Industrial Internet equipment fault prediction method and system based on digital twin

Abstract

The present application discloses an industrial Internet equipment fault prediction method and system based on digital twins, which belongs to the field of industrial Internet. The present application obtains the operating data and data volume processing data of scene equipment related to abnormal behavior of the industrial Internet of Things to perform primary prediction of equipment failure, and then performs final prediction of the faulty equipment based on the operating data of the primary predicted faulty equipment and the primary prediction of equipment failure. Finally, the faulty equipment information obtained by the final prediction is displayed on the digital twin model, and maintenance personnel are reminded to perform equipment maintenance. The abnormal behavior before the fault occurs is accurately judged based on the digital twin model. In the process of analyzing the abnormal behavior, the equipment that causes the abnormal behavior is searched comprehensively through the parameter correlation degree and the spatiotemporal correlation between the equipment and the behavior, thereby improving the efficiency of finding faulty equipment and further improving the security of the industrial Internet scenario.

Description

Technical Field

[0001] This application belongs to the field of industrial Internet, specifically, an industrial Internet equipment fault prediction method and system based on digital twins. Background Art

[0002] The Industrial Internet is a new type of infrastructure, application model and industrial ecology that deeply integrates the new generation of information and communication technology with the industrial economy. Through the comprehensive connection of people, machines, objects, systems, etc., a new manufacturing and service system covering the entire industrial chain and the entire value chain is built. When conducting smart factory production, a large number of Industrial Internet devices are required to fully monitor the factory. When using Industrial Internet devices, it often happens that a certain Industrial Internet device fails and causes the factory monitoring network to be paralyzed. Therefore, it is necessary to predict the failure of Industrial Internet equipment in advance;

[0003] The digital twin is a technology system that integrates new-generation information technologies such as the Internet of Things, cloud computing, big data, and artificial intelligence to build an intelligent economic system that maps physical space with digital space, realizes data aggregation, analysis and mining, and optimizes decisions for people, objects, equipment, environment, and management in physical space, and twins in digital space, and empowers economic and social development. Simply put, a digital twin is a technology system that creates a virtual model that completely corresponds to the real world in the digital space, perceives, recognizes, simulates, and makes decisions about the real world in both augmented reality and virtual reality, and realizes the interactive integration of the real world and virtual models. Introducing digital twin technology into the prediction of industrial Internet equipment failures can quickly discover industrial Internet equipment failures;

[0004] However, in the process of predicting industrial Internet equipment failures, the existing technology cannot accurately judge the abnormal behavior before the failure occurs based on the digital twin model. At the same time, since there are many similar devices in the industrial Internet, the existing technology cannot comprehensively search for the device that causes the abnormal behavior through the parameter correlation degree and spatiotemporal correlation between the device and the behavior, resulting in low efficiency in finding faulty equipment. Most of the existing technologies have the above problems.

[0005] In order to solve the problems raised by this background technology, this application designs an industrial Internet equipment fault prediction method and system based on digital twins. Summary of the invention

[0006] In order to address the deficiencies in the prior art mentioned in the background technology, the present application proposes an industrial Internet equipment fault prediction method and system based on digital twins. The present application obtains the operating data and data volume processing data of scene equipment related to the abnormal behavior of the industrial Internet of Things to perform a primary prediction of equipment failure, and then performs a final prediction of the faulty equipment based on the operating data of the primary predicted faulty equipment and the primary prediction of equipment failure. Finally, the faulty equipment information obtained by the final prediction is displayed on the digital twin model, and maintenance personnel are reminded to perform equipment maintenance. The abnormal behavior before the failure occurs is accurately judged based on the digital twin model, and the failure is reminded in advance, thereby improving the security of the industrial Internet scenario. At the same time, in the process of analyzing abnormal behavior, the present application searches for the equipment that causes the abnormal behavior through the parameter correlation degree and the spatiotemporal correlation between the equipment and the behavior, thereby improving the efficiency of finding faulty equipment and further improving the security of the industrial Internet scenario.

[0007] To achieve the above objectives, the present application provides the following technical solutions: In the first aspect, the present application provides an industrial Internet equipment fault prediction method based on digital twins, which includes the following specific steps:

[0008] S1. Obtain the functions, connection information and attribute information of each device in the industrial Internet scenario, and build a digital twin model of the scenario based on the functions, connection information and attribute information of each device;

[0009] S2. Position and analyze abnormal behaviors of the Industrial Internet of Things through the connection and transmission information of the devices;

[0010] S3, obtaining the operation data and data volume processing data of the scene equipment related to the abnormal behavior of the industrial Internet of Things to perform primary prediction of equipment failure, and obtain primary predicted faulty equipment;

[0011] S4, making a final prediction of the faulty equipment based on the operating data of the primary predicted faulty equipment and the primary prediction of equipment failure;

[0012] S5. The final predicted faulty equipment information is displayed on the digital twin model, and the maintenance personnel are reminded to perform equipment maintenance.

[0013] As the preferred technical solution for the industrial Internet equipment fault prediction method based on digital twins, the specific content of step S1 is:

[0014] S11. Acquire function information and connection location information of the connection device in the selected industrial Internet of Things scenario, wherein the function information is the function of the connection device, for example, the function information of each sensor in the industrial Internet of Things scenario is the value of the change amount of the corresponding parameter of the corresponding component, and the connection location information is the location information of the connection device relative to other connection components in the industrial Internet of Things scenario;

[0015] S12. Acquire data transmission information and operation data of each connected device in the industrial Internet of Things scenario, wherein the data transmission information of the connected devices includes transmission signal data between the connected devices, and the operation data of each connected device includes operation status data of the device within an operation cycle, including data reflecting the operation status of the device, such as the operation voltage, current and temperature of the device;

[0016] S13. Based on the acquired functions, connection information and attribute information of the equipment, the digital twin model of the industrial Internet scenario is constructed by importing the information into the digital twin construction software.

[0017] As a preferred technical solution for the industrial Internet equipment fault prediction method based on digital twins, the positioning analysis of abnormal behaviors of the industrial Internet of Things through the connection transmission information of the device in S2 includes the following specific steps:

[0018] S21, obtaining the output data of the output component to be output and the standard output data of the output component, and importing the output data of the output component and the standard output data of the output component into the output abnormal value calculation formula to calculate the output abnormal value, wherein the output abnormal value calculation formula is: , where T is the test time, N is the output data type of the output component, ai is the proportion coefficient of the i-th output data type, Xit is the output data of the i-th output data type at time t, Xitm is the standard output data of the i-th output data type at time t, and dt is the time integral. In this formula, the output data anomaly is comprehensively analyzed by combining the deviation between the output data of the output component and the standard output data of the output component during the test period;

[0019] S22. Compare the obtained output abnormality value with the set output abnormality threshold. If the obtained output abnormality value is greater than or equal to the set output abnormality threshold, it means that there is abnormal behavior in the industrial Internet of Things scenario, and it is necessary to perform abnormal behavior location analysis. If the obtained output abnormality value is less than the set output abnormality threshold, it means that there is no abnormal behavior in the industrial Internet of Things scenario.

[0020] As a preferred technical solution for the industrial Internet equipment fault prediction method based on digital twins, the acquisition of operation data and data volume processing data of scene equipment related to abnormal behavior of the industrial Internet of Things for primary prediction of equipment faults includes the following specific steps:

[0021] S31, obtaining the data type whose output data of the output component during the test time and the standard output data of the output component deviate by more than the standard deviation value, setting it as the abnormal data type, and obtaining the deviation amount of the abnormal data type, and obtaining the functional information of each connected device in the industrial Internet scenario, and obtaining the adjustment data type and adjustment amount data of each connected device;

[0022] S32, importing the acquired abnormal data type, the deviation of the acquired abnormal data type, the adjustment data type and the adjustment amount data of each connected device into the primary abnormal device probability calculation formula to calculate the primary abnormal device probability, wherein the primary abnormal device probability calculation formula of the jth connected device is: , where c is the weight of the category proportion, m() is the number of elements in the set in brackets, Ac is the set of abnormal data categories, kj is the adjustment data category of the j-th connected device, Aj is the adjustment data category of the j-th connected device, czm is the offset of the z-th abnormal data category corresponding to the adjustment data of the j-th connected device, and czj is the adjustment amount of the z-th abnormal data category corresponding to the adjustment data of the j-th connected device. is the intersection of the sets, is the union of the sets. In this formula, the device anomaly is located and analyzed by analyzing the functional information of the connected device and the deviation from the abnormal data;

[0023] S33, obtaining corresponding devices whose primary abnormal device probability is greater than or equal to the probability threshold, setting them as primary predicted fault devices, and not setting corresponding devices whose primary abnormal device probability is less than the probability threshold as primary predicted fault devices.

[0024] As a preferred technical solution of the industrial Internet equipment fault prediction method based on digital twins, the final prediction of the faulty equipment based on the operating data of the primary predicted faulty equipment and the primary prediction of the equipment fault includes the following specific contents:

[0025] S41, obtaining the operation data of the primary predicted fault device within a period and the output data of the output component within the corresponding period;

[0026] S42, importing the acquired operation data of the primary predicted fault device in the period and the output data of the output component in the corresponding period into the second matching probability calculation formula to calculate the second matching probability, wherein the second matching probability calculation formula of the uth primary predicted fault device is: , where M is the type of operation data of the primary prediction fault device, bm is the weight of the type of operation data of the primary prediction fault device, Ymt is the data of the mth type of operation data of the primary prediction fault device at time t, and Ymtz is the median of the safe operation range of the mth type of operation data of the primary prediction fault device; in this way, the abnormal fault can be accurately identified by comparing the abnormalities between the devices and outputs in the same cycle;

[0027] S43, obtaining the calculated second matching probability and primary abnormal device probability corresponding to the primary predicted fault device, weighting the second matching probability and the primary abnormal device probability and adding them together to obtain the final fault prediction probability of the corresponding device, and setting the device corresponding to the maximum final fault prediction probability as the faulty device.

[0028] As the preferred technical solution for the industrial Internet equipment fault prediction method based on digital twins, the method of displaying the final predicted faulty equipment information on the digital twin model and reminding maintenance personnel to perform equipment maintenance includes the following specific contents: obtaining the function, connection information and attribute information of the corresponding faulty equipment, displaying it on the constructed digital twin model, and reminding maintenance personnel to perform maintenance on the corresponding faulty equipment.

[0029] On the second aspect, the present application provides an industrial Internet equipment fault prediction system based on digital twins, which is implemented based on the above-mentioned industrial Internet equipment fault prediction method based on digital twins, and specifically includes a data acquisition module, a model construction module, a positioning analysis module, an equipment fault primary prediction module, a faulty equipment final prediction module and a maintenance module; wherein, the data acquisition module is used to obtain the function, connection information and attribute information of each device in the industrial Internet scenario; the model construction module constructs a digital twin model about the scene based on the function, connection information and attribute information of each device; the positioning analysis module is used to locate and analyze the abnormal behavior of the Industrial Internet of Things through the connection transmission information of the device; the equipment failure primary prediction module is used to obtain the operating data and data volume processing data of the scene equipment related to the abnormal behavior of the Industrial Internet of Things to perform a primary prediction of equipment failure, and obtain a primary predicted faulty device; the faulty equipment final prediction module performs a final prediction of the faulty device based on the operating data of the primary predicted faulty device and the primary prediction of the equipment failure; the maintenance module is used to display the faulty equipment information obtained by the final prediction on the digital twin model, and remind maintenance personnel to perform equipment maintenance.

[0030] In a third aspect, the present application provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0031] The processor executes the above-mentioned industrial Internet equipment fault prediction method based on digital twins by calling the computer program stored in the memory.

[0032] In a fourth aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute the industrial Internet equipment fault prediction method based on digital twins as described above.

[0033] Compared with the prior art, the beneficial effects of the present application are as follows: the present application locates and analyzes abnormal behaviors of the industrial Internet of Things through the connection transmission information of the equipment, and then obtains the operation data and data volume processing data of the scene equipment related to the abnormal behavior of the industrial Internet of Things to make a primary prediction of equipment failure, and then makes a final prediction of the faulty equipment based on the operation data of the primary predicted faulty equipment and the primary prediction of the equipment failure, and finally displays the faulty equipment information obtained by the final prediction on the digital twin model, and reminds the maintenance personnel to perform equipment maintenance, accurately judges the abnormal behavior before the fault occurs based on the digital twin model, and then gives an advance reminder of the fault, thereby improving the security of the industrial Internet scene;

[0034] At the same time, during the abnormal behavior analysis process, this application searches for the device that causes the abnormal behavior through the parameter correlation degree and time-space correlation between the device and the behavior, thereby improving the efficiency of finding faulty equipment and further improving the security of the industrial Internet scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings;

[0036] Figure 1 This is a schematic diagram of the overall process of the industrial Internet equipment fault prediction method based on digital twins in this application;

[0037] Figure 2 This is a schematic diagram of step S2 of the industrial Internet equipment fault prediction method based on digital twins in this application;

[0038] Figure 3 This is a schematic diagram of step S3 of the industrial Internet equipment fault prediction method based on digital twins in this application;

[0039] Figure 4 This is a schematic diagram of the overall framework of the industrial Internet equipment fault prediction system based on digital twins in this application. DETAILED DESCRIPTION

[0040] In order to better understand the present application, various aspects of the present application will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present application and do not limit the scope of the present application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0041] In the accompanying drawings, the size, dimensions and shape of the elements have been slightly adjusted for ease of explanation. The accompanying drawings are only examples and are not strictly drawn to scale. As used herein, the terms "substantially", "approximately" and similar terms are used as terms to indicate approximation, not as terms to indicate degree, and are intended to illustrate the inherent deviations in measured or calculated values ​​that will be recognized by those of ordinary skill in the art. In addition, in the present application, the order in which the steps are processed does not necessarily represent the order in which these processes occur in actual operation, unless otherwise clearly defined or can be derived from the context. It should also be understood that expressions such as "including", "including", "having", "including" and / or "including" are open rather than closed expressions in this specification, which indicate the presence of the stated features, elements and / or components, but do not exclude the presence of one or more other features, elements, components and / or combinations thereof. In addition, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features, rather than just modifying the individual elements in the list. In addition, when describing the embodiments of the present application, "may" is used to represent "one or more embodiments of the present application". Furthermore, the term "exemplary" is intended to refer to an example or illustration. Unless otherwise specified, all words used herein (including engineering terms and scientific and technological terms) have the same meaning as those commonly understood by those of ordinary skill in the art to which this application belongs. It should also be understood that, unless otherwise clearly stated in this application, words defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense.

[0042] Example 1

[0043] In order to solve the technical problems raised in the background technology, the present application provides a preferred embodiment: Figure 1-Figure 3 As shown in the figure, the industrial Internet equipment fault prediction method based on digital twins includes the following specific steps:

[0044] S1. Obtain the functions, connection information and attribute information of each device in the industrial Internet scenario, and build a digital twin model of the scenario based on the functions, connection information and attribute information of each device;

[0045] In one specific embodiment, the specific content of step S1 is:

[0046] S11. Acquire function information and connection position information of the connection device in the selected industrial Internet of Things scenario, wherein the function information is the function of the connection device, for example, the function information of each sensor in the industrial Internet of Things scenario is the value of the change amount of the corresponding parameter of the corresponding component, for example, the transformer converts the voltage into the required voltage, and the connection position information is the position information of the connection device relative to other connection components in the industrial Internet of Things scenario;

[0047] S12. Acquire data transmission information and operation data of each connected device in the industrial Internet of Things scenario, wherein the data transmission information of the connected devices includes transmission signal data between the connected devices, and the operation data of each connected device includes operation status data of the device within an operation cycle, including data reflecting the operation status of the device, such as the operation voltage, current and temperature of the device;

[0048] S13, based on the acquired functions, connection information and attribute information of the equipment, the digital twin model of the industrial Internet scenario is constructed by importing the acquired functions, connection information and attribute information into the digital twin construction software;

[0049] S2. Position and analyze abnormal behaviors of the Industrial Internet of Things through the connection and transmission information of the devices;

[0050] In one specific embodiment, the location analysis of abnormal behavior of the industrial Internet of Things through the connection transmission information of the device in S2 includes the following specific steps:

[0051] S21, obtaining the output data of the output component to be output and the standard output data of the output component, and importing the output data of the output component and the standard output data of the output component into the output abnormal value calculation formula to calculate the output abnormal value, wherein the output abnormal value calculation formula is: , where T is the test time, N is the output data type of the output component, ai is the proportion coefficient of the i-th output data type, Xit is the output data of the i-th output data type at time t, Xitm is the standard output data of the i-th output data type at time t, and dt is the time integral. In this formula, the output data anomaly is comprehensively analyzed by combining the deviation between the output data of the output component and the standard output data of the output component during the test period;

[0052] S22. Compare the obtained output abnormal value with the set output abnormal threshold. If the obtained output abnormal value is greater than or equal to the set output abnormal threshold, it means that there is abnormal behavior in the industrial Internet of Things scenario, and it is necessary to perform abnormal behavior location analysis. If the obtained output abnormal value is less than the set output abnormal threshold, it means that there is no abnormal behavior in the industrial Internet of Things scenario. In this step, the proportion coefficient of the i-th output data type and the output abnormal threshold are taken as follows: obtain at least 500 sets of equipment operation data of the industrial Internet scenario, observe the judgment results of whether a fault occurs in the industrial Internet scenario in the subsequent monitoring period, and import the output data of the output component into the output abnormal value calculation formula to calculate the output abnormal value, import the calculated output abnormal value and the result of whether a fault occurs into the fitting software, and output the proportion coefficient of the i-th output data type and the output abnormal threshold value that meet the maximum judgment accuracy. It should be noted that the values ​​of the setting parameters in this embodiment are all obtained in this way, which will not be described in detail below.

[0053] S3, obtaining the operation data and data volume processing data of the scene equipment related to the abnormal behavior of the industrial Internet of Things to perform primary prediction of equipment failure, and obtain primary predicted faulty equipment;

[0054] In one specific embodiment, obtaining the operation data and data volume processing data of scene devices related to abnormal behavior of the industrial Internet of Things to perform primary prediction of equipment failure includes the following specific steps:

[0055] S31, obtaining the data type whose output data of the output component during the test time and the standard output data of the output component deviate by more than the standard deviation value, setting it as the abnormal data type, and obtaining the deviation amount of the abnormal data type, and obtaining the functional information of each connected device in the industrial Internet scenario, and obtaining the adjustment data type and adjustment amount data of each connected device;

[0056] S32, importing the acquired abnormal data type, the deviation of the acquired abnormal data type, the adjustment data type and the adjustment amount data of each connected device into the primary abnormal device probability calculation formula to calculate the primary abnormal device probability, wherein the primary abnormal device probability calculation formula of the jth connected device is: , where c is the weight of the category proportion, m() is the number of elements in the set in brackets, Ac is the set of abnormal data categories, kj is the adjustment data category of the j-th connected device, Aj is the adjustment data category of the j-th connected device, czm is the offset of the z-th abnormal data category corresponding to the adjustment data of the j-th connected device, and czj is the adjustment amount of the z-th abnormal data category corresponding to the adjustment data of the j-th connected device. is the intersection of the sets, is the union of the sets. In this formula, the device anomaly is located and analyzed by analyzing the functional information of the connected device and the deviation from the abnormal data. The setting parameters in this formula are obtained in the same way as the proportion coefficient of the i-th output data type and the value of the output abnormality threshold. They are all obtained by fitting software after being substituted into the calculation, and will not be described in detail here.

[0057] S33, obtaining corresponding devices whose primary abnormal device probability is greater than or equal to the probability threshold, setting them as primary predicted fault devices, and not setting corresponding devices whose primary abnormal device probability is less than the probability threshold as primary predicted fault devices;

[0058] S4, making a final prediction of the faulty equipment based on the operating data of the primary predicted faulty equipment and the primary prediction of equipment failure;

[0059] In one specific embodiment, the final prediction of the faulty device based on the operating data of the primary predicted faulty device and the primary prediction of the device fault includes the following specific contents:

[0060] S41, obtaining the operation data of the primary predicted fault device within a period and the output data of the output component within the corresponding period;

[0061] S42, importing the acquired operation data of the primary predicted fault device in the period and the output data of the output component in the corresponding period into the second matching probability calculation formula to calculate the second matching probability, wherein the second matching probability calculation formula of the uth primary predicted fault device is: , where M is the type of operation data of the primary prediction fault device, bm is the weight of the type of operation data of the primary prediction fault device, Ymt is the data of the mth type of operation data of the primary prediction fault device at time t, and Ymtz is the median of the safe operation range of the mth type of operation data of the primary prediction fault device; in this way, the abnormal fault can be accurately identified by comparing the abnormalities between the devices and outputs in the same cycle;

[0062] S43, obtaining the calculated second matching probability and the primary abnormal device probability corresponding to the primary predicted fault device, weighting and adding the second matching probability and the primary abnormal device probability to obtain the final fault prediction probability of the corresponding device, and setting the device corresponding to the maximum final fault prediction probability as the faulty device;

[0063] S5. Display the faulty equipment information finally predicted on the digital twin model and remind the maintenance personnel to perform equipment maintenance;

[0064] In one of the specific embodiments, the final predicted faulty equipment information is displayed on the digital twin model, and the maintenance personnel are reminded to perform equipment maintenance, including the following specific contents: the function, connection information and attribute information of the corresponding faulty equipment are obtained, displayed on the constructed digital twin model, and the maintenance personnel are reminded to perform maintenance on the corresponding faulty equipment, wherein the reminder method can be transmitted to the maintenance personnel in the form of alarm, wired and / or wireless.

[0065] It should be noted in this example that this embodiment has the following advantages over the prior art: the operating data and data volume processing data of the scene equipment related to the abnormal behavior of the Industrial Internet of Things are obtained to perform a primary prediction of equipment failure, and then the final prediction of the faulty equipment is made based on the operating data of the primary predicted faulty equipment and the primary prediction of the equipment failure. Finally, the faulty equipment information obtained by the final prediction is displayed on the digital twin model, and the maintenance personnel are reminded to perform equipment maintenance. The abnormal behavior before the failure occurs is accurately judged based on the digital twin model, and the failure is reminded in advance, thereby improving the security of the Industrial Internet scenario. In the process of analyzing the abnormal behavior, the equipment that causes the abnormal behavior is searched for through the comprehensive search of the parameter correlation degree and the spatiotemporal correlation between the equipment and the behavior, thereby improving the efficiency of finding faulty equipment and further improving the security of the Industrial Internet scenario.

[0066] Example 2

[0067] like Figure 4 As shown, the industrial Internet equipment fault prediction system based on digital twins is implemented based on the above-mentioned industrial Internet equipment fault prediction method based on digital twins, and specifically includes a data acquisition module, a model construction module, a positioning analysis module, an equipment fault primary prediction module, a faulty equipment final prediction module and a maintenance module; wherein the data acquisition module is used to obtain the function, connection information and attribute information of each device in the industrial Internet scenario; the model construction module builds a digital twin model of the scenario based on the function, connection information and attribute information of each device; the positioning analysis module is used to locate and analyze abnormal behaviors of the industrial Internet of Things through the connection transmission information of the device; the equipment fault primary prediction module is used to The operation data and data volume processing data of the scene equipment related to the abnormal behavior of the industrial Internet of Things are obtained to perform primary prediction of equipment failure, and obtain the primary predicted faulty equipment; the final prediction module of the faulty equipment performs the final prediction of the faulty equipment based on the operation data of the primary predicted faulty equipment and the primary prediction of the equipment failure; the maintenance module is used to display the faulty equipment information obtained by the final prediction on the digital twin model, and remind the maintenance personnel to perform equipment maintenance; it can also include a control module, the control module is used to control the operation of the data acquisition module, the model building module, the positioning analysis module, the equipment failure primary prediction module, the faulty equipment final prediction module and the maintenance module; at the same time, the data transmission direction of each module in this embodiment is as follows Figure 4 As shown by the arrow direction in the figure, the specific steps of each module in this embodiment have been described in detail in the above method embodiment and will not be repeated here.

[0068] Example 3

[0069] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0070] The processor executes the above-mentioned digital twin-based industrial Internet equipment fault prediction method by calling the computer program stored in the memory.

[0071] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the industrial Internet equipment fault prediction method based on digital twins provided in the above method embodiment. The electronic device may also include other components for implementing the functions of the device. For example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.

[0072] Example 4

[0073] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0074] When the computer program runs on a computer device, the computer device executes the above-mentioned industrial Internet equipment fault prediction method based on digital twins.

[0075] For example, the computer readable storage medium can be a read-only memory, a random access memory, a read-only CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0076] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0077] The terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus.

[0078] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. The industrial Internet equipment fault prediction method based on digital twins is characterized by: It includes the following specific steps: S1. Obtain the functions, connection information, and attribute information of each device in the industrial Internet scenario, and build a digital twin model of the scenario based on the acquired data; S2. Position and analyze abnormal behaviors of the Industrial Internet of Things through the connection and transmission information of the devices; S3, obtain the operation data and data volume processing data of the scene equipment related to the abnormal behavior of the industrial Internet of Things to make a primary prediction of equipment failure; The specific steps include: Obtain the data type whose output data of the output component and the standard output data of the output component deviate beyond the standard deviation value during the test time, set it as the abnormal data type, and obtain the deviation of the abnormal data type at the same time. At the same time, obtain the functional information of each connected device in the industrial Internet scenario, obtain the adjustment data type and adjustment amount data of each connected device; calculate the primary abnormal device probability through the obtained data; Obtain the corresponding device whose primary abnormal device probability is greater than or equal to the probability threshold, and set it as the primary predicted fault device; otherwise, do not set it as the primary predicted fault device; S4, making a final prediction of the faulty equipment based on the operating data of the primary predicted faulty equipment and the primary prediction of equipment failure; The specific contents include: The operation data of the primary predicted fault device in the cycle and the output data of the output in the corresponding cycle are obtained, and the second matching probability is calculated, wherein the second matching probability calculation formula of the u-th primary predicted fault device is: , where M is the type of operation data of the primary prediction fault device, bm is the weight of the proportion of the type of operation data of the primary prediction fault device, Ymt is the data of the mth type of operation data of the primary prediction fault device at time t, Ymtz is the median of the safe operation range of the mth type of operation data of the primary prediction fault device, T is the test time, N is the output data type of the output component, ai is the proportion coefficient of the i-th type of output data, Xit is the output data of the i-th type of output data at time t, Xitm is the standard output data of the i-th type of output data at time t, and dt is the time integral; Obtain the calculated second matching probability and the primary abnormal device probability corresponding to the primary predicted fault device, weight the second matching probability and the primary abnormal device probability and add them together to obtain the final fault prediction probability of the corresponding device, and set the device corresponding to the maximum final fault prediction probability as the faulty device; S5. The final predicted faulty equipment information is displayed on the digital twin model, and the maintenance personnel are reminded to perform equipment maintenance.

2. The method for predicting faults of industrial Internet equipment based on digital twins according to claim 1, characterized in that: The specific contents of the S1 step are: S11, obtaining function information and connection location information of the connection device in the selected industrial Internet of Things scenario; S12, obtaining data transmission information and operation data of each connected device in the industrial Internet of Things scenario; S13. Based on the acquired functions, connection information and attribute information of the equipment, the digital twin model of the industrial Internet scenario is constructed by importing the information into the digital twin construction software.

3. The method for predicting faults of industrial Internet equipment based on digital twins according to claim 1, characterized in that: The positioning analysis of abnormal behavior of the industrial Internet of Things through the connection transmission information of the device in S2 includes the following specific steps: The output data of the output component to be output and the standard output data of the output component are obtained, and the output data of the output component and the standard output data of the output component are imported into the output abnormal value calculation formula to calculate the output abnormal value, wherein the output abnormal value calculation formula is: , where T is the test time, N is the output data type of the output component, ai is the proportion coefficient of the i-th output data type, Xit is the output data of the i-th output data type at time t, Xitm is the standard output data of the i-th output data type at time t, and dt is the time integral; The obtained output abnormality value is compared with the set output abnormality threshold. If the obtained output abnormality value is greater than or equal to the set output abnormality threshold, it means that there is abnormal behavior in the industrial Internet of Things scenario, and it is necessary to perform abnormal behavior location analysis. If the obtained output abnormality value is less than the set output abnormality threshold, it means that there is no abnormal behavior in the industrial Internet of Things scenario.

4. The method for predicting industrial Internet equipment failure based on digital twins according to claim 3 is characterized in that: The calculation formula for the primary abnormal device probability of the jth connected device is: , where c is the weight of the category proportion, m() is the number of elements in the set in brackets, Ac is the set of abnormal data categories, kj is the adjustment data category of the j-th connected device, Aj is the adjustment data category of the j-th connected device, czm is the offset of the z-th abnormal data category corresponding to the adjustment data of the j-th connected device, and czj is the adjustment amount of the z-th abnormal data category corresponding to the adjustment data of the j-th connected device. is the intersection of the sets, is the union of sets.

5. The method for predicting faults of industrial Internet equipment based on digital twins according to claim 4, characterized in that: The finally predicted faulty equipment information is displayed on the digital twin model, and the maintenance personnel are reminded to perform equipment maintenance, including the following specific contents: The function, connection information, and attribute information of the corresponding faulty device are obtained and displayed on the constructed digital twin model, and the maintenance personnel are reminded to perform maintenance on the corresponding faulty device.

6. An industrial Internet equipment fault prediction system based on digital twins, which is implemented based on the industrial Internet equipment fault prediction method based on digital twins as claimed in any one of claims 1 to 5, characterized in that: It specifically includes a data acquisition module, a model building module, a positioning analysis module, an equipment failure primary prediction module, a faulty equipment final prediction module and a maintenance module; wherein the data acquisition module is used to obtain the functions, connection information and attribute information of each device in the industrial Internet scenario; the model building module constructs a digital twin model of the scenario based on the functions, connection information and attribute information of each device; the positioning analysis module is used to perform positioning analysis on abnormal behaviors of the industrial Internet of Things through the connection transmission information of the device; the equipment failure primary prediction module is used to obtain the operating data and data volume processing data of the scene equipment related to the abnormal behavior of the industrial Internet of Things to perform primary prediction of equipment failure and obtain primary predicted faulty equipment; the faulty equipment final prediction module performs final prediction of the faulty equipment based on the operating data of the primary predicted faulty equipment and the primary prediction of equipment failure; the maintenance module is used to display the faulty equipment information obtained by the final prediction on the digital twin model and remind maintenance personnel to perform equipment maintenance.

7. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; It is characterized in that the processor executes the industrial Internet equipment fault prediction method based on digital twins as described in any one of claims 1 to 5 by calling the computer program stored in the memory.

8. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes the industrial Internet equipment fault prediction method based on digital twins as described in any one of claims 1 to 5.

Images