Digital twin system based on data driving and construction method

Abstract

The invention provides a digital twin system based on data driving and a construction method. The system comprises a data acquisition module used for acquiring multi-source equipment data; the data transmission module is used for comparing the multi-source equipment data with a preset data threshold value, determining the current data priority of each source equipment data, and transmitting the multi-source equipment data to the digital twin system updating module based on the network bandwidth predicted value and the current data priority; and updating the current digital twin system based on the multi-source equipment data. According to the system provided by the invention, the current data priority is determined by comparing the multi-source equipment data with the preset data threshold, and the data transmission is carried out based on the network bandwidth predicted value and the current data priority, so that the self-adaptive data transmission based on whether the source equipment data is abnormal or not and the network bandwidth predicted value is realized; the data transmission efficiency is greatly improved, and the timeliness of equipment data analysis and prediction based on the digital twin system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twin modeling, and in particular to a data-driven digital twin system and construction method. Background Art

[0002] In the process of equipment informatization construction, high-quality analytical data is crucial for making scientific decisions, improving efficiency and ensuring system reliability. With the rapid development of technologies such as the Internet of Things, big data, and artificial intelligence, digital twins have gradually become an important technical means in the field of intelligent systems. Digital twins create virtual digital models of physical objects to monitor, analyze, predict and optimize physical entities, and are widely used in industrial manufacturing, equipment monitoring, smart cities, energy management and other fields.

[0003] However, due to the huge amount of equipment data and the wide variety of data, in the actual application of complex equipment operation, the existing digital twin system still faces the problem of insufficient real-time data transmission and low data transmission efficiency. Summary of the invention

[0004] The present invention provides a data-driven digital twin system and construction method to solve the problems in the prior art that in the actual application of complex equipment operation, the existing digital twin system still has the defects of insufficient real-time data transmission and low data transmission efficiency.

[0005] The present invention provides a data-driven digital twin system, comprising: a data acquisition module, a data transmission module and a digital twin system update module; The data acquisition module is used to acquire multi-source equipment data; The data transmission module is used to compare the multi-source equipment data with a preset data threshold, determine the current data priority of each source equipment data in the multi-source equipment data, and transmit the multi-source equipment data to the digital twin system update module based on the network bandwidth prediction value and the current data priority; The digital twin system update module is used to update the current digital twin system based on the multi-source equipment data; the current digital twin system is constructed based on historical equipment data.

[0006] According to a data-driven digital twin system provided by the present invention, the multi-source equipment data is transmitted to the digital twin system update module based on the network bandwidth prediction value and the current data priority, including: When the predicted network bandwidth value is less than a preset bandwidth threshold, weighted calculation is performed based on the data volume of each source equipment data and the current data priority to determine the data transmission frequency corresponding to each source equipment data; Based on the data transmission frequency corresponding to each source equipment data, the multi-source equipment data is transmitted to the digital twin system update module.

[0007] According to a data-driven digital twin system provided by the present invention, the step of obtaining the network bandwidth prediction value includes: Get real-time bandwidth monitoring value; The network bandwidth prediction value is obtained by performing a moving average calculation based on the real-time bandwidth monitoring value and the historical bandwidth monitoring value.

[0008] According to a data-driven digital twin system provided by the present invention, the digital twin system update module further includes a data analysis module and a system optimization module; The system optimization module is used to extract data features from the multi-source equipment data and the historical equipment data to obtain key equipment change data; Optimizing the data analysis module based on historical fault prediction results and the key equipment change data; The historical fault prediction result is obtained based on the fault prediction performed by the data analysis module on the historical equipment data.

[0009] According to a data-driven digital twin system provided by the present invention, the data feature extraction of the multi-source equipment data and the historical equipment data to obtain key equipment change data includes: Performing multivariate time series fusion on the multi-source equipment data and the historical equipment data to obtain unified source fusion data; Data features are extracted from the unified source fusion data to obtain the key equipment change data.

[0010] According to a data-driven digital twin system provided by the present invention, the data acquisition module is specifically used for: Obtain initial multi-source equipment data; Based on the sampling frequency of the initial multi-source equipment data, time window alignment is performed on the initial multi-source equipment data to obtain aligned equipment data; The aligned equipment data is padded based on a linear interpolation algorithm to obtain the multi-source equipment data.

[0011] The present invention also provides a method for constructing a digital twin system based on data drive, comprising: Obtain equipment data from multiple sources; Compare the multi-source equipment data with a preset data threshold, determine the current data priority of each source equipment data in the multi-source equipment data, and transmit the multi-source equipment data to the digital twin system update module based on the network bandwidth prediction value and the current data priority; The current digital twin system is updated based on the multi-source equipment data; the current digital twin system is constructed based on the historical equipment data.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for constructing a data-driven digital twin system as described in any one of the above is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for constructing a data-driven digital twin system as described in any one of the above is implemented.

[0014] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for constructing a data-driven digital twin system.

[0015] The data-driven digital twin system and construction method provided by the present invention determine the current data priority of the multi-source equipment data by comparing the multi-source equipment data with the preset data threshold, and transmit the multi-source equipment data to the digital twin system update module based on the network bandwidth prediction value and the current data priority, thereby realizing adaptive data transmission based on whether there are abnormalities in the data of each source equipment and the network bandwidth prediction value, greatly improving the transmission efficiency of the multi-source equipment data, ensuring the stable transmission of high-priority data, and thereby improving the timeliness of equipment data analysis and prediction based on the digital twin system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a structural schematic diagram of a data-driven digital twin system provided by the present invention; Figure 2 It is a flow chart of a method for constructing a data-driven digital twin system provided by the present invention; Figure 3It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] In response to the above problems, the present invention provides a data-driven digital twin system to achieve adaptive real-time data transmission, greatly improving the transmission efficiency of equipment data. Figure 1 is a structural diagram of a data-driven digital twin system provided by the present invention, such as Figure 1 As shown, the model includes a data acquisition module 110, a data transmission module 120, and a digital twin system update module 130; The data acquisition module 110 is used to acquire multi-source equipment data; The data transmission module 120 is used to compare the multi-source equipment data with a preset data threshold, determine the current data priority of each source equipment data in the multi-source equipment data, and transmit the multi-source equipment data to the digital twin system update module based on the network bandwidth prediction value and the current data priority; The digital twin system update module 130 is used to update the current digital twin system based on the multi-source equipment data; the current digital twin system is constructed based on historical equipment data.

[0020] Specifically, in the digital twin system of equipment data, the monitoring data corresponding to the equipment can be collected by various sensors arranged on the mechanical equipment to obtain multi-source equipment data. In detail, the temperature sensor, pressure sensor, speed sensor and other types of sensors arranged on the mechanical equipment can be used to collect the monitoring data corresponding to each sensor according to the preset sampling frequency to obtain multi-source equipment data. For example, the sampling frequency of the temperature sensor can be 1HZ; the sampling frequency of the pressure sensor can be 0.5HZ; the sampling frequency of the speed sensor can be 2HZ. It should be noted that the number of sensors of each type is at least 1. The monitoring data here can be used to reflect the current health status of the equipment, and the multi-source equipment data here can comprehensively reflect the current health status of the equipment.

[0021] After obtaining the multi-source equipment data through the data acquisition module 110, the multi-source equipment data can be transmitted to the digital twin system update module 130 through the data transmission module 120, so as to update the digital twin system based on the real-time updated multi-source equipment data and keep the data of the digital twin system synchronized with the actual equipment system.

[0022] In detail, in the data transmission module 120, first, the current data priority of each source equipment data in the multi-source equipment data can be determined by comparing each source equipment data in the multi-source equipment data with a preset data threshold corresponding to each data source.

[0023] For example, the temperature monitoring data can be compared with the temperature exceeding the limit, the pressure monitoring data can be compared with the pressure fluctuation amplitude threshold, and the speed monitoring data can be compared with the speed change threshold. Further, the current data priority corresponding to each source equipment data can be determined by the size of the gap between each source equipment data and the preset data threshold corresponding to each data source, that is, the current data priority of the multi-source equipment data is obtained. It can be understood that the preset data threshold here can be used to reflect the normal value of each source equipment data, or the normal value range. Therefore, the larger the gap between the preset data threshold corresponding to the source equipment data and its data source, the higher the current data priority corresponding to the source equipment data; the smaller the gap between the preset data threshold corresponding to the source equipment data and its data source, the smaller the current data priority corresponding to the source equipment data.

[0024] It should be noted that the current data priority of the multi-source equipment data is determined by comparing the multi-source equipment data acquired in real time with the preset data threshold. The data priority of data from different source equipment is not fixed, but is adaptively determined based on whether there are any abnormalities in the multi-source equipment data acquired in real time.

[0025] Next, the multi-source equipment data can be transmitted to the digital twin system update module 130 by determining the network bandwidth prediction value and combining the network bandwidth prediction value with the data priority of each source equipment data in the multi-source equipment data.

[0026] In one embodiment, the network bandwidth prediction value can be determined by obtaining real-time network bandwidth data. Then, a bandwidth prediction algorithm, such as a moving average prediction algorithm, can be used to analyze the real-time network bandwidth data and the historical network bandwidth data to analyze and obtain the network bandwidth prediction value for the future preset time period. It should be noted that the network bandwidth prediction value here can be used to reflect the network situation in the future preset time period. Further, when the network state reflected by the network bandwidth prediction value is good, such as the network bandwidth prediction value is greater than the preset network bandwidth threshold, the source equipment data of each current data priority can be transmitted simultaneously; when the network state reflected by the network bandwidth prediction value is poor, such as the network bandwidth prediction value is less than the preset network bandwidth threshold, the source equipment data with a high current data priority can be transmitted first, and then the source equipment data with a low current data priority can be transmitted. For example, the network bandwidth prediction value fluctuates between 1 Mbps and 10 Mbps, and the preset bandwidth threshold here can be 5 Mbps. If the network bandwidth prediction value is 3Mbps, the transmission frequency of high priority data can be 1HZ, the transmission frequency of medium priority data is reduced to 0.2 Hz, and low priority data is suspended.

[0027] It should also be noted that the network bandwidth prediction value is used to adjust the transmission strategy of multi-source equipment data, further realizing data transmission that is adaptive to the network bandwidth.

[0028] The digital twin system update module 130 is used to receive multi-source equipment data and update the current digital twin system for the multi-source equipment data to achieve data-driven "virtual-real synchronization". Here, the current digital twin system is constructed based on historical equipment data, using discrete event simulation or finite element modeling, such as AnyLogic simulation software and ANSYS simulation software. It can be understood that the currently updated digital twin system can be used as the current digital twin system for system update after receiving multi-source equipment data in the next round.

[0029] The system provided by the embodiment of the present invention determines the current data priority of the multi-source equipment data by comparing the multi-source equipment data with the preset data threshold, and transmits the multi-source equipment data to the digital twin system update module based on the network bandwidth prediction value and the current data priority, thereby realizing adaptive data transmission based on whether there are abnormalities in the data of each source equipment and the network bandwidth prediction value, greatly improving the transmission efficiency of the multi-source equipment data, ensuring the stable transmission of high-priority data, and thereby improving the timeliness of equipment data analysis and prediction based on the digital twin system.

[0030] Based on any of the above embodiments, in the data transmission module 120, determining the data transmission frequency corresponding to each data priority based on the network bandwidth prediction value and the data priority of the multi-source equipment data includes: When the predicted network bandwidth value is less than a preset bandwidth threshold, weighted calculation is performed based on the data volume of each source equipment data and the current data priority to determine the data transmission frequency corresponding to each source equipment data; Based on the data transmission frequency corresponding to each source equipment data, the multi-source equipment data is transmitted to the digital twin system update module.

[0031] Here, the data priority may be divided into multiple levels, for example, divided into three levels of high, medium and low, and the preset data priority may be set to medium, and the first current data priority is high and medium.

[0032] Specifically, the preset bandwidth threshold can be used to reflect the minimum network bandwidth that can carry and transmit multiple source equipment data at the same time. If the network bandwidth prediction value is greater than or equal to the preset bandwidth threshold, it indicates that the current network state is good, and the multiple source equipment data can be transmitted simultaneously; if the network bandwidth prediction value is less than the preset bandwidth threshold, it indicates that the current network state is poor, and the data transmission frequency corresponding to each source equipment data can be determined by weighted calculation based on the data volume of each source equipment data and the current data priority of each source equipment data. For example, the weight corresponding to the data volume and the current data priority can be determined, and then the weight corresponding to each source equipment data can be obtained by weighted calculation based on the data volume of the source equipment data, the current data priority and the corresponding weight. Finally, the transmission frequency corresponding to the weight of each source equipment data is used as the data transmission frequency corresponding to each source equipment data.

[0033] Based on any of the above embodiments, in the data transmission module 120, the step of obtaining the network bandwidth prediction value includes: Get real-time bandwidth monitoring value; The network bandwidth prediction value is obtained by performing a moving average calculation based on the real-time bandwidth monitoring value and the historical bandwidth monitoring value.

[0034] Specifically, the bandwidth monitoring value can be collected in real time through the network bandwidth monitoring tool to obtain the real-time bandwidth monitoring value. Then, the collected real-time bandwidth monitoring value can be cleaned to remove outliers and invalid data, and the cleaned data can be smoothed to reduce noise and fluctuations. Further, the real-time bandwidth monitoring value and the historical bandwidth monitoring value after smoothing can be predicted based on the moving average window prediction algorithm. In detail, the real-time bandwidth monitoring value and the historical bandwidth monitoring value within the time window can be calculated by moving average according to the selected time window size. For example, if the time window size is 5, the average value of every 5 consecutive data points is calculated, and the result is used as a new data point. Then, based on the calculated moving average value, it can be extended backward to generate a bandwidth usage prediction value for the future time period, that is, to generate a network bandwidth prediction value. It can be understood that the network bandwidth prediction value here can be used to reflect the bandwidth value within the time period corresponding to the time window.

[0035] It should be noted that the method provided in the embodiment of the present invention obtains a network bandwidth prediction value reflecting the time period corresponding to the time window by performing a moving average calculation on the real-time bandwidth monitoring value and the historical bandwidth monitoring value, thereby realizing the network bandwidth prediction in the future time period, which can be more conducive to determining a suitable data transmission strategy and improving the transmission efficiency of equipment data.

[0036] Based on any of the above embodiments, the digital twin system update module 130 further includes a data analysis module 140 and a system optimization module 150; The system optimization module 150 is used to extract data features from the multi-source equipment data and the historical equipment data to obtain key equipment change data; Optimizing the data analysis module based on historical fault prediction results and the key equipment change data; The historical fault prediction result is obtained based on the fault prediction performed by the data analysis module on the historical equipment data.

[0037] Specifically, in the system optimization module 150, the key equipment change data can be obtained by fusing the multi-source equipment data and the historical equipment data, and then extracting features from the fused data, such as extracting characteristic parameters such as the temperature change rate. It can be understood that, compared with only analyzing the received multi-source equipment data, the key equipment change data here can be used to more accurately reflect the current status of the equipment, and can thus serve as a more accurate fault prediction label.

[0038] It should be noted that in the embodiment of the present invention, by fusing multi-source equipment data and historical equipment data, labels that can be used for fault prediction at historical moments are extracted, thereby optimizing the parameters of the data analysis module 140, without the need to obtain additional sample data and spend a lot of manpower on labeling. In addition, dynamic system optimization can be achieved based on multi-source equipment data obtained in real time, thereby continuously improving the performance of the digital twin system.

[0039] Then, the prediction loss can be calculated by obtaining the historical fault prediction results and the key equipment change data. Then, the reinforcement learning algorithm or other machine learning algorithm can be applied to update the parameters of the data analysis module 140 based on the prediction loss, so that the data analysis capability of the data analysis module 140 is stronger and the fault prediction results are more accurate.

[0040] The historical fault prediction result here is obtained based on the fault prediction of the historical equipment data by the data analysis module 140, and the data analysis module 140 here can be constructed based on a machine learning algorithm. For example, the historical equipment data can be feature extracted by the data analysis module 140, and fault prediction can be performed based on the extracted features to obtain the historical fault prediction result.

[0041] It should be noted that the historical fault prediction here refers to the system parameter optimization of the data analysis module. In the actual application of the digital twin system, after the digital twin system is updated based on the multi-source equipment data acquired in real time, fault prediction can be performed based on the received multi-source equipment data and historical equipment data to obtain timely and accurate fault prediction results.

[0042] It should also be noted that by optimizing the parameters of the data analysis module through the system optimization module, the optimized digital twin system can achieve more accurate fault prediction based on the acquired multi-source equipment data, thereby improving the practical applicability of the digital twin system in the field of equipment data.

[0043] Based on any of the above embodiments, extracting data features from the multi-source equipment data and the historical equipment data to obtain key equipment change data includes: Performing multivariate time series fusion on the multi-source equipment data and the historical equipment data to obtain unified source fusion data; Data features are extracted from the unified source fusion data to obtain the key equipment change data.

[0044] Specifically, based on weighted average, Kalman filtering or machine learning models, such as long short-term memory networks, multi-source equipment data and historical equipment data can be fused into multivariate time series to obtain a set of unified source fusion data containing all key information and consistent in time. Then, data feature extraction is performed on the unified source fusion data to obtain key equipment change data. The key equipment change data here has an important impact on fault prediction. For example, it can be the temperature change rate, pressure fluctuation range, and speed change rate.

[0045] Based on any of the above embodiments, the data acquisition module 110 is specifically used for: Obtain initial multi-source equipment data; Based on the sampling frequency of the initial multi-source equipment data, time window alignment is performed on the initial multi-source equipment data to obtain aligned equipment data; The aligned equipment data is padded based on a linear interpolation algorithm to obtain the multi-source equipment data.

[0046] Here, the initial multi-source equipment data refers to the original monitoring data that has not been processed, which can be understood as the monitoring data directly collected by various sensors.

[0047] Specifically, considering that the initial multi-source equipment data contains monitoring data from different sensor sources and the frequency of data collection by each sensor may be different, the number of source equipment in the multi-source equipment data can be aligned in time windows to obtain aligned equipment data.

[0048] It should be noted that during the alignment process, due to the different sampling frequencies of different data sources, data may be missing at certain time points. Therefore, the minimum sampling period can be selected as a benchmark, and the aligned equipment data can be supplemented by a linear interpolation algorithm to obtain multi-source equipment data. In detail, the missing data points in the aligned equipment data can be determined. Then, for each missing data point, the interpolation value can be calculated according to the linear interpolation formula using the values ​​of the two known data points before and after it. Furthermore, the calculated interpolation value replaces the missing data point to obtain complete multi-source equipment data, which provides a solid foundation for subsequent data analysis, feature extraction, and system optimization, and can greatly improve the data processing efficiency of subsequent operations.

[0049] Based on any of the above embodiments, the present invention also provides a data-driven digital twin system, and the system operation process includes: first, the corresponding monitoring data, such as temperature, pressure, and vibration monitoring data, are collected through each source sensor. Then, the collected initial data is time-aligned and data-cleaned to obtain multi-source equipment data. Then, the source equipment data in the multi-source equipment data can be prioritized according to the pre-set priority rules. For example, each source equipment data in the multi-source equipment data can be compared with a preset data threshold, and the priority of each source equipment data is determined according to the difference between each source equipment data and the preset data threshold. It can be understood that when the difference between each source equipment data and the preset data threshold is larger, it means that the source equipment data is more sensitive and more likely to reflect the failure of the equipment, then the priority of the source equipment data is higher; conversely, the priority of the source equipment data is lower.

[0050] Then, the multi-source equipment data can be adaptively transmitted according to the predicted network bandwidth and the current data priority of each source equipment data. For example, high-priority data is transmitted at a high frequency, and the transmission frequency of low-priority data is dynamically adjusted according to the network status. When the bandwidth is limited, low-priority data will be transmitted or temporarily stored through compression.

[0051] Furthermore, the current digital twin system can be updated through multi-source equipment data to perform data analysis such as equipment failure prediction based on the updated digital twin system. The current digital twin system here is built based on historical equipment data. It should be noted that in the process of building the initial digital twin system, the key components can be modeled in a fine-grained manner and the non-key components can be modeled in a coarse-grained manner, thereby improving the computational efficiency of building the initial digital twin system.

[0052] In addition, the system parameters can be optimized through the system optimization module, and key equipment change data can be obtained by extracting data features from multi-source equipment data and historical equipment data. The data analysis module of the digital twin system can be optimized based on historical fault prediction results and key equipment change data.

[0053] It is understandable that the digital twin system may also include a visualization module, which is used to display multi-source equipment data updated in real time and display data analysis results, such as fault prediction results. The fault prediction results here may be, for example, abnormal conditions such as continuous temperature rise. After receiving the fault prediction results, an alarm may be issued based on the fault prediction results.

[0054] It should be noted that under different network bandwidth conditions, the digital twin system provided by the embodiment of the present invention achieves a key data transmission delay of less than 100ms and a packet loss rate of less than 1%, and can automatically adjust the transmission strategy according to the network status to ensure the stability and efficiency of data transmission. Based on the comprehensive experimental results, the case verification indicators are as follows: Time alignment: different sensor data are unified to a 1-second time step. Priority screening: key data is transmitted first, and the delay is controlled at 100 ms. Transmission adjustment: when the bandwidth is insufficient, the packet loss rate is less than 1%, and the frequency of high-priority data is maintained. System update: The prediction accuracy of the virtual digital twin system is over 95%. Feedback optimization: real-time feedback reduces the risk of potential equipment failure.

[0055] In summary, the digital twin system provided by the embodiment of the present invention solves key problems such as real-time data collection, priority screening, adaptive transmission, dynamic modeling and optimization of complex equipment in the digital twin system. In detail, through the priority mechanism, rapid screening and transmission of high-priority key data are achieved, ensuring that the delay of key data is less than 100 ms in a complex network environment. Adaptive adjustment is performed based on bandwidth to achieve the stability of data transmission by dynamically adjusting the transmission frequency of low-priority data in the case of network fluctuations, with a packet loss rate of less than 1% and improved bandwidth utilization.

[0056] In addition, the digital twin system provided by the embodiment of the present invention greatly improves the efficiency of data processing and modeling. In detail, by automatically performing time synchronization after multi-source data collection, data validity is improved and processing efficiency is increased by 20%. Through the dynamic fusion of real-time data and historical data, key state characteristics of equipment (such as temperature change rate and pressure fluctuation amplitude) are quickly extracted to provide high-quality data input for the optimization of the digital twin system.

[0057] The digital twin system provided by the embodiment of the present invention drives the real-time update of the virtual system based on real-time data, realizes high-precision dynamic prediction of equipment status, and the consistency between the model and the actual status reaches more than 95%. In addition, the virtual model optimizes the equipment control strategy through simulation feedback, significantly reduces the risk of potential failures, and realizes two-way optimization of the virtual and real systems.

[0058] From the overall perspective of the digital twin system provided by the embodiment of the present invention, the system has strong adaptability and robustness. For multi-device, multi-scenario operating environments, the system can flexibly adjust data collection and transmission strategies to ensure stable performance. Ability to resist network fluctuations: Within the bandwidth fluctuation range (1 Mbps ~ 10 Mbps), it can still ensure stable transmission of key data and continuous operation of the system. And modular expansion capability: The system adopts a modular design, and each functional module runs independently, which is easy to expand and maintain.

[0059] It can be understood that the digital twin system provided by the embodiment of the present invention is applied to the data monitoring of a certain complex equipment. In the application scenario of a certain complex equipment, the digital twin system provided by the embodiment of the present invention significantly improves the equipment operation monitoring and optimization efficiency, which is reflected in: key data transmission delay: less than 100 ms. System prediction accuracy: reaches more than 95%. Transmission resource saving: After the dynamic adjustment of the low-priority data transmission frequency, the bandwidth occupancy is reduced by 30%. Fault detection time is advanced: through trend analysis, the fault detection time is 10 to 15 minutes earlier than the traditional method. Therefore, the digital twin system provided by the embodiment of the present invention can have good practicality in the monitoring tasks of complex equipment.

[0060] Based on any of the above embodiments, Figure 2 is a flow chart of a method for constructing a data-driven digital twin system provided by the present invention, such as Figure 2 As shown, the method includes: Step 210, acquiring multi-source equipment data; Step 220, comparing the multi-source equipment data with a preset data threshold, determining the current data priority of each source equipment data in the multi-source equipment data, and transmitting the multi-source equipment data to the digital twin system update module based on the network bandwidth prediction value and the current data priority; Step 230, updating the current digital twin system based on the multi-source equipment data; the current digital twin system is constructed based on historical equipment data.

[0061] The method provided by the embodiment of the present invention determines the current data priority of the multi-source equipment data by comparing the multi-source equipment data with the preset data threshold, and transmits the multi-source equipment data to the digital twin system update module based on the network bandwidth prediction value and the current data priority, thereby realizing adaptive data transmission based on whether there are abnormalities in the data of each source equipment and the network bandwidth prediction value, greatly improving the transmission efficiency of the multi-source equipment data, ensuring the stable transmission of high-priority data, and thereby improving the timeliness of equipment data analysis and prediction based on the digital twin system.

[0062] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute a method for constructing a digital twin system based on data drive, the method comprising: obtaining multi-source equipment data; comparing the multi-source equipment data with a preset data threshold, determining the current data priority of each source equipment data in the multi-source equipment data, and transmitting the multi-source equipment data to the digital twin system update module based on the network bandwidth prediction value and the current data priority; updating the current digital twin system based on the multi-source equipment data; the current digital twin system is constructed based on historical equipment data.

[0063] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0064] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the data-driven digital twin system construction method provided by the above methods, the method including: obtaining multi-source equipment data; comparing the multi-source equipment data with a preset data threshold, determining the current data priority of each source equipment data in the multi-source equipment data, and transmitting the multi-source equipment data to the digital twin system update module based on the network bandwidth prediction value and the current data priority; updating the current digital twin system based on the multi-source equipment data; the current digital twin system is constructed based on historical equipment data.

[0065] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the data-driven digital twin system construction method provided by the above-mentioned methods, the method comprising: obtaining multi-source equipment data; comparing the multi-source equipment data with a preset data threshold, determining the current data priority of each source equipment data in the multi-source equipment data, and transmitting the multi-source equipment data to the digital twin system update module based on the network bandwidth prediction value and the current data priority; updating the current digital twin system based on the multi-source equipment data; the current digital twin system is constructed based on historical equipment data.

[0066] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0067] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0068] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data-driven digital twin system, characterized in that: include: Data acquisition module, data transmission module and digital twin system update module; The data acquisition module is used to acquire multi-source equipment data; The data transmission module is used to compare the multi-source equipment data with a preset data threshold, determine the current data priority of each source equipment data in the multi-source equipment data, and transmit the multi-source equipment data to the digital twin system update module based on the network bandwidth prediction value and the current data priority; The digital twin system update module is used to update the current digital twin system based on the multi-source equipment data; the current digital twin system is constructed based on historical equipment data.

2. The data-driven digital twin system according to claim 1, characterized in that: The transmitting the multi-source equipment data to the digital twin system update module based on the network bandwidth prediction value and the current data priority includes: When the predicted network bandwidth value is less than a preset bandwidth threshold, weighted calculation is performed based on the data volume of each source equipment data and the current data priority to determine the data transmission frequency corresponding to each source equipment data; Based on the data transmission frequency corresponding to each source equipment data, the multi-source equipment data is transmitted to the digital twin system update module.

3. The data-driven digital twin system according to claim 1, characterized in that: The step of obtaining the predicted value of network bandwidth includes: Get real-time bandwidth monitoring value; The network bandwidth prediction value is obtained by performing a moving average calculation based on the real-time bandwidth monitoring value and the historical bandwidth monitoring value.

4. The data-driven digital twin system according to any one of claims 1 to 3, characterized in that: The digital twin system update module also includes a data analysis module and a system optimization module; The system optimization module is used to extract data features from the multi-source equipment data and the historical equipment data to obtain key equipment change data; Optimizing the data analysis module based on historical fault prediction results and the key equipment change data; The historical fault prediction result is obtained based on the fault prediction performed by the data analysis module on the historical equipment data.

5. The data-driven digital twin system according to claim 4, characterized in that: The extracting data features from the multi-source equipment data and the historical equipment data to obtain key equipment change data includes: Performing multivariate time series fusion on the multi-source equipment data and the historical equipment data to obtain unified source fusion data; Data features are extracted from the unified source fusion data to obtain the key equipment change data.

6. The data-driven digital twin system according to any one of claims 1 to 3, characterized in that: The data acquisition module is specifically used for: Obtain initial multi-source equipment data; Based on the sampling frequency of the initial multi-source equipment data, time window alignment is performed on the initial multi-source equipment data to obtain aligned equipment data; The aligned equipment data is padded based on a linear interpolation algorithm to obtain the multi-source equipment data.

7. A method for constructing a data-driven digital twin system, characterized in that: include: Obtain equipment data from multiple sources; Compare the multi-source equipment data with a preset data threshold, determine the current data priority of each source equipment data in the multi-source equipment data, and transmit the multi-source equipment data to the digital twin system update module based on the network bandwidth prediction value and the current data priority; The current digital twin system is updated based on the multi-source equipment data; the current digital twin system is constructed based on the historical equipment data.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, it implements the method for constructing a data-driven digital twin system as described in claim 7.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the method for constructing a data-driven digital twin system as described in claim 7.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements the method for constructing a data-driven digital twin system as described in claim 7.

Images