Digital twin data processing method and system based on artificial intelligence

Abstract

The invention discloses a digital twin data processing method and system based on artificial intelligence, and belongs to the technical field of data processing. An artificial intelligence algorithm is adopted to construct a digital twin data processing model, and an intelligent optimization algorithm is adopted to train the digital twin data processing model; the method comprises the following steps: training a digital twinborn data processing model to obtain a trained digital twinborn data processing model, and then processing real-time operation parameters of the digital twinborn model by adopting the trained digital twinborn data processing model in an operation process of the digital twinborn model, so that automatic processing of the digital twinborn data can be realized; the processing efficiency and accuracy of the digital twin data can be effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and particularly relates to a digital twin data processing method and system based on artificial intelligence. Background Art

[0002] A digital twin model is a virtual model that is an accurate digital mapping of physical entities, systems, processes, or services in the real world. This model aims to simulate the behavior, performance, and structure of actual objects for analysis, prediction, and optimization without physical prototypes. Generally, digital twin models play a role in data synchronization and data visualization to facilitate the operation monitoring or debugging of machine equipment by staff. However, when using manual operation monitoring, although there is no need to conduct on-site inspections of machine equipment, it is also time-consuming and laborious, and there are situations where monitoring is not in place. Summary of the Invention

[0003] The present invention provides a digital twin data processing method and system based on artificial intelligence to solve the problems of time-consuming and laborious as well as insufficient monitoring caused by the existing digital twin models only providing data monitoring without automatically processing information.

[0004] On the one hand, the present invention provides a digital twin data processing method based on artificial intelligence, including: Constructing a digital twin model corresponding to the target machine equipment and synchronizing the operating parameters of the target machine equipment into the digital twin model to run the digital twin model; Constructing a digital twin data processing model using artificial intelligence algorithms and training the digital twin data processing model using intelligent optimization algorithms to obtain the trained digital twin data processing model; Collecting the real-time operating parameters corresponding to the digital twin model and processing the real-time operating parameters using the trained digital twin data processing model to obtain a parameter processing result; When the parameter processing result meets the preset requirements, corresponding labels and label-associated real-time operating parameters are generated on the digital twin model to complete the processing of digital twin data.

[0005] 2. The digital twin data processing method based on artificial intelligence according to claim 1, wherein constructing a digital twin data processing model using artificial intelligence algorithms includes: constructing a digital twin data processing model using CNN algorithm, R-CNN algorithm, Fast R-CNN algorithm, YOLO algorithm, and / or BP Net algorithm.

[0006] Further, an intelligent optimization algorithm is used to train the digital twin data processing model to obtain the trained digital twin data processing model, including: Initialize the hyperparameters of the digital twin data processing model to generate a population containing multiple parameter individuals; For each parameter individual in the population, apply the parameter individual to the digital twin data processing model and use the cross-entropy loss function to obtain the loss function value corresponding to the parameter individual; According to the loss function value corresponding to the parameter individual, obtain the optimal parameter individual and use the normal distribution jump strategy to update the optimal parameter individual to obtain the updated optimal parameter individual; For any parameter individual, perform a local fast-guided search on the parameter individual according to the optimal parameter individual to obtain the parameter individual after the local fast-guided search; For any parameter individual after the local fast-guided search, perform a multi-information learning search on the parameter individual to obtain the parameter individual after the multi-information learning search; For any parameter individual after the multi-information learning search, perform an adaptive chain search on the parameter individual to obtain the parameter individual after the adaptive chain search; Judge whether the training end condition is satisfied. If so, obtain the trained digital twin data processing model according to the parameter individual after the adaptive chain search. Otherwise, return to the step of obtaining the loss function value.

[0007] Further, for each parameter individual in the population, apply the parameter individual to the digital twin data processing model and use the cross-entropy loss function to obtain the loss function value corresponding to the parameter individual, including: For each parameter individual in the population, apply the parameter individual to the digital twin data processing model to obtain the digital twin data processing model after applying the parameters; Use the historical operating parameters as the input of the digital twin data processing model to obtain the actual output of the digital twin data processing model; Use the data label corresponding to the historical operating parameters as the expected output of the digital twin data processing model, and according to the expected output and the actual output of the digital twin data processing model, use the cross-entropy loss function to obtain the loss function value corresponding to the parameter individual.

[0008] Further, according to the loss function value corresponding to the parameter individual, obtain the optimal parameter individual and use the normal distribution jump strategy to update the optimal parameter individual to obtain the updated optimal parameter individual, including: According to the loss function value corresponding to the parameter individual, determine the parameter individual with the smallest loss function value as the optimal parameter individual; The random jump factor is generated using a normal distribution as follows:

[0009]

[0010]

[0011]

[0012] Based on the random jump factor, the optimal parameter individual is updated to obtain the updated optimal parameter individual as follows: ; where represents the k -th dimension parameter of the optimal parameter individual during the d -th training process, represents the d -th dimension parameter of the updated optimal parameter individual, represents the random jump factor, R represents the adaptive update coefficient, and , represents the first constant term, represents the d -th dimension parameter of the random parameter individual other than the optimal parameter individual, represents the first random jump control factor, v represents the second random jump control factor, represents a random number between (0, 1), satisfies the normal distribution , satisfies the normal distribution , represents the first intermediate parameter, represents the second constant term and is set to 1; represents the gamma function.

[0013] Furthermore, for any parameter individual, local fast-guided search is performed on the parameter individual based on the optimal parameter individual to obtain the parameter individual after local fast-guided search, including: Based on the standard normal distribution, a random guided control factor between (0, 1) is generated; Based on the random guided control factor and the optimal parameter individual, local fast-guided search is performed on the parameter individual to obtain the parameter individual after local fast-guided search as follows: ; where represents the k -th parameter individual during the -th training process, represents the optimal parameter individual,

[0014] Further, for any parameter individual after local fast-guided search, perform multi-information learning search on the parameter individual to obtain the parameter individual after multi-information learning search, including: For any parameter individual after local fast-guided search, randomly match an other parameter individual to the parameter individual to obtain the paired parameter individual corresponding to each parameter individual; According to the paired parameter individual corresponding to the parameter individual, perform learning search on the parameter individual to obtain the first learning information as: ; where represents the first learning information, represents the k nth parameter individual in the th training process, represents the paired parameter individual corresponding to the parameter individual represents the first learning coefficient, represents a random number between (0, 1); According to the historical optimal value corresponding to the parameter individual, perform learning search on the parameter individual to obtain the second learning information as: ; where represents the second learning information, represents the parameter individual corresponding historical optimal value, represents the second learning coefficient, represents a random number between (0, 1); According to the optimal parameter individual, perform learning search on the parameter individual to obtain the third learning information as: ; where represents the third learning information, represents the optimal parameter individual, represents the third learning coefficient, represents a random number between (0, 1); According to the first learning information, the second learning information, and the third learning information, obtain the parameter individual after multi-information learning search as: ; where represents the parameter individual after multi-information learning search .

[0015] Further, for any parameter individual after multi-information learning search, perform adaptive chained search on the parameter individual to obtain the parameter individual after adaptive chained search, including: For any parameter individual after multi-information learning search, obtain the loss function value corresponding to the parameter individual, and arrange the parameter individuals in ascending order of the loss function value; Based on the arranged parameter individuals, perform an adaptive chain search on the parameter individuals, and the parameter individuals after the adaptive chain search are as follows: ; where represents the i th parameter individual after arrangement, represents the parameter individual after the adaptive chain search , represents the i -1th parameter individual after arrangement, and when i is 1, is set to 's historical optimal value; represents the first chain search factor, represents the second chain search factor, represents the fourth random number between (0, 1), represents the fifth random number between (0, 1), represents the adaptive inertia weight, and ; represents the maximum value of the adaptive inertia weight, represents the minimum value of the adaptive inertia weight, and K represents the preset maximum number of training times.

[0016] Furthermore, when the parameter processing result meets the preset requirements, corresponding labels and label-associated real-time operating parameters are generated on the digital twin model, including: When the parameter processing result is abnormal, a label is generated on the digital twin model, and the real-time operating parameters are associated on the secondary interface of the label.

[0017] On the other hand, the present invention provides an artificial intelligence-based digital twin data processing system, including: a digital twin module, a model construction module, a parameter processing module, and a result processing module; The digital twin module is used to construct a digital twin model corresponding to the target machine device and synchronize the operating parameters of the target machine device into the digital twin model to run the digital twin model; The model construction module is used to construct a digital twin data processing model using an artificial intelligence algorithm and train the digital twin data processing model using an intelligent optimization algorithm to obtain the trained digital twin data processing model; The parameter processing module is used to collect the real-time operating parameters corresponding to the digital twin model and process the real-time operating parameters using the trained digital twin data processing model to obtain a parameter processing result; The result processing module is used to generate corresponding tags and tag-associated real-time operation parameters on the digital twin model when the parameter processing result meets the preset requirements, and complete the processing of digital twin data.

[0018] A method and system for processing digital twin data based on artificial intelligence provided by the present invention constructs a digital twin data processing model by using an artificial intelligence algorithm, trains the digital twin data processing model by using an intelligent optimization algorithm, obtains the trained digital twin data processing model, and then processes the real-time operation parameters of the digital twin model by using the trained digital twin data processing model during the operation of the digital twin model, so as to realize the automated processing of digital twin data and effectively improve the processing efficiency and accuracy of digital twin data. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present invention and used together with the specification to explain the principles of the present invention.

[0020] Figure 1 It is a flowchart of a method for processing digital twin data based on artificial intelligence provided by an embodiment of the present invention.

[0021] Figure 2 It is a schematic structural diagram of a system for processing digital twin data based on artificial intelligence provided by an embodiment of the present invention.

[0022] Through the above accompanying drawings, specific embodiments of the present invention have been shown, and there will be more detailed descriptions hereinafter. These drawings and text descriptions are not intended to limit the scope of the inventive concept in any way, but to illustrate the concept of the present invention to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] Here, the exemplary embodiments will be described in detail, and the examples are shown in the accompanying drawings. When the following description refers to the accompanying 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 the present invention. On the contrary, they are only examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0024] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0025] As Figure 1 shown, an embodiment of the present invention provides a method for processing digital twin data based on artificial intelligence, including: S1. Build a digital twin model corresponding to the target machine device, and synchronize the operating parameters of the target machine device to the digital twin model to run the digital twin model. The target machine device can be various devices, such as motors, robotic arms, etc. The digital twin model corresponding to the target machine device can be built using digital twin technology, so that online monitoring or simulation operation of the target machine device can be realized.

[0026] S2. Build a digital twin data processing model using artificial intelligence algorithms, and train the digital twin data processing model using intelligent optimization algorithms to obtain the trained digital twin data processing model. In the embodiment of the present invention, building a digital twin data processing model using artificial intelligence algorithms includes: building a digital twin data processing model using CNN (Convolutional Neural Network) algorithm, R-CNN algorithm, Fast R-CNN algorithm, YOLO algorithm, and / or BP Net (Back Propagation Neural Network) algorithm.

[0027] However, it should be noted that the above artificial intelligence algorithms are only examples in the embodiment of the present invention. Other artificial intelligence algorithms can also be used to build a digital twin data processing model. Similarly, one artificial intelligence algorithm can be used for data processing, or multiple artificial intelligence algorithms can be used for data processing. For example, when it is necessary to process motor digital twin data and monitor motor faults, the CNN algorithm can be used to identify the motor digital twin data, so that whether the motor is faulty can be quickly found, and it can also be used for motor debugging. When it is necessary to process robotic arm digital twin data, the operating parameters and image parameters may need to be processed separately. The YOLO algorithm can be used to process the image parameters, and the CNN algorithm can be used to process the operating parameters.

[0028] S3. Collect the real-time operating parameters corresponding to the digital twin model, and process the real-time operating parameters using the trained digital twin data processing model to obtain a parameter processing result. The trained digital twin data processing model has the ability to identify digital twin data. Therefore, real-time operating parameters can be collected for identification to determine the operating status, that is, a parameter processing result is obtained. For example, when processing motor digital twin data and it is necessary to identify motor faults, the parameter processing result can be the normal category of the motor or the specific fault type of the motor, and the real-time operating parameters can be operating current, operating voltage, operating speed, operating vibration frequency, etc.

[0029] S4. When the parameter processing result meets the preset requirements, generate corresponding labels and label-associated real-time operating parameters on the digital twin model to complete the processing of digital twin data.

[0030] For example, the preset requirements can set specific fault types. When the parameter processing result is the same as the specific fault type, it proves that the motor has a fault. Therefore, a label can be generated at a specific position on the digital twin model of the motor. Assuming there is a problem with the rotor, a label can be generated on the rotor in the digital twin model of the motor. After clicking on the label, a secondary menu can be popped up, and this secondary menu records the real-time operating parameters during the fault, thereby improving the processing efficiency of the digital twin model data.

[0031] In the embodiment of the present invention, an intelligent optimization algorithm is used to train the digital twin data processing model to obtain the trained digital twin data processing model, including: Initialize the hyperparameters of the digital twin data processing model to generate a population containing multiple parameter individuals; Each hyperparameter has its corresponding upper limit and lower limit, and can be randomly initialized between the upper limit and the lower limit to generate parameter individuals. After repeating the initialization multiple times, a population can be generated. For example, when optimizing the hyperparameters of the CNN algorithm, its weight parameters can be initialized.

[0032] For each parameter individual in the population, apply the parameter individual to the digital twin data processing model, and use the cross-entropy loss function to obtain the loss function value corresponding to the parameter individual; According to the loss function value corresponding to the parameter individual, obtain the optimal parameter individual, and use the normal distribution jump strategy to update the optimal parameter individual to obtain the updated optimal parameter individual; For any parameter individual, perform a local fast-guided search on the parameter individual according to the optimal parameter individual to obtain the parameter individual after the local fast-guided search; For any parameter individual after the local fast-guided search, perform a multi-information learning search on the parameter individual to obtain the parameter individual after the multi-information learning search; For any parameter individual after the multi-information learning search, perform an adaptive chain search on the parameter individual to obtain the parameter individual after the adaptive chain search; Judge whether the training end condition is satisfied. If so, obtain the trained digital twin data processing model according to the parameter individual after the adaptive chain search, otherwise return to the step of obtaining the loss function value.

[0033] Optionally, after each search, the parameter individual can be processed for out-of-bounds to ensure the validity of the parameter.

[0034] In the prior art, during the process of optimizing hyperparameters, there is a problem of being easily trapped in local optima. Therefore, embodiments of the present invention provide a new intelligent optimization algorithm to solve the problems existing in the prior art and improve the processing accuracy of digital twin data.

[0035] In the embodiments of the present invention, for each parameter individual in the population, the parameter individual is applied to the digital twin data processing model, and the cross-entropy loss function is used to obtain the loss function value corresponding to the parameter individual, including: For each parameter individual in the population, the parameter individual is applied to the digital twin data processing model to obtain the digital twin data processing model after applying the parameters; Using the historical operating parameters as the input of the digital twin data processing model to obtain the actual output of the digital twin data processing model; Using the data label corresponding to the historical operating parameters as the expected output of the digital twin data processing model, and according to the expected output and the actual output of the digital twin data processing model, the cross-entropy loss function is used to obtain the loss function value corresponding to the parameter individual.

[0036] It should be noted that in addition to using the cross-entropy loss function to obtain the loss function value, other functions such as root mean square loss and mean square loss can also be used to obtain the loss function value.

[0037] In the embodiments of the present invention, according to the loss function value corresponding to the parameter individual, the optimal parameter individual is obtained, and the optimal parameter individual is updated using the normal distribution jump strategy to obtain the updated optimal parameter individual, including: According to the loss function value corresponding to the parameter individual, the parameter individual with the smallest loss function value is determined as the optimal parameter individual; The random jump factor is generated using the normal distribution as:

[0038]

[0039]

[0040]

[0041] According to the random jump factor, the optimal parameter individual is updated to obtain the updated optimal parameter individual as: ; where represents the k -th dimension parameter of the optimal parameter individual during the d -th training process, represents the d -th dimension parameter of the updated optimal parameter individual, represents the random jump factor, R represents the adaptive update coefficient, and , represents the first constant term, represents the d - dimensional parameter of the random parameter individual except the optimal parameter individual, represents the first random jump control factor, v represents the second random jump control factor, represents a random number between (0, 1), satisfying the normal distribution , satisfying the normal distribution , represents the first intermediate parameter, represents the second constant term, and is set to 1; represents the gamma function.

[0042] The normal distribution jump strategy provided by the embodiments of the present invention can effectively perturb the optimal parameter individual, thereby enhancing the global optimization ability of the algorithm and reducing the complexity of the algorithm.

[0043] Optionally, during the process of updating the optimal parameter individual, a greedy algorithm or an annealing simulation algorithm can be used for control to ensure the convergence speed of the algorithm.

[0044] In the embodiments of the present invention, for any parameter individual, local fast-guided search is performed on the parameter individual according to the optimal parameter individual to obtain the parameter individual after local fast-guided search, including: Based on the standard normal distribution, a random guiding control factor between (0, 1) is generated; According to the random guiding control factor and the optimal parameter individual, local fast-guided search is performed on the parameter individual, and the parameter individual after local fast-guided search is: ; where represents the k m - th parameter individual in the k - th training process, represents the optimal parameter individual,

[0045] The local fast-guided search provided by the embodiments of the present invention can enable all parameter individuals to perform fast search around the optimal position, and can effectively improve the search speed of the algorithm.

[0046] In the embodiments of the present invention, for any parameter individual after local fast-guided search, multi-information learning search is performed on the parameter individual to obtain the parameter individual after multi-information learning search, including: For any parameter individual after local fast-guided search, randomly match a parameter individual with another parameter individual to obtain the paired parameter individual corresponding to each parameter individual; According to the paired parameter individual corresponding to the parameter individual, perform learning search on the parameter individual, and the first learning information obtained is: ; where represents the first learning information, represents the k nth parameter individual in the th training process, represents the paired parameter individual corresponding to the parameter individual represents the first learning coefficient, represents a random number between (0, 1); According to the historical optimal value corresponding to the parameter individual, perform learning search on the parameter individual, and the second learning information obtained is: ; where represents the second learning information, represents the parameter individual corresponding historical optimal value, represents the second learning coefficient, represents a random number between (0, 1); According to the optimal parameter individual, perform learning search on the parameter individual, and the third learning information obtained is: ; where represents the third learning information, represents the optimal parameter individual, represents the third learning coefficient, represents a random number between (0, 1); According to the first learning information, the second learning information, and the third learning information, the parameter individual after multi-information learning search is obtained as: ; where represents the parameter individual after multi-information learning search .

[0047] The multi-information learning search provided by the embodiments of the present invention can continuously move forward to a better explored position during the information interaction process, thereby improving the search ability and local search ability of the algorithm.

[0048] In the embodiments of the present invention, for any parameter individual after multi-information learning search, perform adaptive chained search on the parameter individual to obtain the parameter individual after adaptive chained search, including: For any parameter individual after multi-information learning search, obtain the loss function value corresponding to the parameter individual, and arrange the parameter individuals in ascending order of the loss function value; Based on the arranged parameter individuals, perform an adaptive chain search on the parameter individuals, and the parameter individuals after the adaptive chain search are as follows: ; where represents the i th parameter individual after arrangement, represents the parameter individual after the adaptive chain search , represents the i -1th parameter individual after arrangement, and when i is 1, is set to 's historical optimal value; represents the first chain search factor, represents the second chain search factor, represents the fourth random number between (0, 1), represents the fifth random number between (0, 1), represents the adaptive inertia weight, and ; represents the maximum value of the adaptive inertia weight, represents the minimum value of the adaptive inertia weight, and K represents the preset maximum number of training times.

[0049] The adaptive chain search provided by the embodiments of the present invention can enable all parameter individuals to perform collaborative search, perform chain vortex search in the solution space, improve the solution space search ability, and thus enhance the global search ability.

[0050] In the embodiments of the present invention, when the parameter processing result meets the preset requirements, corresponding labels and label-associated real-time operating parameters are generated on the digital twin model, including: When the parameter processing result is abnormal, a label is generated on the digital twin model, and the real-time operating parameters are associated on the secondary interface of the label.

[0051] As Figure 2 shown, the embodiments of the present invention provide a digital twin data processing system based on artificial intelligence, including: a digital twin module 1, a model construction module 2, a parameter processing module 3, and a result processing module 4; The digital twin module 1 is used to construct a digital twin model corresponding to the target machine device, and synchronize the operating parameters of the target machine device into the digital twin model to run the digital twin model; The model construction module 2 is used to construct a digital twin data processing model using an artificial intelligence algorithm, and train the digital twin data processing model using an intelligent optimization algorithm to obtain the trained digital twin data processing model; The parameter processing module 3 is used to collect the real-time operation parameters corresponding to the digital twin model, and process the real-time operation parameters by using the trained digital twin data processing model to obtain a parameter processing result; The result processing module 4 is used to generate corresponding labels and label-associated real-time operation parameters on the digital twin model when the parameter processing result meets the preset requirements, thereby completing the processing of the digital twin data.

[0052] The digital twin data processing system based on artificial intelligence provided by the embodiments of the present invention can execute the above method technical solutions, and its principle and beneficial effects are similar, so details are not described herein again.

[0053] A method and system for processing digital twin data based on artificial intelligence provided by the present invention constructs a digital twin data processing model by using an artificial intelligence algorithm, trains the digital twin data processing model by using an intelligent optimization algorithm to obtain a trained digital twin data processing model, and then processes the real-time operation parameters of the digital twin model by using the trained digital twin data processing model during the operation of the digital twin model, thereby realizing the automatic processing of digital twin data and effectively improving the processing efficiency and accuracy of digital twin data.

[0054] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0055] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0056] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one process or multiple processes and / or blocks. Figure 1 one process or multiple processes and / or blocks Figure 1 or the functions specified in multiple blocks.

[0057] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are performed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one process or multiple processes and / or blocks. Figure 1 one process or multiple processes and / or blocks Figure 1 or the functions specified in multiple blocks.

[0058] Those of ordinary skill in the art can understand that all or part of the steps in implementing the above-mentioned facts and methods can be completed by instructing relevant hardware through a program. The involved program or the program described above can be stored in a computer-readable storage medium. When the program is executed, it includes the following steps: At this time, the corresponding method steps are introduced. The storage medium can be ROM / RAM, magnetic disk, optical disc, etc.

[0059] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A digital twin data processing method based on artificial intelligence, characterized in that, Including: Construct a digital twin model corresponding to the target machine device, and synchronize the operating parameters of the target machine device to the digital twin model to run the digital twin model; Construct a digital twin data processing model using artificial intelligence algorithms, and train the digital twin data processing model using intelligent optimization algorithms to obtain the trained digital twin data processing model; Collect the real-time operating parameters corresponding to the digital twin model, and process the real-time operating parameters using the trained digital twin data processing model to obtain parameter processing results; When the parameter processing result meets the preset requirements, generate corresponding labels and label-associated real-time operating parameters on the digital twin model to complete the processing of the digital twin data.

2. The method for processing digital twin data based on artificial intelligence according to claim 1, wherein Construct a digital twin data processing model using artificial intelligence algorithms, including: constructing a digital twin data processing model using CNN algorithm, R-CNN algorithm, Fast R-CNN algorithm, YOLO algorithm, and / or BP Net algorithm.

3. The method for processing digital twin data based on artificial intelligence according to claim 1, wherein Train the digital twin data processing model using intelligent optimization algorithms to obtain the trained digital twin data processing model, including: Initialize the hyperparameters of the digital twin data processing model to generate a population containing multiple parameter individuals; For each parameter individual in the population, apply the parameter individual to the digital twin data processing model, and use the cross-entropy loss function to obtain the loss function value corresponding to the parameter individual; According to the loss function value corresponding to the parameter individual, obtain the optimal parameter individual, and use the normal distribution jump strategy to update the optimal parameter individual to obtain the updated optimal parameter individual; For any parameter individual, perform local fast-guided search on the parameter individual according to the optimal parameter individual to obtain the parameter individual after local fast-guided search; For any parameter individual after local fast-guided search, perform multi-information learning search on the parameter individual to obtain the parameter individual after multi-information learning search; For any parameter individual after multi-information learning search, perform adaptive chain search on the parameter individual to obtain the parameter individual after adaptive chain search; Judge whether the training end condition is met. If so, obtain the trained digital twin data processing model according to the parameter individual after adaptive chain search, otherwise return to the step of obtaining the loss function value.

4. The method for processing digital twin data based on artificial intelligence according to claim 3, wherein, For each parameter individual in the population, apply the parameter individual to the digital twin data processing model, and use the cross-entropy loss function to obtain the loss function value corresponding to the parameter individual, including: For each parameter individual in the population, apply the parameter individual to the digital twin data processing model to obtain the digital twin data processing model after applying the parameters; Use the historical operating parameters as the input of the digital twin data processing model to obtain the actual output of the digital twin data processing model; Use the data label corresponding to the historical operating parameters as the expected output of the digital twin data processing model, and according to the expected output and actual output of the digital twin data processing model, use the cross-entropy loss function to obtain the loss function value corresponding to the parameter individual.

5. The method for processing digital twin data based on artificial intelligence according to claim 4, wherein, Obtain the optimal parameter individual according to the loss function value corresponding to the parameter individual, and update the optimal parameter individual using the normal distribution jump strategy to obtain the updated optimal parameter individual, including: Determine the parameter individual with the smallest loss function value as the optimal parameter individual according to the loss function value corresponding to the parameter individual; The random jump factor generated using the normal distribution is as follows: Update the optimal parameter individual according to the random jump factor, and the updated optimal parameter individual is as follows: ; where represents the k -th dimension parameter of the optimal parameter individual in the d -th training process, represents the d -th dimension parameter of the updated optimal parameter individual, represents the random jump factor, R represents the adaptive update coefficient, and , represents the first constant term, represents the d -th dimension parameter of the random parameter individual other than the optimal parameter individual, represents the first random jump control factor, v represents the second random jump control factor, represents a random number between (0, 1), follows the normal distribution , follows the normal distribution , represents the first intermediate parameter, represents the second constant term and is set to 1; represents the gamma function.

6. The method for processing digital twin data based on artificial intelligence according to claim 5, wherein, For any parameter individual, perform local fast-guided search on the parameter individual according to the optimal parameter individual to obtain the parameter individual after local fast-guided search, including: Based on the standard normal distribution, generate a random guidance control factor between (0, 1); Perform local rapid guided search on the parameter individuals according to the random guided control factor and the optimal parameter individual, and the parameter individuals after local rapid guided search are as follows: ; where represents the m-th parameter individual in the k th training process, represents the optimal parameter individual, represents the random guided control factor, and ||*|| represents obtaining the Euclidean distance.

7. The method for processing digital twin data based on artificial intelligence according to claim 6, characterized in that For any parameter individual after local fast-guided search, perform multi-information learning search on the parameter individual to obtain the parameter individual after multi-information learning search, including: For any parameter individual after local fast-guided search, randomly match an other parameter individual to the parameter individual to obtain the paired parameter individual corresponding to each parameter individual; Perform learning search on the parameter individual according to the paired parameter individual corresponding to the parameter individual, and the first learning information obtained is: ; where represents the first learning information, represents the k nth parameter individual in the mth training process, represents the parameter individual corresponding paired parameter individual, represents the first learning coefficient, represents a random number between (0, 1); According to the historical optimal value corresponding to the parameter individual, perform learning search on the parameter individual, and the second learning information obtained is: ; where represents the second learning information, represents the parameter individual corresponding to the historical optimal value, represents the second learning coefficient, represents a random number between (0, 1); Based on the optimal parameter individual, perform learning search on the parameter individuals to obtain the third learning information as follows: ; where represents the third learning information, represents the optimal parameter individual, represents the third learning coefficient, represents a random number between (0, 1); Based on the first learning information, the second learning information, and the third learning information, the parameter individuals obtained after multi-information learning search are: ; among them, represents the parameter individuals after multi-information learning search .

8. The method for processing digital twin data based on artificial intelligence according to claim 7, characterized in that For any parameter individual after multi-information learning search, perform adaptive chain search on the parameter individual to obtain the parameter individual after adaptive chain search, including: For any parameter individual after multi-information learning search, obtain the loss function value corresponding to the parameter individual, and arrange the parameter individuals in ascending order of the loss function value; Based on the arranged parameter individuals, perform an adaptive chain search on the parameter individuals, and the parameter individuals after the adaptive chain search are as follows: ; where represents the i th parameter individual after arrangement, represents the parameter individual after the adaptive chain search , represents the i -1th parameter individual after arrangement, and when i is 1, is set to 's historical optimal value; represents the first chain search factor, represents the second chain search factor, represents the fourth random number between (0, 1), represents the fifth random number between (0, 1), represents the adaptive inertia weight, and ; represents the maximum value of the adaptive inertia weight, represents the minimum value of the adaptive inertia weight, and K represents the preset maximum number of training times.

9. The method for processing digital twin data based on artificial intelligence according to claim 1, characterized in that, When the parameter processing result meets the preset requirements, generate corresponding labels and label-associated real-time operating parameters on the digital twin model, including: When the parameter processing result is abnormal, generate a label on the digital twin model, and associate real-time operating parameters on the secondary interface of the label.

10. A digital twin data processing system based on artificial intelligence, characterized in that, Including: A digital twin module, a model construction module, a parameter processing module, and a result processing module; The digital twin module is used to construct a digital twin model corresponding to the target machine device, and synchronize the operating parameters of the target machine device to the digital twin model to run the digital twin model; The model construction module is used to construct a digital twin data processing model using an artificial intelligence algorithm, and train the digital twin data processing model using an intelligent optimization algorithm to obtain the trained digital twin data processing model; The parameter processing module is used to collect the real-time operating parameters corresponding to the digital twin model, and process the real-time operating parameters using the trained digital twin data processing model to obtain a parameter processing result; The result processing module is used to, when the parameter processing result meets the preset requirements, generate corresponding labels and label-associated real-time operating parameters on the digital twin model to complete the processing of the digital twin data.

Images