Digital twin workshop construction method and device based on fractal mechanism and electronic equipment

Abstract

The invention discloses a digital twinning workshop construction method and device based on a fractal mechanism and electronic equipment, and belongs to the technical field of digital twinning, and the method comprises the steps: designing a mapping state model between workshop elements and a production line based on demand analysis; constructing a digital twin inverse model taking workshop mapping state characteristics as input and workshop element data as output by utilizing an auto-encoder or a generative adversarial network technology; a feedback mechanism is established, data and results in actual operation are fed back to the digital twin model, and the accuracy of the model is continuously optimized and adjusted; a fractal engine is applied to model and analyze a workshop at different levels to provide deeper insight and more accurate control. According to the method, the model output speed of the whole digital twinborn modeling task can be improved, and meanwhile, the efficiency of scheduling various model resources by calling the sub-model tasks of each level by each organization level of the digital twinborn modeling task is also improved.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and in particular to a method, device and electronic equipment for constructing a digital twin workshop based on a fractal mechanism. Background Art

[0002] With the development of Industry 4.0, digital twin technology has been widely used in the field of manufacturing. Digital twin is a technology that combines physical entities with their digital models. Through real-time updating and analysis of digital models, physical entities can be monitored, predicted and optimized. However, existing digital twin construction methods often require a large amount of data collection and processing, and it is difficult to achieve high-precision modeling of complex workshop environments. Therefore, how to build an integrated view of cross-level, cross-scale, and multi-view models covering all aspects of the system life cycle and value chain, and then drive the system's full life cycle activities with a unified model, provide support for decision makers, and improve the efficiency and accuracy of digital twin construction has become a problem that needs to be solved urgently.

[0003] As workflows with twin models and fractal features gradually become the main computing load for building a highly integrated digital twin workshop system, the structural design of the digital twin workshop has gradually extended to a "multi-level" design approach. Its research objects are twin workshop object systems that cannot be explained by Euclidean geometry. These research objects generally have complex structures and self-similarity. Self-similarity is the core description of fractals, and the characteristic quantity of fractals is the fractal dimension (fractal-dimension, referred to as "fractal dimension"). There are many types of fractal dimensions, including topological dimension, Hausdorff dimension, information dimension, correlation dimension, etc. The scale distribution of the twin workshop object system has self-similarity, that is, it meets the characteristics of fractals, and its fractal dimension generally uses the Hausdorff dimension.

[0004] In the processing of multidimensional information, Hausdorff dimension, as a multidimensional metric, is often used in embedded systems in the field of manufacturing to achieve multidimensional positioning and path planning for robot control, navigation and process scheduling. However, the object structure design of a twin workshop in a region tends to be customized, and the same type of twin models are continuously integrated for modeling. It is difficult to improve the multi-scale real-time feedback capability of the entire twin system through horizontal expansion, and it is difficult to meet the twin modeling needs of large-scale production lines. In addition, it is difficult for the existing digital twin workshop system to ensure that each organizational level of the digital twin modeling task can schedule various types of construction resources for the "sub-model" tasks at each level in an efficient manner according to the load characteristics of the twin module workflow. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a method, device and electronic equipment for constructing a digital twin workshop based on a fractal mechanism, so as to continuously improve the speed of model output of the entire digital twin modeling task, while also improving the efficiency of various organizational levels of the digital twin modeling task in calling various levels of "sub-model" tasks to schedule various types of model resources.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In one aspect, the present invention provides a method for constructing a digital twin workshop based on a fractal mechanism, comprising:

[0008] Step S101: Design mapping model: Based on demand analysis, design a mapping state model between workshop elements and production lines to ensure accurate correspondence between physical objects and digital space;

[0009] Step S102: Developing a digital twin inverse model: using an autoencoder or generative adversarial network technology to construct a digital twin inverse model with workshop mapping state features as input and workshop element data as output;

[0010] Step S103: Establish a feedback loop: Establish a feedback mechanism to feed back the data and results in actual operation into the digital twin model, and continuously optimize and adjust the accuracy of the model;

[0011] Step S104: Fractal engine application: Apply the fractal engine to model and analyze the workshop at different levels to provide deeper insights and more precise control.

[0012] On the other hand, the present invention provides a digital twin workshop construction device based on a fractal mechanism, comprising:

[0013] Design module, used to design mapping models: Based on demand analysis, design the mapping state model between workshop elements and production lines to ensure accurate correspondence between physical objects and digital space;

[0014] Development module for developing digital twin inverse model: using autoencoder or generative adversarial network technology to build a digital twin inverse model with workshop mapping state features as input and workshop element data as output;

[0015] Establish modules for establishing feedback loops: Establish a feedback mechanism to feed the data and results from actual operation into the digital twin model to continuously optimize and adjust the accuracy of the model;

[0016] Application module for Fractal Engine Applications: Apply Fractal Engine to model and analyze the shop floor at different levels to provide deeper insights and more precise control.

[0017] On the other hand, the present invention provides an electronic device, comprising: a shell, a processor, a memory, a circuit board and a power supply circuit, wherein the circuit board is placed inside the space enclosed by the shell, and the processor and the memory are arranged on the circuit board; the power supply circuit is used to supply power to various circuits or devices of the above-mentioned electronic device; the memory is used to store executable program code; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the above-mentioned method.

[0018] In yet another aspect, the present invention provides a computer-readable storage medium storing one or more programs, wherein the one or more programs can be executed by one or more processors to implement the above method.

[0019] The present invention has the following beneficial effects:

[0020] The fractal-based digital twin workshop construction method of the present invention can avoid the horizontal expansion construction method to continuously improve the speed of model output of the entire digital twin modeling task; at the same time, it can also improve the efficiency of various organizational levels of the digital twin modeling task in calling various levels of "sub-model" tasks to schedule various types of model resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flow chart of the method for constructing a digital twin workshop based on a fractal mechanism of the present invention;

[0022] Figure 2 A schematic diagram of a fractal-based digital twin model system construction process in a method example of the present invention;

[0023] Figure 3 for Figure 2 Schematic diagram of constructing a process fractal digital twin workshop using a four-layer fractal mechanism;

[0024] Figure 4 for Figure 2 Schematic diagram of constructing operator fractal digital twin workshop using four-layer fractal mechanism;

[0025] Figure 5 It is a structural diagram of a digital twin workshop with multiple partitions of twin modules in the present invention;

[0026] Figure 6 It is a structural schematic diagram of a digital twin workshop construction device based on a fractal mechanism of the present invention;

[0027] Figure 7 It is a schematic structural diagram of the electronic device of the present invention. DETAILED DESCRIPTION

[0028] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0029] The present invention proposes a twin workshop fractal method to study the hierarchical structure of the twin workshop object system. The basic basis of these analysis methods is fractal dimension or its equivalent parameters, such as Zipf dimension, fractal structure factor and difference degree. The present invention mainly relates to the calculation and application of Zipf dimension of object scale distribution of digital twin workshop, and on this basis, proposes a method for constructing digital twin workshop with fractal mechanism.

[0030] On the one hand, the present invention provides a method for constructing a digital twin workshop based on a fractal mechanism, such as Figure 1-2 As shown, including:

[0031] Step S101: Designing a mapping model: Based on demand analysis, designing a mapping state model between workshop elements and production lines to ensure accurate correspondence between physical objects and digital space;

[0032] In this step, the mapping model module is the basis of the digital twin workshop. It maps the status between the physical elements of the workshop and the production line to facilitate the understanding and analysis of the operation of the workshop. This model usually involves the collection and processing of data to ensure that the virtual model can accurately reflect the status of the physical workshop.

[0033] Step S102: Developing a digital twin inverse model: using an autoencoder or generative adversarial network technology to construct a digital twin inverse model with workshop mapping state features as input and workshop element data as output;

[0034] In this step, the digital twin inverse model module is based on the mapping model. The digital twin inverse model uses technologies such as autoencoders or generative adversarial networks, takes the workshop mapping state characteristics as input, and outputs workshop element data. This model can be used for simulation and prediction. By changing the input state characteristics, the changes in workshop element data can be observed and analyzed, thereby exploring potential optimization points.

[0035] Step S103: Establish a feedback loop: Establish a feedback mechanism to feed back the data and results in actual operation to the digital twin model (i.e., the digital twin workshop) to continuously optimize and adjust the accuracy of the model;

[0036] In this step, the feedback loop module is a key link in the digital twin workshop, which ensures that real-time data is transmitted from the physical workshop to the virtual model, and the production process can be adjusted and optimized based on this data. This mechanism helps to continuously improve the production process and ensure synchronization between the virtual and physical workshops.

[0037] Step S104: Fractal engine application: Apply the fractal engine to model and analyze the workshop at different levels to provide deeper insights and more precise control.

[0038] In this step, the Fractal Engine module is an advanced module that uses the mapping model and inverse model mentioned above, as well as the data in the feedback loop, to build a dynamic, multi-level system model. The Fractal Engine can model and analyze the workshop at different levels, providing deeper insights and more precise control.

[0039] The construction of the digital twin workshop is gradually constructed based on the twin workshop objects. The twin workshop objects include mappings such as physical workshops, production lines, production equipment, and equipment components in the digital twin space. The scale distribution of the twin workshop objects refers to the hierarchical distribution of the production capacity scale of the twin workshop objects in a certain factory area. The structural design of the twin workshop objects in a region tends to be customized, and the same type of twin models are continuously integrated for modeling. It is difficult to improve the multi-scale real-time feedback capability of the entire twin system through horizontal expansion, and it is difficult to meet the twin modeling requirements of large-scale production lines. The digital twin workshop construction method based on the fractal mechanism of the present invention can avoid the horizontal expansion construction method to continuously improve the speed of model output of the entire digital twin modeling task; at the same time, it can also improve the efficiency of each organizational level of the digital twin modeling task to call each level of "sub-model" tasks to schedule various model resources.

[0040] Given that the digital twin workshop model construction process has fractal characteristics, namely self-similarity, the scale distribution of the digital twin model can be explained by fractal theory. If a production capacity scale r is given to measure, the number of twin workshop objects N(r) with a production capacity scale greater than r satisfies the relationship between r and N(r) = k·r. -D , k is the coefficient, and D is the fractal dimension of the twin workshop object scale distribution. The derivation process is as follows:

[0041] Point ①: Given a factory area, there are several clusters distributed in it. Since there is no clear classification and belonging boundary between twin workshop objects, a production capacity scale r can be set to measure (r is expressed by the numerical value of production capacity). Obviously, changing the production capacity scale will also change the number of regional twin workshop objects N(r). When r changes from large to small, N(r) continues to increase. When the relationship N(r)∝r is satisfied -D That is, when the cumulative number of regional twin workshop objects and the production capacity scale are distributed in a negative power law, the scale distribution of twin workshop objects can be considered to be fractal. Analogous to the Hausdorff dimension formula, D is the fractal dimension, which is a constant in a certain period of time.

[0042] Point ②: The relationship between N(r) and r is the Pareto form of the twin workshop object scale distribution. After transformation, the Zipf formula P (k) =P1·K -q , where the twin workshop object K is the twin workshop object serial number (K ​​= 1, 2, ..., N, N is the total number of twin workshop objects in the system); P (k) is the production capacity of the twin workshop object with serial number K; P1 is the production capacity of the first workshop object (coefficient); q is the Zipf index.

[0043] Key point ③: Comparing the quantitative relationship between q and D, we can see that q=1 / D, which shows that it has dimensionality significance.

[0044] When q=1, D=1, then P1 / P n =K=N, that is, the ratio of the production capacity of the first twin workshop to that of the smallest twin workshop is exactly the total number of twin workshops in the region.

[0045] When q>1, D<1, the object scale distribution of the twin workshops is relatively dispersed, the distribution of production capacity is quite different, and the integrity of the twin workshops is relatively strong.

[0046] When q<1, D>1, the scale distribution of twin workshop objects is relatively concentrated, the production capacity distribution is relatively balanced, and there are more twin workshop objects in the middle position.

[0047] When q→∞, D→0, there is only one workshop object (such as a production line or equipment) in the area; when q→0, D→∞, all workshop objects (such as the functions and production capacity of production lines and production equipment) are the same size, and the scale of system elements is the same. These two extreme situations do not exist in reality.

[0048] Point ④: The central object model has fractal characteristics, namely self-similarity. Therefore, the scale distribution of the central object model can be explained by fractal theory. Let r represent the scale level of the twin workshop object in the central object model, and the scale of the r-th twin workshop object is Pr. Let N(r) represent the total number of twin workshop objects with a scale greater than or equal to Pr. Where K is the K value in the central object model. To simplify the scenario, N(1)=1 is given.

[0049] According to fractal theory, if the scale Pr is used to measure the twin workshop objects in the central object model, then the total number of twin workshop objects N(r) with a scale greater than or equal to Pr satisfies the relationship N (r) =μ·P r -D , where μ is a constant and D is the fractal dimension. Let r = 1 and we get: N (1) =μ·P1 -D .

[0050] Point ⑤: Combining the derivation process, we can get That is, the twin workshop object level-scale model based on the central object model, in which the score dimension D is calculated by regression method.

[0051] In summary, under the condition that the fractal dimension of the twin workshop object scale distribution is known, the distribution sequence of the level-scale of the regional twin workshop object system under different K values ​​is calculated.

[0052] In step S104, by introducing the fractal mechanism, a digital twin workshop (system) is constructed, and the functional components, manufacturing equipment, production lines and physical workshops are sequentially deployed. In the entire construction process, the present invention relies on the model construction process, and divides the fractal mechanism into two parts: the process fractal mechanism and the operator fractal mechanism. Among them, the process fractal is a mechanism that transforms a complex process into a simple process, and the operator fractal is a mechanism that transforms a complex operator into a simple operator, with different degrees of self-similarity, and usually has good interpretability and reusability.

[0053] That is to say, as an optional embodiment, in step S104, the fractal mechanism adopted by the fractal engine may include a process fractal mechanism and an operator fractal mechanism, wherein:

[0054] The process fractal mechanism fully utilizes the digital twin operator, and is constructed layer by layer in accordance with the functional components, manufacturing equipment, production lines, and physical workshops through a four-layer fractal method. That is, each component / component of the digital twin workshop (system) has a fractal structure;

[0055] Operator fractal mechanism In the process fractal mechanism, at least one operator in the digital twin operator is replaced by a general operator (data operator, model operator, service operator, connection operator are collectively referred to as general operators), and is constructed layer by layer in accordance with functional components, manufacturing equipment, production lines, and physical workshops through a four-layer fractal method. In other words, some digital twin operators are used, and some general operators are used. From small to large, they are divided into four levels, namely functional components, manufacturing equipment, production lines, and physical workshops, and the modeling and calculation components of each layer of the digital twin workshop (system) are constructed layer by layer.

[0056] Process fractal mechanism part

[0057] In specific implementation, since each component of the digital twin workshop has a fractal structure, the constructed digital twin workshop has the characteristics of "process fractal", such as Figure 3 shown.

[0058] As an optional embodiment, in step S104, the method of constructing a process fractal digital twin workshop using a process fractal mechanism may include:

[0059] Al: Build the twin business module equipment components, that is, use the digital twin operator to calculate the calculation partition to obtain the twin business module equipment components, that is, the equipment component data operator, the equipment component model operator, the equipment component service operator and the equipment component connection operator;

[0060] A2: Construct a twin business production equipment module, that is, use the equipment component data operator, equipment component model operator, equipment component service operator, and equipment component connection operator as digital twin operators for constructing the twin business production equipment module, and use the same design method as the equipment component structure to construct the twin business production equipment module in a fractal way;

[0061] A3: Build a digital twin modeling production and manufacturing production line, that is, use the twin business production equipment module as the digital twin operator for building the digital twin modeling production and manufacturing production line, and use the twin business production equipment module as the production equipment of the production and manufacturing production line (IO) resource pool, that is, the production equipment of the data operator (IO) resource pool is the data operator production equipment, the production equipment of the model operator (IO) resource pool is the model operator production equipment, the production equipment of the service operator (IO) resource pool is the service operator production equipment, and the production equipment of the connection operator (IO) resource pool is the connection operator production equipment. Through the fractal method, the production and manufacturing production line includes four (IO) resource pools of the twin module and a scheduling controller;

[0062] A4: Construct a fractal digital twin workshop (system), use the digital twin modeling production line as the digital twin operator for constructing the fractal digital twin workshop (system), and the digital twin modeling production line as the twin operator of each computing unit. Through the fractal method, the digital twin workshop (system) includes data operators, model operators, service operators, connection operators and resource management partitions with scheduler functions. Figure 5 shown.

[0063] Operator fractal mechanism part

[0064] In specific implementation, the digital twin workshop has the characteristics of "operator fractal", such as Figure 4 shown.

[0065] As an optional embodiment, in step S104, the method of constructing an operator fractal digital twin workshop using an operator fractal mechanism may include:

[0066] B1: The digital twin operator includes four independent computing units of the twin module, namely the data operator, model operator, service operator and connection operator;

[0067] B2: Each modeling job occupies computing units in the order of data operator → model operator → service operator → connection operator, and executes modeling tasks in a cyclic manner of data operator → model operator → service operator → connection operator → data operator;

[0068] B3: Each modeling job occupies part or all of the computing resources of the four partitions of the twin module.

[0069] The digital twin workshop construction method with fractal mechanism provided by the present invention can avoid the construction mode of horizontal expansion, so as to continuously improve the speed of the computing module output of the entire digital twin modeling task; at the same time, it can also improve the efficiency of each organizational level of the digital twin modeling task to call each level of "sub-modeling" tasks to schedule various computing resources. The fractal digital twin workshop constructed using the present invention is more suitable for the fractal computing load corresponding to this architecture. The fractal computing load is not only composed of four computing steps of the twin module with a front-and-back dependency relationship. In addition, each computing step can be split into four computing steps of the twin module.

[0070] The present invention combines four types of computing units of the twin module, and the resource management partition uniformly allocates computing resources of each computing unit for each modeling workload running on the twin system. In addition, the digital twin workshop is constructed layer by layer through the fractal mechanism. Using the digital twin operator with the characteristics of the twin business module, the computing components of each layer of the digital twin workshop (system) are constructed in a four-layer fractal manner. And according to the functional components, manufacturing equipment, production lines, and physical workshops, the digital twin workshop (system) is constructed layer by layer in sequence.

[0071] In the above embodiment, preferably, in step A4, the digital twin modeling partitions can respectively include one or more twin operators corresponding thereto, that is, the data operator includes one or more data partitions, the model operator includes one or more atomic models, the service operator includes one or more composite models, and the connection operator includes one or more connection actuators.

[0072] Preferably, in step S104, the functions and structures of the twin operators corresponding to the four computing units of the twin module are the same, that is, the functions and structures of the twin operators corresponding to the data operators are the same, the functions and structures of the twin operators corresponding to the model operators are the same, the functions and structures of the twin operators corresponding to the service operators are the same, and the functions and structures of the twin operators corresponding to the connection operators are the same. The number of twin operators in the digital twin modeling partition is set by the actual needs of the digital twin workshop, while increasing the scalability of the digital twin workshop.

[0073] In addition, in step S104, the digital twin workshop (system) may also include data partitions, (network) device partitions and resource (management) partitions, and the data partitions, device partitions, resource partitions and digital twin modeling partitions (the four may be connected via a high-performance interconnection network) together construct the digital twin workshop. Figure 5As shown, the data partition contains the relational data and time series data of several workshop objects, the equipment partition contains the basic data information and operation information of several workshop equipment or equipment component objects, and the resource partition includes the process data, process data or control data of several twin production lines.

[0074] The step S104 is described in detail below with reference to a specific example. Figure 5 shown.

[0075] At this time, the step S104 may include:

[0076] Step S1041: The fractal digital twin workshop system consists of four computing units, including four independent computing units of the "twin module", each of which consists of multiple twin operators with the same function and structure;

[0077] Step S1042: Each job running in the digital twin modeling task occupies the server nodes of each computing unit in turn in the order of data operator → model operator → service operator → connection operator → data operator, and executes the modeling task in a cyclic manner;

[0078] Step S1043: Each job of the digital twin modeling task will occupy part or all of the computing resources of the four partitions of the twin module respectively; the number of resources occupied by each job in each partition is uniformly managed by the resource management partition to manage the computing resources of the entire twin system;

[0079] Step S1044: The operator unit having the above structural features is called a digital twin operator, such as Figure 4 As shown in the figure. The digital twin operator is fully utilized to construct the computing components of each layer of the digital twin workshop system through a four-layer fractal method. And it is constructed layer by layer in accordance with the functional components, manufacturing equipment, production lines, and physical workshops. Since each component of the digital twin workshop has a twin module fractal structure, the digital twin workshop has the characteristics of "process fractal", such as Figure 3 As shown;

[0080] Step S1045: Use digital twin operators in part and general operators in part to construct the computing components of each layer of the digital twin workshop system through a four-layer fractal method. And build them layer by layer according to functional components, manufacturing equipment, production lines, and physical workshops. The digital twin workshop has the characteristics of "operator fractal", such as Figure 4 As shown;

[0081] Step S1046: Full fractal twin workshop architecture: Digital twin operators are the main computing components that make up the fractal digital twin workshop system. The digital twin operators of each layer that make up the fractal digital twin workshop system are divided into three levels from large to small: computing production and manufacturing production lines, production equipment, and equipment components. The digital twin operators of each layer are constructed in a fractal manner using the "twin module quaternary structure". The twin module quaternary structure means that the computing components of each layer include: data operators, model operators, service operators, connection operators, and operator schedulers;

[0082] Step S1047: Through the “fractal three-step rule”, the full fractal digital twin modeling task is completed.

[0083] This step S1047 may specifically include the following steps:

[0084] Step S10471: Corresponding Figure 3 The first layer of fractal. Use the four digital twin modeling calculation partitions to form the twin business module equipment components. Use the twin business module equipment components as digital twin operators to construct the twin business production equipment module. Use the same design method as the equipment component structure to construct the twin business production equipment module through fractal method;

[0085] Step S10472: Corresponding Figure 3 The second fractal layer. Use the twin business module and equipment module as the digital twin operator to construct the digital twin production line. Use the twin business equipment module as the user of various resources. Through the fractal method, the digital twin production line operator is constructed with the four twin operators of the twin module and the scheduling controller;

[0086] Step S10473: Corresponding Figure 3 The third layer of fractal. The four operators of the digital twin production line are used as operators to construct the fractal digital twin workshop. The digital twin production line is used as the model operator of each computing unit. Through the fractal method, the fractal digital twin workshop system is constructed with four computing units of the twin module and data partitions and resource partitions with scheduler functions;

[0087] Step S10474: The twin module loop is composed of four steps: data, model, service, connection, and executes task decisions in a cyclic manner. The twin fractal construction process completes the thinking process of decision-making or complex problems, and decomposes them into regional rational thinking patterns. In the field of intelligent manufacturing, as business problems become increasingly complex, solving certain key problems in the digital twin model construction process requires multiple "repetitions" and "iterations". The thinking mode of multiple "repetitions" and "iterations" is exactly fractal thinking.

[0088] On the other hand, the present invention provides a digital twin workshop construction device based on fractal mechanism, such as Figure 6 As shown, including:

[0089] Design module 11, used to design a mapping model: based on demand analysis, design a mapping state model between workshop elements and production lines to ensure accurate correspondence between physical objects and digital space;

[0090] Development module 12, used to develop a digital twin inverse model: using autoencoder or generative adversarial network technology to build a digital twin inverse model with workshop mapping state features as input and workshop element data as output;

[0091] Establish module 13 for establishing a feedback loop: Establish a feedback mechanism to feed the data and results from actual operation into the digital twin model to continuously optimize and adjust the accuracy of the model;

[0092] Application module 14, for fractal engine application: Apply fractal engine to model and analyze the shop floor at different levels to provide deeper insights and more precise control.

[0093] The device of this embodiment can be used to perform Figure 1 The technical solution of the method embodiment shown has similar implementation principles and technical effects, which will not be repeated here.

[0094] Preferably, in the application module 14, the digital twin workshop model construction process has fractal characteristics, i.e., self-similarity, and the scale distribution of the digital twin model can be explained by fractal theory, that is, if a production capacity scale r is given to measure, the relationship between the number of twin workshop objects N(r) with a production capacity scale greater than r and r satisfies: N(r) = k·r -D , k is the coefficient, and D is the fractal dimension of the object scale distribution of the twin workshop.

[0095] Preferably, in the application module 14, the fractal mechanism adopted by the fractal engine includes a process fractal mechanism and an operator fractal mechanism, wherein:

[0096] The process fractal mechanism fully utilizes the digital twin operator and is constructed layer by layer in accordance with the functional components, manufacturing equipment, production lines, and physical workshops through a four-layer fractal method. That is, each component of the digital twin workshop has a fractal structure.

[0097] Operator fractal mechanism In the process fractal mechanism, at least one operator in the digital twin operator is replaced by a general operator. It is constructed layer by layer through a four-layer fractal method according to functional components, manufacturing equipment, production lines, and physical workshops.

[0098] Preferably, in the application module 14, the method of constructing a process fractal digital twin workshop using a process fractal mechanism includes:

[0099] Al: Build the twin business module equipment components, that is, use the digital twin operator to calculate the calculation partition to obtain the twin business module equipment components, that is, the equipment component data operator, the equipment component model operator, the equipment component service operator and the equipment component connection operator;

[0100] A2: Construct a twin business production equipment module, that is, use the equipment component data operator, equipment component model operator, equipment component service operator, and equipment component connection operator as digital twin operators for constructing the twin business production equipment module, and use the same design method as the equipment component structure to construct the twin business production equipment module in a fractal way;

[0101] A3: Build a digital twin modeling production and manufacturing production line, that is, use the twin business production equipment module as the digital twin operator for building the digital twin modeling production and manufacturing production line, and use the twin business production equipment module as the production equipment of the production and manufacturing production line resource pool, that is, the production equipment of the data operator resource pool is the data operator production equipment, the production equipment of the model operator resource pool is the model operator production equipment, the production equipment of the service operator resource pool is the service operator production equipment, and the production equipment of the connection operator resource pool is the connection operator production equipment. Through the fractal method, the production and manufacturing production line includes four resource pools of the twin module and a scheduling controller;

[0102] A4: Construct a fractal digital twin workshop, and use the digital twin modeling production line as the digital twin operator for constructing the fractal digital twin workshop. The digital twin modeling production line is used as the twin operator of each computing unit. Through the fractal method, the digital twin workshop includes data operators, model operators, service operators, connection operators and resource management partitions with scheduler functions.

[0103] Preferably, in the application module 14, the method of constructing an operator fractal digital twin workshop using the operator fractal mechanism includes:

[0104] The digital twin operator includes four independent computing units of the twin module, namely, the data operator, the model operator, the service operator and the connection operator; each modeling job occupies the computing units in the order of data operator → model operator → service operator → connection operator, and executes the modeling task in a cycle of data operator → model operator → service operator → connection operator → data operator; each modeling job occupies part or all of the computing resources of the four partitions of the twin module.

[0105] Preferably, in step A4, the digital twin modeling partitions respectively include one or more corresponding twin operators, that is, the data operator includes one or more data partitions, the model operator includes one or more atomic models, the service operator includes one or more composite models, and the connection operator includes one or more connection actuators.

[0106] Preferably, in the application module 14, the functions and structures of the twin operators corresponding to each of the four computing units of the twin module are the same.

[0107] Preferably, in the application module 14, the digital twin workshop also includes data partitions, equipment partitions and resource partitions, and the data partitions, equipment partitions, resource partitions and digital twin modeling partitions jointly construct the digital twin workshop.

[0108] The present invention also provides an electronic device, Figure 7 FIG. 1 is a schematic diagram of the structure of an electronic device of the present invention, which can implement the process shown in FIG. 1 of the present invention. Figure 7 As shown, the electronic device may include: a housing 41, a processor 42, a memory 43, a circuit board 44 and a power supply circuit 45, wherein the circuit board 44 is arranged inside the space enclosed by the housing 41, and the processor 42 and the memory 43 are arranged on the circuit board 44; the power supply circuit 45 is used to supply power to various circuits or devices of the electronic device; the memory 43 is used to store executable program codes; the processor 42 runs the program corresponding to the executable program code by reading the executable program code stored in the memory 43, so as to execute the method described in any of the aforementioned method embodiments.

[0109] For details on the specific execution process of the above steps by the processor 42 and the steps further executed by the processor 42 by running the executable program code, please refer to the present invention. Figure 1 The description of the illustrated embodiment will not be repeated here.

[0110] This electronic device exists in many forms, including but not limited to:

[0111] (1) Mobile communication devices: These devices are characterized by their mobile communication functions and their main purpose is to provide voice and data communications. These terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.

[0112] (2) Ultra-mobile personal computer devices: These devices fall into the category of personal computers, have computing and processing capabilities, and generally also have mobile Internet access features. These terminals include: PDA, MID and UMPC devices, such as iPad.

[0113] (3) Portable entertainment devices: These devices can display and play multimedia content. They include audio and video players (such as iPods), handheld game consoles, e-books, smart toys, and portable car navigation devices.

[0114] (4) Server: A device that provides computing services. The server consists of a processor, hard disk, memory, system bus, etc. The server is similar to a general computer architecture, but because it needs to provide highly reliable services, it has higher requirements in terms of processing power, stability, reliability, security, scalability, and manageability.

[0115] (5) Other electronic devices with data interaction functions.

[0116] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any of the above method embodiments are implemented.

[0117] The present invention also provides an application program, which is executed to implement the method provided by any method embodiment of the present invention.

[0118] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0119] Each embodiment in this specification is described in a related manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. For the convenience of description, the description of the above device is divided into various units / modules according to their functions and described separately. Of course, when implementing the present invention, the functions of each unit / module can be implemented in the same or one or more software and / or hardware.

[0120] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0121] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for constructing a digital twin workshop based on a fractal mechanism, characterized in that: include: Step S101: Designing a mapping model: Based on demand analysis, designing a mapping state model between workshop elements and production lines to ensure accurate correspondence between physical objects and digital space; Step S102: Developing a digital twin inverse model: using an autoencoder or generative adversarial network technology to construct a digital twin inverse model with workshop mapping state features as input and workshop element data as output; Step S103: Establish a feedback loop: Establish a feedback mechanism to feed back the data and results in actual operation into the digital twin model, and continuously optimize and adjust the accuracy of the model; Step S104: Fractal engine application: Apply the fractal engine to model and analyze the workshop at different levels to provide deeper insights and more precise control.

2. The method according to claim 1, characterized in that: In step S104, the digital twin workshop model construction process has a fractal feature, i.e., self-similarity, and the scale distribution of the digital twin model can be explained by fractal theory. That is, if a production capacity scale r is given for measurement, the number of twin workshop objects N(r) with a production capacity scale greater than r satisfies the relationship between r and N(r)=k·r. -D , k is the coefficient, and D is the fractal dimension of the object scale distribution of the twin workshop.

3. The method according to claim 1 or 2, characterized in that: In step S104, the fractal mechanism adopted by the fractal engine includes a process fractal mechanism and an operator fractal mechanism, wherein: The process fractal mechanism fully utilizes the digital twin operator and is constructed layer by layer in accordance with the functional components, manufacturing equipment, production lines, and physical workshops through a four-layer fractal method. That is, each component of the digital twin workshop has a fractal structure. Operator fractal mechanism In the process fractal mechanism, at least one operator in the digital twin operator is replaced by a general operator. It is constructed layer by layer through a four-layer fractal method according to functional components, manufacturing equipment, production lines, and physical workshops.

4. The method according to claim 3, characterized in that In step S104, the method of constructing a process fractal digital twin workshop using a process fractal mechanism includes: A1: Build the twin business module equipment components, that is, use the digital twin operator to calculate the calculation partition to obtain the twin business module equipment components, namely, the equipment component data operator, equipment component model operator, equipment component service operator and equipment component connection operator; A2: Construct a twin business production equipment module, that is, use the equipment component data operator, equipment component model operator, equipment component service operator, and equipment component connection operator as digital twin operators for constructing the twin business production equipment module, and use the same design method as the equipment component structure to construct the twin business production equipment module in a fractal way; A3: Build a digital twin modeling production and manufacturing production line, that is, use the twin business production equipment module as the digital twin operator for building the digital twin modeling production and manufacturing production line, and use the twin business production equipment module as the production equipment of the production and manufacturing production line resource pool, that is, the production equipment of the data operator resource pool is the data operator production equipment, the production equipment of the model operator resource pool is the model operator production equipment, the production equipment of the service operator resource pool is the service operator production equipment, and the production equipment of the connection operator resource pool is the connection operator production equipment. Through the fractal method, the production and manufacturing production line includes four resource pools of the twin module and a scheduling controller; A4: Construct a fractal digital twin workshop, and use the digital twin modeling production line as the digital twin operator for constructing the fractal digital twin workshop. The digital twin modeling production line is used as the twin operator of each computing unit. Through the fractal method, the digital twin workshop includes data operators, model operators, service operators, connection operators and resource management partitions with scheduler functions.

5. The method according to claim 4, characterized in that In step S104, the method of constructing an operator fractal digital twin workshop using an operator fractal mechanism includes: The digital twin operator includes four independent computing units of the twin module, namely, the data operator, the model operator, the service operator and the connection operator; each modeling job occupies the computing units in the order of data operator → model operator → service operator → connection operator, and executes the modeling task in a cycle of data operator → model operator → service operator → connection operator → data operator; each modeling job occupies part or all of the computing resources of the four partitions of the twin module.

6. The method according to claim 4, characterized in that In step A4, the digital twin modeling partitions respectively include one or more corresponding twin operators, that is, the data operator includes one or more data partitions, the model operator includes one or more atomic models, the service operator includes one or more composite models, and the connection operator includes one or more connection actuators.

7. The method according to claim 6, characterized in that In step S104, the functions and structures of the twin operators corresponding to the four computing units of the twin module are the same; And / or, in step S104, the digital twin workshop also includes data partitions, device partitions and resource partitions, and the data partitions, device partitions, resource partitions and digital twin modeling partitions jointly construct the digital twin workshop.

8. A digital twin workshop construction device based on fractal mechanism, characterized in that: include: Design module, used to design mapping models: Based on demand analysis, design the mapping state model between workshop elements and production lines to ensure accurate correspondence between physical objects and digital space; Development module for developing digital twin inverse model: using autoencoder or generative adversarial network technology to build a digital twin inverse model with workshop mapping state features as input and workshop element data as output; Establish modules for establishing feedback loops: Establish a feedback mechanism to feed the data and results from actual operation into the digital twin model to continuously optimize and adjust the accuracy of the model; Application module for Fractal Engine Applications: Apply Fractal Engine to model and analyze the shop floor at different levels to provide deeper insights and more precise control.

9. An electronic device, characterized in that: The electronic device comprises: a housing, a processor, a memory, a circuit board and a power supply circuit, wherein the circuit board is placed inside the space enclosed by the housing, and the processor and the memory are arranged on the circuit board; the power supply circuit is used to supply power to various circuits or devices of the above-mentioned electronic device; the memory is used to store executable program codes; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute any of the methods described in claims 1-7 above.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement any of the methods described in claims 1-7.

Images