Management method and system of smart park based on digital twin

Abstract

The present invention discloses a management method and system for a smart park based on digital twins, and relates to the field of digital modeling technology. When the system is running, a real-time park operation model is established using digital twin technology, thereby realizing comprehensive dynamic monitoring and optimization of the park's operating status. Through feature extraction and preprocessing, the system can accurately obtain resource usage and demand characteristics, and generate a more efficient resource scheduling index OSP. According to the optimized resource scheduling strategy, the production plan factor PPG is generated and tested, so as to adjust the production plan and achieve the balance and optimization of production tasks. The real-time monitoring and feedback module ensures real-time monitoring of the execution status, and generates a comprehensive optimization index COF through feedback vectors, further adjusting resource scheduling and production plans, effectively reducing operating costs, solving the large consumption of human resources, and reducing dependence on personnel mobility, significantly improving the operational flexibility and economic benefits of the park.

Description

Technical Field

[0001] The present invention relates to the technical field of digital modeling, and specifically to a management method and system for a smart park based on digital twins. Background Art

[0002] Digital twin technology originated from intelligent manufacturing. It covers digital modeling and simulation from production lines to the entire factory, realizing the intelligence of all aspects of the park. Digital twin technology plays a vital role in the construction of smart cities. It is widely used in many fields such as smart transportation, smart buildings and energy management. By applying digital twin technology, we can simulate and optimize the operation status of the park in real time and comprehensively, especially in resource scheduling and production planning. Digital twin technology can provide strong data support and wise decision-making basis for the high-quality operation of the park.

[0003] In the invention of Chinese patent publication number CN202211429183.X, a smart park management system based on digital twin is disclosed. Based on data twin technology, the lighting monitoring video representing the lighting effect of the lighting equipment of the smart park is compared with the reference lighting effect video generated when designing the lighting effect of the park, that is, the lighting design video that meets the predetermined lighting effect, and then judges whether the lighting effect of the lighting equipment of the park meets the design requirements. In this way, an optimized smart park management solution is constructed to monitor the lighting equipment of the park to judge whether the lighting effect of the lighting equipment meets the predetermined requirements.

[0004] In the invention of Chinese Patent Publication No. CN202210637211.0, a park management system based on digital twins is disclosed, which relates to the field of digital twin technology. The system includes: a park three-dimensional module, which is used to store and display a three-dimensional model of the target park pre-established by the user; the three-dimensional model of the target park at least includes the equipment installed in the target park; an information acquisition module, which is used to collect the actual location information of each person in the target park in real time, and convert the actual location information of each person into the coordinates of the person in the three-dimensional model of the target park and record it; a control module, which is used to control the working status of the equipment according to the coordinates of each person in the target park in the three-dimensional model of the target park and the coordinates of each device in the three-dimensional model of the target park. The present invention can intelligently and automatically accurately control the working status of the equipment, so as to effectively reduce the carbon emissions of the park.

[0005] It can be seen that in the actual operation of smart parks, the management of resource scheduling and production plans does face many challenges. Although we can control lighting and personnel work arrangements within the park, existing systems often rely on static data analysis and experience judgment, or rely on manual monitoring and regulation of equipment, and lack the ability to respond to dynamic changes in real time. For example, traditional resource scheduling systems have difficulty adjusting resource allocation based on real-time data, which may lead to idle or insufficient resources, thereby affecting production efficiency. Similarly, the formulation of production plans often does not take into account various uncertainties in the actual implementation process, such as equipment failures or sudden changes in demand, which makes it difficult to flexibly adjust production plans, ultimately leading to increased labor costs and reduced efficiency. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention provides a management method and system for a smart park based on digital twins, which solves the problems mentioned in the background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a management system for a smart park based on digital twins, including a data acquisition and modeling module, a feature extraction and preprocessing module, a resource scheduling strategy simulation and optimization module, a production plan generation and simulation module, a real-time monitoring and feedback module, and an optimization evaluation module;

[0008] The data collection and modeling module collects the location information POS, quantity information NUM, energy consumption information NRG and the three-dimensional design file information 3D of the resources in the park to form a collection data group RDS, and uses digital twin technology to establish a park operation model;

[0009] The feature extraction and preprocessing module extracts and preprocesses the collected data group RDS, obtains resource availability feature information, resource demand feature information and resource consumption feature information, and performs denoising preprocessing, data formatting preprocessing and normalization preprocessing to generate a feature vector RFV;

[0010] The resource scheduling strategy simulation and optimization module simulates and optimizes the resource scheduling strategy according to the acquired feature vector RFV, and generates an optimized resource scheduling index OSP;

[0011] The production plan generation and simulation module generates a production plan factor PPG according to the obtained resource scheduling index OSP, and simulates and tests the production plan factor PPG through the established park operation model to obtain the generation plan balance index PPB and regulate the production plan factor PPG;

[0012] The real-time monitoring and feedback module monitors the execution status of the production plan factor PPG generated by the production plan generation and simulation module in real time, synchronously adjusts the data collection frequency after execution to obtain the real-time execution data group EXE, matches it with the production plan factor PPG, obtains the execution deviation coefficient DEV, and generates the feedback vector FBV;

[0013] The optimization evaluation module integrates the feedback vector FBV with the resource scheduling index OSP to obtain the comprehensive optimization index COF, and adjusts the resource scheduling and production plan according to the comprehensive optimization index COF.

[0014] Preferably, the data acquisition and modeling module includes a resource data acquisition unit and a digital twin modeling unit;

[0015] The resource data collection unit collects the location information POS, quantity information NUM, energy consumption information NRG and the three-dimensional design file information 3D of the resources in the park to form a collection data group RDS, specifically RDS={POS, NUM, NRG, 3D};

[0016] Among them, the location information POS includes the spatial coordinates (x, y, z) of all resources;

[0017] The quantity information NUM includes human resource quantity information HRS, equipment resource quantity information EQP and raw material resource quantity information MAT;

[0018] Energy consumption information NRG includes equipment consumption data SXH, production task demand DMD, single production task duration SPD and production qualification rate QLT;

[0019] The digital twin modeling unit uses digital twin technology to establish a park operation model for the collected data group RDS, and distributes, marks and displays the location information, quantity information and energy consumption information in the established park operation model according to the park's three-dimensional design file.

[0020] Preferably, the feature extraction and preprocessing module includes an extraction unit and a processing unit;

[0021] The extraction unit performs feature extraction and preprocessing on the collected data group RDS, obtains resource availability feature information, resource demand feature information and resource consumption feature information, and obtains resource availability feature TNR, resource demand feature RDC and resource consumption feature CEF;

[0022] The resource can be characterized by TNR through Extraction method acquisition;

[0023] The resource demand characteristics RDC are Extraction method acquisition;

[0024] The resource consumption characteristics of CEF are Extraction method to obtain.

[0025] Preferably, the processing unit performs denoising preprocessing, data formatting preprocessing and normalization preprocessing on the resource availability feature TNR, the resource demand feature RDC and the resource consumption feature CEF to generate a feature vector RFV, specifically RFV={TNR, RDC, CEF};

[0026] Among them, denoising includes using a median filter for denoising preprocessing to remove random noise in the feature data; data formatting preprocessing includes using data interpolation method for data formatting preprocessing to deal with the problems of missing feature data and time misalignment; normalization preprocessing includes using Min-Max normalization for normalization preprocessing to eliminate the dimensional influence of the feature data.

[0027] Preferably, the resource scheduling strategy simulation and optimization module simulates the resource scheduling strategy according to the acquired feature vector RFV, obtains the resource scheduling simulation index SIMk of different resources, uses the optimization algorithm to generate the generated resource scheduling simulation index SIMk, and generates the optimized resource scheduling index OSP;

[0028] The resource scheduling simulation index SIMk is obtained by the following calculation formula:

[0029] ;

[0030] Where SIMk represents the resource scheduling simulation index of the k-th resource scheduling, n represents the total number of resource types, TNRi represents the resource availability characteristic TNR of the i-th resource, specifically represents the supply status of the i-th resource, RDCi represents the resource demand characteristic RDC of the i-th resource, specifically represents the supply and demand status of the i-th resource and the current production task, CEFi represents the resource consumption characteristic CEF of the i-th resource, specifically represents the utilization efficiency of the i-th resource, Represents the importance coefficient of the i-th resource in the k-th resource scheduling, which is specifically used to balance the usage priority of different resources in the resource scheduling simulation index SIMk;

[0031] The resource scheduling index OSP is The calculation formula of the optimization algorithm is obtained, and then the peak value of the resource scheduling simulation index SIMk is obtained to determine the resource scheduling, including the allocation of resource availability characteristics TNR, resource demand characteristics RDC and resource consumption characteristics CEF.

[0032] Preferably, the production plan generation and simulation module includes a plan generation unit and a test control unit;

[0033] The plan generation unit generates a production plan factor PPG according to the acquired resource scheduling index OSP;

[0034] The production planning factor PPG is obtained by the following calculation formula:

[0035] ;

[0036] In the formula, PPGj represents the production planning factor PPG of the j-th production task, SPDj represents the single production task duration SPD of the j-th production task, QLTj represents the production qualification rate QLT of the j-th production task, Indicates the importance weight of the i-th resource in the j-th production task, which is specifically used to adjust the priority of the i-th resource in the j-th task;

[0037] The test and control unit performs simulation test on the production plan factor PPG through the established park operation model, obtains the generation plan balance index PPB, and controls the production plan factor PPG;

[0038] The following calculation formula is used for control:

[0039] ;

[0040] In the formula, It represents the adjustment coefficient, which is specifically used to control the adjustment range of the production plan factor PPG by the generated plan balance index PPB. Ttarget represents the preset production plan balance index.

[0041] Preferably, the generation plan balance index PPB is obtained by the following calculation formula:

[0042] ;

[0043] In the formula, PPB represents the generation plan balance index, which is specifically used to measure the balance and efficiency of the production plan factor PPG test, m represents the total number of production tasks, PPGj represents the production plan factor of the j-th production task, SPDj represents the single production task duration SPD of the j-th production task, Cj represents the resource cost of the j-th production task, specifically represents the total resource consumption required to complete the j-th production task, Indicates the task priority weight value;

[0044] The resource cost Cj of the j-th production task is calculated by Obtain the calculation formula.

[0045] Preferably, the real-time monitoring and feedback module includes a monitoring unit and a feedback unit;

[0046] The monitoring unit monitors the execution status of the production plan factor PPG generated by the production plan generation and simulation module in real time, and synchronously regulates the data collection frequency after execution to be 150% of the original data collection frequency, collects and obtains the actual completion quantity SQ, actual resource consumption SR, actual production time ST, actual product quality SQLT and actual cost SC, and forms a real-time execution data group EXE, specifically EXE={SQ, SR, ST, SQLT, SC};

[0047] The feedback unit matches the real-time execution data group EXE with the production plan factor PPG, obtains the execution deviation coefficient DEV, and generates a feedback vector FBV, specifically FBV={DEV1, DEV2, ..., DEVm};

[0048] The execution deviation coefficient DEV is obtained by the following calculation formula:

[0049] ;

[0050] Where DEVj represents the execution deviation coefficient DEV of the j-th task.

[0051] Preferably, the optimization evaluation module integrates the feedback vector FBV with the resource scheduling index OSP to obtain a comprehensive optimization index COF, and adjusts the resource scheduling and production plan according to the comprehensive optimization index COF to obtain an adjusted secondary resource scheduling OSPE and a secondary production plan factor PPGE;

[0052] The comprehensive optimization index COF is obtained by the following calculation formula:

[0053] ;

[0054] Where FBVj represents the feedback vector FBV of the j-th task, OSPj represents the resource scheduling index OSP of the j-th task, and DEVj represents the execution deviation coefficient DEV of the j-th task;

[0055] The secondary resource scheduling OSPE and the secondary production planning factor PPGE are obtained by the following calculation formula:

[0056] ;

[0057] ;

[0058] In the formula, represents the quadratic control coefficient.

[0059] The management method of the smart park based on digital twins includes the following steps:

[0060] Step 1: The data collection and modeling module collects the location information POS, quantity information NUM, energy consumption information NRG and the three-dimensional design file information 3D of the resources in the park to form a collection data group RDS, and uses digital twin technology to establish a park operation model;

[0061] Step 2: The feature extraction and preprocessing module extracts and preprocesses the collected data set RDS, obtains resource availability feature information, resource demand feature information and resource consumption feature information, and performs denoising preprocessing, data formatting preprocessing and normalization preprocessing to generate a feature vector RFV;

[0062] Step 3: The resource scheduling strategy simulation and optimization module simulates and optimizes the resource scheduling strategy according to the acquired feature vector RFV, and generates the optimized resource scheduling index OSP;

[0063] Step 4: The production plan generation and simulation module generates the production plan factor PPG according to the obtained resource scheduling index OSP, and simulates and tests the production plan factor PPG through the established park operation model to obtain the generation plan balance index PPB and regulate the production plan factor PPG;

[0064] Step 5: The real-time monitoring and feedback module monitors the execution status of the production plan factor PPG generated by the production plan generation and simulation module in real time, synchronously adjusts the data collection frequency after execution to obtain the real-time execution data group EXE, matches it with the production plan factor PPG, obtains the execution deviation coefficient DEV, and generates the feedback vector FBV;

[0065] Step 6: The optimization evaluation module integrates the feedback vector FBV with the resource scheduling index OSP to obtain the comprehensive optimization index COF, and adjusts the resource scheduling and production plan according to the comprehensive optimization index COF.

[0066] The present invention provides a management method and system for a smart park based on digital twins, which has the following beneficial effects:

[0067] (1) When the system is running, the digital twin technology is used to establish a real-time park operation model, realizing comprehensive dynamic monitoring and optimization of the park's operating status. Through feature extraction and preprocessing, the system can accurately obtain the usage and demand characteristics of resources, and then optimize the resource scheduling strategy and generate a more efficient resource scheduling index OSP. The production plan generation and simulation module generates and tests the production plan factor PPG according to the optimized resource scheduling strategy, thereby adjusting the production plan to achieve the balance and optimization of production tasks. The real-time monitoring and feedback module ensures the real-time monitoring of the execution status, and generates a comprehensive optimization index COF through feedback vectors to further adjust resource scheduling and production plans. The comprehensive application of this series of functions not only greatly improves resource utilization and production efficiency, but also effectively reduces operating costs, overcomes the defects of traditional systems in insufficient response to dynamic changes, solves the large consumption of human resources, and reduces the dependence on personnel mobility, and significantly improves the operational flexibility and economic benefits of the park.

[0068] (2) By collecting and modeling the location information POS, quantity information NUM, energy consumption information NRG and three-dimensional design file information 3D of the resources in the park, a real-time park operation model is established using digital twin technology, realizing comprehensive dynamic monitoring and optimization of the park's operating status. Through feature extraction and preprocessing, the system can accurately obtain the usage and demand characteristics of resources, and then optimize the resource scheduling strategy and generate a more efficient resource scheduling index OSP. The production plan generation and simulation module generates and tests the production plan factor PPG according to the optimized resource scheduling strategy, thereby adjusting the production plan and achieving the balance and optimization of production tasks.

[0069] (3) Through real-time monitoring and data collection, the execution status of the production planning factor PPG can be quickly and comprehensively evaluated to ensure the timeliness and accuracy of the data. These data include the actual completion quantity, actual resource consumption, actual production time, actual product quality and actual cost, which constitute the real-time execution data group EXE. The feedback unit matches the real-time data with the production planning factor, calculates the execution deviation coefficient DEV, and generates the feedback vector FBV, which is used to quantify the difference between the actual execution and the expected plan. The optimization evaluation module uses these feedback information and the integration of the resource scheduling index OSP to generate the comprehensive optimization index COF, and based on this, obtains the adjusted secondary resource scheduling OSPE and secondary production planning factor PPGE. The advantage of this process lies in its fine dynamic adjustment capability, which enables the park to adapt to changes in the production environment in real time, reduce planning deviations and resource waste, thereby improving the system's response speed and adjustment accuracy, effectively optimizing the overall operational efficiency of the park, and solving the problem of slow execution feedback. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1It is a schematic diagram of a management system block diagram of a smart park based on digital twins of the present invention;

[0071] Figure 2 This is a schematic diagram of the steps of the management method of a smart park based on digital twins of the present invention. DETAILED DESCRIPTION

[0072] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0073] Example 1

[0074] The present invention provides a management system for a smart park based on digital twins. Figure 1 , including data acquisition and modeling module, feature extraction and preprocessing module, resource scheduling strategy simulation and optimization module, production plan generation and simulation module, real-time monitoring and feedback module and optimization evaluation module;

[0075] The data collection and modeling module collects the location information POS, quantity information NUM, energy consumption information NRG and the three-dimensional design file information 3D of the resources in the park to form a collection data group RDS, and uses digital twin technology to establish a park operation model;

[0076] The feature extraction and preprocessing module extracts and preprocesses the collected data set RDS, obtains the resource availability feature information, resource demand feature information and resource consumption feature information, and performs denoising preprocessing, data formatting preprocessing and normalization preprocessing to generate the feature vector RFV;

[0077] The resource scheduling strategy simulation and optimization module simulates and optimizes the resource scheduling strategy based on the acquired feature vector RFV, and generates the optimized resource scheduling index OSP;

[0078] The production plan generation and simulation module generates the production plan factor PPG according to the obtained resource scheduling index OSP, and simulates and tests the production plan factor PPG through the established park operation model to obtain the generation plan balance index PPB and regulate the production plan factor PPG;

[0079] The real-time monitoring and feedback module monitors the execution status of the production plan factor PPG generated by the production plan generation and simulation module in real time, synchronously adjusts the data collection frequency after execution to obtain the real-time execution data group EXE, and matches it with the production plan factor PPG to obtain the execution deviation coefficient DEV and generate the feedback vector FBV;

[0080] The optimization evaluation module integrates the feedback vector FBV with the resource scheduling index OSP to obtain the comprehensive optimization index COF, and adjusts the resource scheduling and production plan according to the comprehensive optimization index COF.

[0081] In this embodiment, by integrating the data acquisition and modeling module, the feature extraction and preprocessing module, the resource scheduling strategy simulation and optimization module, the production plan generation and simulation module, the real-time monitoring and feedback module and the optimization evaluation module, the problems of slow resource scheduling and inflexible production planning in traditional park management can be effectively solved. The system collects and models the location information POS, quantity information NUM, energy consumption information NRG and the park three-dimensional design file information 3D of the resources in the park to form a collection data group RDS, and uses digital twin technology to establish a real-time park operation model, thereby realizing comprehensive dynamic monitoring and optimization of the park operation status. Through feature extraction and preprocessing, the system can accurately obtain the usage and demand characteristics of resources, and then optimize the resource scheduling strategy to generate a more efficient resource scheduling index OSP. The production plan generation and simulation module generates and tests the production plan factor PPG according to the optimized resource scheduling strategy, thereby adjusting the production plan and achieving the balance and optimization of production tasks. The real-time monitoring and feedback module ensures the real-time monitoring of the execution status, and generates a comprehensive optimization index COF through feedback vectors to further adjust resource scheduling and production plans. The comprehensive application of this series of functions not only greatly improves resource utilization and production efficiency, but also effectively reduces operating costs, overcomes the defects of traditional systems in insufficient response to dynamic changes, solves the large consumption of human resources, and reduces dependence on personnel mobility, significantly improving the operational flexibility and economic benefits of the park.

[0082] Example 2

[0083] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the data acquisition and modeling module includes a resource data acquisition unit and a ,digital twin modeling unit;

[0084] The resource data collection unit collects the location information POS, quantity information NUM, energy consumption information NRG and the three-dimensional design file information 3D of the resources in the park to form a collection data group RDS, specifically RDS={POS, NUM, NRG, 3D};

[0085] Among them, the location information POS includes the spatial coordinates (x, y, z) of all resources;

[0086] The quantity information NUM includes human resource quantity information HRS, equipment resource quantity information EQP and raw material resource quantity information MAT;

[0087] Energy consumption information NRG includes equipment consumption data SXH, production task demand DMD, single production task duration SPD and production qualification rate QLT;

[0088] The digital twin modeling unit uses digital twin technology to establish a park operation model for the collected data group RDS, and distributes, marks and displays the location information, quantity information and energy consumption information in the established park operation model according to the park's three-dimensional design files.

[0089] The feature extraction and preprocessing module includes an extraction unit and a processing unit;

[0090] The extraction unit performs feature extraction and preprocessing on the collected data group RDS, obtains resource availability feature information, resource demand feature information and resource consumption feature information, and obtains resource availability feature TNR, resource demand feature RDC and resource consumption feature CEF;

[0091] Resource availability feature TNR through Extraction method acquisition;

[0092] Resource demand characteristics RDC through Extraction method acquisition;

[0093] Resource consumption characteristics CEF through Extraction method to obtain.

[0094] The processing unit performs denoising preprocessing, data formatting preprocessing and normalization preprocessing on the resource availability feature TNR, the resource demand feature RDC and the resource consumption feature CEF to generate a feature vector RFV, specifically RFV={TNR, RDC, CEF};

[0095] Among them, denoising includes using a median filter for denoising preprocessing to remove random noise in the feature data; data formatting preprocessing includes using data interpolation method for data formatting preprocessing to deal with the problems of missing feature data and time misalignment; normalization preprocessing includes using Min-Max normalization for normalization preprocessing to eliminate the dimensional influence of the feature data.

[0096] Example 3

[0097] This embodiment is explained in Example 2. Please refer to Figure 1 ,Specifically: the resource scheduling strategy simulation and optimization module simulates the resource scheduling strategy according to the ,acquired feature vector RFV, obtains the resource scheduling simulation index SIMk of different ,resources, and uses the optimization algorithm for the generated resource scheduling simulation ,index SIMk to generate the optimized resource scheduling index OSP;

[0098] The resource scheduling simulation index SIMk is obtained by the following calculation formula:

[0099] ;

[0100] Where SIMk represents the resource scheduling simulation index of the k-th resource scheduling, n represents the total number of resource types, TNRi represents the resource availability characteristic TNR of the i-th resource, specifically represents the supply status of the i-th resource, RDCi represents the resource demand characteristic RDC of the i-th resource, specifically represents the supply and demand status of the i-th resource and the current production task, CEFi represents the resource consumption characteristic CEF of the i-th resource, specifically represents the utilization efficiency of the i-th resource, Represents the importance coefficient of the i-th resource in the k-th resource scheduling, which is specifically used to balance the usage priority of different resources in the resource scheduling simulation index SIMk;

[0101] Resource Scheduling Index OSP The calculation formula of the optimization algorithm is obtained, and then the peak value of the resource scheduling simulation index SIMk is obtained to determine the resource scheduling, including the allocation of resource availability characteristics TNR, resource demand characteristics RDC and resource consumption characteristics CEF.

[0102] The production plan generation and simulation module includes a plan generation unit and a test control unit;

[0103] The plan generation unit generates a production plan factor PPG according to the obtained resource scheduling index OSP;

[0104] The production planning factor PPG is obtained by the following calculation formula:

[0105] ;

[0106] In the formula, PPGj represents the production planning factor PPG of the j-th production task, SPDj represents the single production task duration SPD of the j-th production task, QLTj represents the production qualification rate QLT of the j-th production task, Indicates the importance weight of the i-th resource in the j-th production task, which is specifically used to adjust the priority of the i-th resource in the j-th task;

[0107] The test and control unit simulates the production plan factor PPG through the established park operation model, obtains the generation plan balance index PPB, and controls the production plan factor PPG;

[0108] The control method is controlled by the following calculation formula:

[0109] ;

[0110] In the formula, It represents the adjustment coefficient, which is specifically used to control the adjustment range of the production plan factor PPG by the generated plan balance index PPB. Ttarget represents the preset production plan balance index.

[0111] The generated plan balance index PPB is obtained by the following calculation formula:

[0112] ;

[0113] In the formula, PPB represents the generation plan balance index, which is specifically used to measure the balance and efficiency of the production plan factor PPG test, m represents the total number of production tasks, PPGj represents the production plan factor of the j-th production task, SPDj represents the single production task duration SPD of the j-th production task, Cj represents the resource cost of the j-th production task, specifically represents the total resource consumption required to complete the j-th production task, Indicates the task priority weight value;

[0114] The resource cost Cj of the j-th production task is calculated by Obtain the calculation formula.

[0115] In this embodiment, by collecting and modeling the location information POS, quantity information NUM, energy consumption information NRG and three-dimensional design file information 3D of the resources in the park, a real-time park operation model is established using digital twin technology, thereby achieving comprehensive dynamic monitoring and optimization of the park's operating status. Through feature extraction and preprocessing, the system can accurately obtain the usage and demand characteristics of resources, thereby optimizing the resource scheduling strategy and generating a more efficient resource scheduling index OSP. The production plan generation and simulation module generates and tests the production plan factor PPG according to the optimized resource scheduling strategy, thereby adjusting the production plan and achieving the balance and optimization of production tasks. It improves resource utilization and production efficiency, effectively reduces operating costs, and overcomes the defect that traditional systems are insufficiently responsive to dynamic changes.

[0116] Example 4

[0117] This embodiment is explained in Example 3, please refer to Figure 1 ,Specifically: the real-time monitoring and feedback module includes a monitoring unit and a feedback unit;

[0118] The detection unit monitors the execution status of the production plan factor PPG generated by the production plan generation and simulation modules in real time, and synchronously regulates the data collection frequency after execution to be 150% of the original data collection frequency, collects and obtains the actual completed quantity SQ, actual resource consumption SR, actual production time ST, actual product quality SQLT and actual cost SC, and forms a real-time execution data group EXE, specifically EXE={SQ, SR, ST, SQLT, SC};

[0119] The feedback unit matches the real-time execution data group EXE with the production plan factor PPG, obtains the execution deviation coefficient DEV, and generates a feedback vector FBV, specifically FBV={DEV1, DEV2, ..., DEVm};

[0120] The execution deviation coefficient DEV is obtained by the following calculation formula:

[0121] ;

[0122] Where DEVj represents the execution deviation coefficient DEV of the j-th task.

[0123] The optimization evaluation module integrates the feedback vector FBV with the resource scheduling index OSP to obtain the comprehensive optimization index COF, and adjusts the resource scheduling and production plan according to the comprehensive optimization index COF to obtain the adjusted secondary resource scheduling OSPE and secondary production planning factor PPGE;

[0124] The comprehensive optimization index COF is obtained by the following calculation formula:

[0125] ;

[0126] Where FBVj represents the feedback vector FBV of the j-th task, OSPj represents the resource scheduling index OSP of the j-th task, and DEVj represents the execution deviation coefficient DEV of the j-th task;

[0127] The secondary resource scheduling OSPE and secondary production planning factor PPGE are obtained through the following calculation formula:

[0128] ;

[0129] ;

[0130] In the formula, represents the quadratic control coefficient.

[0131] In this embodiment, through real-time monitoring and data collection, the execution status of the production plan factor PPG can be quickly and comprehensively evaluated to ensure the timeliness and accuracy of the data. These data include the actual completion quantity, actual resource consumption, actual production time, actual product quality and actual cost, which constitute the real-time execution data group EXE. The feedback unit matches the real-time data with the production plan factor, calculates the execution deviation coefficient DEV, and generates a feedback vector FBV to quantify the difference between the actual execution and the expected plan. The optimization evaluation module uses the integration of these feedback information and the resource scheduling index OSP to generate a comprehensive optimization index COF, and based on this, obtains the adjusted secondary resource scheduling OSPE and secondary production planning factor PPGE. The advantage of this process lies in its fine dynamic adjustment capability, which enables the park to adapt to changes in the production environment in real time, reduce planning deviations and resource waste, thereby improving the system's response speed and adjustment accuracy, and effectively optimizing the overall operational efficiency of the park. Solve the problem of slow execution feedback.

[0132] Example 5

[0133] For management methods of smart parks based on digital twins, please refer to Figure 2 , specifically: including the following steps:

[0134] Step 1: The data collection and modeling module collects the location information POS, quantity information NUM, energy consumption information NRG and the three-dimensional design file information 3D of the resources in the park to form a collection data group RDS, and uses digital twin technology to establish a park operation model;

[0135] Step 2: The feature extraction and preprocessing module extracts and preprocesses the collected data set RDS, obtains resource availability feature information, resource demand feature information and resource consumption feature information, and performs denoising preprocessing, data formatting preprocessing and normalization preprocessing to generate a feature vector RFV;

[0136] Step 3: The resource scheduling strategy simulation and optimization module simulates and optimizes the resource scheduling strategy according to the acquired feature vector RFV, and generates the optimized resource scheduling index OSP;

[0137] Step 4: The production plan generation and simulation module generates the production plan factor PPG according to the obtained resource scheduling index OSP, and simulates and tests the production plan factor PPG through the established park operation model to obtain the generation plan balance index PPB and regulate the production plan factor PPG;

[0138] Step 5: The real-time monitoring and feedback module monitors the execution status of the production plan factor PPG generated by the production plan generation and simulation module in real time, synchronously adjusts the data collection frequency after execution to obtain the real-time execution data group EXE, and matches it with the production plan factor PPG to obtain the execution deviation coefficient DEV and generate the feedback vector FBV;

[0139] Step 6: The optimization evaluation module integrates the feedback vector FBV with the resource scheduling index OSP to obtain the comprehensive optimization index COF, and adjusts the resource scheduling and production plan according to the comprehensive optimization index COF.

[0140] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. The management system of the smart park based on digital twin is characterized by: It includes data acquisition and modeling module, feature extraction and preprocessing module, resource scheduling strategy simulation and optimization module, production plan generation and simulation module, real-time monitoring and feedback module and optimization evaluation module; The data collection and modeling module collects the location information POS, quantity information NUM, energy consumption information NRG and the three-dimensional design file information 3D of the resources in the park to form a collection data group RDS, and uses digital twin technology to establish a park operation model; The feature extraction and preprocessing module extracts and preprocesses the collected data group RDS, obtains resource availability feature information, resource demand feature information and resource consumption feature information, and performs denoising preprocessing, data formatting preprocessing and normalization preprocessing to generate a feature vector RFV; The resource scheduling strategy simulation and optimization module simulates and optimizes the resource scheduling strategy according to the acquired feature vector RFV, and generates an optimized resource scheduling index OSP; The resource scheduling strategy simulation and optimization module simulates the resource scheduling strategy according to the acquired feature vector RFV, obtains the resource scheduling simulation index SIMk of different resources, uses the optimization algorithm to generate the generated resource scheduling simulation index SIMk, and generates the optimized resource scheduling index OSP; The resource scheduling simulation index SIMk is obtained by the following calculation formula: ； Where SIMk represents the resource scheduling simulation index of the k-th resource scheduling, n represents the total number of resource types, TNRi represents the resource availability characteristic TNR of the i-th resource, specifically represents the supply status of the i-th resource, RDCi represents the resource demand characteristic RDC of the i-th resource, specifically represents the supply and demand status of the i-th resource and the current production task, CEFi represents the resource consumption characteristic CEF of the i-th resource, specifically represents the utilization efficiency of the i-th resource, Represents the importance coefficient of the i-th resource in the k-th resource scheduling, which is specifically used to balance the usage priority of different resources in the resource scheduling simulation index SIMk; The resource scheduling index OSP is The optimization algorithm calculation formula is obtained, and then the peak value of the resource scheduling simulation index SIMk is obtained to determine the resource scheduling, including the allocation of resource availability characteristics TNR, resource demand characteristics RDC and resource consumption characteristics CEF; The production plan generation and simulation module includes a plan generation unit and a test control unit; The plan generation unit generates a production plan factor PPG according to the acquired resource scheduling index OSP; The production planning factor PPG is obtained by the following calculation formula: ； In the formula, PPGj represents the production planning factor PPG of the j-th production task, SPDj represents the single production task duration SPD of the j-th production task, QLTj represents the production qualification rate QLT of the j-th production task, Indicates the importance weight of the i-th resource in the j-th production task, which is specifically used to adjust the priority of the i-th resource in the j-th task; The test and control unit performs simulation test on the production plan factor PPG through the established park operation model, obtains the generation plan balance index PPB, and controls the production plan factor PPG; The following calculation formula is used for control: ； In the formula, It represents the adjustment coefficient, which is specifically used to control the adjustment range of the production plan factor PPG by the generated plan balance index PPB. Ttarget represents the preset production plan balance index; The production plan generation and simulation module generates a production plan factor PPG according to the obtained resource scheduling index OSP, and simulates and tests the production plan factor PPG through the established park operation model to obtain the generation plan balance index PPB and regulate the production plan factor PPG; The real-time monitoring and feedback module monitors the execution status of the production plan factor PPG generated by the production plan generation and simulation module in real time, synchronously adjusts the data collection frequency after execution to obtain the real-time execution data group EXE, matches it with the production plan factor PPG, obtains the execution deviation coefficient DEV, and generates the feedback vector FBV; The optimization evaluation module integrates the feedback vector FBV with the resource scheduling index OSP to obtain the comprehensive optimization index COF, and adjusts the resource scheduling and production plan according to the comprehensive optimization index COF.

2. The management system of the smart park based on digital twin according to claim 1 is characterized in that: The data acquisition and modeling module includes a resource data acquisition unit and a digital twin modeling unit; The resource data collection unit collects the location information POS, quantity information NUM, energy consumption information NRG and the three-dimensional design file information 3D of the resources in the park to form a collection data group RDS, specifically RDS={POS, NUM, NRG, 3D}; Among them, the location information POS includes the spatial coordinates (x, y, z) of all resources; The quantity information NUM includes human resource quantity information HRS, equipment resource quantity information EQP and raw material resource quantity information MAT; Energy consumption information NRG includes equipment consumption data SXH, production task demand DMD, single production task duration SPD and production qualification rate QLT; The digital twin modeling unit uses digital twin technology to establish a park operation model for the collected data group RDS, and distributes, marks and displays the location information, quantity information and energy consumption information in the established park operation model according to the park's three-dimensional design file.

3. The management system of the smart park based on digital twin according to claim 2 is characterized in that: The feature extraction and preprocessing module includes an extraction unit and a processing unit; The extraction unit performs feature extraction and preprocessing on the collected data group RDS, obtains resource availability feature information, resource demand feature information and resource consumption feature information, and obtains resource availability feature TNR, resource demand feature RDC and resource consumption feature CEF; The resource can be characterized by TNR through Extraction method acquisition; The resource demand characteristics RDC are Extraction method acquisition; The resource consumption characteristics of CEF are Extraction method to obtain.

4. The management system of the smart park based on digital twin according to claim 3 is characterized by: The processing unit performs denoising preprocessing, data formatting preprocessing and normalization preprocessing on the resource availability feature TNR, the resource demand feature RDC and the resource consumption feature CEF to generate a feature vector RFV, specifically RFV={TNR, RDC, CEF}; Among them, denoising includes using a median filter for denoising preprocessing to remove random noise in the feature data; data formatting preprocessing includes using data interpolation method for data formatting preprocessing to deal with the problems of missing feature data and time misalignment; normalization preprocessing includes using Min-Max normalization for normalization preprocessing to eliminate the dimensional influence of the feature data.

5. The management system of a smart park based on digital twin according to claim 1 is characterized in that: The generation plan balance index PPB is obtained by the following calculation formula: ； In the formula, PPB represents the generation plan balance index, which is specifically used to measure the balance and efficiency of the production plan factor PPG test, m represents the total number of production tasks, PPGj represents the production plan factor of the j-th production task, SPDj represents the single production task duration SPD of the j-th production task, Cj represents the resource cost of the j-th production task, specifically represents the total resource consumption required to complete the j-th production task, Indicates the task priority weight value; The resource cost Cj of the j-th production task is calculated by Obtain the calculation formula.

6. The management system of the smart park based on digital twin according to claim 5 is characterized by: The real-time monitoring and feedback module includes a monitoring unit and a feedback unit; The monitoring unit monitors the execution status of the production plan factor PPG generated by the production plan generation and simulation module in real time, and synchronously regulates the data collection frequency after execution to be 150% of the original data collection frequency, collects and obtains the actual completion quantity SQ, actual resource consumption SR, actual production time ST, actual product quality SQLT and actual cost SC, and forms a real-time execution data group EXE, specifically EXE={SQ, SR, ST, SQLT, SC}; The feedback unit matches the real-time execution data group EXE with the production plan factor PPG, obtains the execution deviation coefficient DEV, and generates a feedback vector FBV, specifically FBV={DEV1, DEV2, ..., DEVm}; The execution deviation coefficient DEV is obtained by the following calculation formula: ； Where DEVj represents the execution deviation coefficient DEV of the j-th task.

7. The management system of the smart park based on digital twin according to claim 6 is characterized by: The optimization evaluation module integrates the feedback vector FBV with the resource scheduling index OSP to obtain the comprehensive optimization index COF, and adjusts the resource scheduling and production plan according to the comprehensive optimization index COF to obtain the adjusted secondary resource scheduling OSPE and secondary production plan factor PPGE; The comprehensive optimization index COF is obtained by the following calculation formula: ； Where FBVj represents the feedback vector FBV of the j-th task, OSPj represents the resource scheduling index OSP of the j-th task, and DEVj represents the execution deviation coefficient DEV of the j-th task; The secondary resource scheduling OSPE and the secondary production planning factor PPGE are obtained by the following calculation formula: ； ； In the formula, represents the quadratic control coefficient.

8. A management method for a smart park based on digital twins, comprising the management system for a smart park based on digital twins as described in any one of claims 1 to 7, characterized in that: The following steps are involved: Step 1: The data collection and modeling module collects the location information POS, quantity information NUM, energy consumption information NRG and the three-dimensional design file information 3D of the resources in the park to form a collection data group RDS, and uses digital twin technology to establish a park operation model; Step 2: The feature extraction and preprocessing module extracts and preprocesses the collected data set RDS, obtains resource availability feature information, resource demand feature information and resource consumption feature information, and performs denoising preprocessing, data formatting preprocessing and normalization preprocessing to generate a feature vector RFV; Step 3: The resource scheduling strategy simulation and optimization module simulates and optimizes the resource scheduling strategy according to the acquired feature vector RFV, and generates the optimized resource scheduling index OSP; Step 4: The production plan generation and simulation module generates the production plan factor PPG according to the obtained resource scheduling index OSP, and simulates and tests the production plan factor PPG through the established park operation model to obtain the generation plan balance index PPB and regulate the production plan factor PPG; Step 5: The real-time monitoring and feedback module monitors the execution status of the production plan factor PPG generated by the production plan generation and simulation module in real time, synchronously adjusts the data collection frequency after execution to obtain the real-time execution data group EXE, matches it with the production plan factor PPG, obtains the execution deviation coefficient DEV, and generates the feedback vector FBV; Step 6: The optimization evaluation module integrates the feedback vector FBV with the resource scheduling index OSP to obtain the comprehensive optimization index COF, and adjusts the resource scheduling and production plan according to the comprehensive optimization index COF.

Images