CN114047735A - Fault detection method, system and service system of multiple industrial hosts - Google Patents
Fault detection method, system and service system of multiple industrial hosts Download PDFInfo
- Publication number
- CN114047735A CN114047735A CN202210029690.8A CN202210029690A CN114047735A CN 114047735 A CN114047735 A CN 114047735A CN 202210029690 A CN202210029690 A CN 202210029690A CN 114047735 A CN114047735 A CN 114047735A
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- fault detection
- preset
- industrial
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/4183—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by data acquisition, e.g. workpiece identification
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/31—From computer integrated manufacturing till monitoring
- G05B2219/31356—Automatic fault detection and isolation
-
- 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
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention discloses a fault detection method, a fault detection system and a fault detection service system of a multiplex business host machine, and relates to the field of fault detection. The method comprises the following steps: the method comprises the steps of obtaining operation data of a plurality of industrial hosts according to a preset data acquisition point, preprocessing the operation data to obtain first characteristic data, carrying out fault analysis on the first characteristic data according to preset model parameters and a trained fault detection model, calling corresponding maintenance reports according to analysis results, and sending the maintenance reports to a terminal, so that faults of the industrial hosts on site can be effectively monitored in real time and uploaded in time, automatic real-time fault detection is realized, detection cost is reduced, maintenance personnel can maintain fault equipment in time conveniently, normal operation of the terminal equipment is guaranteed, better use feeling is provided for the maintenance personnel, and the method is not limited by technical experience.
Description
Technical Field
The invention relates to the field of fault detection, in particular to a fault detection method, a fault detection system and a fault detection service system for multiple industrial hosts.
Background
In the troubleshooting scheme, through the fault detection device, locate the fault recorder at industrial field, connect its operating information of corresponding equipment detection, set up the fault collection machine in the control room, and receive the fault information that the fault recorder gathered through communication module, handle the control through single chip microcomputer control unit to the data information who receives, the artifical equipment that breaks down that fixes a position of rethread staff, overhaul faulty equipment, rely on staff's technical experience very much, and it is more at faulty equipment, the fault reason is when numerous and diverse, the staff can't detail the accurate faulty equipment that obtains, delay the maintenance opportunity, the harm that causes can not be estimated.
Disclosure of Invention
The invention aims to solve the technical problem of the prior art and provides a fault detection method, a fault detection system and a fault detection service system for multiple industrial hosts.
The technical scheme for solving the technical problems is as follows:
a method of fault detection for multiple industrial hosts, comprising:
s1, acquiring the operation data of a plurality of industrial hosts according to a preset data acquisition point;
s2, preprocessing the operation data to obtain first characteristic data;
s3, carrying out fault analysis on the first characteristic data according to preset model parameters and the trained fault detection model;
and S4, calling a corresponding overhaul report according to the analysis result and sending the overhaul report to the terminal.
The invention has the beneficial effects that: according to the scheme, the operation data of the industrial hosts are acquired through the acquisition points, the operation data are preprocessed to obtain first characteristic data, the first characteristic data are subjected to fault analysis according to preset model parameters and a trained fault detection model, corresponding maintenance reports are called according to analysis results and sent to the terminal, and therefore the faults of the industrial hosts on site can be effectively monitored in real time and timely uploaded.
The scheme realizes automatic real-time fault detection, reduces the detection cost, facilitates maintenance personnel to maintain fault equipment in time, guarantees the normal operation of the terminal equipment and provides better use feeling for workers.
Further, the S1 is preceded by:
respectively setting type IDs in a plurality of preset data acquisition points;
distributing matched industrial hosts to corresponding preset data acquisition points according to each type ID;
acquiring through a plurality of preset data acquisition points, and sending operation data of a corresponding industrial host including a type ID;
wherein each type ID is obtained from operational data of each industrial host.
The beneficial effect of adopting the further scheme is that: according to the scheme, the type IDs are set in the plurality of preset data acquisition points, the appropriate data acquisition points can be distributed to the plurality of industrial hosts, the acquired data can be preliminarily divided, and a large amount of running data can be effectively managed.
Further, still include:
dividing the acquired running data according to the type ID to obtain a first data set;
and combining the first data set according to the fault data set of the known fault database to construct a training data set.
The beneficial effect of adopting the further scheme is that: according to the scheme, the training parameters can be better surrounded in the training data set by optimizing the sample data through the type ID, the degree of tightness of the training data is kept moderate, and the model training precision is favorably improved.
Further, still include:
constructing a fault detection model through a neural network structure of a generator and two recognizers;
training the fault detection model according to a plurality of preset model parameters and by combining the training data set to obtain a trained fault detection model;
the two recognizers are respectively a first recognizer and a second recognizer; the first recognizer includes a deep belief network.
The beneficial effect of adopting the further scheme is that: according to the scheme, the fault detection model is built and preset model parameters are combined to associate fault data in the operation data, and the fault data are identified from the operation data.
Further, the preprocessing the operation data to obtain the first feature data specifically includes:
performing variable screening on the operation data to obtain operation parameters including fault parameters of the industrial host;
carrying out format conversion on the operation parameters including the fault parameters of the industrial host;
and carrying out duplicate removal and denoising treatment on the operation parameters after the format conversion to obtain first characteristic data.
The beneficial effect of adopting the further scheme is that: according to the scheme, impurity data and useless repeated data in the operation data are removed through preprocessing, and variables containing fault parameters are screened out, so that the fault identification precision and accuracy are improved.
Further, still include: and obtaining preset model parameters according to the type ID.
Another technical solution of the present invention for solving the above technical problems is as follows:
a fault detection system for multiple business hosts, comprising: the system comprises a data acquisition module, a preprocessing module, a fault analysis module and a calling module;
the data acquisition module is used for acquiring the operating data of the plurality of industrial hosts according to a preset data acquisition point;
the preprocessing module is used for preprocessing the operating data to obtain first characteristic data;
the fault analysis module is used for carrying out fault analysis on the first characteristic data according to preset model parameters and a trained fault detection model;
and the calling module is used for calling the corresponding overhaul report according to the analysis result and sending the overhaul report to the terminal.
The invention has the beneficial effects that: according to the scheme, the operation data of the industrial hosts are acquired through the acquisition points, the operation data are preprocessed to obtain first characteristic data, the first characteristic data are subjected to fault analysis according to preset model parameters and a trained fault detection model, corresponding maintenance reports are called according to analysis results and sent to the terminal, and therefore the faults of the industrial hosts on site can be effectively monitored in real time and timely uploaded.
The scheme realizes automatic real-time fault detection, reduces the detection cost, facilitates maintenance personnel to maintain fault equipment in time, guarantees the normal operation of the terminal equipment and provides better use feeling for workers.
Further, still include: the data acquisition module is used for respectively setting type IDs in a plurality of preset data acquisition points;
distributing matched industrial hosts to corresponding preset data acquisition points according to each type ID;
acquiring through a plurality of preset data acquisition points, and sending operation data of a corresponding industrial host including a type ID;
wherein each type ID is obtained from operational data of each industrial host.
The beneficial effect of adopting the further scheme is that: according to the scheme, the type IDs are set in the plurality of preset data acquisition points, the appropriate data acquisition points can be distributed to the plurality of industrial hosts, the acquired data can be preliminarily divided, and a large amount of running data can be effectively managed.
Further, still include: the training data construction module is used for dividing the acquired operation data according to the type ID to obtain a first data set;
and combining the first data set according to the fault data set of the known fault database to construct a training data set.
The beneficial effect of adopting the further scheme is that: according to the scheme, the training parameters can be better surrounded in the training data set by optimizing the sample data through the type ID, the degree of tightness of the training data is kept moderate, and the model training precision is favorably improved.
Further, still include: the model construction training module is used for constructing a fault detection model through a neural network structure of a generator and two recognizers;
training the fault detection model according to a plurality of preset model parameters and by combining the training data set to obtain a trained fault detection model;
the two recognizers are respectively a first recognizer and a second recognizer; the first recognizer includes a deep belief network.
The beneficial effect of adopting the further scheme is that: according to the scheme, the fault detection model is built and preset model parameters are combined to associate fault data in the operation data, and the fault data are identified from the operation data.
Further, the preprocessing module is specifically configured to perform variable screening on the operating data to obtain operating parameters including fault parameters of the industrial host;
carrying out format conversion on the operation parameters including the fault parameters of the industrial host;
and carrying out duplicate removal and denoising treatment on the operation parameters after the format conversion to obtain first characteristic data.
The beneficial effect of adopting the further scheme is that: according to the scheme, impurity data and useless repeated data in the operating data are removed through preprocessing, and variables containing fault parameters are deleted, so that the fault identification precision and accuracy are improved.
Further, still include: and the model parameter construction module is used for obtaining preset model parameters according to the type ID.
Another technical solution of the present invention for solving the above technical problems is as follows:
a service system including multiple industrial hosts, comprising: the fault detection system for the multi-business-host machine adopts any scheme.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
Fig. 1 is a schematic flow chart illustrating a method for detecting a fault of a multi-industrial host according to an embodiment of the present invention;
fig. 2 is a block diagram of a fault detection system for multiple business hosts according to an embodiment of the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth to illustrate, but are not to be construed to limit the scope of the invention.
As shown in fig. 1, a method for detecting a fault of multiple industrial hosts according to an embodiment of the present invention includes:
s1, acquiring the operation data of a plurality of industrial hosts according to a preset data acquisition point;
it should be noted that, in a certain embodiment, the type IDs are respectively set in a plurality of preset data acquisition points; distributing matched industrial hosts to corresponding preset data acquisition points according to each type ID; acquiring through a plurality of preset data acquisition points, and sending operation data of a corresponding industrial host including a type ID; wherein each type ID is obtained from operational data of each industrial host.
In one embodiment, the plurality of preset data collection points may be modules that are disposed in the industrial host and have functions of remote communication and data writing and reading, for example, a 4G/5G/wifi + storage unit that can be read and written, so as to implement storage and transmission of data operated by the industrial host. It should be noted that different types of industrial hosts are distinguished by type IDs, and corresponding data collection points are allocated according to the type IDs, for example, a type a industrial host and a type B industrial host are allocated to a type a data collection point and a type B data collection point, respectively.
S2, preprocessing the operation data to obtain first characteristic data;
it should be noted that, in a certain embodiment, variable screening is performed on the operation data to obtain operation parameters including fault parameters of the industrial host; carrying out format conversion on the operation parameters including the fault parameters of the industrial host; and carrying out duplicate removal and denoising treatment on the operation parameters after the format conversion to obtain first characteristic data.
S3, carrying out fault analysis on the first characteristic data according to preset model parameters and the trained fault detection model; and obtaining preset model parameters according to the type ID.
It should be noted that, in a certain embodiment, the fault detection model is constructed by a neural network structure of one generator and two recognizers; training the fault detection model according to a plurality of preset model parameters and by combining the training data set to obtain a trained fault detection model;
the two recognizers are respectively a first recognizer and a second recognizer; the first recognizer includes a deep belief network.
And S4, calling a corresponding overhaul report according to the analysis result and sending the overhaul report to the terminal. When needing to be explained, a maintenance report is established in the background server according to the solution corresponding to the fault reason matching, the fault reason in the known analysis result can obtain the maintenance report according to the maintenance report, and when the analysis result is a new fault, the maintenance report is updated according to the new fault and the new solution is matched.
According to the scheme, the operation data of the industrial hosts are acquired through the acquisition points, the operation data are preprocessed to obtain first characteristic data, the first characteristic data are subjected to fault analysis according to preset model parameters and a trained fault detection model, corresponding maintenance reports are called according to analysis results and sent to the terminal, and therefore the faults of the industrial hosts on site can be effectively monitored in real time and timely uploaded.
The scheme realizes automatic real-time fault detection, reduces the detection cost, facilitates maintenance personnel to maintain fault equipment in time, guarantees the normal operation of the terminal equipment and provides better use feeling for workers.
Preferably, in any of the above embodiments, the S1 may further include:
respectively setting type IDs in a plurality of preset data acquisition points;
distributing matched industrial hosts to corresponding preset data acquisition points according to each type ID;
acquiring through a plurality of preset data acquisition points, and sending operation data of a corresponding industrial host including a type ID;
wherein each type ID is obtained from operational data of each industrial host.
According to the scheme, the type IDs are set in the plurality of preset data acquisition points, the appropriate data acquisition points can be distributed to the plurality of industrial hosts, the acquired data can be preliminarily divided, and a large amount of running data can be effectively managed.
Preferably, in any of the above embodiments, further comprising:
dividing the acquired running data according to the type ID to obtain a first data set;
and combining the first data set according to the fault data set of the known fault database to construct a training data set.
According to the scheme, the training parameters can be better surrounded in the training data set by optimizing the sample data through the type ID, the degree of tightness of the training data is kept moderate, and the model training precision is favorably improved.
Preferably, in any of the above embodiments, further comprising:
constructing a fault detection model through a neural network structure of a generator and two recognizers;
training the fault detection model according to a plurality of preset model parameters and by combining the training data set to obtain a trained fault detection model;
the two recognizers are respectively a first recognizer and a second recognizer; the first recognizer includes a deep belief network. In one embodiment, the depth confidence network comprises three layers of limited Boltzmann machines and one soft-max; the number of network nodes of each hidden layer of the limited Boltzmann machine is respectively 400, 200 and 50; the number of network nodes of the output layer of soft-max is 2; the bias initialization of each hidden layer of the restricted boltzmann machine is 0. The weight is initialized to be random numbers which are in accordance with standard normal distribution; the generator and the second recognizer are both formed by a four-layer fully-connected network, parameter initialization is completed by an nn.Linear () function in a pytorch tool, the number of network nodes of each hidden layer of the generator is respectively 400, 400 and 200, and the number of network nodes of an output layer of the generator is 64; the number of the network nodes of each hidden layer of the second recognizer is respectively 400, 400 and 200, and the output layer of the second recognizer is formed by a Sigmoid function;
training a first recognizer, inputting training set data into the first recognizer, performing forward transmission calculation on the network to obtain a predicted result y _ hat, calculating cross entropy between the y _ hat and an actual result y, updating parameters by a backward propagation mechanism through an Adam optimizer, and setting the number of updating iterations to be 300; secondly, training a second recognizer, inputting the generator and the real time sequence message into the second recognizer, setting a loss function as the crossing entropy of the prediction result and the real result and adding a punishment term gp, updating parameters through an Adam optimizer by a back propagation mechanism, and updating iteration parameters for 5 times; training the generator 1 time every 5 times of training of the second recognizer; and finally, training a generator, setting a loss function of the generator as the mean square error between the generated message and the real message, reversely transmitting the loss function, updating the parameters of the generator through an Adam optimization algorithm, forming a second recognizer and the generator into cyclic training for 3000 times, and taking the second recognizer obtained by final training as a final confrontation to generate a neural network model.
According to the scheme, the fault detection model is built and preset model parameters are combined to associate fault data in the operation data, and the fault data are identified from the operation data.
Preferably, in any of the above embodiments, the preprocessing the operation data to obtain the first feature data specifically includes:
performing variable screening on the operation data to obtain operation parameters including fault parameters of the industrial host;
carrying out format conversion on the operation parameters including the fault parameters of the industrial host;
and carrying out duplicate removal and denoising treatment on the operation parameters after the format conversion to obtain first characteristic data.
According to the scheme, impurity data and useless repeated data in the operation data are removed through preprocessing, and variables containing fault parameters are screened out, so that the fault identification precision and accuracy are improved.
Preferably, in any of the above embodiments, further comprising: and obtaining preset model parameters according to the type ID.
In one embodiment, as shown in fig. 2, a system for detecting faults of multiple business hosts includes: the system comprises a data acquisition module 1101, a preprocessing module 1102, a fault analysis module 1103 and a calling module 1104;
the data acquisition module 1101 is configured to acquire operating data of a plurality of industrial hosts according to a preset data acquisition point;
it should be noted that, in a certain embodiment, the type IDs are respectively set in a plurality of preset data acquisition points; distributing matched industrial hosts to corresponding preset data acquisition points according to each type ID; acquiring through a plurality of preset data acquisition points, and sending operation data of a corresponding industrial host including a type ID; wherein each type ID is obtained from operational data of each industrial host.
In one embodiment, the plurality of preset data collection points may be modules that are disposed in the industrial host and have functions of remote communication and data writing and reading, for example, a 4G/5G/wifi + storage unit that can be read and written, so as to implement storage and transmission of data operated by the industrial host. It should be noted that different types of industrial hosts are distinguished by type IDs, and corresponding data collection points are allocated according to the type IDs, for example, a type a industrial host and a type B industrial host are allocated to a type a data collection point and a type B data collection point, respectively.
The preprocessing module 1102 is configured to preprocess the operating data to obtain first feature data;
it should be noted that, in a certain embodiment, variable screening is performed on the operation data to obtain operation parameters including fault parameters of the industrial host; carrying out format conversion on the operation parameters including the fault parameters of the industrial host; and carrying out duplicate removal and denoising treatment on the operation parameters after the format conversion to obtain first characteristic data.
The fault analysis module 1103 is configured to perform fault analysis on the first feature data according to preset model parameters and a trained fault detection model; it should be noted that, in a certain embodiment, the fault detection model is constructed by a neural network structure of one generator and two recognizers; training the fault detection model according to a plurality of preset model parameters and by combining the training data set to obtain a trained fault detection model;
the retrieval module 1104 is configured to retrieve a corresponding overhaul report according to the analysis result and send the overhaul report to the terminal. When needing to be explained, a maintenance report is established in the background server according to the solution corresponding to the fault reason matching, the fault reason in the known analysis result can obtain the maintenance report according to the maintenance report, and when the analysis result is a new fault, the maintenance report is updated according to the new fault and the new solution is matched.
According to the scheme, the operation data of the industrial hosts are acquired through the acquisition points, the operation data are preprocessed to obtain first characteristic data, the first characteristic data are subjected to fault analysis according to preset model parameters and a trained fault detection model, corresponding maintenance reports are called according to analysis results and sent to the terminal, and therefore the faults of the industrial hosts on site can be effectively monitored in real time and timely uploaded.
The scheme realizes automatic real-time fault detection, reduces the detection cost, facilitates maintenance personnel to maintain fault equipment in time, guarantees the normal operation of the terminal equipment and provides better use feeling for workers.
Preferably, in any of the above embodiments, further comprising: the data acquisition module is used for respectively setting type IDs in a plurality of preset data acquisition points;
distributing matched industrial hosts to corresponding preset data acquisition points according to each type ID;
acquiring through a plurality of preset data acquisition points, and sending operation data of a corresponding industrial host including a type ID;
wherein each type ID is obtained from operational data of each industrial host.
According to the scheme, the type IDs are set in the plurality of preset data acquisition points, the appropriate data acquisition points can be distributed to the plurality of industrial hosts, the acquired data can be preliminarily divided, and a large amount of running data can be effectively managed.
Preferably, in any of the above embodiments, further comprising: the training data construction module is used for dividing the acquired operation data according to the type ID to obtain a first data set;
and combining the first data set according to the fault data set of the known fault database to construct a training data set.
According to the scheme, the training parameters can be better surrounded in the training data set by optimizing the sample data through the type ID, the degree of tightness of the training data is kept moderate, and the model training precision is favorably improved.
Preferably, in any of the above embodiments, further comprising: the model construction training module is used for constructing a fault detection model through a neural network structure of a generator and two recognizers;
training the fault detection model according to a plurality of preset model parameters and by combining the training data set to obtain a trained fault detection model;
the two recognizers are respectively a first recognizer and a second recognizer; the first recognizer includes a deep belief network. In one embodiment, the depth confidence network comprises three layers of limited Boltzmann machines and one soft-max; the number of network nodes of each hidden layer of the limited Boltzmann machine is respectively 400, 200 and 50; the number of network nodes of the output layer of soft-max is 2; the bias initialization of each hidden layer of the restricted boltzmann machine is 0. The weight is initialized to be random numbers which are in accordance with standard normal distribution; the generator and the second recognizer are both formed by a four-layer fully-connected network, parameter initialization is completed by an nn.Linear () function in a pytorch tool, the number of network nodes of each hidden layer of the generator is respectively 400, 400 and 200, and the number of network nodes of an output layer of the generator is 64; the number of the network nodes of each hidden layer of the second recognizer is respectively 400, 400 and 200, and the output layer of the second recognizer is formed by a Sigmoid function;
training a first recognizer, inputting training set data into the first recognizer, performing forward transmission calculation on the network to obtain a predicted result y _ hat, calculating cross entropy between the y _ hat and an actual result y, updating parameters by a backward propagation mechanism through an Adam optimizer, and setting the number of updating iterations to be 300; secondly, training a second recognizer, inputting the generator and the real time sequence message into the second recognizer, setting a loss function as the crossing entropy of the prediction result and the real result and adding a punishment term gp, updating parameters through an Adam optimizer by a back propagation mechanism, and updating iteration parameters for 5 times; training the generator 1 time every 5 times of training of the second recognizer; and finally, training a generator, setting a loss function of the generator as the mean square error between the generated message and the real message, reversely transmitting the loss function, updating the parameters of the generator through an Adam optimization algorithm, forming a second recognizer and the generator into cyclic training for 3000 times, and taking the second recognizer obtained by final training as a final confrontation to generate a neural network model.
According to the scheme, the fault detection model is built and preset model parameters are combined to associate fault data in the operation data, and the fault data are identified from the operation data.
Preferably, in any embodiment described above, the preprocessing module 1102 is specifically configured to perform variable screening on the operation data to obtain operation parameters including fault parameters of the industrial host;
carrying out format conversion on the operation parameters including the fault parameters of the industrial host;
and carrying out duplicate removal and denoising treatment on the operation parameters after the format conversion to obtain first characteristic data.
According to the scheme, impurity data and useless repeated data in the operating data are removed through preprocessing, and variables containing fault parameters are deleted, so that the fault identification precision and accuracy are improved.
Preferably, in any of the above embodiments, further comprising: and the model parameter construction module is used for obtaining preset model parameters according to the type ID.
In one embodiment, a service system including multiple industrial hosts includes: the fault detection system for the multi-industry-host machine is adopted.
It is understood that some or all of the alternative embodiments described above may be included in some embodiments.
It should be noted that the above embodiments are product embodiments corresponding to the previous method embodiments, and for the description of each optional implementation in the product embodiments, reference may be made to corresponding descriptions in the above method embodiments, and details are not described here again.
The reader should understand that in the description of this specification, reference to the description of the terms "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed.
Units described as separate parts may or may not be physically separate, and parts displayed 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 can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. A fault detection method for multiple industrial hosts is characterized by comprising the following steps:
s1, acquiring the operation data of a plurality of industrial hosts according to a preset data acquisition point;
s2, preprocessing the operation data to obtain first characteristic data;
s3, carrying out fault analysis on the first characteristic data according to preset model parameters and the trained fault detection model;
s4, calling a corresponding overhaul report according to the analysis result and sending the overhaul report to the terminal;
the S1 may further include:
respectively setting type IDs in a plurality of preset data acquisition points;
distributing matched industrial hosts to corresponding preset data acquisition points according to each type ID;
acquiring through a plurality of preset data acquisition points, and sending operation data of a corresponding industrial host including a type ID;
wherein each type ID is obtained from operational data of each industrial host.
2. The method of claim 1, further comprising:
dividing the acquired running data according to the type ID to obtain a first data set;
and combining the first data set according to the fault data set of the known fault database to construct a training data set.
3. The method as claimed in claim 2, further comprising:
constructing a fault detection model through a neural network structure of a generator and two recognizers;
training the fault detection model according to a plurality of preset model parameters and by combining the training data set to obtain a trained fault detection model;
the two recognizers are respectively a first recognizer and a second recognizer; the first recognizer includes a deep belief network.
4. The method according to claim 1, wherein the preprocessing the operation data to obtain first feature data specifically comprises:
performing variable screening on the operation data to obtain operation parameters including fault parameters of the industrial host;
carrying out format conversion on the operation parameters including the fault parameters of the industrial host;
and carrying out duplicate removal and denoising treatment on the operation parameters after the format conversion to obtain first characteristic data.
5. The method for detecting the fault of the multiple industrial hosts according to claim 1 or 3, further comprising: and obtaining preset model parameters according to the type ID.
6. A system for detecting a failure of a plurality of business hosts, comprising: the system comprises a data acquisition module, a preprocessing module, a fault analysis module and a calling module;
the data acquisition module is used for acquiring the operating data of the plurality of industrial hosts according to a preset data acquisition point;
the preprocessing module is used for preprocessing the operating data to obtain first characteristic data;
the fault analysis module is used for carrying out fault analysis on the first characteristic data according to preset model parameters and a trained fault detection model;
the calling module is used for calling a corresponding overhaul report according to an analysis result and sending the overhaul report to the terminal;
further comprising: the data acquisition module is used for respectively setting type IDs in a plurality of preset data acquisition points;
distributing matched industrial hosts to corresponding preset data acquisition points according to each type ID;
acquiring through a plurality of preset data acquisition points, and sending operation data of a corresponding industrial host including a type ID;
wherein each type ID is obtained from operational data of each industrial host.
7. The system for detecting faults of multiple business owners according to claim 6, further comprising: the training data construction module is used for dividing the acquired operation data according to the type ID to obtain a first data set;
and combining the first data set according to the fault data set of the known fault database to construct a training data set.
8. A service system including multiple industrial hosts, comprising: a fault detection system using a multi-owner machine according to any one of claims 6 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210029690.8A CN114047735A (en) | 2022-01-12 | 2022-01-12 | Fault detection method, system and service system of multiple industrial hosts |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210029690.8A CN114047735A (en) | 2022-01-12 | 2022-01-12 | Fault detection method, system and service system of multiple industrial hosts |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114047735A true CN114047735A (en) | 2022-02-15 |
Family
ID=80196278
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210029690.8A Pending CN114047735A (en) | 2022-01-12 | 2022-01-12 | Fault detection method, system and service system of multiple industrial hosts |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114047735A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116359683A (en) * | 2023-02-28 | 2023-06-30 | 四川大唐国际甘孜水电开发有限公司 | Partial discharge mode identification method and system based on information interaction |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914735A (en) * | 2014-04-17 | 2014-07-09 | 北京泰乐德信息技术有限公司 | Failure recognition method and system based on neural network self-learning |
| CN109635958A (en) * | 2018-12-12 | 2019-04-16 | 成都航天科工大数据研究院有限公司 | A kind of predictive industrial equipment maintaining method and maintenance system based on edge calculations |
| CN110749462A (en) * | 2019-07-19 | 2020-02-04 | 华瑞新智科技（北京）有限公司 | Industrial equipment fault detection method and system based on edge calculation |
| CN112465244A (en) * | 2020-12-04 | 2021-03-09 | 重庆忽米网络科技有限公司 | TensorFlow-based industrial equipment pre-inspection and pre-repair model training method and device |
| CN113612786A (en) * | 2021-08-09 | 2021-11-05 | 上海交通大学宁波人工智能研究院 | Intrusion detection system and method for vehicle bus |
-
2022
- 2022-01-12 CN CN202210029690.8A patent/CN114047735A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914735A (en) * | 2014-04-17 | 2014-07-09 | 北京泰乐德信息技术有限公司 | Failure recognition method and system based on neural network self-learning |
| CN109635958A (en) * | 2018-12-12 | 2019-04-16 | 成都航天科工大数据研究院有限公司 | A kind of predictive industrial equipment maintaining method and maintenance system based on edge calculations |
| CN110749462A (en) * | 2019-07-19 | 2020-02-04 | 华瑞新智科技（北京）有限公司 | Industrial equipment fault detection method and system based on edge calculation |
| CN112465244A (en) * | 2020-12-04 | 2021-03-09 | 重庆忽米网络科技有限公司 | TensorFlow-based industrial equipment pre-inspection and pre-repair model training method and device |
| CN113612786A (en) * | 2021-08-09 | 2021-11-05 | 上海交通大学宁波人工智能研究院 | Intrusion detection system and method for vehicle bus |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116359683A (en) * | 2023-02-28 | 2023-06-30 | 四川大唐国际甘孜水电开发有限公司 | Partial discharge mode identification method and system based on information interaction |
| CN116359683B (en) * | 2023-02-28 | 2023-12-26 | 四川大唐国际甘孜水电开发有限公司 | Partial discharge mode identification method and system based on information interaction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111124840B (en) | Method and device for predicting alarm in business operation and maintenance and electronic equipment | |
| CN103646086B (en) | Junk file cleaning method and device | |
| US7567948B2 (en) | Method and system for obtaining a combination of faulty parts from a dispersed parts tree | |
| CN108334033A (en) | Punching machine group failure prediction method and its system based on Internet of Things and machine learning | |
| CN101536002A (en) | System and method for process monitoring | |
| CN102130783A (en) | Intelligent alarm monitoring method of neural network | |
| KR20180108446A (en) | System and method for management of ict infra | |
| DE102004015504A1 (en) | Method and device for the diagnostic selection of a maintenance concept for a complex system | |
| DE102004015503A1 (en) | Method and device for correcting diagnostic analysis concepts in complex systems | |
| CN116578040A (en) | Digital twin model construction method, system and terminal for machine tool fault diagnosis | |
| CN114047735A (en) | Fault detection method, system and service system of multiple industrial hosts | |
| CN115719283A (en) | Intelligent accounting management system | |
| CN111078457A (en) | Storage fault analysis method and device based on big data | |
| CN114528942A (en) | Construction method of data sample library of engineering machinery, failure prediction method and engineering machinery | |
| CN110399278B (en) | Alarm fusion system and method based on data center anomaly monitoring | |
| CN115757363B (en) | Multi-level management method and system for three-dimensional cadastral database | |
| CN114781473A (en) | Method, device and equipment for predicting state of rail transit equipment and storage medium | |
| CN114818353A (en) | Train control vehicle-mounted equipment fault prediction method based on fault characteristic relation map | |
| CN114936776A (en) | Service data processing method, device, equipment and storage medium | |
| CN114612246A (en) | Object set identification method and device, computer equipment and storage medium | |
| Azvine et al. | Intelligent process analytics for CRM | |
| CN113593605A (en) | Industrial audio fault monitoring system and method based on deep neural network | |
| CN113269368B (en) | Civil aircraft safety trend prediction method based on data driving | |
| CN116543881A (en) | Medical equipment state prediction method and device based on ultra-digital person and storage medium | |
| CN113535655A (en) | Log analysis method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220215 |
|
| RJ01 | Rejection of invention patent application after publication |