Joint service equipment test optimization method and system based on digital twin modeling

Abstract

The invention provides a joint service equipment test optimization method and system based on digital twinning modeling, and relates to the technical field of digital twinning, and the method comprises the steps: collecting target multi-source heterogeneous data of target joint service equipment, and carrying out simulation modeling to generate a target twinning model; performing use association analysis to obtain a plurality of groups of associated twin models; obtaining a running environment condition set; simulation operation is carried out, an operation performance data set is collected for performance deviation analysis, and a first performance short board set is positioned; carrying out a cooperative operation test on the target twin model and the multiple groups of associated twin models, carrying out performance deviation identification based on operation process data, and positioning a second performance short plate set; and carrying out equipment design optimization on the target joint service equipment based on a short board integration analysis result. The technical problems that the prior art depends on limited experimental data, the test data is usually limited in a specific environment, and comprehensive data coverage under multi-dimension and multi-scene is lacked, so that the test efficiency and precision are poor are solved.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and in particular to a joint logistics equipment testing optimization method and system based on digital twin modeling. Background Art

[0002] Joint logistics equipment is logistical support equipment used to support and ensure natural disasters, accidents, medical emergencies and other tasks. There are many types of such equipment, which play a vital role in ensuring the smooth execution of tasks. However, most traditional joint logistics equipment test optimization methods rely on limited experimental data, and the test data is often limited to specific environments or specific conditions. There is a lack of comprehensive data coverage in multiple dimensions and multiple scenarios, which makes it impossible to effectively integrate the data of equipment in different situations, which in turn limits the representativeness and accuracy of the test results. Furthermore, since the equipment will face various complex extreme environments in actual operation, such as high temperature, high humidity, low pressure, etc., it is difficult for traditional test methods to fully simulate these conditions in the actual environment. Even if it is possible to test under extreme conditions, the cost is very high, and it lacks repeatability and flexibility, resulting in low test efficiency. Summary of the invention

[0003] This application provides a joint logistics equipment test optimization method and system based on digital twin modeling, aiming to solve the technical problems that most of the existing joint logistics equipment test optimization methods rely on limited experimental data, and the test data is often limited to a specific environment, lacking comprehensive data coverage in multiple dimensions and multiple scenarios, resulting in poor test efficiency and accuracy.

[0004] The first aspect disclosed in the present application provides a joint logistics equipment test optimization method based on digital twin modeling, the method comprising: acquiring target multi-source heterogeneous data of the target joint logistics equipment, and simulating and modeling the target joint logistics equipment based on the target multi-source heterogeneous data to generate a target twin model; performing usage association analysis on the target joint logistics equipment to obtain multiple groups of associated twin models corresponding to multiple usage scenarios; interactively obtaining an operating environment condition set of the target joint logistics equipment; simulating the operation of the target twin model in a virtual environment with the operating environment condition set as a constraint, and locating a first performance short board set in the target twin model by performing a performance deviation analysis on the operating performance data set acquired during the simulation operation; performing a collaborative operation test on the target twin model and multiple groups of associated twin models with the operating environment condition set as a constraint, and identifying performance deviations based on the operating process data to locate a second performance short board set in the target twin model; integrating and analyzing the first performance short board set and the second performance short board set, and optimizing the equipment design of the target joint logistics equipment based on the short board integrated analysis results.

[0005] The second aspect disclosed in the present application provides a joint logistics equipment test optimization system based on digital twin modeling, and the system is used for the above-mentioned joint logistics equipment test optimization method based on digital twin modeling. The system includes: a simulation modeling module, which is used to collect and obtain target multi-source heterogeneous data of target joint logistics equipment, and simulate and model the target joint logistics equipment based on the target multi-source heterogeneous data to generate a target twin model; a use association analysis module, which is used to perform use association analysis on the target joint logistics equipment to obtain multiple groups of associated twin models corresponding to multiple usage scenarios; an operating environment acquisition module, which is used to interactively obtain a set of operating environment conditions for the target joint logistics equipment; a performance deviation analysis module, which The analysis module is used to simulate the operation of the target twin model in a virtual environment with the operating environment condition set as a constraint, and locate the first performance short board set in the target twin model by performing performance deviation analysis on the operating performance data set collected during the simulation operation; the collaborative operation test module is used to perform collaborative operation tests on the target twin model and multiple groups of related twin models with the operating environment condition set as a constraint, and identify performance deviations based on the operating process data, and locate the second performance short board set in the target twin model; the equipment design optimization module is used to integrate and analyze the first performance short board set and the second performance short board set, and optimize the equipment design of the target joint logistics equipment based on the short board integrated analysis results.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] By collecting multi-source heterogeneous data of the target joint logistics equipment, including physical property data, operational behavior data, environmental condition data, etc., and generating accurate twin models based on these data, it is possible to simulate the physical properties and dynamic behavior of the equipment. Such high-precision modeling provides a basis for subsequent simulation, testing and optimization; through association analysis, multiple groups of associated twin models corresponding to actual mission scenarios are constructed, which enables the equipment to adapt to a variety of complex application scenarios, such as natural disaster rescue, traffic accident handling, etc., so that the equipment performance is tested and optimized in a variety of usage scenarios, making it have a wider range of application adaptability; obtain the operating environment condition set of the target joint logistics equipment, including standard operating environment and multiple extreme operating environments, and then use the operating environment condition set as a constraint to perform twin model simulation in a virtual environment. By carrying out simulation operation, detailed operating performance data can be collected under standard and extreme operating environments, and performance deviation analysis can be performed based on these data, which can accurately locate the performance shortcomings of the equipment and provide direction for subsequent optimization; similarly, with the operating environment condition set as a constraint, the target twin model and multiple groups of associated twin models are tested for collaborative operation, which can not only optimize the performance of a single equipment, but also identify the performance bottlenecks in the collaborative work of the equipment and improve the collaborative efficiency of the overall equipment; through the integrated processing of the first performance shortboard set and the second performance shortboard set, a comprehensive performance shortboard set is obtained, which solves the main bottlenecks in the independent operation and collaborative operation of the equipment, promotes the optimization and upgrading of the overall equipment design, and finally the optimized design scheme can have high stability and high reliability in a variety of operating environments.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic diagram of the flow chart of the joint logistics equipment test optimization method based on digital twin modeling provided in an embodiment of the present application;

[0010] Figure 2 Schematic diagram of the structure of the joint logistics equipment test optimization system based on digital twin modeling provided in an embodiment of the present application.

[0011] Explanation of the reference numerals: simulation modeling module 10 , usage association analysis module 20 , operating environment acquisition module 30 , performance deviation analysis module 40 , collaborative operation test module 50 , equipment design optimization module 60 . DETAILED DESCRIPTION

[0012] The embodiments of the present application provide a joint logistics equipment test optimization method and system based on digital twin modeling, which solves the technical problem that most of the joint logistics equipment test optimization methods in the prior art rely on limited experimental data, and the test data is often limited to a specific environment, lacking comprehensive data coverage in multiple dimensions and multiple scenarios, resulting in poor test efficiency and accuracy.

[0013] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0014] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a joint logistics equipment test optimization method based on digital twin modeling, and the method includes:

[0015] Target multi-source heterogeneous data of the target joint logistics equipment is collected, and simulation modeling is performed on the target joint logistics equipment based on the target multi-source heterogeneous data to generate a target twin model.

[0016] In the test and optimization process of joint logistics equipment, a variety of data types are involved, including physical parameters, operating behaviors, environmental conditions, etc. Corresponding sensors of various types are deployed on the target joint logistics equipment to collect the target multi-source heterogeneous data of the equipment in real time, including physical property data, such as equipment temperature, pressure, vibration, speed, displacement, etc.; operating behavior data, recording the operating behavior of the equipment, such as operating steps, usage mode, control logic, etc.; environmental condition data, recording the external environmental conditions when the equipment is running, such as temperature, humidity, pressure, etc.

[0017] The associated component models are called according to the design information of the target joint logistics equipment. The joint logistics equipment is obtained through standardized production, so the component models can be called and assembled. The target simulation model is assembled based on the calling results, and the collected target multi-source heterogeneous data and the target simulation model are integrated to obtain the target twin model. This model can accurately simulate the operating status and behavior of the equipment in a virtual environment, and support subsequent test optimization.

[0018] Furthermore, target multi-source heterogeneous data of target joint logistics equipment is collected, and simulation modeling is performed on the target joint logistics equipment based on the target multi-source heterogeneous data to generate a target twin model. The method also includes:

[0019] Perform real-time monitoring facility configuration on the target joint logistics equipment to obtain a multi-dimensional monitoring array, wherein the multi-dimensional monitoring array includes a physical property monitoring array, an operation behavior monitoring array and an environmental condition monitoring array; pre-configure an operation monitoring window and an operation condition timing; in the process of operating the target joint logistics equipment with the operation monitoring window as a time constraint and the operation condition timing as a control constraint, use the multi-dimensional monitoring array to collect real-time data of the target joint logistics equipment to obtain the target multi-source heterogeneous data; call the associated component models according to the design information of the target joint logistics equipment, and assemble and construct a target simulation model based on the call results; fuse the target multi-source heterogeneous data and the target simulation model to obtain a target twin model.

[0020] Real-time monitoring facility configuration refers to real-time monitoring of target joint logistics equipment by deploying sensors, monitoring equipment and data acquisition systems to ensure that comprehensive real-time data can be obtained during the operation of the equipment, including the physical state, operation behavior and environmental conditions of the equipment. According to the structure and monitoring requirements of the equipment, sensors and monitoring equipment are reasonably arranged to obtain a multi-dimensional monitoring array, which includes a physical property monitoring array, an operation behavior monitoring array and an environmental condition monitoring array. Among them, the physical property monitoring array is used to monitor the physical state and performance indicators of the joint logistics equipment. The monitoring equipment includes temperature sensors, pressure sensors, accelerometers, vibration monitors, power meters, etc.; the operation behavior monitoring array is used to monitor the operation process of the equipment and the behavior of the operator, and collect data such as the use of the equipment, control input and action feedback. The monitoring equipment includes operation log recorders, action sensors (such as position sensors, rotary encoders), state monitoring instruments, etc.; the environmental condition monitoring array is used to monitor the external conditions of the environment in which the equipment is located. These conditions will directly affect the performance of the equipment. The monitoring equipment includes temperature and humidity sensors, barometers, wind speed and direction meters, GPS, cameras, laser radars, etc.

[0021] The operation monitoring window refers to the time interval for centralized monitoring and data collection of target joint logistics equipment within a set time period. The operation monitoring window can be set for a specific operation stage of the equipment or for a time period under specific operating conditions (such as high temperature or high humidity environment). The operation monitoring window plays a role in time control, ensuring that monitoring and data collection are completed within a reasonable time range and that the collected data can cover the critical period of equipment operation.

[0022] The operating condition sequence refers to the operation time arrangement and control rules of the equipment under different operating conditions, ensuring that sufficient data can be collected under various environmental and operating conditions. The sequence includes multiple operating conditions and the duration of each condition. For example, the equipment runs for 5 hours in a high temperature environment or 3 hours in a high humidity environment, so that the monitoring system can capture the performance of the equipment in different environments. The purpose of pre-configuration is to ensure that the multi-dimensional monitoring array can collect enough data under different operating conditions to meet the requirements of twin modeling by reasonably planning the monitoring window and operating condition sequence.

[0023] Within the operation monitoring window, the target joint logistics equipment is operated with the operation condition timing as the control constraint. In this process, various types of equipment data are collected in real time through the preset multi-dimensional monitoring array to obtain physical property data, operation behavior data, and environmental condition data. The various collected data are integrated to obtain target multi-source heterogeneous data.

[0024] The design information of the target joint logistics equipment refers to a detailed description of the structure, function and component composition of the equipment. This information comes from the CAD drawings, engineering documents or specification sheets provided by the manufacturer of the equipment. According to the design information, the key components of the equipment are identified. For example, the key components of the lifting equipment include the lifting arm, hydraulic cylinder, power system and control panel. Each component of the equipment has a corresponding digital model. These models have been pre-built and stored in the model library. Among them, the joint logistics equipment is obtained through standardized production, so the component structure, function and components of each equipment are unified during the production process. Therefore, the corresponding standardized component model can be called according to the design information of the equipment to avoid modeling one by one from scratch. When the component model is called, these components are assembled into a complete simulation model. For example, according to the design drawings, the geometric models of each component are spliced ​​together to obtain the target simulation model.

[0025] According to the target multi-source heterogeneous data, the parameters of the target simulation model are adjusted so that the model can reflect the operating status of the equipment under specific conditions, and finally a target twin model is formed. This model can not only reflect the static structure of the equipment, but also simulate the dynamic behavior of the equipment under various operating conditions.

[0026] A usage association analysis is performed on the target joint logistics equipment to obtain multiple groups of associated twin models corresponding to various usage scenarios.

[0027] The associated twin model is a collaborative digital twin model of multiple equipment, which can simulate their joint operation in a specific scenario. Specifically, the service records of the target joint equipment are first collected, including the dispatch records of different equipment in past rescue and accident handling. According to different tasks, the use scenarios of the joint equipment are classified, such as natural disaster scenarios, accident handling scenarios, medical emergencies, etc. For example, natural disaster scenarios include earthquakes and floods, and the corresponding use scenarios include building collapse, road obstruction, etc. In this case, the joint equipment includes heavy lifting equipment, support equipment, drones, etc. The dispatch records of joint equipment in different scenarios are aggregated. For example, for the building collapse rescue scenario, heavy lifting equipment and support equipment may be used multiple times. By aggregating these historical dispatch records, the synergy of these equipment in specific tasks can be determined. Based on the model of the aggregated equipment, the corresponding digital twin model is called, and the digital twin models of multiple equipment in the same scenario are assembled together through the simulation platform to form a complete associated twin model that can simulate the scenario.

[0028] Furthermore, the target joint logistics equipment is subjected to usage association analysis to obtain multiple groups of associated twin models corresponding to multiple usage scenarios. The method further includes:

[0029] Interact with the service records of the target joint logistics equipment to obtain historical application data; perform time series decomposition on the historical application data to obtain multiple joint logistics equipment scheduling records, wherein each joint logistics equipment scheduling record in the multiple joint logistics equipment scheduling records includes application scenario information and a joint logistics equipment combination; aggregate the multiple joint logistics equipment scheduling records based on the application scenario type to obtain multiple groups of joint logistics equipment scheduling records corresponding to the multiple usage scenarios; preset an associated frequency threshold, and after performing equipment aggregation on the multiple groups of joint logistics equipment scheduling records, use the associated frequency threshold to filter the aggregation results to obtain multiple groups of associated joint logistics equipment; perform twin model calls on the multiple groups of associated joint logistics equipment based on the equipment model to obtain the multiple groups of associated twin models.

[0030] Service records are records of the use of target joint logistics equipment in different mission scenarios. These records include the equipment's mission execution status, usage frequency, fault records, maintenance logs, etc., and are usually stored in the database of the equipment management system. By interacting with the equipment management system, the service records of the target joint logistics equipment are obtained and historical application data are extracted from them.

[0031] Time series splitting is to split the acquired historical application data in chronological order, divide each separate task execution cycle, and generate a joint logistics equipment scheduling record during each task execution by segmenting the data according to the task timeline. Each joint logistics equipment scheduling record includes application scenario information and joint logistics equipment combination. The application scenario information refers to the equipment in specific task scenarios, such as natural disaster rescue, accident scene processing, emergency medical assistance and other scenarios; the joint logistics equipment combination is the equipment combination used simultaneously in each application scenario, including the type, function and configuration of each equipment.

[0032] According to the scene types in the dispatch records, such as earthquake rescue and traffic accident handling, the equipment combinations used in different tasks are aggregated. For example, in earthquake rescue, drones and lifting equipment are dispatched at the same time, so these equipment combinations can be aggregated together. Through aggregation, multiple sets of scenario-based joint logistics equipment dispatch records are obtained. Each set of records corresponds to an application scenario and records the equipment combination used.

[0033] The association frequency threshold is the frequency threshold of the preset equipment appearing simultaneously in a specific scenario. By setting a threshold, it is possible to screen out those equipment combinations that often work together in specific scenarios. For example, setting the association frequency threshold to 60% means that only equipment combinations that appear more than 60% of the time in a certain scenario will be selected as associated joint logistics equipment.

[0034] By analyzing historical application data, the frequency of each equipment combination in a specific scenario is counted, and screening is performed according to the frequency threshold to obtain high-frequency associated joint logistics equipment in a specific scenario, and multiple groups of associated joint logistics equipment are obtained based on the screening results. Among them, high correlation frequency indicates that the equipment combination works together many times in the same scenario, indicating that these equipment have high coordination efficiency and necessity in the scenario; low correlation frequency indicates that the equipment combination occasionally works together in the scenario, with low correlation, and it may not be necessary to model and simulate as a standard combination.

[0035] According to the screened multiple groups of related joint logistics equipment, their specific models are matched, and the corresponding twin models are called from the twin model library to obtain the multiple groups of related twin models.

[0036] Interactively obtain the operating environment condition set of the target joint logistics equipment.

[0037] Furthermore, the operating environment condition set includes a standard operating environment and multiple extreme operating environments.

[0038] Operating environment conditions refer to various external factors that affect the performance of joint logistics equipment in actual operations, including climatic conditions, geographical location, physical obstacles, etc. when the equipment is operating. The performance of the equipment under these environmental conditions, such as work efficiency, performance, stability, etc., is directly affected by these external conditions, including standard operating environments and multiple extreme operating environments.

[0039] Among them, the standard operating environment is the typical operating environment assumed when the equipment is designed, which usually represents the operating conditions under ideal or normal conditions, such as normal temperature, normal humidity, low altitude, and an environment without serious physical obstacles. The performance of the equipment in this environment is often the most stable, with a low failure rate, and various performance parameters are closest to the design standards; the extreme operating environment refers to relatively harsh conditions. The equipment may face challenges such as performance degradation and increased failure rate in these environments, such as high temperature, high humidity, low temperature, low pressure (high altitude), extreme weather (such as storms, heavy rains, snowstorms), etc. In extreme environments, the performance of the equipment may be greatly reduced. For example, the engine may overheat in a high temperature environment, electronic equipment may fail due to a high humidity environment, and mechanical structures may operate unstably in a high altitude and low pressure environment.

[0040] With the operating environment condition set as a constraint, the target twin model is simulated in a virtual environment, and a performance deviation analysis is performed on the operating performance data set collected during the simulation process to locate the first performance shortcoming set in the target twin model.

[0041] The operating environment condition set, including the standard operating environment and multiple extreme operating environments, is used as the input of the simulation conditions to constrain the simulation process in the virtual environment so that the simulation can realistically reflect the performance of the equipment in the real environment. During the simulation operation, the operating performance data of the equipment is collected in real time, including key performance parameters, status parameters, environmental response data, etc., and the collected data is integrated to obtain the operating performance data set.

[0042] Performance deviation refers to the degree to which the performance indicators of equipment deviate from the design standards during actual operation. By comparing the operating performance data in a simulated environment with the performance parameters under standard operating conditions, it is analyzed which performance indicators deviate from the design expectations. For example, heavy lifting equipment can lift 5 tons of objects under standard conditions, but can only lift 3.5 tons under extremely high temperatures, indicating that its performance is significantly reduced under high temperatures. Multiple performance deviations are classified into a group of performance shortcomings. For example, for heavy lifting equipment, components such as the hydraulic system and engine cooling system perform poorly in a high temperature environment, forming a set of performance shortcomings in a high temperature environment, and the performance shortcomings set is located in the target twin model.

[0043] Furthermore, the target twin model is simulated in a virtual environment with the operating environment condition set as a constraint, and a performance deviation analysis is performed on the operating performance data set collected during the simulation operation to locate the first performance short board set in the target twin model. The method further includes:

[0044] A performance evaluation system is preset, and performance analysis and optimization mapping are performed on the performance evaluation system to obtain performance improvement areas, wherein the performance evaluation system includes M performance indicators, and the performance improvement areas include M key performance components mapped to the M performance indicators; an operation simulation is performed on the target twin model with the standard operating environment as the simulation environment constraint, and the operation performance of the target twin model is collected with the performance evaluation system as the constraint to obtain standard operation performance information, wherein the standard operation performance information includes M standard operation parameters; based on environmental fusion, the multiple extreme operating environments are combined and enumerated to obtain K multimodal operating environments; based on the A virtual environment simulation of the target twin model is performed in multiple extreme operating environments and K multimodal operating environments, and the operating performance of the target twin model is collected with the performance evaluation system as a constraint to obtain W extreme operating performance information sets, wherein each of the W extreme operating performance information sets includes M extreme operating parameters, and W is a positive integer greater than K; a number table is used to store the standard operating performance information and W extreme operating performance information sets to form the operating performance data set; the performance improvement field is fitted to the operating performance data set to hit the first performance short board set, and the first performance short board set is located and identified in the target twin model.

[0045] A preset performance evaluation system is a framework for evaluating the operating performance of target joint logistics equipment under different operating conditions. The system covers M performance indicators of the equipment, where M is a positive integer. Each performance indicator corresponds to a key performance component of the equipment. By evaluating these indicators, the overall performance of the equipment can be comprehensively measured.

[0046] Based on the twin model, each performance indicator is analyzed to determine the performance of the equipment under various environments and operating conditions. For example, the heat dissipation efficiency of the hydraulic system of heavy lifting equipment in a high temperature environment, or the power consumption of the battery of a drone under long-term operation, is analyzed. For each performance indicator, the analysis result is mapped with possible improvement plans. For example, if the hydraulic system efficiency decreases at high temperatures, the heat dissipation system can be optimized or more efficient hydraulic oil can be used. Based on the mapping results, performance improvement areas are obtained. These areas are directly mapped to M key performance components. Each performance component is related to a certain performance indicator. Improving these components can significantly improve the overall performance of the equipment.

[0047] The target twin model is run in a standard operating environment to simulate various operations and functions of the equipment. During the simulation, M performance indicators of the performance evaluation system are monitored to obtain corresponding M standard operating parameters to form the standard operating performance information.

[0048] Environmental integration refers to whether multiple extreme operating environments can coexist. For example, high temperature and high humidity can coexist, but high temperature and extreme cold cannot coexist because they are opposites. Based on environmental integration, the possible combinations of multiple extreme operating environments are enumerated to generate K multimodal operating environments, where K is the number of these combined environments and is a positive integer.

[0049] Construct a virtual operating environment in the target twin model, including simulating each extreme operating environment separately to determine the performance of the equipment under each extreme operating environment, and simulating the combined multimodal operating environment to determine the performance of the equipment under multiple extreme environmental conditions at the same time. Run the target twin model in these extreme environments to simulate the operating performance of the equipment. During the simulation, the M performance indicators of the performance evaluation system are also monitored. Each simulation collects the corresponding M calculation operating parameters to form the extreme operating performance information set of this simulation. Through multiple simulations of multiple extreme operating environments and K multimodal operating environments, W extreme operating performance information sets are finally generated, where W is a positive integer greater than K.

[0050] The table is similar to a spreadsheet, where each row represents a simulation and each column represents a performance parameter. The standard operating performance information collected under the standard operating environment and W sets of extreme operating performance information obtained under the extreme operating environment are stored in a table to form a complete operating performance data set.

[0051] Compare and analyze the standard operating performance information and W sets of extreme operating performance information. By analyzing each performance indicator, identify its deviation in extreme environments, match the parts with larger deviations with performance improvement areas, and identify specific performance components that need to be improved. For example, if it is found that the hydraulic system performs poorly in a high temperature and high humidity environment, the hydraulic system will be identified as a performance shortcoming. Through the fitting process, the key performance components with poor performance are identified to form the first performance shortcoming set, which includes N key performance components.

[0052] Each performance shortcoming is marked in the target twin model to intuitively demonstrate the performance of the equipment in a specific environment. For example, in the twin model's visualization interface, the hydraulic system is marked in red, indicating that it has problems in a high temperature environment.

[0053] Further, fitting the performance improvement area to the operating performance data set to hit the first performance short board set, the method further includes:

[0054] In the operation performance data set, the M standard operation parameters are used to traverse and compare the W extreme operation performance information sets to obtain W groups of hit deviation performance indicators; the W groups of hit deviation performance indicators are de-hierarchicalized, and the deviation performance indicator frequency statistics are performed on the processing results to obtain M deviation recurrence frequencies of the M performance indicators; a component optimization frequency threshold is preset, and the component optimization frequency threshold is used to traverse the M deviation recurrence frequencies to obtain N performance indicators whose deviation recurrence frequencies exceed the component optimization frequency threshold, wherein N is a positive integer less than or equal to M; and the first performance short board set is obtained by calling in the performance improvement field according to the N performance indicators, wherein the first performance short board set includes N key performance components.

[0055] The M standard operating parameters and W extreme operating performance information sets are compared one by one, for example, by directly comparing the values, and the numerical deviation between the extreme operating performance information and the standard operating parameters under each indicator is calculated, and finally W groups of hit deviation performance indicators are obtained.

[0056] After the initial comparison, multiple sets of deviation performance indicators are obtained. These indicators often come from equipment or systems at different levels. Hierarchy means that these deviations are classified according to the system level, such as from component to system level. By removing the hierarchical processing, the deviations at each level are processed uniformly to ensure that each deviation performance indicator can be evaluated independently. This helps to avoid overly complex hierarchical interference and simplify the analysis. For example, the hydraulic pressure problem at the component level and the overall energy consumption problem at the system level are handled separately to avoid confusion.

[0057] After de-hierarchical processing, each performance indicator is counted to obtain the number of deviations in W extreme operating performance information sets. For example, if the pressure of the hydraulic system deviates in 60% of the W tests, the deviation recurrence frequency is 60%. Similarly, M performance indicators are traversed to obtain M deviation recurrence frequencies.

[0058] The preset component optimization frequency threshold is intended to screen out performance indicators that require focus and optimization. If the deviation recurrence frequency of a performance indicator exceeds this threshold, it indicates that the indicator exhibits more frequent problems under extreme operating environments and therefore needs to be optimized. The threshold can be set based on historical data or experience, for example, it can be set to 50% or 60%.

[0059] The M deviation recurrence frequencies obtained by statistics are traversed one by one, and the recurrence frequency of each performance indicator is compared with the preset component optimization frequency threshold. If the deviation recurrence frequency of a certain performance indicator is high, it is considered that the deviation of the performance indicator is not serious and does not need to be optimized first. On the contrary, if it is higher than the preset threshold, the performance indicator is marked as a target that needs to be optimized. After screening, N performance indicators are obtained, where N is a positive integer less than or equal to M. The N performance indicators represent performance indicators that show obvious deviations under multiple extreme operating environments.

[0060] Based on the N screened performance indicators, call the components related to these performance indicators in the performance improvement field, and identify N key performance components that need to be optimized. For example, if the pressure performance of the hydraulic system is poor, call the components related to the hydraulic system in the performance improvement field, such as hydraulic cylinders, hydraulic pumps, etc., and the obtained N key performance components constitute the first performance short board set.

[0061] With the operating environment condition set as a constraint, a collaborative operation test is performed on the target twin model and multiple groups of associated twin models, and performance deviations are identified based on the operating process data to locate the second set of performance shortcomings in the target twin model.

[0062] A set of operating environment conditions, including standard operating environments and multiple extreme operating environments, are used as input for simulation conditions. The target twin model and the associated twin model are tested for collaborative operation in a virtual environment to simulate the scenario of collaborative operation of multiple equipment in actual work. For example, in the rescue mission of building collapse, the lifting equipment works simultaneously with drones and demolition tools to simulate their mutual influence and cooperation. The collaborative operation test can combine the mutual influence between different equipment. For example, drones provide real-time monitoring data to the lifting equipment, and the demolition tools need to suspend the lifting operation at certain stages to carry out demolition operations. Through the simulation platform, these complex work processes and their performance under different environmental conditions are simulated.

[0063] During the collaborative simulation process, the operating performance data of each equipment is collected in real time. By comparing the expected performance data under the standard operating environment and the actual performance data under the extreme operating environment, the existing performance deviations are identified. By analyzing the performance of each equipment in collaborative operation, it can be determined whether the performance deviation is a problem of the individual equipment itself or a synergy problem that occurs when the equipment operates in coordination. For example, a demolition tool may perform normally under high temperature conditions, but when working with other equipment, the operating efficiency decreases due to material stress problems. According to the analysis results, the second performance short board set is obtained. Compared with the first performance short board set, the second performance short board set pays more attention to the performance of the equipment when operating in coordination with other equipment.

[0064] Furthermore, taking the operating environment condition set as a constraint, performing a collaborative operation test on the target twin model and multiple groups of associated twin models, identifying performance deviations based on the operating process data, and locating a second performance short board set in the target twin model, the method further includes:

[0065] Taking the multiple extreme operating environments and K multimodal operating environments as environmental simulation constraints, the target twin model and the first group of associated twin models are tested for collaborative operation, and the operating performance of the target twin model is collected with the performance evaluation system as a constraint to obtain V extreme operating performance information sets, wherein the first group of associated twin models is any group among the multiple groups of associated twin models, and V is a positive integer greater than K; the standard operating performance information and the V extreme operating performance information sets are compared and analyzed, and the performance improvement field is used to identify performance shortcomings to obtain a first associated performance short board subset; similarly, taking the operating environment condition set as a constraint, the target twin model and multiple groups of associated twin models are tested for collaborative operation, and performance deviations are identified based on the operating process data to obtain multiple associated performance short board subsets; the multiple associated performance short board subsets are aggregated to obtain the second performance short board set.

[0066] The target twin model is the twin model of the target joint logistics equipment, and the associated twin model is the twin model of other equipment that works together with the target joint logistics equipment. One group of associated twin models is randomly selected from multiple groups of associated twin models as the analysis object, as the first group of associated twin models.

[0067] A collaborative operation test is performed on the target twin model and the first set of associated twin models. The collaborative operation test simulates the performance of multiple equipment working together in an extreme or multimodal environment. For example, in a rescue mission, the lifting equipment (target twin model) and the drone (associated twin model) work together. Using a simulation platform, the target twin model and the associated twin model are placed in the same extreme or multimodal operating environment to simulate their collaborative working process.

[0068] During the collaborative operation test, the process is the same as the process of obtaining W extreme operation performance information sets. The operation performance of the target twin model is also collected with the performance evaluation system as a constraint to obtain V extreme operation performance information sets, where V is a positive integer greater than K.

[0069] A numerical table is used to contain standard operating performance information and V sets of extreme operating performance information, and the performance improvement field is used to identify performance shortcomings to obtain a first associated performance shortcoming subset, wherein the acquisition process of the first associated performance shortcoming subset is the same as the acquisition process of the first performance shortcoming set, and for the sake of brevity of the specification, it will not be repeated here.

[0070] Similarly, traverse multiple groups of associated twin models, perform multiple collaborative running tests with the target twin model respectively, repeat the above steps, and obtain multiple subsets of associated performance shortcomings.

[0071] The obtained multiple related performance short board subsets are integrated to form a complete second performance short board set. Compared with the first performance short board set, the second performance short board set focuses more on the collaborative work problems between devices rather than just the performance of the device itself.

[0072] The first performance short board set and the second performance short board set are integrated and analyzed, and the equipment design of the target joint logistics equipment is optimized based on the short board integrated analysis results.

[0073] Integrated analysis is to comprehensively analyze all performance shortcomings of equipment during independent and collaborative operation, and iteratively optimize and improve the target twin model in a virtual environment based on the working parameter value ranges of key performance components corresponding to the performance shortcomings. This includes adjusting the working parameters of the components, such as voltage, current, pressure, etc., to optimize their performance. When the standard operating parameters are reached, the target equipment improvement information is output to optimize the equipment design of the target joint logistics equipment.

[0074] Further, the first performance short board set and the second performance short board set are integrated and analyzed, and the equipment design of the target joint logistics equipment is optimized based on the short board integrated analysis result. The method also includes:

[0075] Based on components, the first performance shortcoming set and the second performance shortcoming set are repeatedly integrated to obtain a comprehensive performance shortcoming set; multiple working parameter value ranges of multiple key performance components in the comprehensive performance shortcoming set are interactively obtained; using the multiple working parameter value ranges as performance tuning constraints, the operating environment condition set as environmental constraints, and the M standard operating parameters as qualified constraints, the target twin model is iteratively optimized and improved in a virtual environment to obtain target equipment improvement information, wherein the target equipment improvement information includes multiple improved working parameters of the multiple key performance components; and equipment design optimization of the target joint logistics equipment is performed according to the target equipment improvement information.

[0076] Compare the components in the first performance short board set and the second performance short board set, identify the repeated components that appear in both, and these components show insufficient performance in both independent and collaborative operation of the equipment. These components should be the focus of optimization, and a unified comprehensive performance short board set can be obtained by integrating the repeated components.

[0077] By interacting with the actual operating data or design documents of the equipment, the working parameter value ranges of each key component in the comprehensive performance short board set are obtained. The value range represents the performance range of the equipment under different operating environments, such as the range of parameters such as temperature, pressure, and power consumption.

[0078] The performance tuning constraints are multiple working parameter value ranges, which provide acceptable performance ranges for each component under different conditions, to ensure that the parameters of the equipment are always within the normal range during the optimization and improvement process. The operating environment condition set is used as the environmental constraint to ensure that the optimized equipment can meet these complex environmental conditions. The M standard operating parameters are used as the qualified constraints, which define the ideal performance of the equipment under normal working conditions, to ensure that the equipment can meet the design requirements under standard operating conditions after optimization.

[0079] Through virtual simulation of the digital twin model, the behavior of the equipment in a variety of operating environments is simulated, and the working parameters of the equipment are continuously iteratively optimized based on the tuning constraints, environmental constraints and qualified constraints. Specifically, within the set working parameter value range, key components are optimized, and the optimized performance data is collected and compared with the standard operating parameters and the performance requirements in extreme environments to identify the remaining performance gaps or deficiencies. According to the feedback results, the working parameters of each key performance component are adjusted, especially for components that perform poorly in extreme environments. Through multiple simulations and feedback adjustments, all key performance components of the equipment are gradually optimized until all components meet the qualified constraints and performance tuning constraint requirements in different environments. At this time, multiple improved working parameters of multiple key performance components are output to obtain target equipment improvement information.

[0080] The target equipment improvement information includes multiple improved working parameters of multiple key performance components. These parameters provide the basis for the equipment's optimal performance under standard and extreme environments. Through these improved parameters, the design optimization of the target joint logistics equipment is guided so that the equipment can meet these performance requirements in actual use.

[0081] In summary, the joint logistics equipment test optimization method based on digital twin modeling provided in the embodiment of the present application has the following technical effects:

[0082] By collecting multi-source heterogeneous data of the target joint logistics equipment, including physical property data, operational behavior data, environmental condition data, etc., and generating accurate twin models based on these data, it is possible to simulate the physical properties and dynamic behavior of the equipment. Such high-precision modeling provides a basis for subsequent simulation, testing and optimization; through association analysis, multiple groups of associated twin models corresponding to actual mission scenarios are constructed, which enables the equipment to adapt to a variety of complex application scenarios, such as natural disaster rescue, traffic accident handling, etc., so that the equipment performance is tested and optimized in a variety of usage scenarios, making it have a wider range of application adaptability; obtain the operating environment condition set of the target joint logistics equipment, including standard operating environment and multiple extreme operating environments, and then use the operating environment condition set as a constraint to perform twin model simulation in a virtual environment. By carrying out simulation operation, detailed operating performance data can be collected under standard and extreme operating environments, and performance deviation analysis can be performed based on these data, which can accurately locate the performance shortcomings of the equipment and provide direction for subsequent optimization; similarly, with the operating environment condition set as a constraint, the target twin model and multiple groups of associated twin models are tested for collaborative operation, which can not only optimize the performance of a single equipment, but also identify the performance bottlenecks in the collaborative work of the equipment and improve the collaborative efficiency of the overall equipment; through the integrated processing of the first performance shortboard set and the second performance shortboard set, a comprehensive performance shortboard set is obtained, which solves the main bottlenecks in the independent operation and collaborative operation of the equipment, promotes the optimization and upgrading of the overall equipment design, and finally the optimized design scheme can have high stability and high reliability in a variety of operating environments.

[0083] Embodiment 2 is based on the same inventive concept as the joint logistics equipment test optimization method based on digital twin modeling in the previous embodiment. Figure 2 As shown, the embodiment of the present application provides a joint logistics equipment test optimization system based on digital twin modeling, and the system includes:

[0084] A simulation modeling module 10, the simulation modeling module 10 is used to collect and obtain target multi-source heterogeneous data of target joint logistics equipment, and simulate and model the target joint logistics equipment based on the target multi-source heterogeneous data to generate a target twin model; a use association analysis module 20, the use association analysis module 20 is used to perform use association analysis on the target joint logistics equipment to obtain multiple groups of associated twin models corresponding to multiple usage scenarios; an operating environment acquisition module 30, the operating environment acquisition module 30 is used to interactively obtain the operating environment condition set of the target joint logistics equipment; a performance deviation analysis module 40, the performance deviation analysis module 40 is used to perform simulation modeling of the target joint logistics equipment in a virtual environment with the operating environment condition set as a constraint. The twin model performs simulated operation, and performs performance deviation analysis on the operation performance data set collected during the simulation operation, and locates the first performance short board set in the target twin model; a collaborative operation test module 50, the collaborative operation test module 50 is used to perform collaborative operation tests on the target twin model and multiple groups of related twin models with the operation environment condition set as constraints, and identify performance deviations based on the operation process data, and locate the second performance short board set in the target twin model; an equipment design optimization module 60, the equipment design optimization module 60 is used to integrate and analyze the first performance short board set and the second performance short board set, and optimize the equipment design of the target joint logistics equipment based on the short board integrated analysis results.

[0085] Furthermore, the system also includes a target twin model acquisition module to perform the following operation steps:

[0086] Perform real-time monitoring facility configuration on the target joint logistics equipment to obtain a multi-dimensional monitoring array, wherein the multi-dimensional monitoring array includes a physical property monitoring array, an operation behavior monitoring array and an environmental condition monitoring array; pre-configure an operation monitoring window and an operation condition timing; in the process of operating the target joint logistics equipment with the operation monitoring window as a time constraint and the operation condition timing as a control constraint, use the multi-dimensional monitoring array to collect real-time data of the target joint logistics equipment to obtain the target multi-source heterogeneous data; call the associated component models according to the design information of the target joint logistics equipment, and assemble and construct a target simulation model based on the call results; fuse the target multi-source heterogeneous data and the target simulation model to obtain a target twin model.

[0087] Furthermore, the system also includes multiple groups of associated twin model acquisition modules to perform the following operation steps:

[0088] Interact with the service records of the target joint logistics equipment to obtain historical application data; perform time series decomposition on the historical application data to obtain multiple joint logistics equipment scheduling records, wherein each joint logistics equipment scheduling record in the multiple joint logistics equipment scheduling records includes application scenario information and a joint logistics equipment combination; aggregate the multiple joint logistics equipment scheduling records based on the application scenario type to obtain multiple groups of joint logistics equipment scheduling records corresponding to the multiple usage scenarios; preset an associated frequency threshold, and after performing equipment aggregation on the multiple groups of joint logistics equipment scheduling records, use the associated frequency threshold to filter the aggregation results to obtain multiple groups of associated joint logistics equipment; perform twin model calls on the multiple groups of associated joint logistics equipment based on the equipment model to obtain the multiple groups of associated twin models.

[0089] Furthermore, the operating environment condition set includes a standard operating environment and multiple extreme operating environments.

[0090] Furthermore, the system further includes a positioning identification module to perform the following operation steps:

[0091] A performance evaluation system is preset, and performance analysis and optimization mapping are performed on the performance evaluation system to obtain performance improvement areas, wherein the performance evaluation system includes M performance indicators, and the performance improvement areas include M key performance components mapped to the M performance indicators; an operation simulation is performed on the target twin model with the standard operating environment as the simulation environment constraint, and the operation performance of the target twin model is collected with the performance evaluation system as the constraint to obtain standard operation performance information, wherein the standard operation performance information includes M standard operation parameters; based on environmental fusion, the multiple extreme operating environments are combined and enumerated to obtain K multimodal operating environments; based on the A virtual environment simulation of the target twin model is performed in multiple extreme operating environments and K multimodal operating environments, and the operating performance of the target twin model is collected with the performance evaluation system as a constraint to obtain W extreme operating performance information sets, wherein each of the W extreme operating performance information sets includes M extreme operating parameters, and W is a positive integer greater than K; a number table is used to store the standard operating performance information and W extreme operating performance information sets to form the operating performance data set; the performance improvement field is fitted to the operating performance data set to hit the first performance short board set, and the first performance short board set is located and identified in the target twin model.

[0092] Furthermore, the system further includes a first performance short board set acquisition module to perform the following operation steps:

[0093] In the operation performance data set, the M standard operation parameters are used to traverse and compare the W extreme operation performance information sets to obtain W groups of hit deviation performance indicators; the W groups of hit deviation performance indicators are de-hierarchicalized, and the deviation performance indicator frequency statistics are performed on the processing results to obtain M deviation recurrence frequencies of the M performance indicators; a component optimization frequency threshold is preset, and the component optimization frequency threshold is used to traverse the M deviation recurrence frequencies to obtain N performance indicators whose deviation recurrence frequencies exceed the component optimization frequency threshold, wherein N is a positive integer less than or equal to M; and the first performance short board set is obtained by calling in the performance improvement field according to the N performance indicators, wherein the first performance short board set includes N key performance components.

[0094] Furthermore, the system further includes a second performance short board set acquisition module to perform the following operation steps:

[0095] Taking the multiple extreme operating environments and K multimodal operating environments as environmental simulation constraints, the target twin model and the first group of associated twin models are tested for collaborative operation, and the operating performance of the target twin model is collected with the performance evaluation system as a constraint to obtain V extreme operating performance information sets, wherein the first group of associated twin models is any group among the multiple groups of associated twin models, and V is a positive integer greater than K; the standard operating performance information and the V extreme operating performance information sets are compared and analyzed, and the performance improvement field is used to identify performance shortcomings to obtain a first associated performance short board subset; similarly, taking the operating environment condition set as a constraint, the target twin model and multiple groups of associated twin models are tested for collaborative operation, and performance deviations are identified based on the operating process data to obtain multiple associated performance short board subsets; the multiple associated performance short board subsets are aggregated to obtain the second performance short board set.

[0096] Furthermore, the system also includes a design optimization module to perform the following steps:

[0097] Based on components, the first performance shortcoming set and the second performance shortcoming set are repeatedly integrated to obtain a comprehensive performance shortcoming set; multiple working parameter value ranges of multiple key performance components in the comprehensive performance shortcoming set are interactively obtained; using the multiple working parameter value ranges as performance tuning constraints, the operating environment condition set as environmental constraints, and the M standard operating parameters as qualified constraints, the target twin model is iteratively optimized and improved in a virtual environment to obtain target equipment improvement information, wherein the target equipment improvement information includes multiple improved working parameters of the multiple key performance components; and equipment design optimization of the target joint logistics equipment is performed according to the target equipment improvement information.

[0098] Through the above-mentioned detailed description of the joint logistics equipment testing optimization method based on digital twin modeling in this specification, technical personnel in this field can clearly understand the joint logistics equipment testing optimization system based on digital twin modeling in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0099] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A joint logistics equipment test optimization method based on digital twin modeling, characterized in that: The method comprises: Collect and obtain target multi-source heterogeneous data of target joint logistics equipment, and perform simulation modeling on the target joint logistics equipment based on the target multi-source heterogeneous data to generate a target twin model; Performing usage association analysis on the target joint logistics equipment to obtain multiple groups of associated twin models corresponding to multiple usage scenarios; interactively obtaining an operating environment condition set of the target joint logistics equipment; Taking the operating environment condition set as a constraint, simulate the operation of the target twin model in a virtual environment, and locate the first performance short board set in the target twin model by performing performance deviation analysis on the operating performance data set collected during the simulation operation; Taking the operating environment condition set as a constraint, performing a collaborative operation test on the target twin model and multiple groups of associated twin models, identifying performance deviations based on the operating process data, and locating a second performance short board set in the target twin model; The first performance short board set and the second performance short board set are integrated and analyzed, and the equipment design of the target joint logistics equipment is optimized based on the short board integrated analysis results.

2. The method for joint logistics equipment testing optimization based on digital twin modeling according to claim 1, characterized in that: Acquiring target multi-source heterogeneous data of target joint logistics equipment, and performing simulation modeling on the target joint logistics equipment based on the target multi-source heterogeneous data to generate a target twin model, the method further comprising: Performing real-time monitoring facility configuration on the target joint logistics equipment to obtain a multi-dimensional monitoring array, wherein the multi-dimensional monitoring array includes a physical property monitoring array, an operation behavior monitoring array, and an environmental condition monitoring array; Preconfigure operation monitoring windows and operation condition timing; In the process of operating the target joint logistics equipment with the operation monitoring window as the time constraint and the operation condition sequence as the control constraint, the multi-dimensional monitoring array is used to collect real-time data of the target joint logistics equipment to obtain the target multi-source heterogeneous data; Calling related component models according to the design information of the target joint logistics equipment, and assembling and building a target simulation model based on the calling results; The target multi-source heterogeneous data and the target simulation model are fused to obtain a target twin model.

3. The method for joint logistics equipment testing optimization based on digital twin modeling according to claim 1, characterized in that: Performing usage association analysis on the target joint logistics equipment to obtain multiple groups of associated twin models corresponding to multiple usage scenarios, the method further includes: Interact with the service records of the target joint logistics equipment to obtain historical application data; Performing time series splitting on the historical application data to obtain a plurality of joint logistics equipment scheduling records, wherein each of the plurality of joint logistics equipment scheduling records includes application scenario information and a joint logistics equipment combination; Aggregating the plurality of joint logistics equipment scheduling records based on the application scenario type to obtain a plurality of groups of joint logistics equipment scheduling records corresponding to the plurality of usage scenarios; Preset an associated frequency threshold, and after aggregating the multiple sets of joint logistics equipment scheduling records, use the associated frequency threshold to filter aggregation results to obtain multiple sets of associated joint logistics equipment; Based on the equipment models, twin models are called for the multiple groups of related joint logistics equipment to obtain the multiple groups of related twin models.

4. The method for joint logistics equipment testing optimization based on digital twin modeling as claimed in claim 3 is characterized in that: The operating environment condition set includes a standard operating environment and multiple extreme operating environments.

5. The method for joint logistics equipment testing optimization based on digital twin modeling according to claim 4 is characterized in that: Taking the operating environment condition set as a constraint, simulating the operation of the target twin model in a virtual environment, and performing performance deviation analysis on the operating performance data set collected during the simulation operation to locate the first performance short board set in the target twin model, the method further comprising: Preset a performance evaluation system, and perform performance analysis and optimization mapping on the performance evaluation system to obtain a performance improvement area, wherein the performance evaluation system includes M performance indicators, and the performance improvement area includes M key performance components mapped to the M performance indicators; The target twin model is run simulated with the standard operating environment as the simulation environment constraint, and the running performance of the target twin model is collected with the performance evaluation system as the constraint to obtain standard running performance information, wherein the standard running performance information includes M standard running parameters; Combining and enumerating the multiple extreme operating environments based on environmental fusion to obtain K multimodal operating environments; Based on the multiple extreme operating environments and K multimodal operating environments, a virtual environment simulation of the target twin model is performed, and the operating performance of the target twin model is collected with the performance evaluation system as a constraint to obtain W extreme operating performance information sets, wherein each of the W extreme operating performance information sets includes M extreme operating parameters, and W is a positive integer greater than K; Using a table to store the standard operating performance information and W extreme operating performance information sets to form the operating performance data set; Fitting the performance improvement area to the operating performance data set hits the first performance short board set, and locating and identifying the first performance short board set in the target twin model.

6. The method for joint logistics equipment testing optimization based on digital twin modeling according to claim 5 is characterized in that: Fitting the performance improvement area to the operating performance data set to hit the first performance short board set, the method further comprising: In the operation performance data set, the M standard operation parameters are used to traverse and compare the W extreme operation performance information sets to obtain W groups of hit deviation performance indicators; De-hierarchical processing is performed on the W groups of hit deviation performance indicators, and deviation performance indicator frequency statistics are performed on the processing results to obtain M deviation recurrence frequencies of the M performance indicators; Preset a component optimization frequency threshold, and use the component optimization frequency threshold to traverse the M deviation recurrence frequencies to obtain N performance indicators whose deviation recurrence frequencies exceed the component optimization frequency threshold, where N is a positive integer less than or equal to M; The first performance short board set is obtained by calling the performance improvement field according to the N performance indicators, wherein the first performance short board set includes N key performance components.

7. The method for joint logistics equipment testing optimization based on digital twin modeling according to claim 5 is characterized in that: Taking the operating environment condition set as a constraint, performing a collaborative operation test on the target twin model and multiple groups of associated twin models, identifying performance deviations based on the operating process data, and locating a second performance short board set in the target twin model, the method further includes: Taking the multiple extreme operating environments and K multimodal operating environments as environmental simulation constraints, the target twin model and the first group of associated twin models are tested for collaborative operation, and the operating performance of the target twin model is collected with the performance evaluation system as a constraint to obtain V extreme operating performance information sets, wherein the first group of associated twin models is any group of the multiple groups of associated twin models, and V is a positive integer greater than K; Comparing and analyzing the standard operation performance information and V sets of extreme operation performance information, and using the performance improvement field to identify performance shortcomings, to obtain a first associated performance short board subset; By analogy, with the operating environment condition set as a constraint, the target twin model and multiple groups of associated twin models are tested for collaborative operation, and performance deviations are identified based on the operating process data to obtain multiple associated performance short board subsets; Aggregate the multiple associated performance short board subsets to obtain the second performance short board set.

8. The method for joint logistics equipment testing optimization based on digital twin modeling according to claim 5, characterized in that: Integrate and analyze the first performance short board set and the second performance short board set, and optimize the equipment design of the target joint logistics equipment based on the short board integrated analysis result. The method further includes: Repeatedly integrating the first performance short board set and the second performance short board set based on components to obtain a comprehensive performance short board set; Interactively obtain multiple working parameter value ranges of multiple key performance components in the comprehensive performance short board set; Taking the multiple working parameter value ranges as performance tuning constraints, taking the operating environment condition set as environmental constraints, and taking the M standard operating parameters as qualified constraints, the target twin model is iteratively optimized and improved in a virtual environment to obtain target equipment improvement information, wherein the target equipment improvement information includes multiple improved working parameters of the multiple key performance components; The equipment design of the target joint logistics equipment is optimized according to the target equipment improvement information.

9. The joint logistics equipment test optimization system based on digital twin modeling is characterized by: For implementing the joint logistics equipment test optimization method based on digital twin modeling according to any one of claims 1 to 8, the system comprises: A simulation modeling module, wherein the simulation modeling module is used to collect target multi-source heterogeneous data of target joint logistics equipment, and perform simulation modeling on the target joint logistics equipment based on the target multi-source heterogeneous data to generate a target twin model; A usage association analysis module, wherein the usage association analysis module is used to perform usage association analysis on the target joint logistics equipment to obtain multiple groups of association twin models corresponding to multiple usage scenarios; An operating environment acquisition module, the operating environment acquisition module is used to interactively obtain an operating environment condition set of the target joint logistics equipment; A performance deviation analysis module, wherein the performance deviation analysis module is used to simulate the operation of the target twin model in a virtual environment with the operating environment condition set as a constraint, and locate the first performance short board set in the target twin model by performing performance deviation analysis on the operating performance data set collected during the simulation operation; A collaborative operation test module, wherein the collaborative operation test module is used to perform a collaborative operation test on the target twin model and multiple groups of associated twin models with the operating environment condition set as a constraint, and to identify performance deviations based on the operating process data, and locate a second performance short board set in the target twin model; An equipment design optimization module is used to integrate and analyze the first performance short board set and the second performance short board set, and optimize the equipment design of the target joint logistics equipment based on the short board integrated analysis results.

Images