CN114580255A - Method for constructing residual life prediction model of equipment and terminal equipment - Google Patents
Method for constructing residual life prediction model of equipment and terminal equipment Download PDFInfo
- Publication number
- CN114580255A CN114580255A CN202011384657.4A CN202011384657A CN114580255A CN 114580255 A CN114580255 A CN 114580255A CN 202011384657 A CN202011384657 A CN 202011384657A CN 114580255 A CN114580255 A CN 114580255A
- Authority
- CN
- China
- Prior art keywords
- data
- characteristic data
- equipment
- amplification
- feature data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention is suitable for the technical field of data processing, and provides a method and a device for constructing a residual life prediction model of equipment, wherein the method comprises the following steps: obtaining representative feature data corresponding to the equipment use sample data by obtaining the equipment use sample data and performing symbol regression and horizontal federal learning according to the equipment use sample data, and further, constructing an equipment residual life prediction model according to the representative feature data. Therefore, in a scene based on symbolic regression, the invention provides a characteristic engineering scheme of using sample data by equipment in symbolic regression in a transverse federal learning scene, different nonlinear use characteristic data are constructed on the basis of combining the use characteristic data of using sample data by different equipment, the diversity of the final use characteristic data is increased, the final model effect is improved from the aspect of mining the use characteristic data more deeply, and therefore, the output accuracy of the residual life prediction model of the equipment is improved, namely, the residual life prediction accuracy of the equipment is improved.
Description
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to a method for constructing a residual life prediction model of equipment and terminal equipment.
Background
With the rise of intelligent equipment, people can not only use the equipment for production, but also use the equipment for office work and entertainment, but the habit and frequency of each person using the equipment are different, which means that the loss of the equipment is not always the same, and therefore, the estimation of the residual service life of the traditional equipment is not accurate enough.
Based on the above disadvantages, it is necessary to provide a solution for accurately calculating the remaining life of the device, so as to improve the user satisfaction.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method for constructing a device remaining life prediction model and a terminal device, so as to solve the problem in the prior art how to improve accuracy of device remaining life prediction.
The first aspect of the embodiments of the present invention provides a method for constructing a model for predicting remaining life of equipment, including:
acquiring equipment use sample data;
performing symbol regression and horizontal federal learning according to the equipment use sample data to obtain representative feature data corresponding to the equipment use sample data;
and constructing a device residual life prediction model according to the representative characteristic data.
Optionally, the device usage sample data includes usage characteristic data and a tag corresponding to the usage characteristic data; the obtaining of representative feature data corresponding to the equipment use sample data by performing symbol regression and horizontal federal learning according to the equipment use sample data includes:
performing data amplification processing on the use characteristic data to obtain a plurality of amplification use characteristic data corresponding to the use characteristic data;
determining representative feature data according to a plurality of amplification use feature data corresponding to the use feature data; wherein the representative characteristic data is amplification use characteristic data with the highest fitness of a label corresponding to the use characteristic data in a plurality of amplification use characteristic data corresponding to the use characteristic data;
judging whether an iteration condition is met; wherein the iteration condition is that the iteration screening times of the use characteristic data meet a preset threshold value;
and if the iteration condition is not met, the representative feature data is used as the use feature data, and the data amplification processing is carried out on the use feature data again to obtain a plurality of amplification use feature data corresponding to the use feature data until the iteration condition is met.
Optionally, the data amplification treatment is a random deformation combination treatment.
Optionally, the determining representative feature data according to a plurality of amplification use feature data corresponding to the use feature data includes:
calculating the fitness of the labels respectively corresponding to the plurality of amplification use characteristic data and the use characteristic data;
and determining the amplification use characteristic data with the highest fitness from the fitness corresponding to each of the plurality of amplification use characteristic data, and taking the amplification use characteristic data with the highest fitness as representative characteristic data.
Optionally, the usage characteristic data includes device index data, device usage information, and device fault information; and the label corresponding to the use characteristic data is the residual service life of the equipment.
A second aspect of the embodiments of the present invention provides a device for constructing a model for predicting remaining life of equipment, including:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring device use sample data;
the determining unit is used for performing symbol regression and horizontal federal learning according to the equipment use sample data to obtain representative feature data corresponding to the equipment use sample data;
and the construction unit is used for constructing a device residual life prediction model according to the representative characteristic data.
Optionally, the device usage sample data includes usage characteristic data and a tag corresponding to the usage characteristic data; the determining unit is specifically configured to:
performing data amplification processing on the use characteristic data to obtain a plurality of amplification use characteristic data corresponding to the use characteristic data;
determining representative feature data according to the use feature data and a plurality of amplification use feature data corresponding to the use feature data; wherein the representative feature data is the use feature data with the highest fitness of the label corresponding to the use feature data in the use feature data and the plurality of pieces of amplification use feature data corresponding to the use feature data;
judging whether an iteration condition is met; wherein the iteration condition is that the iteration screening times of the use characteristic data meet a preset threshold value;
and if the iteration condition is not met, the representative feature data is used as the use feature data, and the step of performing data amplification processing on the use feature data again to obtain a plurality of amplified use feature data corresponding to the use feature data is performed until the iteration condition is met.
Optionally, the determining unit is further specifically configured to:
calculating the fitness of the usage characteristic data and the label corresponding to the usage characteristic data;
calculating the fitness of the labels respectively corresponding to the plurality of amplification use characteristic data and the use characteristic data;
and determining the use characteristic data with the highest fitness from the fitness corresponding to the use characteristic data and the fitness corresponding to each of the plurality of amplification use characteristic data, and taking the use characteristic data with the highest fitness as representative characteristic data.
A third aspect of the embodiments of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method according to any one of the first aspect when executing the computer program.
A fourth aspect of embodiments of the present invention provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the method according to any one of the first aspect.
Compared with the prior art, the embodiment of the invention has the following beneficial effects: according to the method for constructing the model for predicting the residual life of the equipment, the representative feature data corresponding to the sample data used by the equipment is obtained by obtaining the sample data used by the equipment and performing symbol regression and horizontal federal learning according to the sample data used by the equipment, and further, the model for predicting the residual life of the equipment can be constructed according to the representative feature data. Therefore, in a scene based on symbolic regression, the invention provides a characteristic engineering scheme of using sample data by equipment in symbolic regression in a transverse federal learning scene, different nonlinear use characteristic data are constructed on the basis of combining the use characteristic data of using sample data by different equipment, the diversity of the final use characteristic data is increased, the final model effect is improved from the aspect of mining the use characteristic data more deeply, and therefore, the output accuracy of the residual life prediction model of the equipment is improved, namely, the residual life prediction accuracy of the equipment is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic flow chart of an implementation of a method for constructing a device remaining life prediction model according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an apparatus for constructing a model for predicting remaining life of a device according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a terminal device for building a device remaining life prediction model according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
Referring to fig. 1, a method for constructing a device remaining life prediction model in an embodiment of the present invention is shown, where the method may be fully applied to a terminal device (e.g., a mobile device such as a mobile phone, a notebook, an electronic communication watch, and the like), or may be fully applied to a server, or may be applied to the terminal device in partial steps, and applied to the server in partial steps. In this embodiment, the method may include, for example, the steps of:
s101: and acquiring device use sample data.
In one implementation, the device usage sample data may include usage characteristic data and a tag corresponding to the usage characteristic data, and it should be noted that the device usage sample data may include multiple sets of usage characteristic data and a tag corresponding to each set of usage characteristic data. The usage characteristic data includes device index data (such as device name, device model, device manufacturer, part model in the device, etc.), device usage information (such as device usage duration, device usage frequency, device usage environment, etc.), device failure information (such as the number of failures, the number of maintenance times, etc. of the device within a preset duration); and the label corresponding to the use characteristic data is the residual service life of the equipment.
S102: and performing symbol regression and horizontal federal learning according to the equipment use sample data to obtain representative feature data corresponding to the equipment use sample data.
Symbolic Regression (symbololic Regression) is a supervised learning method that attempts to find some hidden mathematical formula to predict target variables using characteristic variables. The advantage of symbolic regression is that symbolic systems can be modeled without relying on a priori knowledge or models.
Horizontal federal learning: federal learning (Feature-Aligned federal learning), also known as Feature alignment, i.e., the data features of participants in horizontal federal learning are Aligned; the method is suitable for the situation that the data characteristics of the participants overlap more, and the sample IDs overlap less, for example, the client data of two different regions; wherein the "horizontal" bigram is derived from a "horizontal partitioning (a.k.a.sharing)" of the data; the method combines a plurality of rows of samples with the same characteristics of a plurality of participants for federal learning, namely training data of each participant is divided horizontally and is called horizontal federal learning, and the horizontal federal learning enables the total number of training samples to be increased.
In this embodiment, the usage characteristic data may be subjected to data amplification processing to obtain a plurality of pieces of amplification usage characteristic data corresponding to the usage characteristic data (for example, 3000 pieces of amplification usage characteristic data may be amplified), and when there are a plurality of sets of usage characteristic data, one or more sets of usage characteristic data may be extracted to perform data amplification processing. In one implementation, the data amplification process is a random deformable combination process, for example, the usage characteristics data may be mutated (i.e., randomly deformed and combined), for example, when a set of usage characteristics data is: "manufacturer a + year of use + twice failed" may be combined into manufacturer a/year of use/twice failed, or (manufacturer a + model) one year of use/equipment operating environment.
Then, representative characteristic data can be determined according to a plurality of amplification use characteristic data corresponding to the use characteristic data; wherein the representative feature data is amplification use feature data having the highest fitness of a tag corresponding to the use feature data among the plurality of amplification use feature data corresponding to the use feature data. Specifically, the fitness of the labels corresponding to the usage characteristic data of the amplification usage characteristic data is calculated, for example, a correlation coefficient between the amplification usage characteristic data and the label corresponding to the usage characteristic data may be calculated, and in the case of the second classification of the labels (Y values), an IV value or the like may be calculated, that is, the predictive ability of the variant amplification usage characteristic data with respect to the Y values is evaluated); then, the amplification use characteristic data with the highest fitness among the fitness corresponding to each of the plurality of amplification use characteristic data is determined, and the amplification use characteristic data with the highest fitness is used as the representative characteristic data.
Judging whether an iteration condition is met; the iteration condition is that the iteration screening frequency using the feature data meets a preset threshold, for example, the preset threshold may be 300, and it should be noted that the preset threshold may be set according to an actual requirement.
And if the iteration condition is not met, the representative feature data is used as the use feature data, and the step of performing data amplification processing on the use feature data again to obtain a plurality of amplified use feature data corresponding to the use feature data is performed until the iteration condition is met. Thus, the winner (i.e. the representative feature data with strong prediction ability for the Y value enters the next round of inheritance); the entrants in the next round (the winner in the previous round: the representative feature data) perform cross variation or self variation (the specific variation logic can see the variation logic of symbolic regression), then perform fitness judgment on the Y value, and then inherit and perform variation, the total number of variation rounds (namely the preset threshold) is set in advance, and the final winner (namely the feature data for amplification use) is output as the representative feature data after the number of the preset threshold rounds.
S103: and constructing a device residual life prediction model according to the representative characteristic data.
After the representative feature data is obtained, that is, the representative feature data with a strong prediction capability for the label (that is, the remaining life of the device) corresponding to the use feature data is obtained, a device remaining life prediction model may be constructed based on the representative feature data, for example, a device remaining life prediction model may be constructed based on logistic regression xgboost. That is, the device remaining life prediction model may be constructed based on the relationship between the representative feature data and the label corresponding to the representative feature data (i.e., the label corresponding to the representative feature data that uses the feature data). Therefore, after receiving the use characteristic data to be predicted, the use characteristic data to be predicted can be predicted according to the constructed device residual life prediction model, and the label corresponding to the use characteristic data to be predicted, namely the device residual life, is obtained.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Compared with the prior art, the embodiment of the invention has the following beneficial effects: according to the method for constructing the model for predicting the residual life of the equipment, the representative feature data corresponding to the sample data used by the equipment is obtained by obtaining the sample data used by the equipment and performing symbol regression and horizontal federal learning according to the sample data used by the equipment, and further, the model for predicting the residual life of the equipment can be constructed according to the representative feature data. Therefore, in a scene based on symbolic regression, the invention provides a characteristic engineering scheme of using sample data by equipment in symbolic regression in a transverse federal learning scene, different nonlinear use characteristic data are constructed on the basis of combining the use characteristic data of using sample data by different equipment, the diversity of the final use characteristic data is increased, the final model effect is improved from the aspect of mining the use characteristic data more deeply, and therefore, the output accuracy of the residual life prediction model of the equipment is improved, namely, the residual life prediction accuracy of the equipment is improved.
Corresponding to the above method for constructing a model for predicting remaining life of equipment, an embodiment of the present invention provides an apparatus for constructing a model for predicting remaining life of equipment, the structure of which is shown in fig. 2, and the apparatus includes:
an obtaining unit 201, configured to obtain device usage sample data;
the determining unit 202 is configured to perform symbol regression and horizontal federal learning according to the device usage sample data to obtain representative feature data corresponding to the device usage sample data;
and the constructing unit 203 is used for constructing an equipment residual life prediction model according to the representative characteristic data.
Optionally, the device usage sample data includes usage characteristic data and a tag corresponding to the usage characteristic data; the determining unit 202 is specifically configured to:
performing data amplification processing on the use characteristic data to obtain a plurality of amplification use characteristic data corresponding to the use characteristic data;
determining representative feature data according to the use feature data and a plurality of amplification use feature data corresponding to the use feature data; wherein the representative feature data is the use feature data with the highest fitness of the label corresponding to the use feature data in the use feature data and the plurality of pieces of amplification use feature data corresponding to the use feature data;
judging whether an iteration condition is met; wherein the iteration condition is that the iteration screening times of the use characteristic data meet a preset threshold value;
and if the iteration condition is not met, the representative feature data is used as the use feature data, and the data amplification processing is carried out on the use feature data again to obtain a plurality of amplification use feature data corresponding to the use feature data until the iteration condition is met.
Optionally, the determining unit 202 is further specifically configured to:
calculating the fitness of the usage characteristic data and the label corresponding to the usage characteristic data;
calculating the fitness of the labels respectively corresponding to the plurality of amplification use characteristic data and the use characteristic data;
and determining the use characteristic data with the highest fitness from the fitness corresponding to the use characteristic data and the fitness corresponding to each of the plurality of amplification use characteristic data, and taking the use characteristic data with the highest fitness as representative characteristic data.
Optionally, the data amplification treatment is a random deformation combination treatment.
Optionally, the usage characteristic data includes device index data, device usage information, and device fault information; and the label corresponding to the use characteristic data is the residual service life of the equipment.
Fig. 3 is a schematic diagram of a device/terminal device for constructing a model for predicting remaining life of a device according to an embodiment of the present invention. As shown in fig. 3, the device/terminal apparatus 3 for constructing a device remaining life prediction model according to this embodiment includes: a processor 30, a memory 31 and a computer program 32 stored in said memory 31 and executable on said processor 30, such as a building program of a model for predicting the remaining life of a device. The processor 30, when executing the computer program 32, implements the steps in the above-described method embodiments of constructing the device remaining life prediction model, such as the steps 101 to 103 shown in fig. 1. Alternatively, the processor 30, when executing the computer program 32, implements the functions of each module/unit in each device embodiment described above, for example, the functions of the modules 201 to 203 shown in fig. 2.
Illustratively, the computer program 32 may be partitioned into one or more modules/units that are stored in the memory 31 and executed by the processor 30 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 32 in the building device/terminal device 3 of the device remaining life prediction model. For example, the computer program 32 may be divided into a synchronization module, a summary module, an acquisition module, and a return module (a module in a virtual device), and each module has the following specific functions:
the device/terminal device 3 for constructing the device remaining life prediction model may be a desktop computer, a notebook computer, a palm computer, a cloud server, or other computing devices. The device/terminal device for constructing the device remaining life prediction model may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will understand that fig. 3 is only an example of the device/terminal apparatus 3 for constructing the device remaining life prediction model, and does not constitute a limitation to the device/terminal apparatus 3 for constructing the device remaining life prediction model, and may include more or less components than those shown in the drawings, or combine some components, or different components, for example, the device/terminal apparatus for constructing the device remaining life prediction model may further include an input/output device, a network access device, a bus, etc.
The Processor 30 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 31 may be an internal storage unit of the device/terminal apparatus 3 for constructing the device remaining life prediction model, for example, a hard disk or a memory of the device/terminal apparatus 3 for constructing the device remaining life prediction model. The memory 31 may also be an external storage device of the device residual life prediction model constructing apparatus/terminal device 3, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are equipped on the device residual life prediction model constructing apparatus/terminal device 3. Further, the memory 31 may include both an internal storage unit and an external storage device of the device remaining life prediction model constructing apparatus/terminal device 3. The memory 31 is used for storing the computer program and other programs and data required for constructing the device/terminal apparatus of the device remaining life prediction model. The memory 31 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A method for constructing a residual life prediction model of equipment is characterized by comprising the following steps:
acquiring equipment use sample data;
performing symbol regression and horizontal federal learning according to the equipment use sample data to obtain representative feature data corresponding to the equipment use sample data;
and constructing a device residual life prediction model according to the representative characteristic data.
2. The method for constructing the model for predicting the residual life of the equipment according to claim 1, wherein the sample data of the use of the equipment comprises use characteristic data and a label corresponding to the use characteristic data; the obtaining of representative feature data corresponding to the equipment use sample data by performing symbol regression and horizontal federal learning according to the equipment use sample data includes:
performing data amplification processing on the use characteristic data to obtain a plurality of amplification use characteristic data corresponding to the use characteristic data;
determining representative characteristic data according to a plurality of amplification use characteristic data corresponding to the use characteristic data; wherein the representative characteristic data is amplification use characteristic data with the highest fitness of a label corresponding to the use characteristic data in a plurality of amplification use characteristic data corresponding to the use characteristic data;
judging whether an iteration condition is met; wherein the iteration condition is that the iteration screening times of the use characteristic data meet a preset threshold value;
and if the iteration condition is not met, the representative feature data is used as the use feature data, and the step of performing data amplification processing on the use feature data again to obtain a plurality of amplified use feature data corresponding to the use feature data is performed until the iteration condition is met.
3. The method for constructing the model for predicting the residual life of equipment according to claim 2, wherein the data amplification process is a random deformation combination process.
4. The method for constructing a model for predicting the remaining life of a device according to claim 2, wherein the determining representative feature data according to a plurality of amplification use feature data corresponding to the use feature data comprises:
calculating the fitness of the labels respectively corresponding to the plurality of amplification use characteristic data and the use characteristic data;
and determining the amplification use characteristic data with the highest fitness from the fitness corresponding to each of the plurality of amplification use characteristic data, and taking the amplification use characteristic data with the highest fitness as representative characteristic data.
5. The method for constructing the model for predicting the residual life of the equipment according to any one of claims 1 to 4, wherein the usage characteristic data comprises equipment index data, equipment usage information and equipment failure information; and the label corresponding to the use characteristic data is the residual service life of the equipment.
6. An apparatus for constructing a model for predicting remaining life of a device, comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring device use sample data;
the determining unit is used for performing symbol regression and horizontal federal learning according to the equipment use sample data to obtain representative feature data corresponding to the equipment use sample data;
and the construction unit is used for constructing a device residual life prediction model according to the representative characteristic data.
7. The method for constructing the model for predicting the remaining life of the equipment according to claim 6, wherein the sample data of the use of the equipment comprises use characteristic data and a label corresponding to the use characteristic data; the determining unit is specifically configured to:
performing data amplification processing on the use characteristic data to obtain a plurality of amplification use characteristic data corresponding to the use characteristic data;
determining representative feature data according to the use feature data and a plurality of amplification use feature data corresponding to the use feature data; wherein the representative feature data is the use feature data with the highest fitness of the label corresponding to the use feature data in the use feature data and the plurality of pieces of amplification use feature data corresponding to the use feature data;
judging whether an iteration condition is met; the iteration condition is that the iteration screening times of the use characteristic data meet a preset threshold value;
and if the iteration condition is not met, the representative feature data is used as the use feature data, and the step of performing data amplification processing on the use feature data again to obtain a plurality of amplified use feature data corresponding to the use feature data is performed until the iteration condition is met.
8. The method for constructing a model for predicting remaining life of equipment according to claim 7, wherein the determining unit is further specifically configured to:
calculating the fitness of the usage characteristic data and the label corresponding to the usage characteristic data;
calculating the fitness of the labels respectively corresponding to the plurality of amplification use characteristic data and the use characteristic data;
and determining the use characteristic data with the highest fitness from the fitness corresponding to the use characteristic data and the fitness corresponding to each of the plurality of amplification use characteristic data, and taking the use characteristic data with the highest fitness as representative characteristic data.
9. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 5 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011384657.4A CN114580255A (en) | 2020-11-30 | 2020-11-30 | Method for constructing residual life prediction model of equipment and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011384657.4A CN114580255A (en) | 2020-11-30 | 2020-11-30 | Method for constructing residual life prediction model of equipment and terminal equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114580255A true CN114580255A (en) | 2022-06-03 |
Family
ID=81767099
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011384657.4A Pending CN114580255A (en) | 2020-11-30 | 2020-11-30 | Method for constructing residual life prediction model of equipment and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114580255A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116257972A (en) * | 2022-11-29 | 2023-06-13 | 元始智能科技(南通)有限公司 | Equipment state evaluation method and system based on field self-adaption and federal learning |
-
2020
- 2020-11-30 CN CN202011384657.4A patent/CN114580255A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116257972A (en) * | 2022-11-29 | 2023-06-13 | 元始智能科技(南通)有限公司 | Equipment state evaluation method and system based on field self-adaption and federal learning |
| CN116257972B (en) * | 2022-11-29 | 2024-02-20 | 元始智能科技(南通)有限公司 | Equipment state evaluation method and system based on field self-adaption and federal learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111477290B (en) | Federal learning and image classification method, system and terminal for protecting user privacy | |
| CN112508118B (en) | Target object behavior prediction method aiming at data offset and related equipment thereof | |
| CN108197795B (en) | Malicious group account identification method, device, terminal and storage medium | |
| CN112990583B (en) | Method and equipment for determining model entering characteristics of data prediction model | |
| CN113591900A (en) | Identification method and device for high-demand response potential user and terminal equipment | |
| CN103593444A (en) | Network keyword recognition processing method and device | |
| CN105354721A (en) | Method and device for identifying machine operation behavior | |
| Beutner et al. | Identifiability issues of age–period and age–period–cohort models of the Lee–Carter type | |
| CN111966712A (en) | Data processing method, device, server and storage medium | |
| CN114580255A (en) | Method for constructing residual life prediction model of equipment and terminal equipment | |
| CN113592192A (en) | Short-term power load prediction method and device and terminal equipment | |
| CN111340574B (en) | Risk user identification method and device and electronic equipment | |
| CN112257111A (en) | Dynamic numerical value desensitization method, device and storage medium | |
| CN109242321B (en) | User power load online analysis method and terminal equipment | |
| CN116362894A (en) | Multi-objective learning method, multi-objective learning device, electronic equipment and computer readable storage medium | |
| CN116015811A (en) | Method, device, storage medium and electronic equipment for evaluating network security | |
| CN114356235A (en) | Data standardization processing method and device, electronic equipment and storage medium | |
| CN114090407A (en) | Interface performance early warning method based on linear regression model and related equipment thereof | |
| CN116976712A (en) | Root cause determination method, device, equipment and storage medium for abnormality index | |
| CN109977789B (en) | Method, device, computer equipment and storage medium for evaluating road performance | |
| CN109905722B (en) | Method for determining suspected node and related equipment | |
| CN110087230B (en) | Data processing method, data processing device, storage medium and electronic equipment | |
| CN115564055A (en) | Asynchronous joint learning training method and device, computer equipment and storage medium | |
| CN113139563A (en) | Optimization method and device of image classification model | |
| CN114582502A (en) | Health prediction model construction method and terminal equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |