Clothing production digital twin simulation method and system based on real-time data interaction

Abstract

The application provides a garment production digital twin simulation method and system based on real-time data interaction, and belongs to the technical field of digital twins, and specifically comprises the following steps: based on the adjustment distribution of model influence data in different production batches frequently adjusted production stages, when the data correlation degree of the frequently adjusted production stage meets the requirements, the simulation processing strategy of the digital twin model when different monitoring data are interacted is determined based on the correlated monitoring data, the simulation processing strategy is used for simulation processing to obtain the update processing data of the digital twin model in the preset time period in the frequently adjusted production stage, the overall simulation processing strategy of the digital twin model in the next time period in the frequently adjusted production stage is determined based on the update processing data, and the efficiency of the update processing of the digital twin model is improved.

Description

Technical Field

[0001] This invention belongs to the field of digital twin technology, and in particular relates to a digital twin simulation method and system for garment production based on real-time data interaction. Background Technology

[0002] The garment production process involves a large number of production stages and equipment. Traditional operation and maintenance management methods cannot accurately and intuitively control the production equipment during the garment production process, making it difficult to achieve reliable management of the garment production process.

[0003] Therefore, in order to achieve reliable management of the garment production process, a digital twin model of the garment production factory is built to improve the reliability of garment production management. In invention patent application CN202411276825.6, "Intelligent Garment Industry Production Control Method and System Based on Data Analysis," real-time production data is collected and the garment production digital twin model and garment production knowledge graph are updated, and periodic optimization is performed until the production task is completed. This improves the reliability of production control processing in the garment industry. However, the following technical problems exist:

[0004] In the dynamic simulation process of digital twin models, on the one hand, the overall digital twin model is simulated using a dynamic update cycle, and on the other hand, the digital model is simulated in response to user operation data. Changes in production data, such as changes in cutting dimensions, may lead to changes in the relevant equipment parameters of sewing equipment and quality inspection equipment to meet the needs of garment production. Therefore, how to update the overall digital twin model simulation strategy based on the updates of the digital twin model during interactive processing, and ensure the data reliability of the digital twin model, has become an urgent technical problem to be solved.

[0005] To address the aforementioned technical issues, this application provides a digital twin simulation method and system for garment production based on real-time data interaction. Summary of the Invention

[0006] To achieve the objectives of this invention, the following technical solution is adopted:

[0007] Firstly, this application provides a digital twin simulation method for garment production based on real-time data interaction, specifically including:

[0008] S1 determines the changes in other monitoring data of the digital twin model of the garment production factory based on the historical adjustment of the monitoring data, uses the changes to determine the associated monitoring data of the monitoring data, and uses the associated monitoring data to determine the model influence data in the monitoring data;

[0009] S2 uses different models to influence the historical adjustment of data at different production stages, and identifies the frequently adjusted production stages in the production stages.

[0010] S3, based on the adjustment distribution of model influence data during frequent adjustments of production stages in different production batches, determines that the data correlation degree of the frequent adjustments of production stages meets the requirements, and then proceeds to the next step.

[0011] S4, based on the associated monitoring data, determines the simulation processing strategy of the digital twin model when different monitoring data interact. The simulation processing strategy is used to perform simulation processing to obtain the updated processing data of the digital twin model within a preset time period in the frequently adjusted production stage. Based on the updated processing data, the overall simulation processing strategy of the digital twin model for the next time period in the frequently adjusted production stage is determined.

[0012] The beneficial effects of this invention are as follows:

[0013] Based on the adjustment distribution of model influence data in production stages with frequent adjustments across different production batches, it is determined whether the data correlation of frequently adjusted production stages meets the requirements. This enables the selection of frequently adjusted production stages with high timeliness in data update processing of digital twin models based on the dispersion of the adjustment distribution that has a high degree of influence on the production equipment of the digital twin model, thereby improving the efficiency of updating the digital twin model of relevant frequently adjusted production stages.

[0014] Based on the updated processing data, the overall simulation processing strategy of the digital twin model for the next period in the frequently adjusted production stage is determined. It fully considers the differences in the update processing timeliness of different production equipment due to the frequency of data interaction and the differences in related monitoring data in the frequently adjusted production stage. This also lays the foundation for generating differentiated overall simulation processing strategies for the digital twin model based on the update processing timeliness of different production equipment, and realizes the dynamic adjustment of the overall simulation processing strategy of the digital twin model.

[0015] A further technical solution is that the historical adjustment of the monitoring data includes the number of historical data interactions of the monitoring data and the adjustment amount for different historical data interaction numbers.

[0016] A further technical solution is that the changes in the other monitoring data include the amount of data change under different historical data interaction times.

[0017] A further technical solution is that the method for determining the associated monitoring data is as follows:

[0018] Based on the historical adjustment of the monitoring data, determine the adjustment amount of the monitoring data under different historical data interaction numbers;

[0019] Based on the changes in other monitoring data, determine the amount of data change of the other monitoring data under different historical data interaction numbers of the monitoring data;

[0020] Based on the ratio of the data change to the adjustment amount, the change correlation value under different historical data interaction numbers is determined. Based on the average value of the change correlation value under different historical data interaction numbers, it is determined whether the other monitoring data is the associated monitoring data of the monitoring data.

[0021] A further technical solution is that when the average value of the change correlation value under different historical data interaction times is greater than the preset change correlation value threshold, the other monitoring data are determined to be the associated monitoring data of the monitoring data.

[0022] A further technical solution is that the method for determining the simulation processing strategy of the digital twin model when the monitoring data is interacting is as follows:

[0023] Based on the associated monitoring data of the aforementioned monitoring data, the production equipment with associated monitoring data is identified;

[0024] For production equipment with monitoring data and production equipment with associated monitoring data in the digital twin model, simulation processing is performed based on the changes in the monitoring data to obtain simulation processing results.

[0025] A further technical solution involves determining the overall simulation processing strategy for the digital twin model in the next time period as follows:

[0026] Using the update processing data of the digital twin model within a preset time period during the frequent adjustment production phase, the simulation completion time of different production equipment in the digital twin model is determined, and the simulation completion time is used as the data update time of the production equipment.

[0027] The time interval between adjacent data update times of different production equipment is used as the update interval time interval. The update interval time interval when the duration of different production equipment is greater than the preset duration threshold is determined and used as the update deviation time interval.

[0028] Based on the number of update deviation periods for different production equipment, determine the overall simulation processing strategy for the digital twin model of the frequently adjusted production stage in the next period.

[0029] A further technical solution involves performing overall simulation processing on the digital twin model, specifically including:

[0030] Using all production equipment in the digital twin model as targets, and based on changing monitoring data, the digital twin model is used to simulate the operating status of different targets.

[0031] Secondly, this application provides a digital twin simulation system for garment production based on real-time data interaction, employing the aforementioned digital twin simulation method for garment production based on real-time data interaction, specifically including:

[0032] Interactive data acquisition module, simulation processing module, simulation strategy output module;

[0033] The interactive data acquisition module is responsible for acquiring interactive data from the monitoring data of the digital twin model of the garment production factory.

[0034] The simulation processing module is responsible for performing simulation processing based on the interactive data and simulation processing strategy to obtain the updated processing data of the digital twin model within the most recent preset time period.

[0035] The simulation strategy output module is responsible for determining the overall simulation processing strategy of the digital twin model for the next time period based on the updated processing data.

[0036] A further technical solution is that the interactive data includes changes in the monitoring data of different production equipment in the digital twin model.

[0037] A further technical solution is that the updated processing data includes the data update times of different production equipment.

[0038] Other features and advantages will be set forth in the following description, and the objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0039] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0040] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0041] Figure 1 This is a flowchart of a thermoforming process control method;

[0042] Figure 2 This is a flowchart illustrating the method for determining the correlation and monitoring data.

[0043] Figure 3 This is a flowchart illustrating the method for determining the influence of models on data in monitoring data;

[0044] Figure 4 This is a flowchart of a method for frequently adjusting the production stage during the production phase. Detailed Implementation

[0045] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0046] In this invention, by considering the updates of the digital twin model due to data interaction in the most recent preset time period, the overall simulation processing strategy for the digital twin model in the next time period is determined. This not only ensures that the update processing efficiency of the digital twin model in the period with frequent data interaction is higher because it does not need to undergo overall simulation processing, but also ensures the timeliness of the data of the digital twin model in the period with frequent data interaction.

[0047] Example 1

[0048] like Figure 1 As shown, this application provides a digital twin simulation method for garment production based on real-time data interaction, specifically including:

[0049] S1 determines the changes in other monitoring data of the digital twin model of the garment production factory based on the historical adjustment of the monitoring data, uses the changes to determine the associated monitoring data of the monitoring data, and uses the associated monitoring data to determine the model influence data in the monitoring data;

[0050] Furthermore, the historical adjustment of the monitoring data includes the number of historical data interactions and the adjustment amount for different historical data interaction numbers.

[0051] Specifically, the changes in other monitoring data include the amount of data change under different historical data interaction times.

[0052] Specifically, such as Figure 2 As shown, the method for determining the associated monitoring data is as follows:

[0053] Based on the historical adjustment of the monitoring data, determine the adjustment amount of the monitoring data under different historical data interaction numbers;

[0054] Based on the changes in other monitoring data, determine the amount of data change of the other monitoring data under different historical data interaction numbers of the monitoring data;

[0055] Based on the ratio of the data change to the adjustment amount, the change correlation value under different historical data interaction numbers is determined. Based on the average value of the change correlation value under different historical data interaction numbers, it is determined whether the other monitoring data is the associated monitoring data of the monitoring data.

[0056] Furthermore, when the average value of the change correlation value under different historical data interaction times is greater than the preset change correlation value threshold, the other monitoring data are determined to be the associated monitoring data of the monitoring data.

[0057] Specifically, such as Figure 3 As shown, the method for determining the model influence data in the monitoring data is as follows:

[0058] Based on the production equipment corresponding to the associated monitoring data, determine the production equipment that is associated with the monitoring data and identify it as the associated production equipment;

[0059] The equipment impact value is determined based on the ratio of the number of related production equipment to the number of production equipment in the digital twin model of the garment production factory;

[0060] Based on the equipment impact value, determine whether the monitoring data is model impact data.

[0061] Furthermore, when the device's impact value is greater than a preset impact value threshold, the monitoring data is determined to be model impact data.

[0062] It should be noted that when there is no model affecting the data, a preset time period is used to perform the overall simulation processing of the digital twin model in different production stages.

[0063] In another possible embodiment, the method for determining the model influence data in the monitoring data is as follows:

[0064] Based on the production equipment corresponding to the associated monitoring data, determine the production equipment that is associated with the monitoring data and identify it as the associated production equipment;

[0065] The equipment association value of different associated production equipment is determined by the ratio of the number of associated monitoring data of different associated production equipment to the number of monitoring data in the digital twin model;

[0066] The monitoring data is determined as model-affected data based on the equipment association values ​​of different associated production equipment.

[0067] Furthermore, when the sum of the equipment association values ​​of different related production equipment is greater than a preset association value threshold, the monitoring data is determined to be model influence data.

[0068] In another possible embodiment, the method for determining the model influence data in the monitoring data is as follows:

[0069] Obtain the number of associated monitoring data for the aforementioned monitoring data;

[0070] Specifically, the above steps include the following scenarios:

[0071] Scenario 1: When the number of associated monitoring data and the proportion of monitoring data in the digital twin model are both within a preset range, it is determined that the monitoring data does not belong to the model-affected data.

[0072] Scenario 2: When either the number of associated monitoring data or the proportion of monitoring data in the digital twin model is not within a preset range, or when the number of associated monitoring data is greater than a preset threshold for the number of associated monitoring data or the proportion of monitoring data in the digital twin model is greater than a preset threshold for the proportion of monitoring data, then the monitoring data is determined to be model-affected data.

[0073] Scenario 3: When the number of associated monitoring data is not greater than a preset threshold for the number of associated monitoring data or the proportion of monitoring data in the digital twin model is not greater than a preset threshold for the proportion of monitoring data, the association influence factor of the monitoring data is determined based on the number of associated monitoring data and the proportion of monitoring data in the digital twin model. When the association influence factor of the monitoring data is greater than a preset threshold for the association influence factor, the monitoring data is determined to belong to the model influence data.

[0074] Based on the production equipment corresponding to the associated monitoring data, determine the production equipment that is associated with the monitoring data and identify it as the associated production equipment;

[0075] The above steps include the following scenarios:

[0076] Scenario 1: Based on the ratio of the number of production equipment in the digital twin model of the associated production equipment to the number of production equipment in the garment production factory, determine the equipment impact value. When the equipment impact value is greater than the preset equipment impact value threshold, determine that the monitoring data belongs to the model impact data.

[0077] Scenario 2: When the device influence value is not greater than the preset device influence value threshold: When the device influence value is small, that is, less than the preset influence value, it is determined that the monitoring data does not belong to the model influence data;

[0078] The equipment association value of different related production equipment is determined by the ratio of the number of related monitoring data of different related production equipment to the number of monitoring data in the digital twin model. Based on the equipment association value of different related production equipment, it is determined whether the monitoring data is model influence data.

[0079] It is understood that when the device association value is greater than the preset association threshold, the monitoring data is determined to be model influence data.

[0080] S2 uses different models to influence the historical adjustment of data at different production stages, and identifies the frequently adjusted production stages in the production stages.

[0081] Furthermore, the production stages include a commissioning production stage, a stable production stage, an equipment adjustment production stage, and a garment adjustment production stage.

[0082] Specifically, the debugging production stage is the production stage in which different production equipment has been debugged and the production data of different production equipment has not been stabilized; the stable production stage is the production stage in which the production data of different production equipment are stable; the equipment adjustment production stage is the production stage in which new production equipment is added or in which production equipment is suspended; and the garment adjustment production stage is the production stage in which the type of garment being produced is switched.

[0083] It is understandable that, such as Figure 4 As shown, the method for determining the frequent adjustments to the production stage in the production phase is as follows:

[0084] Based on the historical adjustment of the model's influence data at different production stages, determine the number of adjustments to the model's influence data at different production batches during each production stage;

[0085] Based on the number of adjustments, model adjustment data for the model impact data in different production batches is determined;

[0086] Based on the amount of model adjustment data in different production batches, determine whether the production stage is a frequently adjusted production stage.

[0087] Furthermore, the model adjustment data is model adjustment data with an adjustment number greater than a preset adjustment number threshold.

[0088] Specifically, when the average number of model adjustment data in different production batches is greater than a preset threshold for the number of adjustment data, the production stage is determined to be a frequently adjusted production stage.

[0089] It should be noted that when the production stage is not a frequently adjusted production stage, the digital twin model is simulated as a whole using a preset time period in all production stages.

[0090] In another possible embodiment, the method for determining the frequent adjustments to the production stage in the production phase is as follows:

[0091] Based on the historical adjustment of the model's influence data at different production stages, determine the number of adjustments to the model's influence data at different production batches during each production stage;

[0092] The sum of the number of adjustments for different model influence data in different production batches is determined based on the sum of the number of adjustments in different production batches.

[0093] Whether a production stage is a frequently adjusted production stage is determined based on the average number of adjustments made in different production batches.

[0094] Furthermore, when the average of the number of adjustments in different production batches is greater than a preset adjustment threshold, the production stage is determined to be a frequently adjusted production stage.

[0095] S3, based on the adjustment distribution of model influence data during frequent adjustments of production stages in different production batches, determines that the data correlation degree of the frequent adjustments of production stages meets the requirements, and then proceeds to the next step.

[0096] Specifically, determining that the data correlation level in the frequently adjusted production stage meets the requirements includes:

[0097] By frequently adjusting the distribution of model influence data in different production batches, the time periods in which model influence data is adjusted in different production batches are identified and used as data adjustment periods.

[0098] Based on the proportion of data adjustment periods in different production batches, determine the real-time values ​​for model adjustments in different production batches;

[0099] Based on the average value of the real-time values ​​adjusted by the model in different production batches, it is determined whether the data correlation of the frequently adjusted production stage meets the requirements.

[0100] Furthermore, when the average real-time value of the model adjustment in different production batches is greater than the preset real-time value threshold, it is determined that the data correlation degree of the frequently adjusted production stage does not meet the requirements.

[0101] It should be noted that when the data correlation in the frequently adjusted production stage does not meet the requirements, the overall simulation of the digital twin model will be performed when there is data interaction between the model and the data.

[0102] In another possible embodiment, determining that the data correlation level of the frequently adjusted production phase meets the requirements specifically includes:

[0103] By frequently adjusting the distribution of model influence data in different production batches, the timing of model influence data adjustment in different production batches is determined and used as the data adjustment timing.

[0104] The real-time values ​​for model adjustments in different production batches are determined based on the proportion of data adjustment times in different production batches.

[0105] Based on the average value of the real-time values ​​adjusted by the model in different production batches, it is determined whether the data correlation of the frequently adjusted production stage meets the requirements.

[0106] In another possible embodiment, determining that the data correlation level of the frequently adjusted production phase meets the requirements specifically includes:

[0107] By frequently adjusting the distribution of model influence data in different production batches, the timing of model influence data adjustment in different production batches is determined and used as the data adjustment timing. Based on the proportion of data adjustment timings in different production batches, the real-time values ​​of model adjustment in different production batches are determined.

[0108] It should be noted that the above steps include the following scenarios:

[0109] Scenario 1: When the real-time values ​​of model adjustments in different production batches are all less than the preset threshold, it is determined that the data correlation degree of the frequently adjusted production stage meets the requirements.

[0110] Scenario 2: When there are production batches where the real-time value of the model adjustment is not less than the preset threshold, and there are production batches where the real-time value of the model adjustment is greater than the preset threshold, then it is determined that the data correlation degree of the frequently adjusted production stage does not meet the requirements.

[0111] The time periods in which data adjustments occur are identified. These time periods are then used as data adjustment periods. The frequency of data adjustments for different data adjustment periods is determined by the proportion of data adjustment moments in different data adjustment periods and the time interval between different data adjustment moments.

[0112] The above steps include the following scenarios:

[0113] Scenario 1: When the proportion of time periods with data adjustment in different production batches is less than the preset threshold for the proportion of time periods, it is determined that the data correlation degree of the frequently adjusted production stage meets the requirements.

[0114] Scenario 2: When there is no data adjustment period with a frequency value greater than the preset frequency value threshold for time period adjustment, it is determined that the data correlation degree of the frequently adjusted production stage meets the requirements.

[0115] In another possible embodiment, the frequency value of the data adjustment period is determined based on the output of a mathematical model that takes the proportion of data adjustment moments in different data adjustment periods and the time interval between different data adjustment moments as inputs, wherein the mathematical model is constructed using the analytic hierarchy process.

[0116] By using the frequency of data adjustment periods in different production batches and the time interval between different data adjustment periods, update timeliness values ​​for different production batches are determined. Based on the update timeliness values ​​for different production batches, update evaluation values ​​are determined. Based on the update evaluation values, it is determined whether the data correlation degree of the frequently adjusted production stage meets the requirements.

[0117] The above steps include the following scenarios:

[0118] In one possible embodiment, the update timeliness value is determined based on the output of a mathematical model that takes as input the time interval between different data adjustment periods in different production batches and the time interval between different data adjustment periods, wherein the mathematical model is constructed using the analytic hierarchy process (AHP).

[0119] Scenario 1: When there is a production batch with an update timeliness value greater than the preset update timeliness value threshold, it is determined that the data correlation degree of the frequently adjusted production stage does not meet the requirements;

[0120] Scenario 2: When there is no production batch with an update timeliness value greater than the preset update timeliness value threshold, an update evaluation value is determined based on the average update timeliness value of different production batches, and the data correlation degree of the frequently adjusted production stage is determined based on the update evaluation value.

[0121] Furthermore, when the update evaluation value of the frequently adjusted production stage is greater than the preset update evaluation threshold, it is determined that the data correlation degree of the frequently adjusted production stage does not meet the requirements.

[0122] S4, based on the associated monitoring data, determines the simulation processing strategy of the digital twin model when different monitoring data interact. The simulation processing strategy is used to perform simulation processing to obtain the updated processing data of the digital twin model within a preset time period in the frequently adjusted production stage. Based on the updated processing data, the overall simulation processing strategy of the digital twin model for the next time period in the frequently adjusted production stage is determined.

[0123] Specifically, the method for determining the simulation processing strategy of the digital twin model when the monitoring data is interacting is as follows:

[0124] Based on the associated monitoring data of the aforementioned monitoring data, the production equipment with associated monitoring data is identified;

[0125] For production equipment with monitoring data and production equipment with associated monitoring data in the digital twin model, simulation processing is performed based on the changes in the monitoring data to obtain simulation processing results.

[0126] Furthermore, the method for determining the overall simulation processing strategy of the digital twin model for the next time period is as follows:

[0127] Using the update processing data of the digital twin model within a preset time period during the frequent adjustment production phase, the simulation completion time of different production equipment in the digital twin model is determined, and the simulation completion time is used as the data update time of the production equipment.

[0128] The time interval between adjacent data update times of different production equipment is used as the update interval time interval. The update interval time interval when the duration of different production equipment is greater than the preset duration threshold is determined and used as the update deviation time interval.

[0129] Based on the number of update deviation periods for different production equipment, determine the overall simulation processing strategy for the digital twin model of the frequently adjusted production stage in the next period.

[0130] It is understandable that, based on the number of update deviation periods for different production equipment, the overall simulation processing strategy for the digital twin model of the frequently adjusted production stage in the next period is determined, specifically including:

[0131] Based on the number of update deviation periods for different production equipment, if it is determined that there is no production equipment with an update deviation period number greater than the preset update deviation period number threshold, then there is no need to perform overall simulation processing of the digital twin model in the next stage.

[0132] When the number of production equipment with update deviation periods exceeds a preset threshold, the production equipment with the number of update deviation periods exceeding the preset threshold is designated as update-delayed production equipment. Based on the number of update-delayed production equipment, the overall simulation processing strategy of the digital twin model of the frequently adjusted production stage in the next period is determined.

[0133] Specifically, based on the number of production equipment with update delays, the overall simulation processing strategy for the digital twin model of the frequently adjusted production stage in the next time period is determined, including:

[0134] When the proportion of the production equipment with the update delay in the production equipment in the digital twin model is greater than the preset production equipment proportion threshold, a preset time period is used to perform overall simulation processing of the digital twin model of the frequently adjusted production stage in the next time period.

[0135] When the proportion of the production equipment with the update delay in the production equipment in the digital twin model is not greater than the preset production equipment proportion threshold, the overall simulation processing of the digital twin model will only be performed when there is data interaction in the model's influence data.

[0136] Furthermore, the overall simulation processing of the digital twin model is performed, specifically including:

[0137] Using all production equipment in the digital twin model as targets, and based on changing monitoring data, the digital twin model is used to simulate the operating status of different targets.

[0138] Example 2

[0139] Secondly, this application provides a digital twin simulation system for garment production based on real-time data interaction, employing the aforementioned digital twin simulation method for garment production based on real-time data interaction, specifically including:

[0140] Interactive data acquisition module, simulation processing module, simulation strategy output module;

[0141] The interactive data acquisition module is responsible for acquiring interactive data from the monitoring data of the digital twin model of the garment production factory.

[0142] The simulation processing module is responsible for performing simulation processing based on the interactive data and simulation processing strategy to obtain the updated processing data of the digital twin model within the most recent preset time period.

[0143] The simulation strategy output module is responsible for determining the overall simulation processing strategy of the digital twin model for the next time period based on the updated processing data.

[0144] A further technical solution is that the interactive data includes changes in the monitoring data of different production equipment in the digital twin model.

[0145] A further technical solution is that the updated processing data includes the data update times of different production equipment.

[0146] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0147] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0148] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A digital twin simulation method for garment production based on real-time data interaction, characterized in that, Specifically, it includes: Based on the historical adjustment of monitoring data, determine the changes in other monitoring data of the digital twin model of the garment production factory, use the changes to determine the associated monitoring data, and use the associated monitoring data to determine the model influence data in the monitoring data. By using different models to influence the historical adjustment of data at different production stages, the frequently adjusted production stages in the production stages are identified. Based on the adjustment distribution of model influence data during frequent adjustments of production stages in different production batches, when it is determined that the degree of data correlation in the frequent adjustments of production stages meets the requirements, proceed to the next step. Based on the associated monitoring data, a simulation processing strategy for the digital twin model is determined when different monitoring data interact. The simulation processing strategy is used to perform simulation processing to obtain the updated processing data of the digital twin model within a preset time period in the frequently adjusted production stage. Based on the updated processing data, the overall simulation processing strategy for the digital twin model in the next time period of the frequently adjusted production stage is determined. The method for determining the model impact data in the monitoring data is as follows: Based on the production equipment corresponding to the associated monitoring data, determine the production equipment that is associated with the monitoring data and identify it as the associated production equipment; The equipment impact value is determined based on the ratio of the number of related production equipment to the number of production equipment in the digital twin model of the garment production factory; Determine whether the monitoring data is model-affected data based on the equipment impact value; Determining that the data correlation level of the frequently adjusted production stage meets the requirements specifically includes: By frequently adjusting the distribution of model influence data in different production batches, the time periods in which model influence data is adjusted in different production batches are identified and used as data adjustment periods. Based on the proportion of data adjustment periods in different production batches, determine the real-time values ​​for model adjustments in different production batches; Based on the average value of the real-time values ​​of the model adjustment in different production batches, determine whether the data correlation of the frequently adjusted production stage meets the requirements; When the average real-time value of the model adjustment in different production batches is greater than the preset real-time value threshold, it is determined that the data correlation degree of the frequently adjusted production stage does not meet the requirements.

2. The digital twin simulation method for garment production based on real-time data interaction as described in claim 1, characterized in that, The historical adjustment of the monitoring data includes the number of historical data interactions and the adjustment amount for different historical data interaction numbers.

3. The digital twin simulation method for garment production based on real-time data interaction as described in claim 1, characterized in that, The changes in other monitoring data include the amount of data change under different historical data interaction times.

4. The digital twin simulation method for garment production based on real-time data interaction as described in claim 1, characterized in that, The method for determining the associated monitoring data is as follows: Based on the historical adjustment of the monitoring data, determine the adjustment amount of the monitoring data under different historical data interaction numbers; Based on the changes in other monitoring data, determine the amount of data change of the other monitoring data under different historical data interaction numbers of the monitoring data; Based on the ratio of the data change to the adjustment amount, the change correlation value under different historical data interaction numbers is determined. Based on the average value of the change correlation value under different historical data interaction numbers, it is determined whether the other monitoring data is the associated monitoring data of the monitoring data.

5. The digital twin simulation method for garment production based on real-time data interaction as described in claim 1, characterized in that, When there is no model affecting the data, the digital twin model is simulated as a whole using a preset time period at different production stages.

6. The digital twin simulation method for garment production based on real-time data interaction as described in claim 1, characterized in that, When the data correlation in the frequently adjusted production stage does not meet the requirements, the overall simulation of the digital twin model is performed when there is data interaction between the model and the data.

7. A digital twin simulation system for garment production based on real-time data interaction, employing the digital twin simulation method for garment production based on real-time data interaction as described in any one of claims 1-6, characterized in that, Specifically, it includes: Interactive data acquisition module, simulation processing module, simulation strategy output module; The interactive data acquisition module is responsible for acquiring interactive data from the monitoring data of the digital twin model of the garment production factory. The simulation processing module is responsible for performing simulation processing based on the interactive data and simulation processing strategy to obtain the updated processing data of the digital twin model within the most recent preset time period. The simulation strategy output module is responsible for determining the overall simulation processing strategy of the digital twin model for the next time period based on the updated processing data.

Images