CN116975719A - Fault diagnosis model training method, device, equipment and medium - Google Patents
Fault diagnosis model training method, device, equipment and medium Download PDFInfo
- Publication number
- CN116975719A CN116975719A CN202310978195.6A CN202310978195A CN116975719A CN 116975719 A CN116975719 A CN 116975719A CN 202310978195 A CN202310978195 A CN 202310978195A CN 116975719 A CN116975719 A CN 116975719A
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- fault diagnosis
- training
- reference sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 185
- 238000012549 training Methods 0.000 title claims abstract description 106
- 238000000034 method Methods 0.000 title claims abstract description 54
- 239000013074 reference sample Substances 0.000 claims abstract description 70
- 239000000523 sample Substances 0.000 claims abstract description 25
- 238000004590 computer program Methods 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 7
- 239000013598 vector Substances 0.000 description 12
- 239000011159 matrix material Substances 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 239000004973 liquid crystal related substance Substances 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Biology (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The embodiment of the invention discloses a fault diagnosis model training method, device, equipment and medium, and relates to the technical field of fault diagnosis. The method comprises the following steps: acquiring reference sample data generated by sample equipment under the normal operation condition; determining a fault type of the sample equipment for fault diagnosis; generating fault associated data according to the reference sample data and the fault type; and generating fault diagnosis training data for training a fault diagnosis model according to the fault associated data. According to the scheme, the fault type is introduced, the fault associated data is determined, the fault diagnosis training data is further determined, the accuracy of the determined fault diagnosis training data is improved, the training accuracy of the fault diagnosis model is further improved, and the accuracy of fault diagnosis is carried out by using the trained fault diagnosis model subsequently.
Description
Technical Field
The embodiment of the invention relates to the technical field of fault diagnosis, in particular to a fault diagnosis model training method, device, equipment and medium.
Background
In recent years, fault diagnosis technology of industrial processes is often used for monitoring the industrial processes, and provides timely judgment for whether abnormal signals occur in the industrial processes.
In the prior art, fault diagnosis is generally performed by adopting a model mode. Therefore, how to improve the training accuracy of the model, and further improve the accuracy of fault diagnosis based on the trained model is important.
Disclosure of Invention
The invention provides a fault diagnosis model training method, device, equipment and medium, which are used for improving the training precision of a model and further improving the accuracy of fault diagnosis based on the trained model.
According to an aspect of the present invention, there is provided a fault diagnosis model training method, comprising:
acquiring reference sample data generated by sample equipment under the normal operation condition;
determining a fault type of the sample equipment for fault diagnosis;
generating fault associated data according to the reference sample data and the fault type;
and generating fault diagnosis training data for training a fault diagnosis model according to the fault associated data.
According to another aspect of the present invention, there is provided a fault diagnosis model training apparatus comprising:
the reference sample data acquisition module is used for acquiring reference sample data generated by the sample equipment under the normal operation condition;
the fault type determining module is used for determining the fault type of the sample equipment for fault diagnosis;
the fault associated data generation module is used for generating fault associated data according to the reference sample data and the fault type;
the fault diagnosis model training module is used for generating fault diagnosis training data according to the fault association data and used for training a fault diagnosis model.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the fault diagnosis model training method of any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the fault diagnosis model training method according to any one of the embodiments of the present invention when executed.
The embodiment of the invention provides a fault diagnosis model training scheme, which is implemented by acquiring reference sample data generated by sample equipment under the normal running condition; determining the fault type of the sample equipment for fault diagnosis; generating fault associated data according to the reference sample data and the fault type; and generating fault diagnosis training data for training a fault diagnosis model according to the fault correlation data. According to the scheme, the fault type is introduced, the fault associated data is determined, the fault diagnosis training data is further determined, the accuracy of the determined fault diagnosis training data is improved, the training accuracy of the fault diagnosis model is further improved, and the accuracy of fault diagnosis is carried out by using the trained fault diagnosis model subsequently.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a fault diagnosis model training method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a training method for a fault diagnosis model according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a fault diagnosis model training device according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device for implementing a training method of a fault diagnosis model according to a fourth embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Example 1
Fig. 1 is a flowchart of a fault diagnosis model training method according to an embodiment of the present invention, where the method may be implemented by a fault diagnosis device, and the device may be implemented in hardware and/or software, and the device may be configured in an electronic apparatus that carries a function of training a fault diagnosis model.
Referring to the fault diagnosis model training method shown in fig. 1, the method includes:
s110, acquiring reference sample data generated by the sample equipment under the normal operation condition.
Wherein, the sample device refers to an industrial device that can provide reference sample data. The reference sample data refers to data that can be used to train a fault diagnosis model. Normal operation refers to the situation in which the sample device is in trouble-free operation. The method for acquiring the reference sample data according to the embodiment of the invention is not limited, and can be set by a technician according to experience. For example, a sensor may be employed to obtain reference sample data.
It should be noted that, when the sensor is used to obtain the reference sample data, since the sensitivity of the different types of sensors to the different fault types is different, at least one type of sensor may be used to obtain the reference sample data in order to improve the diversity and the comprehensiveness of the reference sample data.
Specifically, the reference sample data generated at different moments is obtained when the sample device is in normal operation.
S120, determining the fault type of the sample equipment for fault diagnosis.
The fault type refers to the direction or the type of fault diagnosis. The embodiment of the invention does not limit the types and/or the number of the fault types, and can be set by a technician according to experience. In an alternative embodiment, the type of fault may be determined based on the type of sensor.
S130, generating fault associated data according to the reference sample data and the fault type.
The fault associated data refers to data related to fault diagnosis generated according to the reference sample data and the fault type. Illustratively, the fault-associated data may be a set of feature vectors.
And S140, generating fault diagnosis training data according to the fault association data, and training a fault diagnosis model.
The fault diagnosis training data refers to data which can be used for providing basis for adjusting parameters of a fault diagnosis model. For example, the fault diagnosis training data may be expressed in the form of a matrix. In particular, the fault diagnosis training data may be a projection matrix (or projection data).
The embodiment of the invention provides a fault diagnosis model training scheme, which is implemented by acquiring reference sample data generated by sample equipment under the normal running condition; determining the fault type of the sample equipment for fault diagnosis; generating fault associated data according to the reference sample data and the fault type; and generating fault diagnosis training data for training a fault diagnosis model according to the fault correlation data. According to the scheme, the fault type is introduced, the fault associated data is determined, the fault diagnosis training data is further determined, the accuracy of the determined fault diagnosis training data is improved, the training accuracy of the fault diagnosis model is further improved, and the accuracy of fault diagnosis is carried out by using the trained fault diagnosis model subsequently.
Example two
FIG. 2 is a flowchart of a training method for a fault diagnosis model according to a second embodiment of the present invention, where the operation of generating fault associated data according to reference sample data and fault type is further subdivided into generating fault class associated data according to reference sample data based on the above embodiments; generating sub-fault class association data of different fault types according to the reference sample data and the fault types; obtaining fault inter-class association data according to the sub-fault inter-class association data; fault correlation data "including intra-fault class correlation data and inter-fault class correlation data is generated to perfect a fault correlation data determination mechanism. It should be noted that, for the part of the embodiments of the present invention that are not described in detail, reference may be made to the description of other embodiments.
Referring to the fault diagnosis model training method shown in fig. 2, the method includes:
s210, acquiring reference sample data generated by the sample equipment under the normal operation condition.
S220, determining the fault type of the sample equipment for fault diagnosis.
S230, generating fault intra-class association data according to the reference sample data.
The fault intra-class associated data is used for representing intra-class aggregation of the reference sample data acquired at any acquisition time. Illustratively, the fault-class correlation data may be represented in the form of a matrix. Specifically, the intra-fault class association data (or intra-fault class association matrix) may be determined by the following formula:
wherein S is W Representing associated data within the fault class; e, e n An n-dimensional vector representing all 1 s; t represents torque;representing tensor kroneck products; x represents a set of reference sample data, X ε R d×n The method comprises the steps of carrying out a first treatment on the surface of the d represents the dimension or number of sensors; n represents the number of reference sample data of the time series, i.e. the number of reference sample data at a certain time.
It should be noted that, the purpose of generating the related data in the fault class is to make the reference sample data acquired at different time points realize intra-class aggregation, so as to avoid the reference sample data acquired at different time points from being too scattered.
Specifically, based on the reference sample data acquired at different moments, the fault intra-class associated data at the corresponding moments is generated.
S240, generating sub-fault class-to-class association data of different fault types according to the reference sample data and the fault types.
The sub-fault inter-class association data is used for representing inter-class dispersion of different fault types and reference sample data. Illustratively, the sub-fault inter-class association data may be represented in the form of a matrix. Specifically, the inter-sub-fault class association data (or inter-sub-fault class association matrix) may be determined by the following formula:
S Fi ＝(Ξ i ·f i )(Ξ i ·f i ) T ；
wherein S is Fi The sub-fault inter-class association data representing the i-th class fault type composition; xi (xi) i A direction vector representing a fault type; f (f) i A fault magnitude representing a type i fault; i represents the i-th dimension or sensor.
It should be noted that, when determining the correlation data between the sub-fault classes according to the above formula, the expected E may be added, so that the determined correlation data between the sub-fault classes is more accurate. Specifically, the expression after addition of the desired E is:
S Fi ＝(Ξ i ·E(f i ))(Ξ i ·E(f i )) T ；
specifically, a sensor sensitive to the fault type is determined based on the determined fault type. For example, if the number of sensors is d, and the sensitivity direction for a given fault type is the sensitivity direction for the first s sensors, then the sensors that are insensitive to the determined fault type are the remaining d-s sensors, so the fault sensitivity direction vector, xi 1 To xi s The following conditions are satisfied:
Ξ 1 ＝[100…0] T
Ξ 2 ＝[0100…0] T
further, for the fault direction vector corresponding to the sensor with insensitive determined fault type, the following conditions are satisfied:
wherein epsilon represents a very small positive number, so that the matrix pathological problem in the generalized eigenvalue problem solving process can be avoided, and the subspace dimension is not constrained.
Further, in order to reduce the amount of computation, it is considered that the same magnitude may occur equally for each sensor directionBarrier, under the condition that more accurate fault information can not be obtained, can set that the fault amplitude of each fault type is equal, namely I F 1 ||＝||f 2 ||＝…||f i I, wherein i f i I represents the fault magnitude.
In an alternative embodiment, generating fault inter-class association data for different fault types based on the reference sample data and the fault type includes: carrying out normalization processing on the reference sample data to enable the average value of each reference sample data to be a default value; and generating sub-fault class association data of different fault types according to the fault types.
The default value is not limited in any way, and may be set by a technician according to experience. Illustratively, the default value may be 0. The normalization processing method in the embodiment of the invention is not limited, and can be set by a technician according to experience. For example, if the default value is 0, zero mean normalization and unit variance normalization may be employed accordingly.
It can be understood that by introducing normalization processing, the mean value of each reference sample data is a default value, so that the efficiency of determining the associated data among sub-fault classes is improved, and the operation amount is reduced.
S250, obtaining the association data between the fault classes according to the association data between the sub-fault classes.
The inter-fault-class association data refers to a set of sub-fault inter-class association data. Illustratively, the inter-fault class association data may be represented in the form of a matrix. Specifically, the inter-fault class association data (or inter-fault class association matrix) may be determined by the following formula:
wherein S is F Representing the association data among fault classes, namely the collection of the association data among fault classes formed by different fault types.
S260, generating fault associated data comprising the fault intra-class associated data and the fault inter-class associated data.
The feature vectors are stored in the fault class-associated data and the fault class-to-class associated data.
S270, generating fault diagnosis training data according to the fault association data, and training a fault diagnosis model.
In an alternative embodiment, generating fault diagnosis training data from the fault-related data includes: determining fault association characteristic data according to the fault intra-class association data and the fault inter-class association data; obtaining fault diagnosis characteristic data according to the fault association characteristic data; and generating fault diagnosis training data according to the fault diagnosis characteristic data.
The fault-associated feature data refers to feature values of feature vectors in the fault-associated data. For example, fault-related characteristic data may be characterized by a characteristic value versus a corner array. The fault diagnosis feature data refers to feature values of at least part of feature vectors in the fault correlation data. For example, the fault diagnosis feature data may be characterized by a maximum feature value versus a corner array.
Illustratively according toThe fault-associated feature data is determined by the following formula:
S F B＝λS W B；
where tr represents the trace of the matrix (trace); lambda represents a characteristic value; b represents the failure diagnosis training data.
It can be understood that by introducing the fault-associated feature data, the fault diagnosis feature data is obtained, and then the fault diagnosis training data is generated according to the fault diagnosis feature data, so that the dimension of the fault diagnosis training data is reduced while the comprehensiveness of the fault diagnosis training data is ensured, and the efficiency of subsequent processing is improved.
In an alternative embodiment, obtaining fault diagnosis feature data according to the fault associated feature data includes: selecting larger preset threshold value fault associated characteristic data as fault diagnosis characteristic data; correspondingly, generating fault diagnosis training data according to the fault diagnosis characteristic data comprises the following steps: determining fault-related data corresponding to the fault diagnosis feature data; and taking fault-related data corresponding to the fault diagnosis characteristic data as fault diagnosis training data.
The magnitude of the preset threshold is not limited in any way, and the preset threshold can be set by a technician according to experience. The preset threshold may be a subspace dimension, and the size of the subspace dimension may be determined according to a preset rule, for example. The embodiment of the invention does not limit the preset rule at all, and can be set by a technician according to experience. For example, the preset rule may be a cumulative variance contribution (cumulative percentage variance, CPV) criterion or an AIC criterion (Akaike information criterion, AIC).
Specifically, subspace dimension number fault-associated feature data with larger feature values are selected from the fault-associated feature data to serve as fault diagnosis feature data; and determining fault-related data corresponding to the fault diagnosis feature data, and taking the determined fault-related data as fault diagnosis training data.
In an alternative embodiment, the fault associated data may be regarded as a metaspace, and the metaspace is subjected to dimension reduction processing to obtain a subspace containing at least part of the feature vectors in the metaspace; and performing fault detection of corresponding fault types through the determined subspaces so as to improve the performance of fault diagnosis. Wherein, the metaspace contains feature vectors which characterize each fault type. The subspace contains feature vectors that characterize the more important fault types.
It can be understood that by introducing the preset threshold, dimension reduction of the fault associated data is realized, dimension of the fault diagnosis training data is reduced, and subsequent fault diagnosis is facilitated.
According to the fault diagnosis model training scheme provided by the embodiment of the invention, the operation of generating fault associated data according to the reference sample data and the fault type is refined into the operation of generating the fault intra-class associated data according to the reference sample data; generating sub-fault class association data of different fault types according to the reference sample data and the fault types; obtaining fault inter-class association data according to the sub-fault inter-class association data; and generating fault associated data comprising the associated data in the fault classes and the associated data among the fault classes, thereby perfecting a fault associated data determining mechanism. According to the scheme, the fault associated data are determined by introducing the fault intra-class associated data and the fault inter-class associated data, so that corresponding data are respectively determined under the condition of considering normal operation and faults, and the comprehensiveness and the accuracy of the determined fault associated data are improved.
On the basis of the technical scheme, the method further comprises the following steps: determining a fault detection threshold value for fault diagnosis according to a preset threshold value; and determining the fault state of the reference sample data according to the fault detection threshold value.
Wherein the fault detection threshold may be used to determine whether the data is faulty. Exemplary, the fault detection threshold may be T 2 The control limit to which the statistics correspond. Fault conditions may include faulty and non-faulty.
Exemplary, when the failure detection threshold is T 2 The control limit corresponding to the statistic may determine the fault detection threshold by the following equation:
wherein, the liquid crystal display device comprises a liquid crystal display device,representing T 2 A control limit corresponding to the statistic; p represents the subspace dimension; f represents F distribution; alpha represents a level of significance; η (eta) 2 Representing a control limit.
It can be appreciated that by introducing the fault detection threshold, accurate determination of the fault state is achieved, and accuracy of the determined fault state is improved.
In the embodiment of the invention, when the fault diagnosis model is trained, the input data can comprise reference sample data X epsilon R d×n Direction vector of fault type xi i Of the fault typeFault amplitude f i Preset threshold (or subspace dimension p) and significance level α; the output data may include fault diagnosis training data B, fault diagnosis feature data Λ, and fault detection threshold (or T 2 The control limit to which the statistics correspond).
In an alternative embodiment, the method further comprises: obtaining a fault diagnosis model; the fault diagnosis model is obtained by training a fault diagnosis model training method; acquiring data to be detected of equipment to be detected running at the current time; and inputting the data to be detected into a fault diagnosis model, and determining the fault state of the data to be detected.
The data to be detected refers to data which needs to be subjected to fault diagnosis. The device to be detected refers to a device that needs to perform fault diagnosis.
In an alternative embodiment, the fault diagnosis model, when in use, the input data may include the data to be detected xεR d The obtained fault diagnosis training data B and fault diagnosis feature data Λ, and a fault detection threshold (or T) 2 A control limit corresponding to the statistic); the output data is the fault state of the data to be detected.
Specifically, when the fault diagnosis model is used, the T corresponding to the data to be detected can be determined through the following formula 2 Statistics:
T 2 ＝x T BΛ -1 F T x；
further, ifDetermining that the fault state of the data to be detected is faulty; if not, determining that the fault state of the data to be detected is fault-free, namely that the data to be detected is normal data.
It can be understood that by using the fault diagnosis model obtained by training by the method, fault diagnosis is carried out on the data to be detected, and the accuracy of the determined fault state is improved.
When the fault diagnosis model is trained or used, the input data needs to be preprocessed. The embodiment of the invention does not limit the pretreatment mode, and can be set by a technician according to experience.
Example III
Fig. 3 is a schematic structural diagram of a fault diagnosis model training device according to a third embodiment of the present invention. The embodiment is applicable to the case of training a fault diagnosis model, and the method can be executed by a fault diagnosis device, which can be implemented in the form of hardware and/or software, and which can be configured in an electronic apparatus carrying the function of training the fault diagnosis model.
As shown in fig. 3, the apparatus includes: a reference sample data acquisition module 310, a fault type determination module 320, a fault correlation data generation module 330, and a fault diagnosis model training module 340. Wherein, the liquid crystal display device comprises a liquid crystal display device,
a reference sample data obtaining module 310, configured to obtain reference sample data generated by the sample device under normal operation conditions;
a fault type determining module 320, configured to determine a fault type of the sample device for fault diagnosis;
a fault associated data generation module 330, configured to generate fault associated data according to the reference sample data and the fault type;
the fault diagnosis model training module 340 is configured to generate fault diagnosis training data according to the fault correlation data, and is configured to train a fault diagnosis model.
The embodiment of the invention provides a fault diagnosis model training scheme, which comprises the steps of acquiring reference sample data generated by sample equipment under the normal running condition through a reference sample data acquisition module; determining the fault type of the sample equipment for fault diagnosis through a fault type determining module; generating fault associated data according to the reference sample data and the fault type through a fault associated data generation module; and generating fault diagnosis training data for training a fault diagnosis model according to the fault correlation data through a fault diagnosis model training module. According to the scheme, the fault type is introduced, the fault associated data is determined, the fault diagnosis training data is further determined, the accuracy of the determined fault diagnosis training data is improved, the training accuracy of the fault diagnosis model is further improved, and the accuracy of fault diagnosis is carried out by using the trained fault diagnosis model subsequently.
Optionally, the fault associated data generating module 330 includes:
the intra-class associated data generation unit is used for generating fault intra-class associated data according to the reference sample data;
the sub-class association data generation unit is used for generating sub-fault inter-class association data of different fault types according to the reference sample data and the fault types;
the inter-class association data generation unit is used for obtaining fault inter-class association data according to the sub-fault inter-class association data;
and the association data generation unit is used for generating fault association data comprising the association data in the fault class and the association data between the fault classes.
Optionally, the inter-class association data generating unit is specifically configured to:
carrying out normalization processing on the reference sample data to enable the average value of each reference sample data to be a default value;
and generating sub-fault class association data of different fault types according to the fault types.
Optionally, the fault diagnosis model training module 340 includes:
the fault associated characteristic data determining unit is used for determining fault associated characteristic data according to the fault intra-class associated data and the fault inter-class associated data;
the fault diagnosis feature data determining unit is used for obtaining fault diagnosis feature data according to the fault association feature data;
the fault diagnosis training data determining unit is used for generating fault diagnosis training data according to the fault diagnosis characteristic data.
Optionally, the fault diagnosis feature data determining unit is specifically configured to:
selecting larger preset threshold value fault associated characteristic data as fault diagnosis characteristic data;
correspondingly, generating fault diagnosis training data according to the fault diagnosis characteristic data comprises the following steps:
determining fault-related data corresponding to the fault diagnosis feature data;
and taking fault-related data corresponding to the fault diagnosis characteristic data as fault diagnosis training data.
Optionally, the apparatus further comprises:
a fault detection threshold determining unit for determining a fault detection threshold for fault diagnosis according to a preset threshold;
and the fault state determining unit is used for determining the fault state of the reference sample data according to the fault detection threshold value.
Optionally, the apparatus further comprises:
the model acquisition module is used for acquiring a fault diagnosis model; the fault diagnosis model is obtained by training a fault diagnosis model training method;
the to-be-detected data acquisition module is used for acquiring to-be-detected data of to-be-detected equipment running at the current moment;
the fault state determining module is used for inputting the data to be detected into the fault diagnosis model and determining the fault state of the data to be detected.
The fault diagnosis model training device provided by the embodiment of the invention can execute the fault diagnosis model training method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the fault diagnosis model training methods.
In the technical scheme of the invention, the related processes of collection, storage, use, processing, transmission, provision, disclosure and the like of the reference sample data, the fault type, the data to be detected and the like all conform to the regulations of related laws and regulations, and the public order is not violated.
Example IV
Fig. 4 is a schematic structural diagram of an electronic device for implementing a training method of a fault diagnosis model according to a fourth embodiment of the present invention. The electronic device 410 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 4, the electronic device 410 includes at least one processor 411, and a memory, such as a Read Only Memory (ROM) 412, a Random Access Memory (RAM) 413, etc., communicatively connected to the at least one processor 411, wherein the memory stores computer programs executable by the at least one processor, and the processor 411 may perform various suitable actions and processes according to the computer programs stored in the Read Only Memory (ROM) 412 or the computer programs loaded from the storage unit 418 into the Random Access Memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the electronic device 410 may also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other through a bus 414. An input/output (I/O) interface 415 is also connected to bus 414.
Various components in the electronic device 410 are connected to the I/O interface 415, including: an input unit 416 such as a keyboard, a mouse, etc.; an output unit 417 such as various types of displays, speakers, and the like; a storage unit 418, such as a magnetic disk, optical disk, or the like; and a communication unit 419 such as a network card, modem, wireless communication transceiver, etc. The communication unit 419 allows the electronic device 410 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The processor 411 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 411 performs the various methods and processes described above, such as the fault diagnosis model training method.
In some embodiments, the fault diagnosis model training method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 418. In some embodiments, some or all of the computer program may be loaded and/or installed onto the electronic device 410 via the ROM 412 and/or the communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the fault diagnosis model training method described above may be performed. Alternatively, in other embodiments, the processor 411 may be configured to perform the fault diagnosis model training method in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A fault diagnosis model training method, comprising:
acquiring reference sample data generated by sample equipment under the normal operation condition;
determining a fault type of the sample equipment for fault diagnosis;
generating fault associated data according to the reference sample data and the fault type;
and generating fault diagnosis training data for training a fault diagnosis model according to the fault associated data.
2. The method of claim 1, wherein generating fault correlation data from the reference sample data and the fault type comprises:
generating fault intra-class association data according to the reference sample data;
generating sub-fault class-to-class association data of different fault types according to the reference sample data and the fault types;
obtaining fault inter-class association data according to the sub-fault inter-class association data;
generating fault association data comprising the fault intra-class association data and the inter-fault class association data.
3. The method of claim 2, wherein generating sub-fault inter-class association data for different fault types based on the reference sample data and the fault type comprises:
carrying out normalization processing on the reference sample data to enable the mean value of each reference sample data to be a default value;
and generating sub-fault class association data of different fault types according to the fault types.
4. The method of claim 2, wherein generating fault diagnosis training data from the fault-related data comprises:
determining fault association characteristic data according to the fault intra-class association data and the fault inter-class association data;
obtaining fault diagnosis characteristic data according to the fault associated characteristic data;
and generating fault diagnosis training data according to the fault diagnosis characteristic data.
5. The method of claim 4, wherein obtaining fault diagnosis feature data from the fault-associated feature data comprises:
selecting larger preset threshold value fault associated characteristic data as fault diagnosis characteristic data;
correspondingly, the generating fault diagnosis training data according to the fault diagnosis characteristic data comprises the following steps:
determining fault-related data corresponding to the fault diagnosis feature data;
and taking fault associated data corresponding to the fault diagnosis characteristic data as fault diagnosis training data.
6. The method of claim 5, wherein the method further comprises:
determining a fault detection threshold value for fault diagnosis according to the preset threshold value;
and determining the fault state of the reference sample data according to the fault detection threshold.
7. The method according to any one of claims 1-6, further comprising:
obtaining a fault diagnosis model; wherein the fault diagnosis model is trained by the method of any one of claims 1-6;
acquiring data to be detected of equipment to be detected running at the current time;
and inputting the data to be detected into a fault diagnosis model, and determining the fault state of the data to be detected.
8. A fault diagnosis model training apparatus, comprising:
the reference sample data acquisition module is used for acquiring reference sample data generated by the sample equipment under the normal operation condition;
the fault type determining module is used for determining the fault type of the sample equipment for fault diagnosis;
the fault associated data generation module is used for generating fault associated data according to the reference sample data and the fault type;
the fault diagnosis model training module is used for generating fault diagnosis training data according to the fault association data and used for training a fault diagnosis model.
9. An electronic device, comprising:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, causes the one or more processors to implement a fault diagnosis model training method as claimed in any one of claims 1 to 7.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements a fault diagnosis model training method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310978195.6A CN116975719A (en) | 2023-08-04 | 2023-08-04 | Fault diagnosis model training method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310978195.6A CN116975719A (en) | 2023-08-04 | 2023-08-04 | Fault diagnosis model training method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116975719A true CN116975719A (en) | 2023-10-31 |
Family
ID=88484786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310978195.6A Pending CN116975719A (en) | 2023-08-04 | 2023-08-04 | Fault diagnosis model training method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116975719A (en) |
-
2023
- 2023-08-04 CN CN202310978195.6A patent/CN116975719A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116049146B (en) | Database fault processing method, device, equipment and storage medium | |
| CN115373888A (en) | Fault positioning method and device, electronic equipment and storage medium | |
| CN116089231B (en) | Fault alarm method and device, electronic equipment and storage medium | |
| WO2019019429A1 (en) | Anomaly detection method, device and apparatus for virtual machine, and storage medium | |
| CN116087787A (en) | Battery fault judging method and system based on principal component analysis method | |
| CN116975719A (en) | Fault diagnosis model training method, device, equipment and medium | |
| CN116975081A (en) | Log diagnosis set updating method, device, equipment and storage medium | |
| CN116962272A (en) | Abnormality detection method, device, equipment and storage medium for network index | |
| CN116359738A (en) | Method, device, equipment and storage medium for monitoring health state of battery | |
| CN115361308B (en) | Industrial control network data risk determination method, device, equipment and storage medium | |
| CN116842837A (en) | Transformer fault diagnosis method and device, electronic equipment and storage medium | |
| CN117571321B (en) | Bearing fault detection method, device, equipment and storage medium | |
| CN117803475A (en) | Fault diagnosis method, device, equipment and medium for fuel system | |
| CN117851853A (en) | Method, device, equipment and storage medium for positioning electricity stealing user | |
| CN117590239A (en) | Battery abnormality detection method, battery abnormality detection device, electronic equipment and storage medium | |
| CN116956042A (en) | Method, device, equipment and medium for establishing fault type detection model | |
| CN116961229A (en) | Transformer substation fault positioning method and device, electronic equipment and storage medium | |
| CN118210670A (en) | Log abnormality detection method and device, electronic equipment and storage medium | |
| CN117891643A (en) | Abnormality index sorting method and device, electronic equipment and storage medium | |
| CN116845287A (en) | Method, device, equipment and medium for predicting test data of fuel cell | |
| CN117371506A (en) | Model training method, model testing device, electronic equipment and storage medium | |
| CN116754898A (en) | Cable fault diagnosis method, device, equipment and medium based on cable wave recording | |
| CN116112339A (en) | Root cause alarm positioning method, device, equipment and medium | |
| CN117349747A (en) | Offline fault reason classification method for electric power Internet of things intelligent terminal | |
| CN118074625A (en) | Equipment fault detection method, device, equipment and storage medium |
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 |