CN114298362A - Equipment fault prediction method and device, readable storage medium and computing equipment - Google Patents
Equipment fault prediction method and device, readable storage medium and computing equipment Download PDFInfo
- Publication number
- CN114298362A CN114298362A CN202011010347.6A CN202011010347A CN114298362A CN 114298362 A CN114298362 A CN 114298362A CN 202011010347 A CN202011010347 A CN 202011010347A CN 114298362 A CN114298362 A CN 114298362A
- Authority
- CN
- China
- Prior art keywords
- data
- sample
- model
- training
- equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012549 training Methods 0.000 claims abstract description 77
- 238000013145 classification model Methods 0.000 claims description 29
- 238000004364 calculation method Methods 0.000 claims description 19
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 abstract description 11
- 238000013508 migration Methods 0.000 abstract description 5
- 230000005012 migration Effects 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 7
- 238000002372 labelling Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for predicting equipment failure, a readable storage medium and computing equipment, wherein the method comprises the following steps: acquiring a training data set for establishing a prediction model for target equipment according to the attribute of the target equipment, wherein sample data in the data set is shared data; calculating the weight of each sample data in the training data set; training by using the weight to obtain a fault prediction local model of the target equipment; establishing a joint model based on the fault prediction local model and a joint learning algorithm; and performing fault prediction on the target equipment according to the combined model. The invention adopts a sample migration method based on a joint learning mode, is used for equipment predictive maintenance, can jointly learn data acquired from a plurality of pieces of equipment, and migrates the data to target equipment to train a predictive maintenance model aiming at the target equipment, realizes multi-party joint learning, ensures that each party of data is not local, and avoids the data security problem caused by directly sharing the data.
Description
Technical Field
The invention relates to the technical field of Internet of things, in particular to a method and a device for predicting equipment failure, a readable storage medium and computing equipment.
Background
The equipment predictive maintenance is to predict the failure probability of the equipment or the residual service life of the equipment and the like according to the characteristic information of the running state of the equipment. The data-driven method is to use historical operation data of the equipment, including measurement of each sensor of the equipment, and establish a mapping relation between the measurement and the fault probability of the equipment through a machine learning method. In order to learn an effective model, high-quality labeling data is generally required, that is, a large amount of fault label data is required; the fault data of a single device is limited, and a plurality of devices of the same type need to be combined to obtain enough data.
The existing technical scheme can solve the problem of self fault prediction of the equipment, but the existing technical scheme is to directly share the data of each equipment in the internet of things and does not consider the requirement of protecting data privacy among the equipment in the internet of things for data sharing among different equipment.
Disclosure of Invention
The present invention aims to solve at least one of the above technical problems to at least some extent.
Therefore, a first object of the present invention is to provide an apparatus failure prediction method, which is based on sample migration in a joint learning manner, and is used for predictive maintenance of apparatuses, and may jointly learn data collected on multiple apparatuses, and migrate the data to a target apparatus, so as to train a predictive maintenance model for the target apparatus, and simultaneously ensure that data of each party is not local, so as to ensure privacy of data of each party.
The second objective of the present invention is to provide an apparatus failure prediction device, which is based on sample migration in a joint learning manner, and is used for predictive maintenance of equipment, and can jointly learn data collected from multiple pieces of equipment, and migrate the data to a target equipment, so as to train a predictive maintenance model for the target equipment, and simultaneously ensure that data of each party is not local, so as to ensure privacy of data of each party.
A third object of the invention is to propose a readable storage medium.
A fourth object of the invention is to propose a computing device.
In a first aspect, an embodiment of the present invention provides an apparatus failure prediction method, where the apparatus failure prediction method includes:
acquiring a training data set for establishing a prediction model for target equipment according to the attribute of the target equipment, wherein sample data in the data set is shared data;
calculating the weight of each sample data in the training data set;
training by using the weight to obtain a fault prediction local model of the target equipment;
establishing a joint model based on the fault prediction local model and a joint learning algorithm;
and performing fault prediction on the target equipment according to the combined model.
Optionally, the sample data in the training data set includes feature data of a target device, feature data of a sample device, and fault data of the sample device; the sample device is a device related or similar to the target device.
Optionally, the calculating the weight of each sample data in the training data set comprises, for each of the sample devices:
distinguishing the characteristic data of the sample device from the characteristic data of the target device;
training a classification model according to the distinguished characteristic data;
and calculating the weight of each piece of feature data of the sample equipment according to the trained classification model.
Optionally, the calculating the weight of each sample data in the training data set comprises, for each of the sample devices:
marking the characteristic data of the sample device as first data, and marking the characteristic data of the target device as second data;
training a classification model according to the first data and the second data, wherein the classification model is based on joint learning;
calculating the weight of each piece of feature data of the sample equipment according to the trained classification model, wherein the calculation formula of the weight is as follows:
wherein, ω isiIs the weight of the ith piece of data in the first data, P1iIs the probability, P, that the ith piece of data belongs to the sample device2iIs the probability that the ith piece of data belongs to the target device.
Optionally, the obtaining of the local model of the target device for the fault prediction by using the weight training includes:
and training on the training data set with the weight of the sample equipment by using a neural network respectively according to the feature data of each sample equipment, the weight of each feature data of the sample equipment and the fault data of each sample equipment to obtain a local fault prediction model of the target equipment.
Optionally, the building a joint model based on the fault prediction local model and a joint learning algorithm includes:
and according to the fault prediction local model, repeatedly iterating by using a joint learning algorithm to obtain a joint model of the sample equipment on the training data set relative to the target equipment.
Optionally, the target device and each sample device are edge nodes in the internet of things, the feature data of the target device is not exposed to other sample devices, and the feature data and the fault data of each sample device are not exposed to other sample devices and the target device.
In a second aspect, an embodiment of the present invention provides an apparatus failure prediction device, where the apparatus failure prediction device includes: a data acquisition module, a weight calculation module, a local model training module, a combined model establishing module and a fault prediction module, wherein,
the data acquisition module is used for acquiring a training data set used for establishing a prediction model for target equipment according to the attribute of the target equipment, wherein sample data in the data set is shared data;
the weight calculation module is used for calculating the weight of each sample data in the training data set;
the local model training module is used for obtaining a fault prediction local model of the target equipment by utilizing the weight training;
the joint model establishing module is used for establishing a joint model based on the fault prediction local model and a joint learning algorithm;
and the fault prediction module is used for carrying out fault prediction on the target equipment according to the combined model.
Optionally, the sample data in the training data set includes feature data of a target device, feature data of a sample device, and fault data of the sample device; the sample device is a device related or similar to the target device.
Optionally, the weight calculation module comprises a data marking unit, a data classification unit and a data calculation unit, wherein, for each of the sample devices,
the data marking unit is used for distinguishing the characteristic data of the sample device acquired by the data acquisition module from the characteristic data of the target device;
the data classification unit is used for training a classification model according to the characteristic data distinguished by the data marking unit;
and the data calculation unit is used for calculating the weight of each piece of characteristic data of the sample equipment according to the classification model trained by the data classification unit.
Optionally, for each of the sample devices:
the data marking unit is specifically configured to mark the feature data of the sample device acquired by the data acquisition module as first data, and mark the feature data of the target device acquired by the data acquisition module as second data;
the data classification unit is specifically configured to train a classification model according to the first data and the second data labeled by the data labeling unit, where the classification model is a classification model based on joint learning;
the data calculation unit is specifically configured to calculate a weight of each piece of feature data of the sample device according to the classification model trained by the data classification unit, where a calculation formula of the weight is as follows:
wherein, ω isiIs the weight of the ith piece of data in the first data, P1iIs the probability, P, that the ith piece of data belongs to the sample device2iIs the probability that the ith piece of data belongs to the target device.
Optionally, the local model training module is specifically configured to train, according to the feature data of each sample device, the weight of each feature data of the sample device, and the fault data of each sample device, on the training data set with the weight of the sample device by using a neural network, respectively, to obtain the fault prediction local model of the target device.
Optionally, the joint model establishing module is specifically configured to use a joint learning algorithm to iterate repeatedly according to the local fault prediction model to obtain a joint model of the sample device on the training data set with respect to the target device.
Optionally, the target device and each sample device are edge nodes in the internet of things, the feature data of the target device is not exposed to other sample devices, and the feature data and the fault data of each sample device are not exposed to other sample devices and the target device.
In a third aspect, embodiments of the present invention provide a readable storage medium having executable instructions thereon, which when executed, cause a computer to perform the operations as included in the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computing device, including: one or more processors, memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors to perform the operations included in the first aspect.
Compared with the prior art, the invention has at least the following beneficial effects:
because different equipment data are distributed at different nodes of the Internet of things, and a shared data training model can generate a data security problem, the invention adopts a sample migration method based on a joint learning mode for equipment predictive maintenance, can jointly learn data acquired from a plurality of pieces of equipment and migrate the data to target equipment for training a predictive maintenance model aiming at the target equipment, realizes multi-party joint learning, ensures that all data are not out of local, and avoids the data security problem caused by directly sharing data. And additional advantages will be set forth in the detailed description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for predicting a failure of a device according to an embodiment of the present invention;
FIG. 2 is a flow chart of another method for predicting a failure of a device according to an embodiment of the present invention;
fig. 3 is a block diagram of a device failure prediction apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention, and based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts belong to the scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides an apparatus failure prediction method, where the apparatus failure prediction method includes:
acquiring a training data set for establishing a prediction model for target equipment according to the attribute of the target equipment, wherein sample data in the data set is shared data;
calculating the weight of each sample data in the training data set;
training by using the weight to obtain a fault prediction local model of the target equipment;
establishing a joint model based on the fault prediction local model and a joint learning algorithm;
and performing fault prediction on the target equipment according to the combined model.
In this embodiment, the sample data in the training data set includes feature data of the target device, feature data of the sample device, and fault data of the sample device; the sample device is a device related or similar to the target device. The fault prediction local model and the joint model are the relationship between the characteristic data of the equipment and the fault of the equipment. The embodiment adopts a sample migration method based on a joint learning mode, is used for equipment predictive maintenance, can jointly learn data acquired from a plurality of pieces of equipment and migrate the data to target equipment, is used for training a predictive maintenance model aiming at the target equipment, realizes multi-party joint learning, ensures that data of all parties are not local, and avoids the data security problem caused by directly sharing the data.
In one embodiment of the present invention, the calculating the weight of each sample data in the training data set includes, for each of the sample devices:
distinguishing the characteristic data of the sample device from the characteristic data of the target device;
training a classification model according to the distinguished characteristic data;
and calculating the weight of each piece of feature data of the sample equipment according to the trained classification model.
Because the sample device and the device to be predicted can be respectively distributed at any node in the internet of things, the data of the sample device and the device to be predicted cannot be shared in order to ensure the data privacy. Therefore, a classification model based on joint learning, such as the XGBoost model based on joint learning, may be employed in this embodiment.
In one embodiment of the present invention, the calculating the weight of each sample data in the training data set includes, for each of the sample devices:
marking the characteristic data of the sample device as first data, and marking the characteristic data of the device to be predicted as second data;
training a classification model according to the first data and the second data, wherein the classification model is based on joint learning;
calculating the weight of each piece of feature data of the sample equipment according to the trained classification model, wherein the calculation formula of the weight is as follows:
wherein, ω isiIs the weight of the ith piece of data in the first data, P1iIs the probability, P, that the ith piece of data belongs to the sample device2iIs the probability that the ith piece of data belongs to the target device.
In an embodiment of the present invention, the training to obtain the local model of the target device for the fault prediction by using the weight includes:
and training on the training data set with the weight of the sample equipment by using a neural network respectively according to the feature data of each sample equipment, the weight of each feature data of the sample equipment and the fault data of each sample equipment to obtain a local fault prediction model of the target equipment.
In an embodiment of the present invention, the building a joint model based on the local fault prediction model and a joint learning algorithm includes:
and according to the fault prediction local model, repeatedly iterating by using a joint learning algorithm to obtain a joint model of the sample equipment on the training data set relative to the target equipment.
In an embodiment of the present invention, the target device and each of the sample devices are edge nodes in the internet of things, the feature data of the target device is not exposed to other sample devices, and the feature data and the fault data of each of the sample devices are not exposed to other sample devices and the target device.
As shown in fig. 2, an embodiment of the present invention provides an apparatus failure prediction method, where the apparatus failure prediction method includes:
s1, acquiring sensor characteristic data of each sample device and corresponding fault data; collecting sensor characteristic data of target equipment;
s2, respectively labeling the characteristic data of the target equipment and the sample equipment to obtain label data;
s3 training a classifier (second classification) by adopting a joint learning mode based on the label data of the step S2;
s4 calculating the weight of the sample device feature data according to the classifier of the step S3;
s5 repeating the above steps to calculate the weight of each sample device feature data;
s6, based on the data of each sample device, establishing the relationship between the sensor characteristic data and the device failure by adopting a joint learning mode;
s7, the model of the step S6 is used for predicting the failure probability of the target equipment.
Assume feature data with various stations such as device A, B, C, and corresponding fault labels, i.e., all feature data and fault data (label data) with device A, B, C; meanwhile, the feature data of the same measuring point of the device D, that is, all the feature data of the device D, do not have fault data, and the fault occurrence probability of the device D needs to be predicted according to the feature data.
The goal is to learn a probabilistic model that predicts the failure of device D using the signature data of device A, B, C, the failure data, and the signature data of device D for failure prediction of device D.
It should be noted that in the process, it is assumed that A, B, C, D and the like are edge nodes in the internet of things, each party has data privacy and security requirements, and neither the characteristic data nor the fault data of the party can be exposed to the outside in the training process.
In this embodiment, the device failure prediction method includes:
1. collecting training data set the training data set includes all of the characteristic data of device A, B, C, as well as fault data, as well as characteristic data of device D;
2. the weight of each piece of feature data of the device A, B, C is calculated, taking the device a as an example, and the cases of B and C are the same, and the calculation steps are as follows:
a) labeling the characteristic data of the equipment A and the equipment D, and assuming that the label of the equipment A is 0 and the label of the equipment D is 1;
b) training a classifier (second classification) based on the label data of the device A and the device D (in this example, a joint learning-based XGboost model is used, and in practice, any joint learning-based probabilistic classification model can be used without using the XGboost);
c) for each piece of data x in the device A, calculating the probability P that the data x belongs to the device A according to the trained binary classifierA(x) And belong to the device D probability PD(x) (ii) a Calculating the weight of data x, ω (x) PD(x)/PA(x)；
3. Training model
a) The characteristic data and the fault data of the device A, B, C and the corresponding weight of each characteristic data are obtained through the steps;
b) training a local model, and respectively training on the weighted data set of the device A, B, C by using a neural network or a related regression algorithm to obtain a fault prediction local model of the device D (the specific training process is a standard process and is not described again);
c) a computational combination model based on the above-described fault prediction local model of device D trained on the device A, B, C dataset; iterative iterations using model averaging (joint learning algorithm) to compute a joint model for device D fault prediction on the device A, B, C dataset, i.e., a fault prediction model; in this embodiment, the number of iterations is determined by the preset accuracy of the model and the preset number of iterations.
4. And using the obtained combined model for the fault prediction of the equipment D.
In this embodiment, it is assumed that the device A, B, C participates in joint training, and in practice, the number of joint devices is not limited.
It should be noted that the device failure data mentioned in the present invention may be replaced with the remaining service life of the device, so as to predict the remaining service life of the device.
As shown in fig. 3, an embodiment of the present invention provides an apparatus failure prediction device, where the apparatus failure prediction device includes: a data acquisition module, a weight calculation module, a local model training module, a combined model establishing module and a fault prediction module, wherein,
the data acquisition module is used for acquiring a training data set used for establishing a prediction model for target equipment according to the attribute of the target equipment, wherein sample data in the data set is shared data;
the weight calculation module is used for calculating the weight of each sample data in the training data set;
the local model training module is used for obtaining a fault prediction local model of the target equipment by utilizing the weight training;
the joint model establishing module is used for establishing a joint model based on the fault prediction local model and a joint learning algorithm;
and the fault prediction module is used for carrying out fault prediction on the target equipment according to the combined model.
In one embodiment of the present invention, the sample data in the training data set includes feature data of a target device, feature data of a sample device, and fault data of the sample device; the sample device is a device related or similar to the target device.
In one embodiment of the present invention, the weight calculation module includes a data labeling unit, a data classifying unit, and a data calculating unit, wherein, for each of the sample devices,
the data marking unit is used for distinguishing the characteristic data of the sample device acquired by the data acquisition module from the characteristic data of the target device;
the data classification unit is used for training a classification model according to the characteristic data distinguished by the data marking unit;
and the data calculation unit is used for calculating the weight of each piece of characteristic data of the sample equipment according to the classification model trained by the data classification unit.
In one embodiment of the invention, for each of the sample devices:
the data marking unit is specifically configured to mark the feature data of the sample device acquired by the data acquisition module as first data, and mark the feature data of the target device acquired by the data acquisition module as second data;
the data classification unit is specifically configured to train a classification model according to the first data and the second data labeled by the data labeling unit, where the classification model is a classification model based on joint learning;
the data calculation unit is specifically configured to calculate a weight of each piece of feature data of the sample device according to the classification model trained by the data classification unit, where a calculation formula of the weight is as follows:
wherein, ω isiIs the weight of the ith piece of data in the first data, P1iIs the probability, P, that the ith piece of data belongs to the sample device2iIs the probability that the ith piece of data belongs to the target device.
In an embodiment of the present invention, the local model training module is specifically configured to train, according to the feature data of each sample device, the weight of each feature data of the sample device, and the fault data of each sample device, on the training data set with weights of the sample devices by using a neural network, respectively, to obtain the fault prediction local model of the target device.
In an embodiment of the present invention, the joint model building module is specifically configured to obtain, according to the local fault prediction model, a joint model of the sample device on the training data set with respect to the target device by using a joint learning algorithm through repeated iteration.
In an embodiment of the present invention, the target device and each of the sample devices are edge nodes in the internet of things, the feature data of the target device is not exposed to other sample devices, and the feature data and the fault data of each of the sample devices are not exposed to other sample devices and the target device.
The information interaction, execution process and other contents between the modules and units in the device are based on the same concept as the method embodiment of the present invention, and specific contents can be referred to the description in the method embodiment of the present invention, and are not described herein again.
It should be understood that the various techniques described herein may be implemented in connection with hardware or software or, alternatively, with a combination of both. Thus, the methods and apparatus of the present invention, or certain aspects or portions thereof, may take the form of program code (i.e., instructions) embodied in tangible media, such as floppy diskettes, CD-ROMs, hard drives, or any other machine-readable storage medium, wherein, when the program is loaded into and executed by a machine, such as a computer, the machine becomes an apparatus for practicing the invention.
In the case of program code execution on programmable computers, the computing device will generally include a processor, a storage medium readable by the processor (including volatile and non-volatile memory and/or storage elements), at least one input device, and at least one output device. Wherein the memory is configured to store program code; the processor is configured to perform the various methods of the present invention according to instructions in the program code stored in the memory.
By way of example, and not limitation, computer readable media may comprise computer storage media and communication media. Computer-readable media includes both computer storage media and communication media. Computer storage media store information such as computer readable instructions, data structures, program modules or other data. Communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. Combinations of any of the above are also included within the scope of computer readable media.
It should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the method of the invention should not be construed to reflect the intent: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing inventive embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules or units or components of the apparatus in the examples invented herein may be arranged in an apparatus as described in this embodiment or alternatively may be located in one or more apparatuses different from the apparatus in this example. The modules in the foregoing examples may be combined into one module or may be further divided into multiple sub-modules.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features of the invention in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so invented, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature of the invention in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
Furthermore, some of the described embodiments are described herein as a method or combination of method elements that can be performed by a processor of a computer system or by other means of performing the described functions. A processor having the necessary instructions for carrying out the method or method elements thus forms a means for carrying out the method or method elements. Further, the elements of the apparatus embodiments described herein are examples of the following apparatus: the apparatus is used to implement the functions performed by the elements for the purpose of carrying out the invention.
As used herein, unless otherwise specified the use of the ordinal adjectives "first", "second", "third", etc., to describe a common object, merely indicate that different instances of like objects are being referred to, and are not intended to imply that the objects so described must be in a given sequence, either temporally, spatially, in ranking, or in any other manner.
While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of this description, will appreciate that other embodiments can be devised which do not depart from the scope of the invention as described herein. Furthermore, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The present invention is to be considered as illustrative and not restrictive in character, with the scope of the invention being indicated by the appended claims.
Claims (10)
1. An apparatus failure prediction method, comprising:
acquiring a training data set for establishing a prediction model for target equipment according to the attribute of the target equipment, wherein sample data in the data set is shared data;
calculating the weight of each sample data in the training data set;
training by using the weight to obtain a fault prediction local model of the target equipment;
establishing a joint model based on the fault prediction local model and a joint learning algorithm;
and performing fault prediction on the target equipment according to the combined model.
2. The device failure prediction method according to claim 1, wherein the sample data in the training data set includes feature data of a target device, feature data of a sample device, and failure data of the sample device; the sample device is a device related or similar to the target device.
3. The method of claim 2, wherein the calculating the weight for each sample data in the training data set comprises, for each of the sample devices:
distinguishing the characteristic data of the sample device from the characteristic data of the target device;
training a classification model according to the distinguished characteristic data;
and calculating the weight of each piece of feature data of the sample equipment according to the trained classification model.
4. The method of claim 3, wherein the calculating the weight for each sample data in the training data set comprises, for each of the sample devices:
marking the characteristic data of the sample device as first data, and marking the characteristic data of the target device as second data;
training a classification model according to the first data and the second data, wherein the classification model is based on joint learning;
calculating the weight of each piece of feature data of the sample equipment according to the trained classification model, wherein the calculation formula of the weight is as follows:
wherein, ω isiIs the weight of the ith piece of data in the first data, P1iIs the probability, P, that the ith piece of data belongs to the sample device2iIs the probability that the ith piece of data belongs to the target device.
5. The device failure prediction method according to claim 2, wherein the training with the weights to obtain the failure prediction local model of the target device comprises:
and training on the training data set with the weight of the sample equipment by using a neural network respectively according to the feature data of each sample equipment, the weight of each feature data of the sample equipment and the fault data of each sample equipment to obtain a local fault prediction model of the target equipment.
6. The method according to claim 5, wherein the building a joint model based on the local fault prediction model and a joint learning algorithm comprises:
and according to the fault prediction local model, repeatedly iterating by using a joint learning algorithm to obtain a joint model of the sample equipment on the training data set relative to the target equipment.
7. The device failure prediction method according to claim 2, wherein the target device and each of the sample devices are edge nodes in the internet of things, the feature data of the target device is not exposed to the other sample devices, and the feature data and the failure data of each of the sample devices are not exposed to the other sample devices and the target device.
8. An apparatus for predicting a failure of a device, comprising: a data acquisition module, a weight calculation module, a local model training module, a combined model establishing module and a fault prediction module, wherein,
the data acquisition module is used for acquiring a training data set used for establishing a prediction model for target equipment according to the attribute of the target equipment, wherein sample data in the data set is shared data;
the weight calculation module is used for calculating the weight of each sample data in the training data set;
the local model training module is used for obtaining a fault prediction local model of the target equipment by utilizing the weight training;
the joint model establishing module is used for establishing a joint model based on the fault prediction local model and a joint learning algorithm;
and the fault prediction module is used for carrying out fault prediction on the target equipment according to the combined model.
9. A readable storage medium having executable instructions thereon that, when executed, cause a computer to perform operations as recited in any of claims 1-7.
10. A computing device, comprising: one or more processors, memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors to perform the operations included in any of claims 1-7.
Priority Applications (5)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011010347.6A CN114298362A (en) | 2020-09-23 | 2020-09-23 | Equipment fault prediction method and device, readable storage medium and computing equipment |
| PCT/CN2021/101314 WO2022062502A1 (en) | 2020-09-23 | 2021-06-21 | Prediction method and apparatus, readable medium, and electronic device |
| JP2022564514A JP2023543100A (en) | 2020-09-23 | 2021-06-21 | Prediction methods, devices, readable media and electronic devices |
| EP21870883.2A EP4131094A4 (en) | 2020-09-23 | 2021-06-21 | Prediction method and apparatus, readable medium, and electronic device |
| US18/050,055 US20230070276A1 (en) | 2020-09-23 | 2022-10-27 | Prediction method and apparatus, readable medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011010347.6A CN114298362A (en) | 2020-09-23 | 2020-09-23 | Equipment fault prediction method and device, readable storage medium and computing equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114298362A true CN114298362A (en) | 2022-04-08 |
Family
ID=80964636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011010347.6A Pending CN114298362A (en) | 2020-09-23 | 2020-09-23 | Equipment fault prediction method and device, readable storage medium and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114298362A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115310561A (en) * | 2022-09-29 | 2022-11-08 | 中国空气动力研究与发展中心设备设计与测试技术研究所 | Electromagnetic valve fault monitoring method based on integrated instant learning |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107025153A (en) * | 2016-01-29 | 2017-08-08 | 阿里巴巴集团控股有限公司 | The failure prediction method and device of disk |
| CN110335168A (en) * | 2019-04-22 | 2019-10-15 | 山东大学 | Method and system based on GRU optimization power information acquisition terminal fault prediction model |
| CN110603547A (en) * | 2017-03-02 | 2019-12-20 | 约翰霍普金斯大学 | Medical adverse event prediction, reporting and prevention |
| CN111090631A (en) * | 2020-03-24 | 2020-05-01 | 中国人民解放军国防科技大学 | Information sharing method and device under distributed environment and electronic equipment |
| CN111314113A (en) * | 2020-01-19 | 2020-06-19 | 赣江新区智慧物联研究院有限公司 | Internet of things node fault detection method and device, storage medium and computer equipment |
-
2020
- 2020-09-23 CN CN202011010347.6A patent/CN114298362A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107025153A (en) * | 2016-01-29 | 2017-08-08 | 阿里巴巴集团控股有限公司 | The failure prediction method and device of disk |
| CN110603547A (en) * | 2017-03-02 | 2019-12-20 | 约翰霍普金斯大学 | Medical adverse event prediction, reporting and prevention |
| CN110335168A (en) * | 2019-04-22 | 2019-10-15 | 山东大学 | Method and system based on GRU optimization power information acquisition terminal fault prediction model |
| CN111314113A (en) * | 2020-01-19 | 2020-06-19 | 赣江新区智慧物联研究院有限公司 | Internet of things node fault detection method and device, storage medium and computer equipment |
| CN111090631A (en) * | 2020-03-24 | 2020-05-01 | 中国人民解放军国防科技大学 | Information sharing method and device under distributed environment and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115310561A (en) * | 2022-09-29 | 2022-11-08 | 中国空气动力研究与发展中心设备设计与测试技术研究所 | Electromagnetic valve fault monitoring method based on integrated instant learning |
| CN115310561B (en) * | 2022-09-29 | 2022-12-20 | 中国空气动力研究与发展中心设备设计与测试技术研究所 | Electromagnetic valve fault monitoring method based on integrated instant learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112257774B (en) | Target detection method, device, equipment and storage medium based on federal learning | |
| US8473432B2 (en) | Issue resolution in expert networks | |
| WO2019224694A1 (en) | Anomaly detection | |
| CN112801718B (en) | User behavior prediction method, device, equipment and medium | |
| JP7310718B2 (en) | Road obstacle detection device, road obstacle detection method, and road obstacle detection program | |
| AU2021309929B2 (en) | Anomaly detection in network topology | |
| US20220180240A1 (en) | Transaction composition graph node embedding | |
| US20230334375A1 (en) | Machine learning model error detection | |
| CN114707644A (en) | Method and device for training graph neural network | |
| US11488083B2 (en) | Risk failure prediction for line assets | |
| CN114298362A (en) | Equipment fault prediction method and device, readable storage medium and computing equipment | |
| Karimzadeh et al. | Optimal clustering of pavement segments using K-prototype algorithm in a high-dimensional mixed feature space | |
| CN115049836B (en) | Image segmentation method, device, equipment and storage medium | |
| CN115952438B (en) | Social platform user attribute prediction method, system, mobile device and storage medium | |
| Tsai et al. | Simulation optimization in security screening systems subject to budget and waiting time constraints | |
| US20200380446A1 (en) | Artificial Intelligence Based Job Wages Benchmarks | |
| US20240070269A1 (en) | Automatic selection of data for target monitoring | |
| US20230342594A1 (en) | Artificial intelligence based system and method for recognition of dimensional information within engineering drawings | |
| US20230052540A1 (en) | Trend-informed demand forecasting | |
| Datta | Predicting bike-share usage patterns with machine learning | |
| CN115239958A (en) | Wheel hub damage detection method based on artificial intelligence and related equipment | |
| US10915711B2 (en) | Numerical representation in natural language processing techniques | |
| CN114841355A (en) | Joint learning method and system based on attention mechanism | |
| CN114298363A (en) | Method and device for measuring oxygen content in boiler flue gas | |
| Abassi et al. | Iterative aggregation of crowdsourced tasks within the belief function theory |
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 |