A dynamic optimization and publishing method for digital twin models

Abstract

The present invention relates to the field of data processing technology, and in particular to a method for dynamic optimization and publishing of digital twin models, the method comprising: collecting real-time data; determining a temporary grid; determining a simulation grid; calculating a predicted optimization index; simulating to form an optimization index; adjusting the grid side length; and publishing an optimized twin model. The present invention achieves high-precision, adaptive optimization of digital twin models by dynamically collecting and analyzing the real-time density of personnel in each grid within an industrial area, the real-time average movement speed of personnel, and the operating rate of equipment associated therewith. Personnel density reflects the degree of concentration of operations in a certain area, and the average movement speed reveals the strength of personnel mobility. The two together constitute the spatial and temporal distribution characteristics of personnel behavior, effectively solving the problems of slow response speed and low processing accuracy to dynamic changes due to over-reliance on historical data and a single optimization strategy.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a dynamic optimization and publishing method for a digital twin model. Background Art

[0002] With the continuous advancement of industrial automation and intelligence, traditional production management models are no longer able to meet the needs of real-time optimization in complex and dynamic environments. Digital twin technology, as a virtualization technology, enables real-time interaction between virtual models and physical systems, enabling precise simulation, monitoring, and prediction of complex production processes. This helps companies optimize resource allocation and improve production efficiency. Therefore, building efficient digital twin models and enabling their dynamic optimization and precise release has become a key development direction for modern intelligent manufacturing and the Industrial Internet of Things.

[0003] Patent document with publication number CN118657254A discloses a digital twin system for energy efficiency optimization of industrial parks based on large model algorithms. The system includes: a data acquisition module, a digital twin module, an energy efficiency calculation module and a simulation optimization module; the data acquisition module is used to collect operation information in the park, the digital twin module builds a digital twin model according to the operation information, the energy efficiency calculation module is used to calculate the energy efficiency information of the operation, and the simulation optimization module is used to simulate the operation of the digital twin module and give process optimization suggestions; the data acquisition module includes an operation monitoring unit, an information collection unit and a data sorting unit, the operation monitoring unit is used to monitor the operation status of each operation, the information collection unit is used to collect data information during the operation of the operation, and the data sorting unit is used to classify and sort the collected data information; the digital twin module includes an operation basic unit, an operation linkage unit, a data storage unit and an operation link unit. The storage unit and the real-time display unit, the operation basic unit is used to record the basic data of each operation, the operation linkage unit is used to record the linkage relationship and linkage data between operations, the data storage unit is used to save the collected data information, and the real-time display unit is used to display real-time operation information; the energy efficiency calculation module includes an energy consumption calculation unit, an efficiency calculation unit and a comprehensive calculation unit, the energy efficiency calculation unit is used to calculate the energy consumption information of the operation, the efficiency calculation unit is used to calculate the efficiency information of the operation, and the comprehensive calculation unit is used to calculate the energy efficiency information of the entire park; the simulation optimization module includes a model construction unit, a simulation operation unit and an optimization output unit, the model construction unit constructs a data conversion model based on historical data, the simulation operation unit simulates the operation status of operations under different strategies based on real-time data and data conversion models, and the optimization output unit is used to select the strategy with the best energy efficiency as the optimization solution.

[0004] It can be seen that the digital twin system for energy efficiency optimization of industrial parks based on large model algorithms has the following problems: the system relies too much on model construction and simulation operation units based on historical data, which causes the model to not respond quickly enough when facing a rapidly changing production environment; the system is mainly aimed at unified energy efficiency optimization within the park, assuming that the operations or equipment within the park are relatively simple, but in actual industrial parks, multiple different types of equipment, different types of operations and diverse operating environments are involved. In such a heterogeneous system, a single optimization strategy is difficult to adapt to the needs and characteristics of different equipment. Summary of the Invention

[0005] To this end, the present invention provides a dynamic optimization and publishing method for digital twin models, which is used to overcome the problems of slow response speed to dynamic changes and low processing accuracy in the existing technology due to over-reliance on historical data and a single optimization strategy by introducing real-time data feedback and adaptive optimization mechanism.

[0006] To achieve the above objectives, the present invention provides a method for dynamic optimization and publishing of digital twin models, comprising:

[0007] Collect the real-time operation rate of several devices in each grid to be simulated in the industrial area constructed based on the preset grid side length, the real-time density of targets in each grid to be simulated, and the real-time average moving speed;

[0008] Determining a number of temporary grids according to the real-time operating rate within a preset time period and a preset operating rate fluctuation threshold;

[0009] Filter out a number of simulation grids according to the real-time density in any two adjacent temporary grids within a preset determination time;

[0010] Calculating a prediction optimization index according to the real-time operation rate and the real-time density in each simulation grid;

[0011] Using a preset digital twin model to simulate all the grids to be simulated, and generating a simulation optimization index;

[0012] Adjusting the preset grid side length according to the predicted optimization index and the simulated optimization index to form an adjusted grid side length;

[0013] The preset digital twin model is trained using the real-time operation rate, the real-time density, and the real-time average moving speed of all the simulation grids determined based on the adjustment of the grid side length to form an optimized twin model;

[0014] Correcting the preset operating rate fluctuation threshold according to the simulation optimization index obtained by re-simulating the optimization twin model within the preset correction time period to form a corrected operating rate fluctuation threshold;

[0015] Publish the optimized twin model reformed based on the modified operating rate fluctuation threshold.

[0016] Furthermore, the process of determining a plurality of temporary grids according to the real-time operation rate within a preset determined time period and a preset operation rate fluctuation threshold includes:

[0017] Calculating a standard deviation of the real-time operating rate to form an operating rate fluctuation value;

[0018] When the operation rate fluctuation value is greater than the preset operation rate fluctuation threshold, the grid to be simulated is determined to be a temporary grid, and a plurality of temporary grids are formed.

[0019] Furthermore, the process of selecting a plurality of simulation grids according to the real-time density in any two adjacent temporary grids within a preset determination time period includes:

[0020] Calculating the standard deviation of the real-time density of each temporary grid to form a density fluctuation value;

[0021] A number of simulation grids are selected according to the density fluctuation values ​​of any two adjacent temporary grids.

[0022] Furthermore, the process of selecting a plurality of simulation grids according to the density fluctuation values ​​of any two adjacent temporary grids includes:

[0023] Calculating the relative deviation of the density fluctuation values ​​of any two adjacent temporary grids to form a fluctuation consistency;

[0024] When the fluctuation consistency is greater than a preset consistency threshold, it is determined that all of the temporary grids are the simulation grids, and a plurality of simulation grids are formed.

[0025] Furthermore, the process of calculating the prediction optimization index according to the real-time operation rate and the real-time density in each simulation grid includes:

[0026] Performing normalization calculation on the real-time density of all the simulation grids to form a normalized density;

[0027] Normalizing the real-time operating rates of all the simulation grids to form a normalized operating rate;

[0028] A weighted sum is performed according to the preset density weight, the preset airflow rate weight, the normalized density, and the normalized operating rate to form a prediction optimization index.

[0029] Furthermore, the process of simulating all the grids to be simulated using the preset digital twin model and generating a simulation optimization index includes:

[0030] The real-time operation rate and the real-time density of all the grids to be simulated are obtained and input into the preset digital twin model to form a simulation optimization index.

[0031] Furthermore, the process of adjusting the preset grid side length according to the predicted optimization index and the simulated optimization index includes:

[0032] Calculating a relative deviation between the predicted optimization index and the simulated optimization index to form an index deviation;

[0033] The preset grid side length is adjusted according to the exponential deviation and the real-time average moving speed.

[0034] Furthermore, the process of adjusting the preset grid side length according to the index deviation and the real-time average moving speed includes:

[0035] When the deviation comparison result shows that the index deviation is greater than the preset deviation threshold, increasing the preset grid side length according to the relative deviation between the index deviation and the preset deviation threshold and the preset adjustment coefficient to form a temporary grid side length;

[0036] The temporary grid side length is adjusted according to all the temporary grid side lengths within a preset adjustment time period and the real-time average moving speed to form an adjusted grid side length.

[0037] Furthermore, the temporary grid side length is adjusted according to all the temporary grid side lengths within the preset adjustment time and the real-time average moving speed, and the process of adjusting the grid side length includes:

[0038] Calculating the standard deviation of the number of times all the temporary grid side lengths are formed and normalizing the result to form a normalized number fluctuation value;

[0039] Calculating the standard deviation of all the real-time average moving speeds and normalizing them to form a normalized moving speed fluctuation value;

[0040] Calculating the correlation coefficient between the normalized number fluctuation value and the normalized movement speed fluctuation value to form a change synchronization degree;

[0041] When the change synchronization degree is less than the preset standard synchronization degree, the temporary grid side length is increased according to the relative deviation between the preset standard synchronization degree and the change synchronization degree and the preset adjustment coefficient to form an adjusted grid side length.

[0042] Furthermore, the preset operating rate fluctuation threshold is corrected according to the simulation optimization index obtained by re-simulating the optimized twin model within the preset correction time period. The process of forming the corrected operating rate fluctuation threshold includes:

[0043] Calculating the standard deviation of the simulated optimization index to form an optimization index fluctuation value;

[0044] When the optimization index fluctuation value is greater than the preset index fluctuation threshold, the preset operating rate fluctuation threshold is reduced according to the relative deviation between the optimization index fluctuation value and the preset index fluctuation threshold and the preset correction coefficient to form a corrected operating rate fluctuation threshold.

[0045] Compared with the existing technology, the beneficial effect of the present invention is that by dynamically collecting and analyzing the real-time density of personnel in each grid within the industrial area, the real-time average movement speed of personnel, and the associated equipment operation rate, high-precision and adaptive optimization of the digital twin model is achieved. Personnel density reflects the degree of concentration of work in a certain area, and the average movement speed reveals the strength of personnel mobility. The two together constitute the spatial and temporal distribution characteristics of personnel behavior. As an external influencing factor of personnel behavior, the fluctuation of equipment operation rate reflects the changes in the status of personnel operating equipment. Combining density and speed changes can comprehensively determine the work intensity and rhythm of personnel in the area. Introducing "change synchronization" as a natural feedback regulation mechanism, by measuring the consistency between personnel mobility and regional adjustment behavior, it guides the dynamic update of the grid structure, thereby making the twin model have higher stability and response efficiency in complex environments, significantly improving the intelligence level of personnel behavior simulation, efficiency evaluation and spatial resource allocation, and effectively solving the problems of slow response speed and low processing accuracy to dynamic changes due to over-reliance on historical data and a single optimization strategy.

[0046] Furthermore, the calculation of real-time operating rate and fluctuation value directly reflects the operating stability of equipment or areas. Therefore, temporary grid identification when the fluctuation value exceeds the threshold helps to discover potential operating problems or abnormal areas, enhances the dynamic response capability of the model, and can quickly adapt to changing operating conditions and perform targeted optimization and adjustments to improve the overall stability and efficiency of the system.

[0047] Furthermore, by comparing the density fluctuation values ​​of adjacent temporary grids, dynamic area division is achieved, effectively improving the rationality and accuracy of the simulation grid. The relationship between the density fluctuation value and the simulation grid reflects the stability and consistency of the personnel distribution. When the density fluctuation is large, it means that there are strong dynamic changes in the area, requiring a more refined division; when the fluctuation is small, it means that the distribution of people or objects in the area is relatively uniform and can be merged into a larger simulation grid. The ability to accurately divide the grid according to real-time changes helps to optimize the model simulation effect, improve computational efficiency, and ensure the reliability of the simulation results.

[0048] Furthermore, the merging of adjacent temporary grids is determined by fluctuation consistency, ensuring the rationality and accuracy of the simulation grid. The relationship between fluctuation consistency and density fluctuation values ​​can reflect the stability of the population distribution within the area. When the density fluctuations of two adjacent grids are very similar, it means that the dynamic changes within the two grids are almost identical. Merging them into a single simulation grid can simplify model calculations without affecting accuracy. The simulation grid division can be dynamically adjusted based on the actual density fluctuation characteristics, optimizing the efficiency and accuracy of the simulation and avoiding unnecessary over-division, thereby improving overall simulation performance.

[0049] Furthermore, by comprehensively considering the impact of real-time density and operating rate on optimization results, the accuracy of predictions and operational feasibility can be improved. Through normalization and weighting, the impact of each parameter is quantified and standardized, making the optimization index more realistic and effective in evaluating the performance of different simulation grids, providing a reliable basis for subsequent grid adjustments and optimization decisions.

[0050] Furthermore, by introducing real-time average movement speed as a third parameter, the model can more comprehensively reflect the dynamic behavior of personnel, namely their movement speed. This additional dynamic parameter allows the model to go beyond analyzing static data and further optimize system simulation by incorporating personnel flow. Specifically, the introduction of movement speed allows the model to identify the flow trends of personnel between different grids, further optimizing the match between personnel density and equipment operating efficiency, and avoiding congestion or inefficiency caused by excessive personnel density or overloaded equipment.

[0051] Furthermore, by introducing a comparison between the predicted optimization index and the simulated optimization index, the deviation of the current grid design in actual application can be effectively evaluated. The index deviation reflects the difference between the predicted results and the actual simulation results, and is the basis for adjusting the grid side length. It provides the gap between the model prediction and the actual situation, helping to identify the optimization space. Combined with the real-time average moving speed, it takes into account the impact of personnel mobility and helps adjust the grid side length to adapt to the personnel dynamics in actual operation.

[0052] Furthermore, by combining exponential deviation and real-time average movement speed, a more refined grid adjustment strategy is implemented. The exponential deviation provides a measure of the difference between the model prediction and the actual situation, making grid adjustment more targeted. When the exponential deviation exceeds the preset deviation threshold, the grid edge length is adjusted to quickly address the deviation between the model and reality, thereby improving model precision and accuracy. Introducing real-time average movement speed as a dynamic factor and taking into account the impact of personnel flow on grid distribution can further optimize grid adjustment to ensure that it can adapt to actual personnel flow and avoid overly large or undersized grid divisions, thereby improving resource scheduling efficiency.

[0053] Furthermore, by normalizing the number of times temporary grid edge lengths are formed and the fluctuation of the real-time average movement speed, and measuring the synchronization of their changes, the relationship between grid edge lengths and personnel flow can be captured more accurately. This process ensures the model's adaptability in the face of dynamic changes and avoids incorrect predictions caused by excessive fluctuations or asynchrony. The normalized number of fluctuations reflects the changes in grid edge lengths and shows the impact of system status or environmental changes on grid division. The normalized movement speed fluctuation reflects the fluctuations in the dynamic flow speed of personnel and reveals the impact of personnel mobility on the entire area. The synchronization of changes provides the correlation between the two, measures the matching degree between personnel mobility and grid division, and ensures that in actual applications, grid adjustments and personnel dynamics can change synchronously.

[0054] Furthermore, by calculating the fluctuation value of the simulated optimization index and comparing it with the preset threshold, the operating rate fluctuation threshold can be dynamically adjusted according to the deviation, ensuring that the model can more accurately adapt to changes in the actual operating environment. The self-correction mechanism improves the flexibility and adaptability of the system, avoids errors caused by overly strict or loose threshold settings, and ensures the efficient and accurate operation of the model in different scenarios, thereby improving the overall optimization capability and stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a flow chart of the dynamic optimization and publishing method for the digital twin model in this embodiment;

[0056] Figure 2 A decision logic diagram for determining a temporary grid for this embodiment;

[0057] Figure 3 This is a decision logic diagram for determining the simulation grid in this embodiment;

[0058] Figure 4 A decision logic diagram for adjusting the grid side length is formed for this embodiment. DETAILED DESCRIPTION

[0059] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0060] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0061] See also Figure 1As shown, it is a flow chart of the dynamic optimization and publishing method for the digital twin model in this embodiment;

[0062] This embodiment provides a method for dynamic optimization and publishing of a digital twin model, including:

[0063] Collect the real-time operation rate of several devices in each grid to be simulated in the industrial area constructed based on the preset grid side length, the real-time density of targets in each grid to be simulated, and the real-time average moving speed;

[0064] Determining a number of temporary grids according to the real-time operating rate within a preset time period and a preset operating rate fluctuation threshold;

[0065] Filter out a number of simulation grids according to the real-time density in any two adjacent temporary grids within a preset determination time;

[0066] Calculating a prediction optimization index according to the real-time operation rate and the real-time density in each simulation grid;

[0067] Using a preset digital twin model to simulate all the grids to be simulated, and generating a simulation optimization index;

[0068] Adjusting the preset grid side length according to the predicted optimization index and the simulated optimization index to form an adjusted grid side length;

[0069] The preset digital twin model is trained using the real-time operation rate, the real-time density, and the real-time average moving speed of all the simulation grids determined based on the adjustment of the grid side length to form an optimized twin model;

[0070] Correcting the preset operating rate fluctuation threshold according to the simulation optimization index obtained by re-simulating the optimization twin model within the preset correction time period to form a corrected operating rate fluctuation threshold;

[0071] Publish the optimized twin model reformed based on the modified operating rate fluctuation threshold.

[0072] The process of publishing the optimized twin model, re-formed based on the revised operating rate fluctuation thresholds, involves inputting the adjusted and revised model parameters and related data into the system, updating the core algorithms of the digital twin model, and publishing the updated optimized model through system interfaces or platforms to ensure that all relevant modules can promptly access and apply the new optimization rules and operating thresholds. After publication, the new optimized model is automatically confirmed and applied in actual operations, providing real-time monitoring and feedback on system performance to continuously optimize operational efficiency and safety.

[0073] The real-time operation rate of a device refers to the ratio of the number of devices in a grid that are actually in operation at a specific moment or time window to the total number of devices in the grid. It reflects the activeness of device usage and is an important basis for measuring the "functional activity" of the grid.

[0074] The real-time density of targets within each simulated grid refers to the number of targets per unit area within each simulated grid. "Targets" specifically refer to people. This metric reflects crowd distribution and is a crucial parameter for digital twin models in modeling human behavior, simulating mobility, and providing safety alerts.

[0075] The real-time average moving speed refers to the average moving speed of all people in a grid or multiple grids within a time window, which represents the activity intensity and flow trend of people in the area.

[0076] The preset grid side length refers to the size of the basic grid used to divide industrial areas or environments in the digital twin model. During the simulation process, the industrial area is divided into multiple square grids, each representing an independent computing unit. The setting of the grid side length directly affects the simulation accuracy and computational efficiency, depending on the size of the target area, the density of personnel within the area, the distribution of equipment, the mobility, and the frequency of real-time data updates of the system. Generally, the grid side length of smaller industrial areas is set between 40 and 100 meters. In this embodiment, it is set to 50 meters to balance computational accuracy and efficiency. It can better adapt to the distribution of personnel and equipment operation within the area, and provide efficient real-time dynamic optimization within the scope of computing power.

[0077] The preset judgment time refers to a time window within a certain period of time used to determine whether the equipment operation rate and personnel density in the grid fluctuate. It depends on the timing characteristics of personnel activities, the operation cycle of the equipment, and the speed of change. It is usually set between 5 minutes and 30 minutes. In this embodiment, it is set to 10 minutes. It can effectively detect fluctuations in personnel flow or equipment operation rate in a relatively short period of time, facilitating rapid response and adjustment.

[0078] The preset correction time refers to the time window used to correct the optimization model. It depends on the length of the optimization cycle, the rate of environmental change, and the convergence time of the model. It is usually set between 30 minutes and 2 hours. In this embodiment, it is set to 30 minutes, which is sufficient to cover the periodic fluctuations of personnel activities and ensure the timeliness and accuracy of model adjustments, thereby effectively optimizing the grid edge length and operation rate fluctuation threshold.

[0079] The simulated optimization index is directly calculated using multiple parameters pre-set in the digital twin model. First, the model simulates the operating state of the entire system based on the real-time operating rate, real-time density, and average movement speed of the equipment. The model then calculates the average optimization state value for all grid cells, ultimately generating a comprehensive optimization index.

[0080] By collecting data such as the real-time operating rate, real-time density, and real-time average movement speed of equipment within each simulated grid within an industrial area, constructed based on a preset grid edge length, the dynamic behavior of the industrial area is optimized and published in real time. First, several temporary grids are identified by comparing the real-time operating rate with a preset fluctuation threshold. Then, the simulation grid is determined by analyzing the real-time density of adjacent grids within the temporary grid, and a predicted optimization index is calculated. The grids are simulated using a digital twin model to generate a simulated optimization index. Combining the predicted optimization index, simulated optimization index, and real-time average movement speed, the grid edge length is adjusted to form an optimized model. Finally, the real-time operating rate, real-time density, and real-time average movement speed of each simulated grid are used as input features, combined with actual operating conditions, to train the digital twin model, enabling it to more accurately predict and simulate dynamic changes in actual operations. This training optimizes the model's parameters and rules to better reflect the actual behavior of the target area under different scenarios, thereby forming an optimized twin model. Finally, the operating rate fluctuation threshold is adjusted based on the optimized twin model, and the final optimized model is published.

[0081] By dynamically collecting and analyzing the real-time density of personnel, the average movement speed of personnel, and the associated equipment operation rates within each grid within an industrial area, a high-precision, adaptive optimization of the digital twin model is achieved. Personnel density reflects the concentration of work within a given area, while average movement speed reveals the strength of personnel mobility. Together, these two factors constitute the spatial and temporal distribution characteristics of personnel behavior. Fluctuations in equipment operation rate, as an external factor influencing personnel behavior, reflect changes in the status of personnel operating equipment. Combining density and speed changes can comprehensively determine the intensity and pace of personnel work within the area. By introducing "change synchronization" as a natural feedback regulation mechanism, this approach guides the dynamic update of the grid structure by measuring the consistency between personnel mobility and regional adjustment behavior. This results in a more stable and responsive twin model in complex environments, significantly improving the intelligent level of personnel behavior simulation, efficiency assessment, and spatial resource allocation. This effectively addresses the slow response and low processing accuracy associated with over-reliance on historical data and a single optimization strategy to address dynamic changes.

[0082] Please continue reading Figure 2 As shown, it is a decision logic diagram for determining a temporary grid in this embodiment;

[0083] The process of determining a plurality of temporary grids according to the real-time operation rate and the preset operation rate fluctuation threshold within a preset determined time period includes:

[0084] Calculating a standard deviation of the real-time operating rate to form an operating rate fluctuation value;

[0085] When the operation rate fluctuation value is greater than the preset operation rate fluctuation threshold, the grid to be simulated is determined to be a temporary grid, and a plurality of temporary grids are formed.

[0086] The preset operating rate fluctuation threshold is a standard value used to determine the stability of the device or system's operating status. It depends on the device type, workload, and expected stability requirements in the target area. Generally, the operating rate fluctuation threshold is set between 5% and 20%. In this embodiment, it is set to 10%. This ensures that optimization and adjustment mechanisms are activated promptly when the operating rate fluctuates significantly, while maintaining system stability, improving response speed and efficiency.

[0087] First, real-time operating rate data for the grid to be simulated is collected over a preset time period, and its standard deviation is calculated to determine the operating rate fluctuation value. Next, this real-time operating rate fluctuation value is compared with a preset operating rate fluctuation threshold. If the fluctuation value exceeds the threshold, the grid is designated as a "temporary grid." This process identifies grids with significant operating fluctuations over the preset time period and identifies them as areas requiring further attention and optimization.

[0088] The calculation of real-time operating rates and fluctuation values ​​directly reflects the operational stability of equipment or areas. Therefore, temporary grid identification when the fluctuation value exceeds the threshold helps to identify potential operational problems or abnormal areas, enhances the dynamic response capability of the model, enables rapid adaptation to changing operating conditions, and performs targeted optimization and adjustments to improve the overall stability and efficiency of the system.

[0089] Specifically, the process of selecting a plurality of simulation grids according to the real-time density in any two adjacent temporary grids within a preset determination time period includes:

[0090] Calculating the standard deviation of the real-time density of each temporary grid to form a density fluctuation value;

[0091] A number of simulation grids are selected according to the density fluctuation values ​​of any two adjacent temporary grids.

[0092] Within a preset judgment period, the real-time density within the temporary grid is analyzed, and the standard deviation of the real-time density within each temporary grid is calculated to form a density fluctuation value. The density fluctuation values ​​of any two adjacent temporary grids are then compared to determine which temporary grids can be merged into a simulation grid. Specifically, temporary grids with relatively consistent density fluctuation values ​​are identified as the same simulation grid, which improves simulation efficiency and accuracy and ensures that density variations within each simulation grid remain within a controllable range.

[0093] By comparing the density fluctuation values ​​of adjacent temporary grids, dynamic area division is achieved, effectively improving the rationality and accuracy of the simulation grid. The relationship between the density fluctuation value and the simulation grid reflects the stability and consistency of the personnel distribution. When the density fluctuation is large, it means that there are strong dynamic changes in the area, requiring a more refined division; when the fluctuation is small, it means that the distribution of people or objects in the area is relatively uniform and can be merged into a larger simulation grid. The ability to accurately divide the grid according to real-time changes helps optimize the model simulation effect, improve computational efficiency, and ensure the reliability of the simulation results.

[0094] Please continue reading Figure 3 As shown, it is a decision logic diagram for determining the simulation grid in this embodiment;

[0095] The process of selecting a plurality of simulation grids according to the density fluctuation values ​​of any two adjacent temporary grids includes:

[0096] Calculating the relative deviation of the density fluctuation values ​​of any two adjacent temporary grids to form a fluctuation consistency;

[0097] When the fluctuation consistency is greater than a preset consistency threshold, it is determined that all of the temporary grids are the simulation grids, and a plurality of simulation grids are formed.

[0098] First, the relative deviation of the density fluctuation values ​​of any two adjacent temporary grids (i.e., those with the closest horizontal distance) is calculated to form a fluctuation consistency index. The relative deviation is calculated by comparing the difference between the two density fluctuation values ​​with their average value, resulting in a measure of fluctuation consistency. When the fluctuation consistency index exceeds a preset consistency threshold, it indicates that the two adjacent temporary grids have a high degree of consistency in the fluctuation of occupant density. Multiple temporary grids with similar density fluctuation characteristics are then identified as simulation grids, ultimately forming a number of simulation grids.

[0099] The preset consistency threshold is the criterion for determining whether adjacent temporary grids should be merged into a simulation grid. It depends on the required grid merging accuracy and the characteristics of the target area, such as the pattern of personnel flow and the magnitude of density changes. It is typically set between 0.1 and 0.3. In this embodiment, it is set to 0.2. This ensures that while ensuring grid merging, it avoids oversimplification, ensuring the rationality and accuracy of simulation grid division, and ensuring that personnel flow simulation can be performed quickly and accurately in actual operations.

[0100] Adjacent temporary grids are judged by their fluctuation consistency, ensuring the rationality and accuracy of the simulation grid. The relationship between fluctuation consistency and density fluctuation values ​​can reflect the stability of the population distribution within the area. When the density fluctuations of two adjacent grids are very similar, it indicates that the dynamic changes within these two grids are almost identical. Merging them into a single simulation grid can simplify model calculations without affecting accuracy. The simulation grid division can be dynamically adjusted based on the actual density fluctuation characteristics, optimizing simulation efficiency and accuracy, and avoiding unnecessary over-division, thereby improving overall simulation performance.

[0101] Specifically, the process of calculating the prediction optimization index according to the real-time operation rate and the real-time density in each simulation grid includes:

[0102] Performing normalization calculation on the real-time density of all the simulation grids to form a normalized density;

[0103] Normalizing the real-time operating rates of all the simulation grids to form a normalized operating rate;

[0104] A weighted sum is performed according to the preset density weight, the preset operation rate weight, the normalized density and the normalized operation rate to form a prediction optimization index.

[0105] The preset density weight is used to adjust the contribution of real-time density to the final optimization result when calculating the predicted optimization index. This weight is determined by the importance of density in the simulation grid and its impact on system optimization. It is generally set between 0.3 and 0.6, but in this example is set to 0.4 to ensure that the density factor has a reasonable impact on the optimization calculation.

[0106] The preset operating rate weight refers to the weight value used to adjust the contribution of the real-time operating rate to the final optimization result when calculating the predicted optimization index. The operating rate reflects the working status and efficiency of the equipment or system in a certain period of time. The setting of its weight is usually based on the degree of influence of the operating efficiency of the equipment or system on the overall performance. Generally, the equipment operating rate has a greater impact on system optimization, especially in large-scale systems, so the operating rate weight is generally set between 0.4 and 0.7. In this embodiment, the operating rate weight is set to 0.6, which can ensure that the equipment operating status occupies an important position in the optimization process, thereby better improving the overall efficiency.

[0107] Based on the real-time operating rate and real-time density of each simulation grid, the real-time density and real-time operating rate of all simulation grids are first normalized to a uniform numerical range. Then, using preset density weights and preset operating rate weights, the normalized real-time density and operating rate are weighted and summed to obtain the predicted optimization index. This weighted integration of various important factors ensures that the optimization index fully reflects the operational efficiency and personnel distribution within the target area.

[0108] By comprehensively considering the impact of real-time density and operating rate on optimization results, we can improve prediction accuracy and operational feasibility. Through normalization and weighting, the impact of each parameter is quantified and standardized, making the optimization index more consistent with actual needs. This allows for effective evaluation of the performance of different simulation grids, providing a reliable basis for subsequent grid adjustments and optimization decisions.

[0109] Specifically, the process of simulating all the grids to be simulated using the preset digital twin model and generating a simulation optimization index includes:

[0110] The real-time operation rate, the real-time density and the real-time average moving speed of all the grids to be simulated are obtained and input into the preset digital twin model to form a simulation optimization index.

[0111] Each grid to be simulated has three key data at a certain moment: real-time operation rate R, real-time density D, and real-time average moving speed:

[0112] In the preset digital twin model, there is a calculation formula:

[0113] Q=a×R+b×(1-D / Dmax)+c×V / Vmax;

[0114] Q is a single optimization index obtained for a single grid to be simulated. a, b, and c are all predetermined model weight coefficients, a=0.5, b=0.3, c=0.2, Dmax is the preset maximum value of density, and Vmax is the preset maximum value of average moving speed, which is used for normalization processing.

[0115] The average value of all the individual optimization indices is calculated to obtain a simulated optimization index.

[0116] First, data such as the real-time operating rate, real-time density, and real-time average movement speed of all grids to be simulated is collected. This data reflects the operating status of equipment, personnel density, and personnel flow. This real-time data is then fed into a pre-configured digital twin model, which performs simulation calculations based on this input information and ultimately generates a simulation optimization index. This index comprehensively reflects the system's current operational efficiency and personnel flow, providing data support for further optimization.

[0117] Introducing real-time average movement speed as an additional input parameter significantly enhances the accuracy and dynamic adaptability of digital twin models during simulation and optimization. Real-time operating rate and real-time density primarily reflect equipment load and personnel distribution density, but these parameters fail to fully capture the dynamic and changing nature of personnel flow. Average movement speed, as a dynamic factor, provides information on personnel flow trends and behavioral patterns in space, which is crucial for analyzing personnel migration and distribution across different grids.

[0118] When the real-time average movement speed of personnel is incorporated into the model, the system can more accurately reflect the dynamic behavior of personnel, thereby optimizing the match between personnel distribution and equipment load, avoiding the congestion or uneven load that can arise from relying solely on static density and equipment operating rates. Personnel mobility can affect the load of a grid, especially in high-mobility areas, where the concentration of personnel and equipment load can fluctuate dramatically over time. By comprehensively considering real-time movement speed, the model not only captures the distribution of personnel within the grid but also tracks the flow of personnel between grids, making the optimization process more responsive to the dynamic changes in the actual environment. Therefore, incorporating real-time average movement speed allows the model to adaptively adjust grid boundaries and operation strategies in complex and dynamic working environments, achieving more refined and efficient optimization. This not only improves the accuracy of the overall optimization index, but also effectively adapts to various changes in real-world scenarios, improving the reliability and efficiency of system operation.

[0119] By introducing real-time average movement speed as a third parameter, the model can more comprehensively reflect the dynamic behavior of personnel, namely their movement speed. This additional dynamic parameter allows the model to go beyond analyzing static data and further optimize system simulation by incorporating personnel flow. Specifically, the introduction of movement speed allows the model to identify personnel flow trends between different grids, further optimizing the match between personnel density and equipment operating efficiency, and avoiding congestion or inefficiencies caused by excessive personnel density or overloaded equipment.

[0120] Specifically, the process of adjusting the preset grid side length according to the prediction optimization index and the simulation optimization index includes:

[0121] Calculating a relative deviation between the predicted optimization index and the simulated optimization index to form an index deviation;

[0122] The preset grid side length is adjusted according to the exponential deviation and the real-time average moving speed.

[0123] In the process of adjusting the preset grid side length, the relative deviation between the predicted optimization index and the simulated optimization index is first calculated to obtain the index deviation. Then, based on the index deviation and the real-time average moving speed, the preset grid side length is adjusted. By comparing the difference between the predicted results and the simulation results, combined with the flow speed of personnel, the grid size is optimized in real time, thereby improving the responsiveness and accuracy of the overall system.

[0124] By introducing a comparison between the predicted optimization index and the simulated optimization index, the deviation of the current grid design in actual application can be effectively evaluated. The index deviation reflects the difference between the predicted results and the actual simulation results. It is the basis for adjusting the grid side length, provides the gap between the model prediction and the actual situation, and helps identify the optimization space. In combination with the real-time average moving speed, the impact of personnel mobility is taken into account, which helps adjust the grid side length to adapt to the personnel dynamics in actual operation.

[0125] Specifically, the process of adjusting the preset grid side length according to the exponential deviation and the real-time average moving speed includes:

[0126] When the deviation comparison result shows that the index deviation is greater than the preset deviation threshold, increasing the preset grid side length according to the relative deviation between the index deviation and the preset deviation threshold and the preset adjustment coefficient to form a temporary grid side length;

[0127] The temporary grid side length is adjusted according to all the temporary grid side lengths within a preset adjustment time period and the real-time average moving speed to form an adjusted grid side length.

[0128] The preset deviation threshold is a standard for measuring the deviation between the predicted optimization index and the simulated optimization index. It depends on the accuracy requirements of the system, historical data, and industry standards. It is usually set between 0.5% and 10%. In this embodiment, it is set to 5%. It can ensure that the adjustment of the grid edge length is only performed when the difference between the predicted optimization index and the simulated optimization index is large without causing frequent adjustments, thereby improving computing efficiency and resource utilization.

[0129] The preset adjustment coefficient is a weight factor used to adjust the grid side length when the deviation exceeds the preset threshold. It depends on the stability requirements and error tolerance of the system and is usually set between 0.1 and 1.0. In this embodiment, the preset adjustment coefficient is set to 0.5. Under the premise of ensuring stable operation of the system, the grid side length can be flexibly adjusted according to the deviation situation to ensure more accurate grid division.

[0130] When adjusting the preset grid length, the system first determines whether the exponential deviation exceeds a preset deviation threshold. If so, the preset grid length is increased based on the relative deviation between the exponential deviation and the preset deviation threshold, along with a preset adjustment factor, to form a temporary grid length. Then, within the preset adjustment period, the temporary grid length is further adjusted, taking into account all temporary grid lengths and the real-time average movement speed. This ultimately results in the adjusted grid length, ensuring real-time grid size adjustment based on actual deviations and dynamic changes in personnel flow.

[0131] By combining exponential deviation and real-time average movement speed, a more refined grid adjustment strategy is achieved. The exponential deviation provides a measure of the difference between the model prediction and the actual situation, making grid adjustments more targeted. When the exponential deviation exceeds the preset deviation threshold, the grid edge length is adjusted to quickly address the deviation between the model and reality, thereby improving model precision and accuracy. Introducing real-time average movement speed as a dynamic factor and taking into account the impact of personnel flow on grid distribution can further optimize grid adjustment to ensure that it can adapt to actual personnel flow and avoid overly large or undersized grid divisions, thereby improving resource scheduling efficiency.

[0132] Please continue reading Figure 4 As shown, it is a decision logic diagram for adjusting the grid side length in this embodiment;

[0133] The process of adjusting the temporary grid side length according to all the temporary grid side lengths and the real-time average moving speed within the preset adjustment time period includes:

[0134] Calculating the standard deviation of the number of times all the temporary grid side lengths are formed and normalizing the result to form a normalized number fluctuation value;

[0135] Calculating the standard deviation of all the real-time average moving speeds and normalizing them to form a normalized moving speed fluctuation value;

[0136] Calculating the correlation coefficient between the normalized number fluctuation value and the normalized movement speed fluctuation value to form a change synchronization degree;

[0137] When the change synchronization degree is less than the preset standard synchronization degree, the temporary grid side length is increased according to the relative deviation between the preset standard synchronization degree and the change synchronization degree and the preset adjustment coefficient to form an adjusted grid side length.

[0138] The preset adjustment time refers to the time range allowed for adjusting the grid edge length during the adjustment process. It depends on the system response requirements, operational stability and business needs. It is usually set between 5 minutes and 40 minutes. In this embodiment, it is set to 30 minutes, which can effectively balance the system's response speed and operational stability, ensure that each adjustment of the grid edge length is based on sufficient real-time data analysis, and avoid the instability caused by excessive adjustment.

[0139] The preset standard synchronization degree is a standard value used to measure the degree of synchronization between the number of temporary grid side length changes and the fluctuations in the real-time average moving speed during the grid side length adjustment process. It depends on the system stability requirements and the responsiveness of the adjustment. It is usually set between 0.5 and 0.9. In this embodiment, it is set to 0.8, which can balance the system's responsiveness to small changes and the system's stability.

[0140] First, the standard deviation of the number of times all temporary grid side lengths are formed is calculated and normalized to obtain the normalized number fluctuation value. The standard deviation of all real-time average movement speeds is also calculated and normalized to obtain the normalized movement speed fluctuation value. Then, the correlation coefficient between these two fluctuation values ​​is calculated to form the change synchronization degree, which reflects the synchronization relationship between the change in grid side length and the movement speed of the person. When the change synchronization degree is lower than the preset standard synchronization degree, the temporary grid side length is increased based on the relative deviation between the preset standard synchronization degree and the change synchronization degree, as well as the preset adjustment coefficient, to finally form the adjusted grid side length.

[0141] By normalizing the number of times temporary grid edge lengths are formed and the fluctuations in real-time average movement speed, and measuring the degree of synchronization of their changes, the relationship between grid edge lengths and personnel flow can be captured more accurately. This process ensures the model's adaptability in the face of dynamic changes and avoids incorrect predictions due to excessive fluctuations or asynchrony. The normalized number of fluctuations reflects the changes in grid edge lengths and shows the impact of system status or environmental changes on grid division. The normalized movement speed fluctuation reflects the fluctuations in the dynamic flow speed of personnel and reveals the impact of personnel mobility on the entire area. The degree of synchronization of changes provides a correlation between the two, measuring the matching degree between personnel mobility and grid division, ensuring that in actual applications, grid adjustments and personnel dynamics can change synchronously.

[0142] Specifically, the preset operating rate fluctuation threshold is corrected according to the simulation optimization index obtained by re-simulating the optimization twin model within the preset correction time period, and the process of forming the corrected operating rate fluctuation threshold includes:

[0143] Calculating the standard deviation of the simulated optimization index to form an optimization index fluctuation value;

[0144] When the optimization index fluctuation value is greater than the preset index fluctuation threshold, the preset operating rate fluctuation threshold is reduced according to the relative deviation between the optimization index fluctuation value and the preset index fluctuation threshold and the preset correction coefficient to form a corrected operating rate fluctuation threshold.

[0145] The preset index fluctuation threshold refers to the maximum range of fluctuations allowed in the simulated optimization index within the optimization twin model. This threshold is determined by the actual application scenario, primarily based on the system's tolerance for fluctuations and the stability of historical data. It is typically set between 0.1 and 0.2, and in this example, it is set to 0.15 to avoid unnecessary frequent adjustments during model correction while maintaining system stability.

[0146] The preset correction factor is the proportional coefficient used to adjust the preset operating rate fluctuation threshold based on the deviation of the optimization index fluctuation value when correcting the operating rate fluctuation threshold. It reflects the optimization model's sensitivity to fluctuation correction and depends on the system's response speed and accuracy requirements for fluctuation adjustments. It is typically set between 0.2 and 0.3. In this example, it is set to 0.25, which ensures smoother fluctuation correction and prevents model instability caused by large fluctuations.

[0147] By resimulating the optimization twin model, a new simulated optimization index is obtained. The standard deviation of this optimization index is calculated to form the optimization index fluctuation value. This fluctuation value is then compared with a preset index fluctuation threshold. If the optimization index fluctuation value is greater than the preset threshold, the preset operating rate fluctuation threshold is adjusted based on the relative deviation between the two, resulting in a revised operating rate fluctuation threshold. This dynamic adjustment ensures the adaptability of the model to actual operating conditions and improves the optimization effect.

[0148] By calculating the fluctuation value of the simulated optimization index and comparing it with the preset threshold, the operating rate fluctuation threshold can be dynamically adjusted according to the deviation, ensuring that the model can more accurately adapt to changes in the actual operating environment. The self-correction mechanism improves the flexibility and adaptability of the system, avoids errors caused by overly strict or loose threshold settings, and ensures the efficient and accurate operation of the model in different scenarios, thereby improving the overall optimization capability and stability.

[0149] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

Claims

1. A dynamic optimization and publishing method for a digital twin model, characterized in that: include: Collect the real-time operation rate of several devices in each grid to be simulated in the industrial area constructed based on the preset grid side length, the real-time density of targets in each grid to be simulated, and the real-time average moving speed; Determining a number of temporary grids according to the real-time operating rate within a preset time period and a preset operating rate fluctuation threshold; Filter out a number of simulation grids according to the real-time density in any two adjacent temporary grids within a preset determination time; Calculating a prediction optimization index according to the real-time operation rate and the real-time density in each simulation grid; Using a preset digital twin model to simulate all the grids to be simulated, and generating a simulation optimization index; Adjusting the preset grid side length according to the predicted optimization index and the simulated optimization index to form an adjusted grid side length; The preset digital twin model is trained using the real-time operation rate, the real-time density, and the real-time average moving speed of all the simulation grids determined based on the adjustment of the grid side length to form an optimized twin model; Correcting the preset operating rate fluctuation threshold according to the simulation optimization index obtained by re-simulating the optimization twin model within the preset correction time period to form a corrected operating rate fluctuation threshold; Publishing the optimized twin model re-formed based on the modified operating rate fluctuation threshold; The process of adjusting the preset grid side length according to the prediction optimization index and the simulation optimization index includes: Calculating a relative deviation between the predicted optimization index and the simulated optimization index to form an index deviation; Adjusting the preset grid side length according to the index deviation and the real-time average moving speed; The process of adjusting the preset grid side length according to the index deviation and the real-time average moving speed includes: When the deviation comparison result shows that the index deviation is greater than the preset deviation threshold, increasing the preset grid side length according to the relative deviation between the index deviation and the preset deviation threshold and the preset adjustment coefficient to form a temporary grid side length; The temporary grid side length is adjusted according to all the temporary grid side lengths within a preset adjustment time period and the real-time average moving speed to form an adjusted grid side length.

2. The dynamic optimization and publishing method for a digital twin model according to claim 1, characterized in that: The process of determining a plurality of temporary grids according to the real-time operation rate and the preset operation rate fluctuation threshold within a preset determined time period includes: Calculating a standard deviation of the real-time operating rate to form an operating rate fluctuation value; When the operation rate fluctuation value is greater than the preset operation rate fluctuation threshold, the grid to be simulated is determined to be a temporary grid, and a plurality of temporary grids are formed.

3. The dynamic optimization and publishing method for a digital twin model according to claim 2, characterized in that: The process of selecting a plurality of simulation grids according to the real-time density in any two adjacent temporary grids within a preset determination time period includes: Calculating the standard deviation of the real-time density of each temporary grid to form a density fluctuation value; A number of simulation grids are selected according to the density fluctuation values ​​of any two adjacent temporary grids.

4. The dynamic optimization and publishing method for a digital twin model according to claim 3, characterized in that: The process of selecting a plurality of simulation grids according to the density fluctuation values ​​of any two adjacent temporary grids includes: Calculating the relative deviation of the density fluctuation values ​​of any two adjacent temporary grids to form a fluctuation consistency; When the fluctuation consistency is greater than a preset consistency threshold, it is determined that all of the temporary grids are the simulation grids, and a plurality of simulation grids are formed.

5. The dynamic optimization and publishing method for a digital twin model according to claim 4, characterized in that: The process of calculating the prediction optimization index according to the real-time operation rate and the real-time density in each simulation grid includes: Performing normalization calculation on the real-time density of all the simulation grids to form a normalized density; Normalizing the real-time operating rates of all the simulation grids to form a normalized operating rate; A weighted sum is performed according to the preset density weight, the preset airflow rate weight, the normalized density, and the normalized operating rate to form a prediction optimization index.

6. The dynamic optimization and publishing method for a digital twin model according to claim 5, characterized in that: The process of simulating all the grids to be simulated using the preset digital twin model and generating a simulation optimization index includes: The real-time operation rate and the real-time density of all the grids to be simulated are obtained and input into the preset digital twin model to form a simulation optimization index.

7. The dynamic optimization and publishing method for a digital twin model according to claim 6, characterized in that: The process of adjusting the temporary grid side length according to all the temporary grid side lengths and the real-time average moving speed within the preset adjustment time period includes: Calculating the standard deviation of the number of times all the temporary grid side lengths are formed and normalizing the result to form a normalized number fluctuation value; Calculating the standard deviation of all the real-time average moving speeds and normalizing them to form a normalized moving speed fluctuation value; Calculating the correlation coefficient between the normalized number fluctuation value and the normalized movement speed fluctuation value to form a change synchronization degree; When the change synchronization degree is less than the preset standard synchronization degree, the temporary grid side length is increased according to the relative deviation between the preset standard synchronization degree and the change synchronization degree and the preset adjustment coefficient to form an adjusted grid side length.

8. The dynamic optimization and publishing method for a digital twin model according to claim 7, characterized in that: The process of correcting the preset operating rate fluctuation threshold according to the simulation optimization index obtained by re-simulating the optimization twin model within the preset correction time period to form the corrected operating rate fluctuation threshold includes: Calculating the standard deviation of the simulated optimization index to form an optimization index fluctuation value; When the optimization index fluctuation value is greater than the preset index fluctuation threshold, the preset operating rate fluctuation threshold is reduced according to the relative deviation between the optimization index fluctuation value and the preset index fluctuation threshold and the preset correction coefficient to form a corrected operating rate fluctuation threshold.

Images