Digital twin model updating method, device and equipment, medium and product

Abstract

The invention relates to a digital twin model updating method and device, equipment, a medium and a product, and is applied to the technical field of computers. The method comprises the following steps: acquiring current equipment operation data of a digital twin model from a plurality of data sources; and determining an equipment operation deviation value according to the predicted equipment operation data and the current equipment operation data of the digital twin model. And under the condition that the equipment operation deviation value is greater than a preset threshold value, calculating a current value of a model parameter based on the current equipment operation data and the model parameter of the digital twin model at the previous moment. And updating the digital twin model according to the current values of the model parameters. And determining the deviation between the actual operation of the equipment and the prediction result of the digital twinborn model in real time through redundant current equipment operation data from a plurality of data sources, and updating and correcting the model parameters of the digital twinborn model so as to enable the digital twinborn model to accord with the actual operation condition of the current equipment. Therefore, the updating accuracy of the digital twin model is improved.

Description

Technical Field

[0001] The present application belongs to the field of computer technology, and specifically relates to a method, device, equipment, medium and product for updating a digital twin model. Background Art

[0002] Digital twins make full use of data such as physical models, sensors, and operation history, integrate multi-disciplinary, multi-physical, multi-scale, and multi-probability simulation processes, and complete mapping in virtual space to reflect the entire life cycle of the corresponding physical equipment. The digital twin model is not a fixed transient simulation model, but can be adjusted and updated in real time based on external data.

[0003] Generally, the digital twin model can be corrected offline for a specific type of data source. However, this makes it difficult to meet the needs of multi-dimensional status monitoring of complex systems, resulting in reduced accuracy and robustness of digital twin model predictions, thereby reducing the accuracy of digital twin model updates. Summary of the invention

[0004] In view of the above problems, the present disclosure is proposed. The present disclosure provides a method, device, equipment, medium and product for updating a digital twin model, which can improve the accuracy of updating the digital twin model.

[0005] According to one aspect of the present disclosure, a method for updating a digital twin model is provided, comprising:

[0006] Obtain current equipment operation data for digital twin models from multiple data sources;

[0007] Determine a device operation deviation value according to the predicted device operation data of the digital twin model and the current device operation data;

[0008] When the device operation deviation value is greater than a preset threshold, the current value of the model parameter is calculated based on the current device operation data and the model parameter of the digital twin model at the previous moment;

[0009] The digital twin model is updated according to the current values ​​of the model parameters.

[0010] Optionally, when the device operation deviation value is greater than a preset threshold, calculating the current value of the model parameter based on the current device operation data and the model parameter of the digital twin model at the previous moment includes:

[0011] Obtaining a Kalman gain matrix, model parameters of the digital twin model at the previous moment, and a Kalman filter measurement matrix, wherein the model parameters are model state parameters;

[0012] The current value of the model state parameter is calculated according to the model state parameter at the previous moment, the Kalman gain matrix, the Kalman filter measurement matrix, the predicted device operation data and the current device operation data.

[0013] Optionally, when the device operation deviation value is greater than a preset threshold, calculating the current value of the model parameter based on the current device operation data and the model parameter of the digital twin model at the previous moment includes:

[0014] Obtaining the model parameters of the digital twin model at the previous moment and the occurrence probability of the current device operation data, wherein the model parameters are particle weight parameters;

[0015] The current value of the particle weight parameter is calculated according to the particle weight parameter at the last moment and the occurrence probability of the current device operation data.

[0016] Optionally, obtaining the Kalman gain matrix includes:

[0017] Obtaining a state error covariance matrix and a measurement noise covariance matrix of the digital twin model;

[0018] The Kalman gain matrix is ​​calculated according to the state error covariance matrix of the digital twin model, the Kalman filter measurement matrix and the measurement noise covariance matrix.

[0019] Optionally, obtaining the occurrence probability of the current device operation data includes:

[0020] Get the particle preset parameters of the particle filter;

[0021] The occurrence probability of the current device operation data is calculated according to the particle preset parameters and the current device operation data.

[0022] Optionally, obtaining current equipment operation data of the digital twin model from multiple data sources includes:

[0023] Based on multiple different types of sensors, collect current device collection data of the digital twin model;

[0024] Cleaning the data collected by the current device to obtain first device data;

[0025] Perform data fusion according to the first device data and the weight corresponding to each of the first device data to determine current device fusion data;

[0026] Generate a device operation feature vector of the digital twin model according to the current device fusion data and the model weighted matrix;

[0027] The device operation feature vector is used as the current device operation data.

[0028] According to another aspect of the present disclosure, there is provided a device for updating a digital twin model, comprising:

[0029] An acquisition module is used to obtain the current equipment operation data of the digital twin model from multiple data sources;

[0030] A determination module, used to determine a device operation deviation value according to the predicted device operation data of the digital twin model and the current device operation data;

[0031] A calculation module, configured to calculate a current value of the model parameter based on the current device operation data and the model parameter of the digital twin model at a previous moment when the device operation deviation value is greater than a preset threshold;

[0032] An updating module is used to update the digital twin model according to the current values ​​of the model parameters.

[0033] According to another aspect of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor runs the computer program to implement the above-mentioned digital twin model updating method.

[0034] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and the program is executed by a processor to implement the above-mentioned digital twin model update method.

[0035] According to another aspect of the present disclosure, a computer program product is provided, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the update method for implementing the above-mentioned digital twin model.

[0036] In the present disclosure, the current device operation data of the digital twin model from multiple data sources is obtained. According to the predicted device operation data and the current device operation data of the digital twin model, the device operation deviation value is determined. When the device operation deviation value is greater than the preset threshold, the current value of the model parameter is calculated based on the current device operation data and the model parameters of the digital twin model at the previous moment. According to the current value of the model parameter, the digital twin model is updated. Through the redundant current device operation data from multiple data sources, the deviation between the actual operation of the device and the predicted result of the digital twin model is determined in real time, and the model parameters of the digital twin model are updated and corrected so that the digital twin model conforms to the actual operation of the current device. Therefore, the accuracy of the update of the digital twin model is improved.

[0037] It is to be understood that both the foregoing general description and the following detailed description are exemplary, and are intended to provide further explanation of the technology as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and other purposes, features and advantages of the present disclosure will become more apparent by describing the embodiments of the present disclosure in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0039] Figure 1 A flowchart of a method for updating a digital twin model provided in the present invention.

[0040] Figure 2 A schematic diagram of the structure of a digital twin model updating device provided in the present invention.

[0041] Figure 3 A hardware block diagram of an electronic device provided by the present disclosure.

[0042] Figure 4 A schematic diagram of a computer program product provided by the present disclosure. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the application scenario of the solution of the present application is first described below.

[0044] With the increase in the complexity of modern equipment structure and the degree of discipline integration, traditional fault prediction and health management technologies face many challenges. First, due to the limitations of sensor layout, the accuracy of key parameter data collection is difficult to guarantee; second, the data collected during equipment operation is often interfered by factors such as environmental noise, which affects the validity of the data; in addition, the maintenance and data collection costs of complex equipment are high, and traditional methods are difficult to quickly and economically achieve efficient health management and fault prediction. Digital twins make full use of physical models, sensors, operation history and other data, integrate multi-disciplinary, multi-physical quantity, multi-scale, and multi-probability simulation processes, complete mapping in virtual space, and thus reflect the entire life cycle of the corresponding physical equipment. The digital twin model is not a fixed transient simulation model, but can be adjusted and updated in real time according to external data to reflect the actual status of the equipment, and then used for fault prediction and health management.

[0045] Currently, digital twin models can be corrected offline for specific types of data sources. However, this makes it difficult to meet the needs of multi-dimensional status monitoring of complex systems, resulting in reduced accuracy and robustness of digital twin model predictions, thereby reducing the accuracy of digital twin model updates.

[0046] In the present disclosure, the current device operation data of the digital twin model from multiple data sources is obtained. According to the predicted device operation data and the current device operation data of the digital twin model, the device operation deviation value is determined. When the device operation deviation value is greater than the preset threshold, the current value of the model parameter is calculated based on the current device operation data and the model parameters of the digital twin model at the previous moment. According to the current value of the model parameter, the digital twin model is updated. Through the redundant current device operation data from multiple data sources, the deviation between the actual operation of the device and the predicted result of the digital twin model is determined in real time, and the model parameters of the digital twin model are updated and corrected so that the digital twin model conforms to the actual operation of the current device. Therefore, the accuracy of the update of the digital twin model is improved.

[0047] In order to make the purpose, technical solution and advantages of the present disclosure more obvious, the exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described here.

[0048] Figure 1 The present invention provides a flowchart of a method for updating a digital twin model. Figure 1 As shown, the method includes:

[0049] S101: Obtain current equipment operation data of the digital twin model from multiple data sources.

[0050] Specifically, in this embodiment, multiple sensors are set at different positions of the physical device corresponding to the digital twin model to collect the current device operation data. The sensor layout can be optimized according to the working characteristics and key parameters of the physical device to ensure real-time monitoring of the core components and key operating status of the physical device. Through reasonable sensor layout, the impact of space limitations on data collection can be reduced. Collecting data from multiple data sources can improve the accuracy and reliability of data collection, and at the same time overcome the data noise problem that may be caused by a single sensor. Among them, multiple data sources can be understood as setting multiple sensors for monitoring each key parameter, and monitoring key parameters in multiple dimensions at the same time.

[0051] For example, the digital twin system of a wind turbine needs to monitor key parameters including wind speed, rotation speed, and torque, which constitute multi-dimensional key parameters. Multiple sensors for monitoring wind speed, multiple sensors for monitoring rotation speed, and multiple sensors for monitoring torque are set on the corresponding components of the wind turbine. These sensors are multiple data sources for multi-dimensional key parameters.

[0052] S102: Determine the equipment operation deviation value according to the predicted equipment operation data and the current equipment operation data of the digital twin model.

[0053] Specifically, the digital twin model completes the mapping of the physical device in the virtual space through the simulation process. The digital twin model can predict the device operation data of the physical device based on the current operation status of the model, that is, predict the device operation data. Based on the predicted device operation data and the current device operation data collected by the sensor from the physical device in real time, deviation detection can be performed to determine the deviation value between the digital twin model and the physical device at the current moment, that is, the device operation deviation value.

[0054] The equipment operation deviation value can be calculated according to the following formula:

[0055] ΔF(t)=F(t)-M(t)

[0056] Among them, ΔF(t) is the equipment operation deviation value, F(t) is the current equipment operation data, and M(t) is the predicted equipment operation data.

[0057] S103: When the equipment operation deviation value is greater than a preset threshold, the current value of the model parameter is calculated based on the current equipment operation data and the model parameters of the digital twin model at the previous moment.

[0058] Specifically, when the device operation deviation value is greater than the preset threshold, it means that there is a difference between the digital twin model and the physical device, and the digital twin model cannot accurately map the current state of the physical device, and the model parameter update process needs to be triggered. The current value of the model parameter can be calculated based on the current device operation data and the model parameters of the digital twin model at the previous moment.

[0059] Among them, the model parameters may include model state parameters and particle weight parameters. The digital twin model can use the Kalman filter method to estimate the parameters of linear, approximately linear, or nonlinear systems that can be processed by linearization, so the model state parameters that affect the output results of the Kalman filter can be a type of model parameter. The digital twin model can use the particle filter method to estimate the parameters of complex nonlinear models, so the particle weight parameter that affects the output results of the particle filter is a type of model parameter.

[0060] S104: Update the digital twin model according to the current values ​​of the model parameters.

[0061] Specifically, after calculating the current values ​​of the model parameters of the digital twin model, the digital twin model is self-updated to achieve online adjustment of the model parameters of the digital twin model to ensure the real-time and accuracy of the digital twin model.

[0062] In the present disclosure, the current device operation data of the digital twin model from multiple data sources is obtained. According to the predicted device operation data and the current device operation data of the digital twin model, the device operation deviation value is determined. When the device operation deviation value is greater than the preset threshold, the current value of the model parameter is calculated based on the current device operation data and the model parameters of the digital twin model at the previous moment. According to the current value of the model parameter, the digital twin model is updated. Through the redundant current device operation data from multiple data sources, the deviation between the actual operation of the device and the predicted result of the digital twin model is determined in real time, and the model parameters of the digital twin model are updated and corrected so that the digital twin model conforms to the actual operation of the current device. Therefore, the accuracy of the update of the digital twin model is improved.

[0063] In a possible implementation, when the equipment operation deviation value is greater than a preset threshold, an exemplary method for calculating the current value of the model parameter based on the current equipment operation data and the model parameter of the digital twin model at the previous moment includes:

[0064] Obtain the Kalman gain matrix, the model parameters of the digital twin model at the previous moment, and the Kalman filter measurement matrix.

[0065] Specifically, in this embodiment, the model parameters are model state parameters. The Kalman gain matrix is ​​used to characterize the weight relationship between the state of the physical device estimated by the digital twin model and the physical device's own measurement. The Kalman filter measurement matrix is ​​the data that maps the model state parameters at the previous moment to the space where the physical device is located, so that the state of the physical device estimated by the digital twin model is aligned with the dimension of the physical device's own measurement.

[0066] For example, the method of obtaining the Kalman gain matrix includes:

[0067] Obtain the state error covariance matrix and measurement noise covariance matrix of the digital twin model; calculate the Kalman gain matrix based on the state error covariance matrix, Kalman filter measurement matrix and measurement noise covariance matrix of the digital twin model.

[0068] Specifically, the measurement noise covariance matrix represents the difference between the measured value and the true value, which is determined by the Kalman filter itself. The state error covariance matrix is ​​a matrix composed of the covariances between states. The Kalman gain matrix can be calculated according to the following formula:

[0069] K(t)=P(t)H T (H*P(t)*H T +R) -1

[0070] Where K(t) is the Kalman gain matrix, P(t) is the state error covariance matrix, H is the Kalman filter measurement matrix, R is the measurement noise covariance matrix, and H T is the transposed matrix of the Kalman filter measurement matrix.

[0071] Afterwards, the current values ​​of the model state parameters are calculated based on the model state parameters at the previous moment, the Kalman gain matrix, the Kalman filter measurement matrix, the predicted device operation data, and the current device operation data.

[0072] Specifically, the current value of the model state parameter can be calculated according to the following formula:

[0073] θ(t+1)=θ(t)+K(t)*(F(t)-H*M(t))

[0074] Among them, θ(t+1) is the current value of the model state parameter, θ(t) is the model state parameter at the previous moment, K(t) is the Kalman gain matrix, F(t) is the current equipment operation data, H is the Kalman filter measurement matrix, and M(t) is the predicted equipment operation data.

[0075] In a possible implementation, when the equipment operation deviation value is greater than a preset threshold, an exemplary method for calculating the current value of the model parameter based on the current equipment operation data and the model parameter of the digital twin model at the previous moment includes:

[0076] Obtain the model parameters of the digital twin model at the previous moment and the probability of occurrence of the current equipment operation data.

[0077] Specifically, in this embodiment, the model parameter is a particle weight parameter. Particle filtering is based on the Monte Carlo method, does not rely on the assumption of Gaussian distribution, and is applicable to systems with nonlinear and / or non-Gaussian noise. Since particle filtering does not rely on a specific distribution assumption, it can have better robustness to deviations from model errors and noise distribution.

[0078] For example, obtaining the occurrence probability of the current device operation data includes:

[0079] Obtain particle preset parameters of the particle filter; calculate the occurrence probability of the current device operation data according to the particle preset parameters and the current device operation data.

[0080] Specifically, the particle preset parameters are pre-given parameters based on the likelihood function. The probability of occurrence of the current device operation data is calculated according to the following formula:

[0081]

[0082] in, is the probability of occurrence of the current device operation data, is the preset parameters for the particles, and F(t) is the current device operation data.

[0083] Afterwards, the current value of the particle weight parameter is calculated based on the particle weight parameter at the previous moment and the occurrence probability of the current device operation data.

[0084] Specifically, the current value of the particle weight parameter is calculated according to the following formula:

[0085]

[0086] in, is the current value of the particle weight parameter, is the particle weight parameter at the previous moment, The probability of occurrence of the current device running data.

[0087] In one possible implementation, an exemplary method for obtaining current equipment operation data of a digital twin model from multiple data sources includes:

[0088] Based on multiple different types of sensors, the current equipment collection data of the digital twin model is collected.

[0089] Specifically, multiple sensors are set up at different locations of the physical equipment corresponding to the digital twin model to collect the current equipment operation data. Through reasonable sensor layout, the impact of space limitations on data collection can be reduced. Collecting data from multiple data sources can improve the accuracy and reliability of data collection, and at the same time overcome the data noise problem that may be caused by a single sensor.

[0090] The data collected by the current device is cleaned to obtain the first device data.

[0091] Specifically, the data collected by the current device is cleaned, denoised, interpolated, and other data cleaning processes are performed to obtain first device data with better quality.

[0092] Data fusion is performed according to the first device data and the weight corresponding to each first device data to determine current device fusion data.

[0093] Specifically, when multiple sensors are laid out, due to different layout positions and different characteristics of measurement parameters, the data collected by different sensors will have different weights. By using weights to fuse data, more accurate and reliable fused data of the current device can be obtained.

[0094] The current device fusion data is calculated according to the following formula:

[0095]

[0096] Among them, X(t) is the current device fusion data, w i is the weight corresponding to the first device data, S i (t) is the first device data, and n is the number of the first device data.

[0097] According to the current device fusion data and the model weighted matrix, the device operation feature vector of the digital twin model is generated; the device operation feature vector is used as the current device operation data.

[0098] Specifically, the model weighted matrix is ​​used to extract features from the current device fusion data and generate device operation feature vectors to facilitate the simulation of the digital twin model.

[0099] The equipment operation characteristic vector is calculated according to the following formula:

[0100] F(t)=W*X(t)

[0101] Among them, F(t) is the device operation feature vector, W is the model weighting matrix, and X(t) is the current device fusion data.

[0102] In a possible implementation, after the digital twin model is updated according to the current values ​​of the model parameters, the digital twin model can accurately reflect the actual operating status of the equipment. The updated digital twin model can be used to perform fault prediction and health management of the physical equipment, including degradation monitoring, fault diagnosis, and remaining life prediction. Based on the prediction results of the digital twin model, equipment maintenance recommendations are generated to reduce the maintenance frequency and cost of the actual equipment.

[0103] Figure 2 The following is a schematic diagram of the structure of a digital twin model update device provided by the present disclosure. Figure 2 As shown, the device 200 includes: an acquisition module 210, a determination module 220, a calculation module 230 and an update module 240.

[0104] An acquisition module 210 is used to acquire current equipment operation data of the digital twin model from multiple data sources;

[0105] A determination module 220, configured to determine a device operation deviation value according to the predicted device operation data of the digital twin model and the current device operation data;

[0106] A calculation module 230 is used to calculate the current value of the model parameter based on the current device operation data and the model parameter of the digital twin model at the previous moment when the device operation deviation value is greater than a preset threshold;

[0107] The updating module 240 is used to update the digital twin model according to the current value of the model parameter.

[0108] Optionally, the calculation module is used to:

[0109] Obtaining a Kalman gain matrix, model parameters of the digital twin model at the previous moment, and a Kalman filter measurement matrix, wherein the model parameters are model state parameters;

[0110] The current value of the model state parameter is calculated according to the model state parameter at the previous moment, the Kalman gain matrix, the Kalman filter measurement matrix, the predicted device operation data and the current device operation data.

[0111] Optionally, the calculation module is used to:

[0112] Obtaining the model parameters of the digital twin model at the previous moment and the occurrence probability of the current device operation data, wherein the model parameters are particle weight parameters;

[0113] The current value of the particle weight parameter is calculated according to the particle weight parameter at the last moment and the occurrence probability of the current device operation data.

[0114] Optionally, the calculation module is used to:

[0115] Obtaining a state error covariance matrix and a measurement noise covariance matrix of the digital twin model;

[0116] The Kalman gain matrix is ​​calculated according to the state error covariance matrix of the digital twin model, the Kalman filter measurement matrix and the measurement noise covariance matrix.

[0117] Optionally, the calculation module is used to:

[0118] Get the particle preset parameters of the particle filter;

[0119] The occurrence probability of the current device operation data is calculated according to the particle preset parameters and the current device operation data.

[0120] Optionally, the acquisition module is used to:

[0121] Based on multiple different types of sensors, collect current device collection data of the digital twin model;

[0122] Cleaning the data collected by the current device to obtain first device data;

[0123] Perform data fusion according to the first device data and the weight corresponding to each of the first device data to determine current device fusion data;

[0124] Generate a device operation feature vector of the digital twin model according to the current device fusion data and the model weighted matrix;

[0125] The device operation feature vector is used as the current device operation data.

[0126] The present application also provides an electronic device to execute the above-mentioned method for updating the digital twin model. Figure 3 It shows a schematic diagram of an electronic device provided by some embodiments of the present application. Figure 3 As shown, the electronic device 30 includes: a processor 300, a memory 301, a bus 302 and a communication interface 303, and the processor 300, the communication interface 303 and the memory 301 are connected through the bus 302; the memory 301 stores a computer program that can be run on the processor 300, and when the processor 300 runs the computer program, it executes the updating method of the digital twin model provided in any of the aforementioned embodiments of the present application.

[0127] The memory 301 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the device network element and at least one other network element is realized through at least one communication interface 303 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0128] The bus 302 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 301 is used to store programs, and the processor 300 executes the program after receiving the execution instruction. The updating method of the digital twin model disclosed in any implementation of the embodiment of the present application may be applied to the processor 300, or implemented by the processor 300.

[0129] The processor 300 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 300. The above processor 300 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 301, and the processor 300 reads the information in the memory 301 and completes the steps of the above method in combination with its hardware.

[0130] The electronic device provided in the embodiment of the present application and the method for updating the digital twin model provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0131] An embodiment of the present application also provides a computer-readable storage medium corresponding to the method for updating the digital twin model provided in the aforementioned embodiment. The computer-readable storage medium shown may be a CD on which a computer program is stored. When the computer program is run by a processor, it will execute the method for updating the digital twin model provided in any of the aforementioned embodiments.

[0132] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0133] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the method for updating the digital twin model provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0134] The present application embodiment also provides a computer program product 400, such as Figure 4 The computer program product carries a computer program 401, and the instructions included in the program code can be used to execute the steps of the digital twin model update method described in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.

[0135] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is implemented as a computer storage medium. In another optional embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0136] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0137] The block diagrams of the devices, apparatuses, equipment, and systems involved in this disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including," "comprising," "having," and the like are open words, referring to "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or," and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0138] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0139] It should also be noted that in the system and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0140] Various changes, substitutions, and modifications of the techniques described herein may be made without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of the present disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and actions described above. Currently existing or later to be developed processes, machines, manufactures, compositions of events, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects described herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or actions within their scope.

[0141] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0142] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for updating a digital twin model, characterized in that: include: Obtain current equipment operation data for digital twin models from multiple data sources; Determine a device operation deviation value according to the predicted device operation data of the digital twin model and the current device operation data; When the device operation deviation value is greater than a preset threshold, the current value of the model parameter is calculated based on the current device operation data and the model parameter of the digital twin model at the previous moment; The digital twin model is updated according to the current values ​​of the model parameters.

2. The method according to claim 1, characterized in that When the device operation deviation value is greater than a preset threshold, the current value of the model parameter is calculated based on the current device operation data and the model parameter of the digital twin model at the previous moment, including: Obtaining a Kalman gain matrix, model parameters of the digital twin model at the previous moment, and a Kalman filter measurement matrix, wherein the model parameters are model state parameters; The current value of the model state parameter is calculated according to the model state parameter at the previous moment, the Kalman gain matrix, the Kalman filter measurement matrix, the predicted device operation data and the current device operation data.

3. The method according to claim 1 or 2, characterized in that: When the device operation deviation value is greater than a preset threshold, the current value of the model parameter is calculated based on the current device operation data and the model parameter of the digital twin model at the previous moment, including: Obtaining the model parameters of the digital twin model at the previous moment and the occurrence probability of the current device operation data, wherein the model parameters are particle weight parameters; The current value of the particle weight parameter is calculated according to the particle weight parameter at the last moment and the occurrence probability of the current device operation data.

4. The method according to claim 2, characterized in that: The obtaining of the Kalman gain matrix comprises: Obtaining a state error covariance matrix and a measurement noise covariance matrix of the digital twin model; The Kalman gain matrix is ​​calculated according to the state error covariance matrix of the digital twin model, the Kalman filter measurement matrix and the measurement noise covariance matrix.

5. The method according to claim 3, characterized in that: The obtaining the occurrence probability of the current device operation data includes: Get the particle preset parameters of the particle filter; The occurrence probability of the current device operation data is calculated according to the particle preset parameters and the current device operation data.

6. The method according to claim 1, characterized in that The obtaining of current equipment operation data of the digital twin model from multiple data sources includes: Based on multiple different types of sensors, collect current device collection data of the digital twin model; Cleaning the data collected by the current device to obtain first device data; Perform data fusion according to the first device data and the weight corresponding to each of the first device data to determine current device fusion data; Generate a device operation feature vector of the digital twin model according to the current device fusion data and the model weighted matrix; The device operation feature vector is used as the current device operation data.

7. A digital twin model updating device, characterized in that: include: An acquisition module is used to obtain the current equipment operation data of the digital twin model from multiple data sources; A determination module, used to determine a device operation deviation value according to the predicted device operation data of the digital twin model and the current device operation data; A calculation module, configured to calculate a current value of the model parameter based on the current device operation data and the model parameter of the digital twin model at a previous moment when the device operation deviation value is greater than a preset threshold; An updating module is used to update the digital twin model according to the current values ​​of the model parameters.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor runs the computer program to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The invention comprises a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code, and when the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes any one of claims 1 to 6.

Images