CN117608971A - Fault detection method, device, storage medium and equipment based on digital twin - Google Patents
Fault detection method, device, storage medium and equipment based on digital twin Download PDFInfo
- Publication number
- CN117608971A CN117608971A CN202311651220.6A CN202311651220A CN117608971A CN 117608971 A CN117608971 A CN 117608971A CN 202311651220 A CN202311651220 A CN 202311651220A CN 117608971 A CN117608971 A CN 117608971A
- Authority
- CN
- China
- Prior art keywords
- target system
- digital
- operation data
- model
- initial
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 42
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 238000004458 analytical method Methods 0.000 claims abstract description 64
- 238000004088 simulation Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 7
- 230000009467 reduction Effects 0.000 claims description 7
- 238000012544 monitoring process Methods 0.000 claims description 6
- 230000003068 static effect Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 4
- 238000000034 method Methods 0.000 description 22
- 238000004891 communication Methods 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000036962 time dependent Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/302—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a software system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3089—Monitoring arrangements determined by the means or processing involved in sensing the monitored data, e.g. interfaces, connectors, sensors, probes, agents
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3447—Performance evaluation by modeling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a fault detection method, a device, a storage medium and equipment based on digital twinning, which are characterized in that an initial twinning digital model of a target system and a performance analysis model of the target system are constructed, the performance analysis model is adopted to predict operation data of the target system at the next moment based on the acquired operation data of the target system, and the prediction result is substituted into the initial twinning digital model, and whether the target system can have faults at the next moment or not can be predicted by analyzing the output result of the initial twinning digital model, so that the fault which is about to occur in the target system can be found out in time before the fault occurs, the working condition of the target system can be adjusted in a targeted manner by a user, the occurrence of the fault is prevented, and the reliability of the target system is improved.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a fault detection method, device and equipment based on digital twinning.
Background
At the moment of the rapid development of information technology, large group enterprises have the requirement of building an informatization system. To meet disaster recovery requirements, or based on cost considerations, large group enterprises typically build network rooms in multiple locations.
Meanwhile, based on different service scenes and operation and maintenance scenes, a plurality of physical devices or software devices generally exist in a machine room of a large-scale group enterprise. Common devices on hardware include hardware load balancing devices, minicomputers, enterprise-level servers, dedicated routers, and the like. Common resources on software include virtual machines, iaaS service pools, saaS servers, cloud computing resource pools and the like.
Large group enterprises can build own information systems based on the software and hardware resources so as to meet the requirements of internal and external business scenes. Because the deployment architecture of the information system is extremely complex, the fault condition of the system is difficult to discover in time.
Disclosure of Invention
In view of this, the embodiment of the invention provides a fault detection method based on digital twinning, and a fault of a target system is discovered in time.
In order to achieve the above object, the embodiment of the present invention provides the following technical solutions:
a digital twinning-based fault detection method, comprising:
constructing an initial twin digital model of the target system;
acquiring operation data of a target system;
constructing a performance analysis model of the target system based on the operation data by adopting a dynamic Bayesian network;
performing simulation prediction based on the operation data of the target system by adopting the performance analysis model to obtain predicted operation data of the target system at the next moment;
substituting the predicted operational data into the initial twin digital model;
and carrying out fault analysis based on the output result of the initial twin digital model substituted into the predicted operation data.
Optionally, in the fault detection method based on digital twinning, constructing an initial twinning digital model of the target system includes:
constructing a first initial twin digital model matched with a software part of the target system by using code static analysis and dynamic monitoring;
a second initial twin digital model is constructed that matches the hardware portion of the target system based on the state data of the target system detected by the sensor.
Optionally, in the fault detection method based on digital twinning, the operation data of the target system at least includes:
one or more of network bandwidth, CPU usage, memory usage, and disk read/write speed of the target system.
Optionally, in the fault detection method based on digital twin, a dynamic bayesian network is adopted to construct a performance analysis model of the target system based on the operation data, including:
noise reduction and filtering are carried out on the operation data;
clustering and grouping the operation data after noise reduction and filtering processing by using a clustering algorithm,
and constructing a performance analysis model of the target system based on the clustering grouping result by using a dynamic Bayesian network.
Optionally, in the fault detection method based on digital twin, after the performance analysis model of the target system is constructed based on the clustering grouping result by using a dynamic bayesian network, the method further includes:
and training the performance analysis model by utilizing the historical data of the target system.
Optionally, in the fault detection method based on digital twin, after obtaining the operation data of the target system, the method further includes:
and comparing the real-time operation data with the operation data of the initial twin digital model, and detecting whether the target system has faults or not.
A digital twinning-based fault detection device, comprising:
the initial twin digital model building unit is used for building an initial twin digital model of the target system;
the prediction model construction unit is used for acquiring the operation data of the target system; constructing a performance analysis model of the target system based on the operation data by adopting a dynamic Bayesian network;
the prediction fault analysis unit is used for performing simulation prediction based on the operation data of the target system by adopting the performance analysis model to obtain the predicted operation data of the target system at the next moment; substituting the predicted operational data into the initial twin digital model; and carrying out fault analysis based on the output result of the initial twin digital model substituted into the predicted operation data.
Optionally, in the fault detection device based on digital twinning, the initial twinning digital model building unit is specifically configured to:
constructing a first initial twin digital model matched with a software part of the target system by using code static analysis and dynamic monitoring;
a second initial twin digital model is constructed that matches the hardware portion of the target system based on the state data of the target system detected by the sensor.
A storage medium, comprising:
the storage medium having stored thereon a plurality of instructions adapted to be loaded by a processor,
to perform the steps in the digital twinning based fault detection method of any one of the preceding claims.
A fault detection device based on digital twinning comprises a memory and a processor;
the memory is used for storing programs;
the processor is configured to execute the program to implement the steps of the fault detection method based on digital twinning as described in any one of the above.
Based on the technical scheme, the scheme provided by the embodiment of the invention is that by constructing the initial twin digital model of the target system and the performance analysis model of the target system, the performance analysis model is adopted to predict the operation data of the target system at the next moment based on the acquired operation data of the target system, the prediction result is substituted into the initial twin digital model, and whether the target system fails at the next moment can be predicted by analyzing the output result of the initial twin digital model, so that the fault which is about to occur in the target system can be found in time before the fault occurs, the working condition of the target system can be adjusted in a targeted manner by a user, the occurrence of the fault is prevented, and the reliability of the target system is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a digital twinning-based fault detection method disclosed in an embodiment of the present application;
FIG. 2 is a flow chart of a digital twinning-based fault detection method disclosed in another embodiment of the present application;
FIG. 3 is a schematic structural diagram of a digital twinning-based fault detection device disclosed in an embodiment of the present application;
FIG. 4 is a schematic diagram of a physical framework of a digital twinning-based fault detection device disclosed in an embodiment of the present application;
fig. 5 is a schematic structural diagram of a digital twin-based fault detection device disclosed in an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
First, terms used in the present application will be explained:
digital twinning: digital twinning is the creation of a digital version of a "clone" on the basis of a device or system. Compared with the traditional modeling graph, the digital twin body has the greatest characteristics that: it is a dynamic simulation of physical objects. The real-time state of the entity object, as well as the external environment conditions, are reproduced on the twin body.
Machine learning: machine learning is a branch of artificial intelligence that uses algorithms and statistical models to enable computer systems to learn from data and automatically improve and optimize prediction and decision making capabilities. Through machine learning, a computer can identify and understand complex data by training patterns and rules in the sample, and classify, predict, and make decisions based on the data. Machine learning can be used in a variety of fields, such as natural language processing, computer vision, medical diagnostics, and the like
Dynamic bayesian networks: a system model in the form of a directed acyclic graph describes the time-dependent behavior of the system, reflecting the time-dependent behavior of the system.
The clustering analysis method comprises the following steps: an unsupervised learning method in which patterns can be mined by measuring operating parameters.
The digital twin technology is a technology for establishing a virtual model of a physical entity by using a digitizing technology so as to simulate, predict and optimize the entity. The technology is initially applied to aspects of product design, production process, performance optimization and the like in the manufacturing industry, but with development of computer technology and improvement of data processing capacity, the digital twin technology is also beginning to be applied to other fields such as construction, transportation, medical treatment and the like.
The applicant finds that the target system can be monitored, analyzed and predicted in real time by establishing a digital twin model of the system, so that the fault prevention and treatment can be realized.
Referring to fig. 1, a digital twin-based fault detection method disclosed in an embodiment of the present application may include:
step S101: an initial twin digital model of the target system is constructed.
The target system refers to an information system, the method is used for an initial twin digital model of the target system, physical components and operation logic of the target system are respectively converted into the digital model when the initial twin digital model is built, the information comprises information such as structures, functions and parameters of the system, and further, in order to ensure the reliability of the digital model, the digital model can be trained and optimized by using a machine learning algorithm after the initial twin digital model is built.
Specifically, in this step, a first initial twin digital model matched with a software portion (running logic) of the target system may be constructed by combining the device set of the target system, the running environment, and the actual deployment structure of the information system, and technologies such as static analysis of codes and dynamic monitoring, and a second initial twin digital model matched with a hardware portion of the target system may be constructed based on state data (such as network traffic, link state, and device temperature of the target system) of the target system detected by the sensor. After the first initial twin digital model and the second initial twin digital model are built, the corresponding relation between the target system and the first initial twin digital model and the second initial twin digital model is built, and at the moment, the first initial twin digital model and the second initial twin digital model can be used as initial twin digital models of the target system.
Step S102: and acquiring the operation data of the target system.
In this scheme, in order to collect the operation data of the target system, a sensor and a software dynamic operation data collection tool may be deployed in the target system in advance, through which the operation data of the target system may be collected in real time, where the type of the operation data may be selected according to the user's needs, for example, in the technical scheme disclosed in this embodiment, the operation data may include data indexes such as network bandwidth, CPU usage, memory usage, and disk read/write speed.
Step S103: and constructing a performance analysis model of the target system based on the operation data by adopting a dynamic Bayesian network.
In this step, referring to fig. 2, after the operation data of the target system is obtained, the operation data may be preprocessed, where the preprocessing includes noise reduction processing and filtering processing, the noise reduction processing and filtering processing remove abnormal values and noise in the operation data, then the processed operation data is converted into a data format that can be used for data analysis by the system of the method, then the operation data after the noise reduction and filtering processing and the format conversion is clustered by using a clustering algorithm, so as to divide the operation data into a plurality of data clusters that can be analyzed, and then a performance analysis model of the target system is constructed based on the clustering result by using a dynamic bayesian network, and the value of the operation data of the target system when the next unit time arrives can be predicted by using the performance analysis model. Specifically, the construction process of constructing the performance analysis model of the target system based on the operation data by using the dynamic bayesian network may refer to an existing scheme, and the overall process of the existing scheme may include: classifying the operation data of the target system by using cluster analysis, determining the relation among the operation data, calculating a distance matrix, distributing each data point in the operation data to the center point closest to the operation data to form a plurality of clusters, and then recalculating the center point of each cluster based on the values of all the data points in each cluster, for example, taking the average value of all the data points in each cluster as the recalculation center point of the cluster. After the center point of each cluster is redetermined, calculating a similarity measurement formula in the cluster by adopting modes such as average value or maximum value of the distance between samples, and further adopting a dynamic Bayesian network to construct a performance analysis model of the target system. It should be noted that the above-described construction process of the performance analysis model is only one overview of the existing construction process, and specific implementation details of each detail of the construction process will be apparent to those skilled in the art.
In the technical scheme disclosed in the embodiment, after determining the performance analysis model of the target system, training the performance analysis model by using historical data may be further adopted, so that an output result of the performance analysis model is more reliable.
Furthermore, in order to improve the reliability of the target system, in the present application, the performance analysis model may be further adopted to simulate the target system, and based on a simulation result, a gradient descent algorithm is used to perform optimization adjustment on the target system.
Step S104: and performing simulation prediction based on the operation data of the target system by adopting the performance analysis model to obtain the predicted operation data of the target system at the next moment.
In the step, after the performance analysis model is determined, the operation data of the target system is used as the input data of the performance analysis model, and the predicted operation data of the target system at the next moment is obtained by predicting the performance analysis model.
Step S105: substituting the predicted operational data into the initial twin digital model.
In the step, the predicted operation data of the next moment of the target system is substituted into the initial twin digital model, so that the operation state data of the next moment of the initial twin digital model can be obtained.
Step S106: and carrying out fault analysis based on the output result of the initial twin digital model substituted into the predicted operation data.
In this step, since the initial twin digital model is a twin system of the target system, the running state data of the next moment of the initial twin digital model can be used as the running state of the next moment of the target system, so that the output result after substituting the predicted running data into the initial twin digital model is subjected to fault analysis, and whether the target system will fail in the future or not and the cause of the failure can be predicted.
By using the scheme disclosed by the application, the initial twin digital model of the target system and the performance analysis model of the target system are constructed, the performance analysis model is adopted to predict the operation data of the target system at the next moment based on the obtained operation data of the target system, the prediction result is substituted into the initial twin digital model, and whether the target system fails at the next moment can be predicted by analyzing the output result of the initial twin digital model, so that the upcoming failure of the target system can be found in time before the failure occurs, the user can adjust the working condition of the target system in a targeted manner, the occurrence of the failure is prevented, and the reliability of the target system is improved.
In the technical scheme disclosed in the embodiment, the running state of the target system can be displayed through a display device, and when the fault of the target system is detected or predicted, the position of the fault is marked.
In the scheme, besides the prediction of the faults to be generated by the target system, the initial twin digital model can be adopted to perform fault analysis on the current running state of the target system, and based on the fault analysis result of the initial twin digital model, whether the target system generates faults and the positions and reasons of the faults are judged. When the initial twin digital model is adopted to perform fault analysis on the current running state of the target system, the running data of the initial twin digital model and the running data of the target system can be compared and analyzed, and the fault position of the target system can be rapidly positioned.
Furthermore, in the application, the performance of the target system can be measured by performing simulation analysis on the initial twin digital model, so that a designer optimizes and improves the target system according to a simulation result to improve the running stability and safety of the target system.
Further, in the technical solution disclosed in this embodiment, based on the initial twin digital model and the real-time monitored operation data of the target system, visual display of the operation state of the target system may also be performed, for example, the operation data of the target system, the operation data of the initial twin digital model, and the output predicted operation data of the initial twin digital model may be displayed in a manner of using a chart, a thermodynamic diagram, or the like, so that a user may better understand the current state, the predicted state, and the system performance of the target system, and the display interface may also provide an interactive function, so that the user may further explore the operation data of the target system. For example, the user can select different time periods and server configurations to check the performance of the target system under different conditions, so that a manager of the system can intuitively know the running condition and the fault condition of the target system, timely send out alarm notification, and improve the management efficiency and response speed of the target system.
The embodiment also discloses a fault detection device based on digital twinning, and specific working contents of each unit in the device are referred to the contents of the above method embodiment.
The digital twin-based fault detection device provided by the embodiment of the invention is described below, and the digital twin-based fault detection device described below and the digital twin-based fault detection method described above can be referred to correspondingly.
Referring to fig. 3, the apparatus may include:
an initial twin digital model construction unit 10 for constructing an initial twin digital model of the target system;
a prediction model construction unit 20 for acquiring operation data of the target system; constructing a performance analysis model of the target system based on the operation data by adopting a dynamic Bayesian network;
a predicted fault analysis unit 30, configured to perform simulation prediction based on the operation data of the target system by using the performance analysis model, so as to obtain predicted operation data of the target system at a next time; substituting the predicted operational data into the initial twin digital model; and carrying out fault analysis based on the output result of the initial twin digital model substituted into the predicted operation data.
Referring to fig. 4, the operation data of the target system may be obtained by data acquisition of the target system by the data acquisition device 40, the prediction model building unit 20 may be integrated at the data analysis device 50, the simulation parts of the initial twin digital model building unit 10 and the prediction fault analysis unit 30 may be integrated at the simulation device 60, and the fault detection part of the prediction fault analysis unit 30 may be integrated at the fault detection device 70, where the operation state of the target system and the location fault point are displayed by the fault detection device.
Corresponding to the method, the initial twin digital model building unit is specifically configured to:
constructing a first initial twin digital model matched with a software part of the target system by using code static analysis and dynamic monitoring;
a second initial twin digital model is constructed that matches the hardware portion of the target system based on the state data of the target system detected by the sensor.
Corresponding to the above method, the present application also discloses a storage medium, including: the storage medium stores a plurality of instructions adapted for loading by a processor to perform the steps in the digital twinning-based fault detection method of any one of the preceding claims.
Fig. 5 is a hardware structure diagram of a fault detection device based on digital twin according to an embodiment of the present invention, which is shown in fig. 5, and may include: at least one processor 100, at least one communication interface 200, at least one memory 300, and at least one communication bus 400;
in the embodiment of the present invention, the number of the processor 100, the communication interface 200, the memory 300 and the communication bus 400 is at least one, and the processor 100, the communication interface 200 and the memory 300 complete the communication with each other through the communication bus 400; it will be apparent that the communication connection schematic shown in the processor 100, the communication interface 200, the memory 300 and the communication bus 400 shown in fig. 5 is only optional;
alternatively, the communication interface 200 may be an interface of a communication module, such as an interface of a GSM module;
the processor 100 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention.
Memory 300 may comprise high-speed RAM memory or may further comprise non-volatile memory (non-volatile memory), such as at least one disk memory.
The processor 100 is specifically configured to:
constructing an initial twin digital model of the target system;
acquiring operation data of a target system;
constructing a performance analysis model of the target system based on the operation data by adopting a dynamic Bayesian network;
performing simulation prediction based on the operation data of the target system by adopting the performance analysis model to obtain predicted operation data of the target system at the next moment;
substituting the predicted operational data into the initial twin digital model;
and carrying out fault analysis based on the output result of the initial twin digital model substituted into the predicted operation data.
For convenience of description, the above system is described as being functionally divided into various modules, respectively. Of course, the functions of each module may be implemented in the same piece or pieces of software and/or hardware when implementing the present invention.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for a system or system embodiment, since it is substantially similar to a method embodiment, the description is relatively simple, with reference to the description of the method embodiment being made in part. The systems and system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. 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.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
It is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A digital twinning-based fault detection method, comprising:
constructing an initial twin digital model of the target system;
acquiring operation data of a target system;
constructing a performance analysis model of the target system based on the operation data by adopting a dynamic Bayesian network;
performing simulation prediction based on the operation data of the target system by adopting the performance analysis model to obtain predicted operation data of the target system at the next moment;
substituting the predicted operational data into the initial twin digital model;
and carrying out fault analysis based on the output result of the initial twin digital model substituted into the predicted operation data.
2. The digital twinning-based fault detection method of claim 1, wherein constructing an initial twinning digital model of the target system comprises:
constructing a first initial twin digital model matched with a software part of the target system by using code static analysis and dynamic monitoring;
a second initial twin digital model is constructed that matches the hardware portion of the target system based on the state data of the target system detected by the sensor.
3. The digital twinning-based fault detection method of claim 1, wherein the operational data of the target system includes at least:
one or more of network bandwidth, CPU usage, memory usage, and disk read/write speed of the target system.
4. The digital twinning-based fault detection method of claim 1, wherein constructing a performance analysis model of the target system based on the operational data using a dynamic bayesian network comprises:
noise reduction and filtering are carried out on the operation data;
clustering and grouping the operation data after noise reduction and filtering processing by using a clustering algorithm,
and constructing a performance analysis model of the target system based on the clustering grouping result by using a dynamic Bayesian network.
5. The digital twin based fault detection method according to claim 4, further comprising, after constructing a performance analysis model of the target system based on clustering grouping results using a dynamic bayesian network:
and training the performance analysis model by utilizing the historical data of the target system.
6. The digital twinning-based fault detection method of claim 1, further comprising, after obtaining the operational data of the target system:
and comparing the real-time operation data with the operation data of the initial twin digital model, and detecting whether the target system has faults or not.
7. A digital twinning-based fault detection device, comprising:
the initial twin digital model building unit is used for building an initial twin digital model of the target system;
the prediction model construction unit is used for acquiring the operation data of the target system; constructing a performance analysis model of the target system based on the operation data by adopting a dynamic Bayesian network;
the prediction fault analysis unit is used for performing simulation prediction based on the operation data of the target system by adopting the performance analysis model to obtain the predicted operation data of the target system at the next moment; substituting the predicted operational data into the initial twin digital model; and carrying out fault analysis based on the output result of the initial twin digital model substituted into the predicted operation data.
8. The fault detection device based on digital twinning according to claim 7, wherein the initial twinning digital model building unit is specifically configured to:
constructing a first initial twin digital model matched with a software part of the target system by using code static analysis and dynamic monitoring;
a second initial twin digital model is constructed that matches the hardware portion of the target system based on the state data of the target system detected by the sensor.
9. A storage medium, comprising:
the storage medium having stored thereon a plurality of instructions adapted to be loaded by a processor,
to perform the steps in the digital twinning-based fault detection method of any one of claims 1 to 6.
10. A fault detection device based on digital twinning, which is characterized by comprising a memory and a processor;
the memory is used for storing programs;
the processor for executing the program to implement the steps of the digital twin based fault detection method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311651220.6A CN117608971A (en) | 2023-12-04 | 2023-12-04 | Fault detection method, device, storage medium and equipment based on digital twin |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311651220.6A CN117608971A (en) | 2023-12-04 | 2023-12-04 | Fault detection method, device, storage medium and equipment based on digital twin |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117608971A true CN117608971A (en) | 2024-02-27 |
Family
ID=89944180
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311651220.6A Pending CN117608971A (en) | 2023-12-04 | 2023-12-04 | Fault detection method, device, storage medium and equipment based on digital twin |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117608971A (en) |
-
2023
- 2023-12-04 CN CN202311651220.6A patent/CN117608971A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110865929B (en) | Abnormality detection early warning method and system | |
| KR101984730B1 (en) | Automatic predicting system for server failure and automatic predicting method for server failure | |
| Yang et al. | A time efficient approach for detecting errors in big sensor data on cloud | |
| US11294754B2 (en) | System and method for contextual event sequence analysis | |
| CN111310139B (en) | Behavior data identification method and device and storage medium | |
| CN110942086A (en) | Data prediction optimization method, device and equipment and readable storage medium | |
| US11847130B2 (en) | Extract, transform, load monitoring platform | |
| CN109670690A (en) | Data information center monitoring and early warning method, system and equipment | |
| CN111669281B (en) | Alarm analysis method, device, equipment and storage medium | |
| CN112769605B (en) | Heterogeneous multi-cloud operation and maintenance management method and hybrid cloud platform | |
| CN110162445A (en) | The host health assessment method and device of Intrusion Detection based on host log and performance indicator | |
| US20170109638A1 (en) | Ensemble-Based Identification of Executions of a Business Process | |
| CN115454778A (en) | Intelligent monitoring system for abnormal time sequence indexes in large-scale cloud network environment | |
| CN111949429A (en) | Server fault monitoring method and system based on density clustering algorithm | |
| CN112148561A (en) | Service system running state prediction method and device and server | |
| CN115204536A (en) | Building equipment fault prediction method, device, equipment and storage medium | |
| CN110766100A (en) | Bearing fault diagnosis model construction method, bearing fault diagnosis method and electronic equipment | |
| CN114598719A (en) | Smart city Internet of things event management method, device and readable medium | |
| CN110490132B (en) | Data processing method and device | |
| US20170109637A1 (en) | Crowd-Based Model for Identifying Nonconsecutive Executions of a Business Process | |
| CN111901156A (en) | Method and device for monitoring fault | |
| JP7062505B2 (en) | Equipment management support system | |
| CN117608971A (en) | Fault detection method, device, storage medium and equipment based on digital twin | |
| CN115080397A (en) | System reliability testing method, device, equipment and storage medium | |
| CN114676002A (en) | PHM technology-based system operation and maintenance method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |