Real-time detection method and system for key parameters based on digital twinning

Abstract

The application relates to a key parameter real-time detection method and system based on digital twinning; the method comprises the following steps: collecting data through a sensor as input data of numerical simulation of a target structure; based on secondary development of finite element analysis software, a joint simulation system of a program language and a finite element model is established; numerical simulation is performed on the input data through the joint simulation system to obtain real-time and all-around data of the target structure; and an improved hash algorithm based on binary is used to detect the numerical simulation result data and return an abnormal value and a corresponding position. The technical scheme of the application realizes all-around detection of the target structure through data interaction between reality and virtuality based on digital twinning technology, solves the all-around data detection that cannot be achieved by a traditional algorithm, realizes real-time feedback of important data parameters, and provides a more convenient and more comprehensive option for health detection of the target structure.

Description

Technical Field

[0001] This application relates to the field of key parameter detection technology, specifically to a method and system for real-time detection of key parameters based on digital twins. Background Technology

[0002] Traditional structural health parameters, such as temperature field, are detected using sensors to acquire relevant data. However, traditional structural data detection methods cannot achieve complete detection because sensors cannot be deployed on all targets. For example, in special detection tasks such as the internal temperature field of a transformer structure, excessively high temperatures and sealed environments may prevent the deployment of sensors, potentially leading to the loss of detection at critical locations, particularly the detection of temperature changes in the internal iron core.

[0003] In related technologies, traditional methods currently use finite element analysis software to perform numerical simulations of the target structure to achieve comprehensive detection. However, since finite element analysis is performed offline, it cannot provide real-time detection, which may result in the failure to capture outliers. Furthermore, when faced with large amounts of monitoring data, detecting outliers or maximum values ​​using traditional algorithms is often very time-consuming. Summary of the Invention

[0004] To at least partially overcome the problem in related technologies where finite element analysis is performed offline and cannot provide real-time detection, which may result in the failure to capture outliers, this application provides a method and system for real-time detection of key parameters based on digital twins.

[0005] According to a first aspect of the embodiments of this application, a method for real-time detection of key parameters based on digital twins is provided, comprising:

[0006] Data is collected through sensors and used as input data for numerical simulation of the target structure.

[0007] Based on the secondary development of finite element analysis software, a joint simulation system of programming language and finite element model is established.

[0008] The joint simulation system is used to perform numerical simulation on the input data to obtain real-time all-round data of the target structure.

[0009] An improved binary-based hash algorithm is used to detect outliers in numerical simulation results and return their locations.

[0010] Furthermore, the input data are health parameters of physical information; the input data includes: stress, temperature and / or magnetic field strength.

[0011] Furthermore, the numerical simulation of the input data using the co-simulation system includes the following steps:

[0012] The transformer is parametrically modeled and numerically simulated using data collected by sensors through a co-simulation system. The parametrically modeled simulation model is established at a 1:1 scale, thereby obtaining real-time all-round data of the target structure.

[0013] Furthermore, an improved binary-based hash algorithm is used to examine the numerical simulation results data, including the following steps:

[0014] The numerical simulation results are divided into two sets of data: numerical simulation data and node coordinate information, and then converted into two sets of binary data respectively; the numerical simulation data and the node coordinate information correspond one-to-one.

[0015] Highly repetitive data was removed based on Hamming distance;

[0016] The numerical simulation results are mapped into a table using a hash function, and then compared and sorted.

[0017] You can directly obtain the maximum value from the table or compare it with the threshold to determine if there are any outliers.

[0018] Furthermore, the numerical simulation results are divided into two sets of data, and then converted into two sets of binary data respectively, including the following steps:

[0019] The numerical simulation results are C = {A; B}, where A represents the numerical simulation data and B represents the node coordinate information.

[0020] Convert the two sets of data, A and B, into two sets of binary data respectively, and establish a Hamming space of equal dimension, namely C. bin ={A bin B bin}; where the subscript bin indicates that the data is binary data.

[0021] Furthermore, the process of removing highly repetitive data based on Hamming distance includes the following steps:

[0022] For any two data C i ={A i B i} and C j ={A j B j If A i With A j Hamming distance, B i With B j If the Hamming distances of C and C are both less than or equal to 1, then C i With C j This is highly complex data.

[0023] Furthermore, the numerical simulation results are mapped to a table using a hash function, and then compared and sorted, including the following steps:

[0024] C bin Mapped to a table using a hash function;

[0025] Define a family of hash functions H, divide each hash table into multiple hash buckets, and use the hash functions to assign sequences to the corresponding hash buckets;

[0026] Only for A in the hash bucket bin Perform a comparative sort and merge the sorted data from each hash bucket in an ordered manner, while ensuring that B bin Follow A bin The order of change.

[0027] According to a second aspect of the embodiments of this application, a real-time detection system for key parameters based on digital twins is provided, comprising:

[0028] The data acquisition module is used to collect data through sensors as input data for numerical simulation of the target structure.

[0029] The model building module is used for secondary development based on finite element analysis software to establish a joint simulation system of programming language and finite element model;

[0030] The numerical simulation module is used to perform numerical simulation on the input data through the co-simulation system to obtain real-time all-round data of the target structure;

[0031] The data detection module is used to detect numerical simulation results data based on an improved binary hash algorithm and return outliers and their corresponding locations.

[0032] According to a third aspect of the embodiments of this application, a computer device is provided, comprising: a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program in the memory to implement the operation steps of the method as described in any of the above embodiments.

[0033] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided, on which a computer program is stored, wherein when the computer program is executed by a processor, it implements the operation steps of the method as described in any of the above embodiments.

[0034] The technical solutions provided by the embodiments of this application have the following beneficial effects:

[0035] The technical solution of this application is based on digital twin technology. It achieves comprehensive detection of the target structure through data interaction between reality and virtuality. It not only solves the problem of comprehensive data detection that traditional algorithms cannot achieve, but also realizes real-time feedback of important data parameters. At the same time, it performs comprehensive detection of simulation result data through an improved binary-based hash algorithm and can return outliers and their locations, providing a more convenient and comprehensive option for the health detection of the target structure and effectively preventing accidents from occurring.

[0036] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0037] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0038] Figure 1 This is a flowchart of a real-time detection method for key parameters based on digital twins according to an embodiment of the present invention.

[0039] Figure 2 This is a flowchart illustrating a real-time detection method for key parameters according to an embodiment of the present invention.

[0040] Figure 3 This is a flowchart of an improved binary-based hash algorithm according to an embodiment of the present invention.

[0041] Figure 4 This is a block diagram of a real-time detection system for key parameters based on digital twins, according to an embodiment of the present invention. Detailed Implementation

[0042] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of methods and systems consistent with some aspects of this application as detailed in the appended claims.

[0043] Traditional methods for detecting structural health parameters such as temperature fields rely on sensors to acquire relevant data. However, real-time monitoring of certain positional parameters is insufficient using only the finite element method. To address this issue, this patent establishes a digital twin platform. Based on a joint simulation system using programming languages ​​and finite element analysis software, the data collected by sensors is transmitted in real-time to this joint simulation system for numerical simulation. Finally, an improved hash algorithm is used to quickly identify maximum or outlier values ​​in the numerically simulated structure and pinpoint their corresponding locations.

[0044] Figure 1 This is a flowchart illustrating a real-time detection method for key parameters based on digital twins, according to an exemplary embodiment. The method may include the following steps:

[0045] Step S1: Collect data through sensors as input data for numerical simulation of the target structure. The input data consists of physical health parameters, including stress, temperature, and / or magnetic field strength.

[0046] In many cases, it is not possible to deploy sensors at all monitoring points on the target equipment. For example, in special detections such as the internal temperature field of a transformer structure, due to factors such as excessively high temperatures and a sealed environment, it is impossible to deploy sensors inside the transformer, which may result in the loss of detection at critical locations, especially the detection of changes in the internal core temperature.

[0047] The solution proposed in this application only requires the placement of sensors at conventional locations. For example, in transformer monitoring, relevant sensors can be set up at external monitoring points to collect measured data from these points in real time, which can then be used as input data for numerical simulation of the target structure.

[0048] Step S2: Based on the secondary development of finite element analysis software, establish a joint simulation system of programming language and finite element model.

[0049] This solution is based on digital twin technology and utilizes the secondary development of finite element analysis software to establish a co-simulation system. For example, for transformer monitoring, a 1:1 simulation model of the transformer can be established as the basis for establishing a co-simulation system for numerical simulation.

[0050] Step S3: Perform numerical simulation on the input data using the co-simulation system to obtain real-time all-around data of the target structure.

[0051] Based on a pre-established simulation model, numerical simulation is performed using real-time measured data from selected locations to obtain real-time, comprehensive data of the target structure. Since both the measured data and the numerical simulation are performed in real time, the resulting comprehensive data is also real-time. For example, in transformer monitoring, only measured data from some external monitoring points can be collected, and real-time data from some key points inside the transformer can be obtained through simulation.

[0052] Step S4: The numerical simulation result data is detected using an improved binary hash algorithm, and outliers and their corresponding locations are returned.

[0053] The technical solution of this application is based on digital twin technology. It achieves comprehensive detection of the target structure through data interaction between reality and virtuality. It not only solves the problem of comprehensive data detection that traditional algorithms cannot achieve, but also realizes real-time feedback of important data parameters. At the same time, it performs comprehensive detection of simulation result data through an improved binary-based hash algorithm and can return outliers and their locations, providing a more convenient and comprehensive option for the health detection of the target structure and effectively preventing accidents from occurring.

[0054] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0055] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0056] This embodiment utilizes the aforementioned real-time detection method for key parameters to perform real-time detection of key transformer parameters. The specific implementation process is as follows: Figure 2 As shown.

[0057] (1) Build a digital twin platform and use sensors to collect physical information such as the appearance of the transformer and the internal iron core winding, structural and material parameters, stress, temperature, and electromagnetic (current, voltage, intensity, etc.) as input data for numerical simulation of the target structure.

[0058] (2) Based on the secondary development of finite element analysis software, the joint simulation of programming language and finite element model is realized; Since the transformer structure is relatively complex, it is necessary to make appropriate simplifications when establishing the model. After simplification, it mainly includes the following parts: three-column iron core, high, medium and low voltage windings on the iron core, oil tank and transformer oil between the three. The simulation model is established at 1:1; The joint simulation system is embedded into the digital twin platform to realize the real-time detection of transformer data in all aspects.

[0059] (3) Figure 3As shown, step S4 uses an improved binary hash algorithm to detect numerical simulation results data, specifically including the following steps: dividing the numerical simulation results data into two groups: numerical simulation data and node coordinate information, and converting them into two groups of binary data respectively; wherein the numerical simulation data and node coordinate information correspond one-to-one; removing highly repetitive data based on Hamming distance; mapping the numerical simulation results data to a table through a hash function, and then comparing and sorting them; directly obtaining the maximum value from the table, or comparing it with a threshold to determine whether there are outliers.

[0060] First, the dataset is preprocessed, and the numerical simulation data and node coordinate information are divided into two groups of data, A and B, i.e., data C = {A; B}. Each data corresponds to a node coordinate information, and the coordinate information is transformed in xyz order.

[0061] Convert data A and B into two different sets of binary data, and establish a Hamming space of equal dimension, namely C. bin ={A bin B bin}, where the subscript bin indicates that the data is binary data, measured via Hamming distance. Highly repetitive data is removed to optimize data storage space. If the Hamming distance between physical information and coordinate information is simultaneously less than or equal to 1, then highly repetitive data is removed based on this criterion. For example, for any two data C... i ={A i B i} and C j ={A j B j If A i With A j Hamming distance, B i With B j If the Hamming distances of C and C are both less than or equal to 1, then C i With C j This is highly complex data; in this case, C can be removed. i and C j Any one of the data in the dataset.

[0062] Secondly, C bin A hash table is mapped using hash functions. A family of hash functions H is defined, and each hash table is divided into multiple hash buckets. Sequences are assigned to their corresponding hash buckets using hash functions. Only sequences A within a hash bucket are processed. bin Perform a comparative sort and merge the sorted data in each hash bucket in an ordered manner, while ensuring B bin Follow A bin Changes, thereby obtaining information about A bin The sorted table is in order and the corresponding B is not missing. bin Information.

[0063] Finally, the maximum value can be directly obtained from the table. At the same time, threshold comparison can be performed to determine whether there are outliers and their corresponding positions. The maximum value or outlier is used as query data, and the corresponding hash bucket is obtained through the hash function. The candidate results are obtained by union.

[0064] (4) Redirect the returned maximum value or outlier to C bin The data is converted to floating-point number to obtain coordinate information; abnormal changes are found by comparing the coordinate information, or the data and coordinate information are returned directly through the outlier, thus achieving comprehensive detection.

[0065] If an outlier occurs, the data and its coordinates are returned directly with a warning. Alternatively, the position corresponding to the maximum output value is compared, the similarity between the coordinates of the candidate result set data is calculated, and it is determined whether the coordinates of the maximum value have changed beyond the normal range. If it is a normal operating condition, the position of the approximate data point will remain basically unchanged. If it changes, the fault risk can be detected in time and a warning can be issued.

[0066] Figure 4 This is a block diagram illustrating a real-time detection system for key parameters based on a digital twin, according to an exemplary embodiment. (Refer to...) Figure 4 The system includes a data acquisition module 401, a model building module 402, a numerical simulation module 403, and a data detection module 404.

[0067] The data acquisition module 401 is used to collect data through sensors as input data for the numerical simulation of the target structure. The model building module 402 is used to establish a co-simulation system of programming language and finite element model based on the secondary development of finite element analysis software. The numerical simulation module 403 is used to perform numerical simulation on the input data through the co-simulation system to obtain real-time all-round data of the target structure. The data detection module 404 is used to detect the numerical simulation result data based on an improved binary hash algorithm and return outliers and their corresponding locations.

[0068] Regarding the systems in the above embodiments, the specific steps for each module to perform operations have been described in detail in the embodiments related to the method, and will not be elaborated further here. Each module in the above-described real-time detection system for key parameters based on digital twins can be implemented entirely or partially through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0069] In one embodiment, a computer device is provided, comprising a processor and a memory connected via a system bus. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. When executed by the processor, the computer program implements a real-time detection method for key parameters based on digital twins: data is collected by sensors as input data for numerical simulation of the target structure; a co-simulation system integrating the programming language and the finite element model is established based on secondary development of finite element analysis software; numerical simulation is performed on the input data through the co-simulation system to obtain real-time omnidirectional data of the target structure; and an improved binary hash algorithm is used to detect the numerical simulation results and return outliers and their corresponding locations.

[0070] In one embodiment, a computer-readable storage medium is also provided, on which a computer program is stored. When executed by a processor, the computer program implements a real-time detection method for key parameters based on digital twins: data is collected by sensors as input data for numerical simulation of the target structure; a co-simulation system of programming language and finite element model is established based on secondary development of finite element analysis software; numerical simulation is performed on the input data through the co-simulation system to obtain real-time all-round data of the target structure; and the numerical simulation result data is detected based on an improved binary hash algorithm, and outliers and their corresponding locations are returned.

[0071] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0072] It should be noted that in the description of this application, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this application, unless otherwise stated, "a plurality of" means at least two.

[0073] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the function involved, as will be understood by those skilled in the art to which embodiments of this application pertain.

[0074] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0075] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0076] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0077] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0078] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0079] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for real-time detection of key parameters based on digital twins, characterized in that, include: Data is collected through sensors and used as input data for numerical simulation of the target structure. Based on the secondary development of finite element analysis software, a joint simulation system of programming language and finite element model is established. The joint simulation system is used to perform numerical simulation on the input data to obtain real-time all-round data of the target structure. An improved binary hash algorithm is used to detect numerical simulation results data and return outliers and their corresponding locations. The detection of numerical simulation results data using this improved binary hash algorithm includes the following steps: dividing the numerical simulation results data into two groups: numerical simulation data and node coordinate information, and converting each group into two sets of binary data; wherein the numerical simulation data and node coordinate information correspond one-to-one. The process of dividing the numerical simulation results data into two groups and converting each group into two sets of binary data includes the following steps: the numerical simulation results data is C={A; B}, where A represents the numerical simulation data and B represents the node coordinate information; converting the two sets of data A and B into two sets of binary data respectively, and establishing a Hamming space of equal dimension, i.e., C... bin = {A bin B bin }; where the subscript bin indicates that the data is binary data; high repetition data is removed based on Hamming distance; the numerical simulation results data are mapped to a table through a hash function, and then compared and sorted; the maximum value is directly obtained from the table, or a threshold comparison is performed to determine whether there are outliers.

2. The method according to claim 1, characterized in that, The input data are health parameters of physical information; the input data includes: stress, temperature and / or magnetic field strength.

3. The method according to claim 1, characterized in that, The numerical simulation of the input data using the co-simulation system includes the following steps: The transformer is parametrically modeled and numerically simulated using data collected by sensors through a co-simulation system. The parametrically modeled simulation model is established at a 1:1 scale, thereby obtaining real-time all-round data of the target structure.

4. The method according to claim 1, characterized in that, Removing highly repetitive data based on Hamming distance includes the following steps: For any two data C i ={A i B i } and C j ={A j B j If A i With A j Hamming distance, B i With B j If the Hamming distances of C and C are both less than or equal to 1, then C i With C j This is highly complex data.

5. The method according to claim 1, characterized in that, The numerical simulation results are mapped to a table using a hash function, and then compared and sorted, including the following steps: C bin Mapped to a table using a hash function; Define a family of hash functions H, divide each hash table into multiple hash buckets, and use the hash functions to assign sequences to the corresponding hash buckets; Only for A in the hash bucket bin Perform a comparative sort and merge the sorted data from each hash bucket in an orderly manner, while ensuring that B bin Follow A bin The order of change.

6. A real-time detection system for key parameters based on digital twins, characterized in that, include: The data acquisition module is used to collect data through sensors as input data for numerical simulation of the target structure. The model building module is used for secondary development based on finite element analysis software to establish a joint simulation system of programming language and finite element model; The numerical simulation module is used to perform numerical simulation on the input data through the co-simulation system to obtain real-time all-round data of the target structure; The data detection module is used to detect numerical simulation result data based on an improved binary hash algorithm and return outliers and their corresponding locations. The detection of numerical simulation result data using the improved binary hash algorithm includes the following steps: dividing the numerical simulation result data into two groups: numerical simulation data and node coordinate information, and converting each group into two sets of binary data; wherein the numerical simulation data and node coordinate information correspond one-to-one. The process of dividing the numerical simulation result data into two groups and converting each group into two sets of binary data includes the following steps: the numerical simulation result data is C={A; B}, where A represents the numerical simulation data and B represents the node coordinate information; converting the two sets of data A and B into two sets of binary data respectively, and establishing a Hamming space of equal dimension, i.e., C... bin = {A bin B bin }; where the subscript bin indicates that the data is binary data; high repetition data is removed based on Hamming distance; the numerical simulation results data are mapped to a table through a hash function, and then compared and sorted; the maximum value is directly obtained from the table, or a threshold comparison is performed to determine whether there are outliers.

7. A computer device, characterized in that, include: Memory, used to store computer programs; A processor for executing a computer program in the memory to implement the operational steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the operational steps of the method according to any one of claims 1 to 5.

Images