part data set;
and ending training to obtain the BP residual error neural network model, the depth residual error convolutional neural network model and the fault diagnosis model under the condition that a first loss function value corresponding to the initial BP residual error neural network model, a second loss function value corresponding to the initial depth residual error convolutional neural network model and a third loss function value corresponding to the initial fault diagnosis model meet target conditions.
7. A target failure information determining apparatus, comprising:
the first acquisition module is used for acquiring reference structural parameters and reference vibration signal data of a rolling component in the operation process of target equipment, wherein the rolling component is a component included by the target equipment;
a determining module for determining target fault information of the rolling component based on the reference structural parameter and the reference vibration signal data;
the determining module is further used for generating target structural features corresponding to the reference structural parameters and target vibration signal features corresponding to the reference vibration signal data through a feature generation model; determining target fault information of the rolling component according to the target structural characteristics and the target vibration signal characteristics;
the determining module is further used for generating target structural features corresponding to the reference structural parameters through a BP residual neural network model; and generating target vibration signal characteristics corresponding to the reference vibration signal data through a depth residual convolution neural network model.
8. A storage medium comprising a stored program, wherein the program when run performs the method of any one of the preceding claims 1 to 6.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor performs the method according to any of the preceding claims 1 to 6 by means of the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011388672.6A CN112611563B (en) | 2020-12-01 | 2020-12-01 | Method and device for determining target fault information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011388672.6A CN112611563B (en) | 2020-12-01 | 2020-12-01 | Method and device for determining target fault information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112611563A CN112611563A (en) | 2021-04-06 |
| CN112611563B true CN112611563B (en) | 2023-07-14 |
Family
ID=75228536
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011388672.6A Active CN112611563B (en) | 2020-12-01 | 2020-12-01 | Method and device for determining target fault information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112611563B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110031226A (en) * | 2019-04-12 | 2019-07-19 | 佛山科学技术学院 | A kind of diagnostic method and device of bearing fault |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7027953B2 (en) * | 2002-12-30 | 2006-04-11 | Rsl Electronics Ltd. | Method and system for diagnostics and prognostics of a mechanical system |
| RU2623177C2 (en) * | 2015-05-28 | 2017-06-22 | Федеральное государственное казенное военное образовательное учреждение высшего образования "Военный учебно-научный центр Военно-Морского Флота "Военно-морская академия имени Адмирала флота Советского Союза Н.Г. Кузнецова" | Method for monitoring technical state of rolling bearings |
| CN106874957A (en) * | 2017-02-27 | 2017-06-20 | 苏州大学 | A kind of Fault Diagnosis of Roller Bearings |
| CN107356432B (en) * | 2017-07-12 | 2019-05-07 | 石家庄铁道大学 | Fault Diagnosis of Roller Bearings based on frequency domain window experience small echo resonance and demodulation |
| CN109061474A (en) * | 2018-10-15 | 2018-12-21 | 株洲中车时代电气股份有限公司 | A kind of motor bearings trouble-shooter |
| CN109932179B (en) * | 2019-04-09 | 2021-07-27 | 东南大学 | Rolling bearing fault detection method based on DS self-adaptive spectrum reconstruction |
| CN110795843B (en) * | 2019-10-24 | 2024-03-29 | 北京建筑大学 | Method and device for identifying faults of rolling bearing |
| CN111141519A (en) * | 2019-12-27 | 2020-05-12 | 西安交通大学 | Rolling bearing fault quantitative evaluation method |
| CN111721536B (en) * | 2020-07-20 | 2022-05-27 | 哈尔滨理工大学 | Rolling bearing fault diagnosis method for improving model migration strategy |
| CN111929091A (en) * | 2020-08-17 | 2020-11-13 | 上海明略人工智能(集团)有限公司 | Equipment abnormality detection method and device, readable storage medium and electronic equipment |
-
2020
- 2020-12-01 CN CN202011388672.6A patent/CN112611563B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110031226A (en) * | 2019-04-12 | 2019-07-19 | 佛山科学技术学院 | A kind of diagnostic method and device of bearing fault |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112611563A (en) | 2021-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112162878B (en) | Database fault discovery method and device, electronic equipment and storage medium | |
| CN108846484A (en) | Fault self-recovery system, method, computer equipment and storage medium | |
| CN112052890B (en) | Method and device for predicting vibration of water supply pump | |
| CN111091278A (en) | Edge detection model construction method and device for mechanical equipment anomaly detection | |
| US10545465B2 (en) | System and method for selecting controllable parameters for equipment operation safety | |
| CN108322917B (en) | Wireless network access fault positioning method, device, system and storage medium | |
| CN113670434A (en) | Transformer substation equipment sound abnormality identification method and device and computer equipment | |
| CN112611563B (en) | Method and device for determining target fault information | |
| US20210102527A1 (en) | System and method for monitoring a device | |
| US20200341878A1 (en) | Determining, encoding, and transmission of classification variables at end-device for remote monitoring | |
| US20200118152A1 (en) | Linking user feedback to telemetry data | |
| CN112488163A (en) | Abnormal account identification method and device, computer equipment and storage medium | |
| CN116629379A (en) | Federal learning aggregation method and device, storage medium and electronic equipment | |
| CN116582414A (en) | Fault root cause positioning method, device, equipment and readable storage medium | |
| CN111327487A (en) | Power communication network running state monitoring method and device based on deep learning | |
| CN113499037A (en) | Method and device for determining sleep quality of user, electronic equipment and storage medium | |
| CN113705840A (en) | Equipment predictive maintenance method and device, computer equipment and storage medium | |
| CN113052060A (en) | Bearing residual life prediction method and device based on data enhancement and electronic equipment | |
| JP2021140400A (en) | Learning model creation system and learning model creation method | |
| CN112232419A (en) | Rotating equipment fault monitoring method and system based on big data and readable storage medium | |
| CN112989603B (en) | Workflow adjusting method and device | |
| CN108710891A (en) | Cyclo-stationary signal dimensionality reduction, recognition methods and system based on perceptual hash | |
| CN113641726B (en) | Unsupervised sheath current data mining system based on generation of countermeasure network | |
| CN114911491A (en) | Model deployment method, device, storage medium and electronic equipment | |
| CN118018394A (en) | Fault positioning model training method, network fault positioning method and related equipment |
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 |