WO2022257925A1

WO2022257925A1 - Fault prediction method and apparatus based on digital twin, server, and storage medium

Info

Publication number: WO2022257925A1
Application number: PCT/CN2022/097396
Authority: WO
Inventors: 崔岩; 常青玲; 侯宇灿; 揭英达
Original assignee: 五邑大学; 广东四维看看智能设备有限公司; 中德（珠海）人工智能研究院有限公司; 珠海市四维时代网络科技有限公司
Priority date: 2021-06-09
Filing date: 2022-06-07
Publication date: 2022-12-15
Also published as: CN113379123A

Abstract

The present application is applicable to the technical field of data mapping, and provides a fault prediction method and apparatus based on digital twin, a server, and a storage medium. The method comprises: obtaining real-time data of a target real object; generating a digital twin virtual object according to the real-time data; obtaining simulation data in a digital twin virtual model; and obtaining a fault prediction result according to the simulation data and a pre-trained fault prediction model. Hence, in embodiments of the present application, accurate fault prediction of a real object (such as a production line or a workshop) can be realized by means of a combination of the digital twin technology and unsupervised learning characteristics of the pre-trained fault prediction model.

Description

Fault prediction method, device, server and storage medium based on digital twin

technical field

The present application belongs to the technical field of data mapping, and in particular relates to a digital twin-based fault prediction method, device, server and storage medium.

Background technique

With the introduction of the concept of "Industry 4.0", factories have higher and higher demand for intelligent production lines, but most production lines are not intelligent enough. In the prior art, a post-alarm method is generally used to provide fault prompts for production line faults, but such post-alarm fault prompts can only reduce the impact of production line faults.

Contents of the invention

The embodiment of the present application provides a fault prediction method, device, server, and storage medium based on digital twins to realize early prediction of production line faults.

In the first aspect, the embodiment of the present application provides a fault prediction method based on digital twins, including:

Obtain real-time data of the target real object;

generating a digital twin virtual object based on said real-time data;

Obtain the simulation data in the digital twin virtual model;

According to the simulation data and the pre-trained fault prediction model, a fault prediction result is obtained.

In a possible implementation manner of the first aspect, the simulation data is input into a pre-trained fault prediction model, and before the fault prediction result is obtained, the method further includes:

Obtain real-time training data of the target real object;

extracting fault data in the real-time data sample;

Import the fault data into the preset fault prediction model for training to obtain a pre-trained fault prediction model.

In a possible implementation manner of the first aspect, extracting the fault data in the real-time data includes:

The fault data in the real-time training data is extracted according to a preset fault data extraction model.

In a possible implementation manner of the first aspect, the pre-trained fault prediction model includes a generation network and a discrimination network;

Import the fault data into the preset fault prediction model for training to obtain a pre-trained fault prediction model, including:

generate noisy data;

importing the noise data into the generating network to obtain false sample data;

The fault data is used as real data, the real data and the fake sample data are used as input, and the discrimination result is used as the output, and the discrimination result is used as the feedback input of the generation network, and according to the preset objective function The discrimination network and the generation network are trained to obtain a pre-trained fault prediction model.

In a possible implementation of the first aspect, the preset objective function is:

in,

Represents the preset objective function, D represents the generation network, G represents the confrontation network, E represents the expected function, x represents the fault data, x～pdata(x) represents the fault data obeys the pdata(x) distribution, z represents the noise data, z～ p _(z) indicates that the noise data obeys the p _(z) distribution, D(x) indicates the output data after the fault data is imported into the generation network, and G(z) indicates the output data after the noise data is imported into the judgment network.

In a possible implementation manner of the first aspect, the fault prediction result is obtained according to the simulation data and the pre-trained fault prediction model, including:

The simulation data and the data generated by the generating network according to the noise data are imported into the discriminant network, and the fault prediction result is output.

In a possible implementation manner of the first aspect, after the fault prediction result is obtained according to the simulation data and the pre-trained fault prediction model, the method further includes:

registering the simulation data and the failure prediction results;

Sending the registered simulation data and fault prediction results to the user terminal to instruct the user terminal to generate a monitoring screen according to the registered simulation data and fault prediction results, and display the monitoring screen to the user.

In the second aspect, the embodiment of the present application provides a digital twin-based fault prediction device, including:

The first acquisition module is used to acquire the real-time data of the target real object;

A generating module, configured to generate a digital twin virtual object according to the real-time data;

The second acquisition module, the simulation data in the digital twin virtual model;

The fault prediction module is used to obtain the fault prediction result according to the simulation data and the pre-trained fault prediction model.

In a possible implementation manner, the device further includes:

The third obtaining module is used to obtain the real-time training data of the target real object;

An extraction module, configured to extract fault data in the real-time data samples;

The training module is used to import fault data into a preset fault prediction model for training to obtain a pre-trained fault prediction model.

In a possible implementation manner, the extraction module includes:

The extraction unit is configured to extract fault data in the real-time training data according to a preset fault data extraction model.

In a possible implementation manner, the pre-trained fault prediction model includes a generation network and a discrimination network;

The training modules include:

generate noisy data;

In a possible implementation manner, the preset objective function is:

in,

In a possible implementation manner, the fault prediction module includes:

The fault prediction unit is used to import the simulation data and the data generated by the generation network according to the noise data into the discrimination network, and output a fault prediction result.

In a possible implementation manner, the digital twin-based fault diagnosis equipment further includes:

The registration module is used to register simulation data and fault prediction results.

A sending module, configured to send the registered simulation data and fault prediction results to the user terminal to instruct the user terminal to display a monitoring picture to the user, the monitoring picture including the operating status of the target real object and the marked fault prediction analyze.

In a third aspect, an embodiment of the present application provides a server, including a memory, a processor, and a computer program stored in the memory and operable on the processor, and the computer program is implemented when the processor executes the computer program. The method as described in the first aspect above.

In a fourth aspect, an embodiment of the present application provides a storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method as described in the first aspect above is implemented.

Compared with the prior art, the embodiments of the present application have the following beneficial effects:

In the embodiment of this application, by obtaining real-time data of the target real object, a digital twin virtual object is generated according to the real-time data, the simulation data in the digital twin virtual model is obtained, and the fault prediction result is obtained according to the simulation data and the pre-trained fault prediction model . It can be seen that the embodiment of the present application can achieve the effect of accurate fault prediction for real objects (such as production lines or workshops, etc.) by combining the digital twin technology with the unsupervised learning characteristics of the pre-trained fault prediction model.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the accompanying drawings that need to be used in the descriptions of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings in the following description are only for the present application For some embodiments, those of ordinary skill in the art can also obtain other drawings based on these drawings without paying creative efforts.

FIG. 1 is a schematic flow diagram of a digital twin-based fault prediction method provided in an embodiment of the present application;

Fig. 2 is a schematic flow chart before step S108 in Fig. 1 of the digital twin-based fault prediction method provided by the embodiment of the present application;

Fig. 3 is a specific implementation flowchart of step S206 in Fig. 2 of the digital twin-based fault prediction method provided by the embodiment of the present application;

Fig. 4 is a schematic flow chart after step S204 in Fig. 2 of the digital twin-based fault prediction method provided by the embodiment of the present application;

FIG. 5 is a schematic structural diagram of a digital twin-based fault prediction device provided by an embodiment of the present application;

FIG. 6 is a schematic structural diagram of a server provided by an embodiment of the present application;

Fig. 7 is the training process of the fault prediction model of the digital twin-based fault prediction method provided by the embodiment of the present application.

Detailed ways

In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments without 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 application with unnecessary detail.

It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and/or components, but does not exclude one or more other Presence or addition of features, wholes, steps, operations, elements, components and/or collections thereof.

It should also be understood that the term "and/or" used in the description of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

As used in this specification and the appended claims, the term "if" may be construed, depending on the context, as "when" or "once" or "in response to determining" or "in response to detecting ". Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be construed, depending on the context, to mean "once determined" or "in response to the determination" or "once detected [the described condition or event] ]” or “in response to detection of [described condition or event]”.

In addition, in the description of the specification and appended claims of the present application, the terms "first", "second", "third" and so on are only used to distinguish descriptions, and should not be understood as indicating or implying relative importance.

Reference to "one embodiment" or "some embodiments" or the like in the specification of the present application means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in other embodiments," etc. in various places in this specification are not necessarily All refer to the same embodiment, but mean "one or more but not all embodiments" unless specifically stated otherwise. The terms "including", "comprising", "having" and variations thereof mean "including but not limited to", unless specifically stated otherwise.

In order to facilitate the understanding of the embodiments of the present application, the following explains the concepts of names involved in the embodiments of the present application:

Digital twin: Digital twin is a simulation process that makes full use of data such as physical models, sensor updates, and operating history, integrates multi-disciplinary, multi-physical quantities, multi-scale, and multi-probability, and completes the mapping in the virtual space to reflect the corresponding physical equipment. whole life cycle process. A digital twin is a concept beyond reality that can be viewed as a digital twin of one or more important, interdependent equipment systems.

The technical solutions provided by the embodiments of the present application will be introduced below through specific embodiments.

Referring to FIG. 1 , it is a schematic flow diagram of a digital twin-based fault prediction method provided by the embodiment of the present application. As an example and not a limitation, the method can be applied to a server connected to a sensor set on a target real object. The server may be a computing device such as a cloud server, and the method may include the following steps:

Step S102, acquiring real-time data of the target real object.

Wherein, the target real object refers to a real-world production line or workshop, etc., and real-time data includes static data (such as equipment parameters) and dynamic data (such as equipment operating status). In a specific application, the real-time data of the target real object is collected through sensors installed on various devices in the production line or workshop.

Step S104, generating a digital twin virtual object according to the real-time data.

Among them, the digital twin virtual object refers to the digital twin corresponding to the target real object. In specific applications, an editable logic controller is used to generate digital twin virtual objects based on real-time data.

Step S106, acquiring simulation data in the digital twin virtual model.

Among them, the simulation data refers to the data generated by the digital twin virtual model to dynamically map the operating conditions of the target real object according to the real-time data.

Step S108 , according to the simulation data and the pre-trained fault prediction model, a fault prediction result is obtained.

Among them, the pre-trained fault prediction model includes a generative network and a discriminative network.

In a specific application, the fault prediction result is obtained according to the simulation data and the pre-trained fault prediction model, including: importing the simulation data and the data generated by the generation network based on the noise data into the discriminant network, and outputting the fault prediction result.

Among them, the fault prediction result is the fault equipment number, fault type, fault cause and fault time.

It can be understood that, in the embodiment of the present application, the simulation data and the data generated by the generation network based on the noise data are judged as real data or generated samples according to the discrimination network, so as to determine the fault data in the simulation data as the fault prediction result.

In an optional implementation, as shown in Figure 2, the embodiment of the present application provides a schematic flow chart before step S108 in Figure 1 of the digital twin-based fault prediction method, based on simulation data and pre-trained fault prediction The model, before getting the fault prediction results, also includes:

Step S202, acquiring real-time training data of the target real object.

Among them, real-time training data is obtained from open source datasets.

Step S204, extracting fault data in the real-time training data.

Wherein, the fault data includes fault equipment number, fault type, fault content and fault time.

In the specific application, according to the fault data extraction model, the named entity recognition is directly carried out on the real-time data, and the fault equipment number, fault type, fault content and fault time in the entity data are extracted.

Among them, the fault data extraction model can be trained on the basis of Bi-LSTM+CRF neural network. Exemplarily, the process of training the fault data extraction model on the Bi-LSTM+CRF neural network can be:

1. Label each word in the real-time training data to obtain the label type of each word in the real-time training data, for example, perform BIO labeling on each word in the real-time training data to obtain the BIO label type of each word. What needs to be understood here is that the so-called BIO annotation is to mark each element as "B-X", "I-X" or "O", where "B-X" means that the segment where this element is located belongs to the X type and this element is in this segment. At the beginning, "I-X" indicates that the segment where the element is located belongs to the X type and the element is in the middle of the segment, "O" indicates that it does not belong to any type, and "X" is the category to which the keyword belongs. The category of the embodiment of this application is Faulty equipment number, fault type, fault content and fault time, etc.

2. Input the labeled real-time training data into the Bi-LSTM neural network model, divide the real-time training data into data segments, each data segment is expressed as x=(x1,x2,...,xn), where n represents The number of words contained in the data segment, x{i} represents the id of the i-th word in the data segment in the dictionary, and then the one-hot vector of each word can be obtained, and the dimension is the size of the dictionary. It should be noted that the dictionary may be a pre-downloaded character dictionary file.

3. Input the data segment into the CRF neural network model to obtain the fault data corresponding to each data segment.

4. Repeat steps 1-4 above according to a preset loss function (such as an absolute value loss function) to train a Bi-LSTM neural network model and a CRF neural network model to obtain a fault data extraction model.

Step S206, importing the fault data into a preset fault prediction model for training to obtain a pre-trained fault prediction model.

In a specific application, the fault data is imported into the preset fault prediction model for training to obtain a pre-trained fault prediction model, including: importing the fault data and the data generated by the generation network based on the noise data to the discriminant network, and outputting the fault prediction result.

Specifically, as shown in FIG. 3, it is a specific implementation flow chart of step S206 in FIG. 2 of the digital twin-based fault prediction method provided by the embodiment of the present application. The fault data is imported into the preset fault prediction model for training, and the obtained Pre-trained failure prediction models, including:

Step S302, generating noise data.

Among them, the noise data is randomly generated variables, which are used to train the generation network to generate fake sample data.

Step S304, importing the noise data into the generation network to obtain fake sample data.

Among them, the generating network is preferably a naive Bayesian model.

Step S306, using the fault data as the real data, the real data and the fake sample data as the input, the discrimination result as the output, and the discrimination result as the feedback input of the generation network, and training the discrimination network and the generation network according to the preset objective function , to get the pre-trained fault prediction model.

Among them, the discriminant network is preferably a decision tree.

Specifically, the preset objective function is:

in,

Represents the preset objective function, D represents the generation network, G represents the confrontation network, E represents the expected function, X represents the fault data, x～pdata(x) represents the fault data obeys the pdata(x) distribution, z represents the noise data, z～ p _(z) indicates that the noise data obeys the p _(z) distribution, D(x) indicates the output data after the fault data is imported into the generation network, and G(z) indicates the output data after the noise data is imported into the judgment network. Exemplarily, pdata(x) distribution and p _(z) distribution may respectively refer to Gaussian distribution, uniform distribution and the like.

Schematically, for steps S302 to S306, reference may be made to the training process of the fault prediction model as shown in FIG. 7 .

In the embodiment of the present application, the named entity recognition technology is used to directly extract the fault data to train the fault prediction data, without additional manual data labeling, which reduces the difficulty of training the fault prediction model.

In another optional implementation, as shown in FIG. 4 , it is a schematic flow chart after step S204 in FIG. 2 of the digital twin-based fault prediction method provided by the embodiment of the present application. According to the simulation data, and The trained fault prediction model, after obtaining the fault prediction results, also includes:

Step S402, registering the simulation data and the fault prediction result.

Specifically, find the corresponding faulty device in the digital twin virtual model corresponding to the simulation data according to the faulty device number in the fault prediction result, and then mark the fault type, fault cause and fault time for the corresponding faulty device in the digital twin virtual model corresponding to the simulation data.

Step S404, sending the registered simulation data and fault prediction results to the user terminal to instruct the user terminal to generate a monitoring screen according to the registered simulation data and fault prediction results, and display the monitoring screen to the user.

Among them, the monitoring screen includes the equipment generation of each equipment in the digital twin virtual model, the equipment operation status and the fault prediction results of the faulty equipment.

It can be understood that, in the embodiment of the present application, the simulation data and fault prediction results are obtained by combining the digital twin technology with the pre-trained fault prediction model, and a monitoring screen is generated according to the simulation data and fault prediction results for customers to view, so as to realize the user through monitoring. The screen can check the running status of the target real object and the prediction and analysis of the faulty equipment in the target real object in real time, and detect the faulty equipment in time.

In the embodiment of the present application, by obtaining real-time data of the target real object, a digital twin virtual object is generated according to the real-time data, the simulation data in the digital twin virtual model is obtained, and the fault prediction result is obtained according to the simulation data and the pre-trained fault prediction model . It can be seen that in the embodiment of the present application, the effect of accurate fault prediction on real objects (such as production lines or workshops) can be achieved by combining the digital twin technology with the unsupervised learning characteristics of the pre-trained fault prediction model.

It should be understood that the sequence numbers of the steps in the above embodiments do not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiment of the present application.

Corresponding to the method described in the above embodiment, Fig. 5 shows a structural block diagram of the digital twin-based fault prediction device provided by the embodiment of the present application. For the convenience of description, only the parts related to the embodiment of the present application are shown.

Referring to Figure 5, the digital twin-based fault prediction device includes:

The first obtaining module 51 is used to obtain the real-time data of the target real object;

A generating module 52, configured to generate a digital twin virtual object according to the real-time data;

The second acquisition module 53, the simulation data in the digital twin virtual model;

The fault prediction module 54 is configured to obtain a fault prediction result according to the simulation data and the pre-trained fault prediction model.

In a possible implementation manner, the device further includes:

The training module is used to import the fault data into a preset fault prediction model for training to obtain a pre-trained fault prediction model.

In a possible implementation manner, the extraction module includes:

The training modules include:

generate noisy data;

In a possible implementation manner, the preset objective function is:

in,

In a possible implementation manner, the fault prediction module includes:

It should be noted that the information interaction and execution process between the above-mentioned devices/units are based on the same concept as the method embodiment of the present application, and its specific functions and technical effects can be found in the method embodiment section. I won't repeat them here.

Referring to FIG. 6 is a schematic structural diagram of a server provided by an embodiment of the present application. As shown in FIG. 6 , the server 6 of this embodiment includes: at least one processor 60, a memory 61, and a computer program 62 stored in the memory 61 and operable on the at least one processor 60, so When the processor 60 executes the computer program 62, the steps in any of the foregoing method embodiments are implemented.

The server 6 may be a computing device such as a cloud server. The server may include, but not limited to, a processor 60 and a memory 61 . Those skilled in the art can understand that Fig. 6 is only an example of server 6, and does not constitute a limitation to server 6, and may include more or less components than those shown in the figure, or combine some components, or different components, for example It may also include input and output devices, network access devices, etc.

The so-called processor 60 can be a central processing unit (Central Processing Unit, CPU), and the processor 60 can also be other general processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit) , ASIC), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, 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 61 may be an internal storage unit of the server 6 in some embodiments, such as a hard disk or memory of the server 6 . The memory 61 can also be an external storage device of the server 6 in other embodiments, such as a plug-in hard disk equipped on the server 6, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, flash memory card (Flash Card), etc. Further, the storage 61 may also include both an internal storage unit of the server 6 and an external storage device. The memory 61 is used to store operating system, application program, boot loader (BootLoader), data and other programs, such as the program code of the computer program. The memory 61 can also be used to temporarily store data that has been output or will be output.

Those skilled in the art can clearly understand that for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used for illustration. In practical applications, the above-mentioned functions can be assigned to different functional units, Completion of modules means that the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated into one processing unit, or each unit may exist separately physically, or two or more units may be integrated into one unit, and the above-mentioned integrated units may adopt hardware It can also be implemented in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the present application. For the specific working process of the units and modules in the above system, reference may be made to the corresponding process in the foregoing method embodiments, and details will not be repeated here.

The embodiment of the present application also provides a storage medium, the storage medium is a computer-readable storage medium, and the readable storage medium stores a computer program, and when the computer program is executed by a processor, it can realize the above-mentioned various method embodiments. in the steps.

If the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments in the present application can be completed by instructing related hardware through computer programs, and the computer programs can be stored in a computer-readable storage medium. The computer program When executed by a processor, the steps in the above-mentioned various method embodiments can be realized. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random-access memory (RAM, Random Access Memory), electrical carrier signals, telecommunication signals, and software distribution media. Such as U disk, mobile hard disk, magnetic disk or CD, etc. In some jurisdictions, computer readable media may not be electrical carrier signals and telecommunication signals under legislation and patent practice.

In the above-mentioned embodiments, the descriptions of each embodiment have their own emphases, and for parts that are not detailed or recorded in a certain embodiment, refer to the relevant descriptions of other embodiments.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present application.

In the embodiments provided in this application, it should be understood that the disclosed device/network device and method may be implemented in other ways. For example, the device/network device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units Or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still implement the foregoing embodiments Modifications to the technical solutions described in the examples, or equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the application, and should be included in the Within the protection scope of this application.

Claims

A method for fault prediction based on digital twins, characterized in that it includes:

Obtain real-time data of the target real object;

generating a digital twin virtual object based on said real-time data;

Obtain the simulation data in the digital twin virtual model;

According to the simulation data and the pre-trained fault prediction model, a fault prediction result is obtained.
The fault prediction method based on digital twins according to claim 1, wherein the simulation data is input into a pre-trained fault prediction model, and before the fault prediction result is obtained, it also includes:

Obtain real-time training data of the target real object;

extracting fault data in the real-time data sample;

Import the fault data into the preset fault prediction model for training to obtain a pre-trained fault prediction model.
The fault prediction method based on digital twins according to claim 2, wherein extracting the fault data in the real-time data comprises:

The fault data in the real-time training data is extracted according to a preset fault data extraction model.
The fault prediction method based on digital twins according to claim 2, wherein the pre-trained fault prediction model includes a generation network and a discrimination network;

Import the fault data into the preset fault prediction model for training to obtain a pre-trained fault prediction model, including:

generate noisy data;

importing the noise data into the generating network to obtain false sample data;

The fault data is used as real data, the real data and the fake sample data are used as input, and the discrimination result is used as the output, and the discrimination result is used as the feedback input of the generation network, and according to the preset objective function The discrimination network and the generation network are trained to obtain a pre-trained fault prediction model.
The fault prediction method based on digital twins according to claim 4, wherein the preset objective function is:

in,
Represents the preset objective function, D represents the generation network, G represents the confrontation network, E represents the expected function, x represents the fault data, x～pdata(x) represents the fault data obeys the pdata(x) distribution, z represents the noise data, z～ p (z) indicates that the noise data obeys the p (z) distribution, D(x) indicates the output data after the fault data is imported into the generation network, and G(z) indicates the output data after the noise data is imported into the judgment network.
The digital twin-based fault prediction method according to any one of claims 1 to 5, wherein the fault prediction results are obtained according to the simulation data and the pre-trained fault prediction model, including:

The simulation data and the data generated by the generating network according to the noise data are imported into the discriminant network, and the fault prediction result is output.
The digital twin-based fault prediction method according to any one of claims 1 to 5, wherein, after obtaining the fault prediction result according to the simulation data and the pre-trained fault prediction model, further comprising:

registering the simulation data and the failure prediction result;

Sending the registered simulation data and fault prediction results to the user terminal to instruct the user terminal to generate a monitoring screen according to the registered simulation data and fault prediction results, and display the monitoring screen to the user.
A fault prediction device based on digital twins, characterized in that it includes:

The first acquisition module is used to acquire the real-time data of the target real object;

A generating module, configured to generate a digital twin virtual object according to the real-time data;

The second acquisition module is used to acquire the simulation data in the digital twin virtual model;

The prediction module is used to obtain the fault prediction result according to the simulation data and the pre-trained fault prediction model.
A server, comprising a memory, a processor, and a computer program stored in the memory and operable on the processor, wherein the computer program according to claims 1 to 7 is implemented when the processor executes the computer program. any one of the methods described.
A storage medium storing a computer program, wherein the computer program implements the method according to any one of claims 1 to 7 when executed by a processor.