Model migration method, computing device and machine readable storage medium

Abstract

The embodiment of the invention discloses a model migration method, computing equipment and a machine readable storage medium, and belongs to the technical field of digital twinning. The model migration method comprises the steps of determining a component configuration set of the engineering machinery in response to a component configuration request of the engineering machinery; selecting from a preset agent model library according to the component configuration set to obtain all corresponding target component agent models; respectively determining whether the precision of each target component agent model is greater than preset precision or not; and under the condition that the precision of each target component agent model is greater than the preset precision, assembling all the target component agent models according to the component connection relationship of the engineering machinery to obtain a complete machine agent model of the engineering machinery. When the component configuration of the engineering machinery is changed, the complete machine agent model can be flexibly and quickly assembled, so that quick migration of the agent model is realized, and the agent model deployment efficiency of the engineering machinery is improved.

Description

Technical Field

[0001] The present application relates to the field of digital twin technology, and specifically to a model migration method, a computing device, and a machine-readable storage medium. Background Art

[0002] With the rapid development of control technology for construction machinery, digital twin technology is widely used in various types of construction machinery control scenarios. Digital twin refers to the use of real-time data and modeling technology to complete the mapping of construction machinery in virtual space, thereby reflecting the operating status of the physical equipment corresponding to the construction machinery. In the control scenarios of construction machinery such as tower cranes, the whole machine proxy model of the tower crane is usually built based on digital twin technology, and the stress of the tower crane is predicted and optimized through the whole machine proxy model to improve the operating reliability of the tower crane.

[0003] However, construction machinery such as tower cranes are usually complex systems composed of multiple interchangeable parts. During use, tower cranes and other construction machinery usually assemble different interchangeable parts to form different assembly configurations to adapt to complex construction environments. When the assembly configuration of the tower crane changes, the tower crane's proxy model needs to be rebuilt, and the tower crane's proxy model needs to be retrained and tested. Changes in the assembly configuration of construction machinery require a lot of time to redeploy the proxy model, which leads to inefficient deployment of the construction machinery's proxy model. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a model migration method, a computing device, and a machine-readable storage medium to solve the problem of low efficiency in the deployment of agent models of engineering machinery in the prior art.

[0005] In order to achieve the above-mentioned object, the first aspect of the present application provides a model migration method, which includes:

[0006] In response to a component configuration request of the engineering machinery, a component configuration set of the engineering machinery is determined;

[0007] Select from a preset proxy model library according to the component configuration set to obtain corresponding proxy models of all target components, wherein the preset proxy model library stores component proxy models of engineering machinery;

[0008] Determine respectively whether the accuracy of each target component proxy model is greater than a preset accuracy;

[0009] When the accuracy of each target component proxy model is greater than the preset accuracy, all target component proxy models are assembled according to the component connection relationship of the engineering machinery to obtain the whole machine proxy model of the engineering machinery.

[0010] In an embodiment of the present application, each target component proxy model includes at least one sub-network;

[0011] Model migration methods also include:

[0012] When the accuracy of at least one target component proxy model is less than or equal to a preset accuracy, for each target component proxy model whose accuracy is less than or equal to the preset accuracy, the target component proxy model is trained based on the accuracy error of each sub-network in the target component proxy model until the accuracy of the target component proxy model is greater than the preset accuracy.

[0013] In an embodiment of the present application, training the target component proxy model based on the accuracy error of each sub-network in the target component proxy model includes:

[0014] Obtaining the precision error of each sub-network in the target component proxy model respectively, and determining whether the precision error of each sub-network is greater than a preset error respectively;

[0015] When the accuracy error of each sub-network is greater than a preset error, determining the deviation of the accuracy errors of all sub-networks;

[0016] Based on the deviations, the target component proxy model is trained.

[0017] In an embodiment of the present application, each target component proxy model further includes a summary network, and each sub-network is connected to the summary network;

[0018] According to the deviation, the target component proxy model is trained, including:

[0019] Train the summary network when the bias is linear;

[0020] All subnetworks are trained with biases other than linear biases, and the summary network is trained.

[0021] In an embodiment of the present application, training the target component proxy model based on the accuracy error of each sub-network in the target component proxy model includes:

[0022] When the accuracy error of at least one subnetwork is greater than or equal to the preset error, and the number of subnetworks with accuracy errors less than the preset error is greater than the number corresponding to a preset percentage, train the subnetworks with accuracy errors greater than the preset error, wherein the preset percentage is the percentage between the subnetworks with accuracy errors less than the preset error and the total number of subnetworks.

[0023] In the embodiment of the present application, the preset proxy model library is obtained according to the following steps:

[0024] Determine all replaceable parts corresponding to the construction machinery;

[0025] Build proxy models for each replaceable part separately;

[0026] Build a proxy model library based on the proxy models of all replaceable parts.

[0027] In the embodiment of the present application, constructing the proxy model of each replaceable component includes:

[0028] The load between the replaceable component and the first component is used as the input of the proxy model, and the load and stress between the replaceable component and the second component are used as the output of the proxy model to construct a proxy model of the replaceable component, wherein the first component is connected to the second component through the replaceable component.

[0029] In the embodiment of the present application, all corresponding target component proxy models are obtained by selecting from a preset proxy model library according to a component configuration set, including:

[0030] Obtaining an initial component configuration set of the construction machinery and an initial whole machine proxy model corresponding to the initial component configuration set;

[0031] Determine components to be added and components to be subtracted according to the component configuration set and the initial component configuration set;

[0032] The proxy model of the component to be added is selected from the proxy module library, and the proxy model of the component to be subtracted is subtracted from the initial whole machine proxy model to obtain all target component proxy models corresponding to the component configuration set.

[0033] A second aspect of the present application provides a computing device, including:

[0034] a memory configured to store instructions;

[0035] The processor is configured to call instructions from the memory and implement the above-mentioned model migration method when executing the instructions.

[0036] A third aspect of the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the above-mentioned model migration method.

[0037] The present application provides a model migration method, including: responding to a component configuration request of an engineering machinery, determining a component configuration set of the engineering machinery; selecting from a preset proxy model library according to the component configuration set to obtain corresponding proxy models of all target components; determining whether the accuracy of each target component proxy model is greater than the preset accuracy; when the accuracy of each target component proxy model is greater than the preset accuracy, assembling all target component proxy models according to the component connection relationship of the engineering machinery to obtain a whole-machine proxy model of the engineering machinery. A whole-machine proxy model of an engineering machinery that is based on components and can be assembled is constructed. When the component configuration of the engineering machinery changes, the whole-machine proxy model can be assembled flexibly and quickly, thereby realizing rapid migration of the proxy model. The efficiency of proxy model migration of engineering machinery with different configurations is improved, and there is no need to spend a lot of time to redeploy a new whole-machine proxy model, thereby improving the efficiency of proxy model deployment of engineering machinery.

[0038] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0040] Figure 1 A schematic diagram of a process flow of a model migration method according to an embodiment of the present application is schematically shown;

[0041] Figure 2 A diagram schematically shows an example of the accuracy of a proxy model according to an embodiment of the present application;

[0042] Figure 3 An example diagram of a whole-machine proxy model according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0044] It should be noted that if directional indication is involved in the embodiments of the present application, the directional indication is only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0045] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0046] Figure 1 The following schematically shows a flow chart of a model migration method according to an embodiment of the present application. Figure 1 As shown, the embodiment of the present application provides a model migration method, which may include the following steps:

[0047] S110, responding to a component configuration request of the engineering machinery and determining a component configuration set of the engineering machinery.

[0048] The type of engineering machinery is set according to actual needs and is not limited here. For ease of understanding, the engineering machinery in the embodiment of the present application is a tower crane. When the configuration of the tower crane changes, for example, when it is necessary to add or reduce components to the tower crane. The computing device responds to the component configuration request of the engineering machinery and determines a new component configuration set corresponding to the engineering machinery.

[0049] The method in the embodiment of the present application selects from a preset proxy model library according to a component configuration set to obtain corresponding proxy models of all target components, including:

[0050] Obtaining an initial component configuration set of the construction machinery and an initial whole machine proxy model corresponding to the initial component configuration set;

[0051] Determine components to be added and components to be subtracted according to the component configuration set and the initial component configuration set;

[0052] The proxy model of the component to be added is selected from the proxy module library, and the proxy model of the component to be subtracted is subtracted from the initial whole machine proxy model to obtain all target component proxy models corresponding to the component configuration set.

[0053] When the component configuration of the construction machinery changes, it may be necessary to add or subtract components. Obtain the initial component configuration set of the construction machinery and the initial whole machine proxy model corresponding to the initial component configuration set. Determine the components to be added and to be subtracted based on the component configuration set and the initial component configuration set. Select the proxy model of the component to be added from the proxy module library, and subtract the proxy model of the component to be subtracted from the initial whole machine proxy model. According to the component configuration set, add the proxy model of the new component, and subtract the proxy model of the redundant components in the initial component configuration, and quickly obtain all the target component proxy models corresponding to the component configuration set.

[0054] S120 , selecting from a preset proxy model library according to the component configuration set to obtain corresponding proxy models of all target components, wherein the preset proxy model library stores component proxy models of engineering machinery.

[0055] Taking the components of the tower crane as units, pre-construct the general component proxy models of the tower crane, and then form a preset proxy model database. According to the component configuration set, select from the preset proxy model library to obtain the corresponding proxy models of all target components. Specifically, determine the target components that need to be added and / or subtracted from the tower crane according to the component configuration set. When the tower crane needs to subtract a certain target component, directly remove the proxy model corresponding to the target component. When the tower crane needs to add a certain target component, select from the preset proxy model library to obtain the corresponding proxy models of all target components.

[0056] S130, determining whether the accuracy of each target component proxy model is greater than a preset accuracy.

[0057] Determine whether the accuracy of each target component proxy model is greater than the preset accuracy. If the accuracy of the target component proxy model is less than or equal to the preset accuracy, it is determined that the target component proxy model needs to be recalibrated until the accuracy of each target component proxy model is greater than the preset accuracy.

[0058] S140, when the accuracy of each target component proxy model is greater than a preset accuracy, assembling all target component proxy models according to the component connection relationship of the engineering machinery to obtain a whole machine proxy model of the engineering machinery.

[0059] When the accuracy of each target component proxy model is greater than the preset accuracy, all target component proxy models are assembled according to the component connection relationship of the construction machinery, that is, based on the real topological connection relationship of the tower crane, to obtain the whole machine proxy model of the construction machinery. The whole machine proxy model can be used to predict the stress and other parameters of each key component in the construction machinery. It should be understood that the key components are components with relatively large load-bearing capacity and components with relatively weak fatigue life.

[0060] By building a whole-machine proxy model of construction machinery that can be assembled based on components, the whole-machine proxy model can be assembled flexibly and quickly when the component configuration of the construction machinery changes, thereby realizing the rapid migration of the proxy model. The efficiency of proxy model migration of construction machinery with different configurations is improved, and there is no need to spend a lot of time to redeploy a new whole-machine proxy model, thereby improving the efficiency of proxy model deployment for construction machinery.

[0061] In an embodiment of the present application, each target component proxy model includes at least one sub-network;

[0062] Model migration methods also include:

[0063] When the accuracy of at least one target component proxy model is less than or equal to a preset accuracy, for each target component proxy model whose accuracy is less than or equal to the preset accuracy, the target component proxy model is trained based on the accuracy error of each sub-network in the target component proxy model until the accuracy of the target component proxy model is greater than the preset accuracy.

[0064] In this embodiment, each target component proxy model includes at least one network, and each sub-network corresponds to a sub-model. For components that need to output loads, the target component proxy model includes at least two networks, one of which is used to output loads, and the remaining at least one network is used to output data such as stress and / or displacement. For example, the foundation section of a tower crane is the lowest component. Since there is no next-level connecting component in the foundation section, the proxy model of the foundation section does not need to output loads. For components that do not need to output loads, the target component proxy model includes at least one network, excluding the network for outputting loads, and the proxy model includes at least one network for outputting data such as stress and / or displacement. In the case where the accuracy error of each sub-network in the target proxy model is small, the target proxy model can be used directly. In the case where the accuracy of at least one target component proxy model is less than or equal to the preset accuracy, the target component proxy model with an accuracy less than or equal to the preset accuracy is a proxy model that needs to be re-corrected.

[0065] Obtain the precision error of each sub-network in the target component proxy model whose precision is less than or equal to the preset precision. For each target component proxy model whose precision is less than or equal to the preset precision, train the target component proxy model based on the precision error of each sub-network in the target component proxy model until the precision of the target component proxy model is greater than the preset precision.

[0066] In the embodiment of the present application, based on the accuracy error of each sub-network in the target component proxy model, the target component proxy model is trained, including:

[0067] Obtaining the precision error of each sub-network in the target component proxy model respectively, and determining whether the precision error of each sub-network is greater than a preset error respectively;

[0068] When the accuracy error of each sub-network is greater than a preset error, determining the deviation of the accuracy errors of all sub-networks;

[0069] Based on the deviations, the target component proxy model is trained.

[0070] For each target component proxy model whose accuracy is less than or equal to the preset accuracy, the accuracy error of the nodes of each sub-network in the target component proxy model is obtained respectively, and it is determined whether the accuracy error of each sub-network is greater than the preset error, so as to determine the error category of different proxy models.

[0071] Recalibrate the proxy model according to the error category of the proxy model so that the accuracy of all target component proxy models is greater than the preset accuracy. Specifically, when the accuracy error of each sub-network is greater than the preset error, determine the deviation of the accuracy error of all sub-networks. According to the deviation, determine whether the overall prediction accuracy of each network output node maintains approximately the same error level, and then train the target component proxy model to recalibrate the proxy model.

[0072] In an embodiment of the present application, each target component proxy model further includes a summary network, and each sub-network is connected to the summary network;

[0073] According to the deviation, the target component proxy model is trained, including:

[0074] Train the summary network when the bias is linear;

[0075] All subnetworks are trained with biases other than linear biases, and the summary network is trained.

[0076] In this embodiment, each target component proxy model also includes a summary network, the output layer of each sub-network is connected to the input layer of the summary network, the input of each sub-network is the connection load of the previous component, and the output of the summary network is the key node parameters of the target component. The key nodes are the node positions with relatively large load-bearing capacity in the component and the node positions with relatively weak fatigue life.

[0077] When the deviation is a linear deviation, it is determined that the accuracy error of each network output node is maintained at roughly the same error level as a whole, and the summary network is trained without retraining the sub-network. When the deviation is not a linear deviation, it is determined that the accuracy error of each network output node is poor, and the accuracy error varies, and all sub-networks are trained, and the summary network is trained.

[0078] In an embodiment of the present application, training the target component proxy model based on the accuracy error of each sub-network in the target component proxy model includes:

[0079] When the accuracy error of at least one subnetwork is greater than or equal to the preset error, and the number of subnetworks with accuracy errors less than the preset error is greater than the number corresponding to a preset percentage, train the subnetworks with accuracy errors greater than the preset error, wherein the preset percentage is the percentage between the subnetworks with accuracy errors less than the preset error and the total number of subnetworks.

[0080] The preset percentage is used to determine whether the precision errors of a large number of sub-networks are all low. If the precision error of at least one sub-network is greater than or equal to the preset error, and the number of sub-networks with precision errors less than the preset error is greater than the number corresponding to the preset percentage, it is determined that only some of the website nodes have high precision errors, then only the sub-networks with precision errors greater than the preset error are trained, and there is no need to train all the sub-networks.

[0081] See also Figure 2 , Figure 2 An example diagram of the accuracy of an agent model according to an embodiment of the present application is schematically shown.

[0082] As shown in the figure, 15 target component proxy models are obtained in the embodiment of the present application, and the names of the 15 proxy models are respectively: QZB1, QZB2, QZB3, QZB4, QZB4, QZB5, QZB5, QZB6, QZB7, PHB1, PHB2, PHB3, TT, SZZ, XZZ, BZJ and GDJ. The accuracy of the proxy model is inversely proportional to the error, that is, the higher the accuracy of the proxy model, the lower the error of the proxy model.

[0083] The errors of the proxy models named QZB6, QZB3, PHB3, PHB2, and SZZ are relatively concentrated, while the errors of the other proxy models are relatively consistent, and the summary network needs to be retrained. Some sub-networks of the proxy models named QZB4, QZB5, QZB1, XZZ, and BZJ need to be retrained. The accuracy of the proxy model named QZB7 is greater than or less than or equal to the preset accuracy and does not need to be retrained. The proxy models named QZB6, QZB3, PHB3, PHB2, and SZZ need to retrain the summary model.

[0084] In the embodiment of the present application, the preset proxy model library is obtained according to the following steps:

[0085] Determine all replaceable parts corresponding to the construction machinery;

[0086] Build proxy models for each replaceable part separately;

[0087] Build a proxy model library based on the proxy models of all replaceable parts.

[0088] The parts of the construction machinery include replaceable parts and non-replaceable parts. Determine all the replaceable parts corresponding to the construction machinery. In this embodiment, all the replaceable parts of the tower crane include 7 booms, 3 balance arms, a tower head, an upper support, a lower support, a standard section and a transition section. Take the parts as units and build the proxy model of each replaceable part. Based on the proxy models of all replaceable parts, build a proxy model library.

[0089] In the embodiment of the present application, constructing the proxy model of each replaceable component includes:

[0090] The load between the replaceable component and the first component is used as the input of the proxy model, and the load and stress between the replaceable component and the second component are used as the output of the proxy model to construct a proxy model of the replaceable component, wherein the first component is connected to the second component through the replaceable component.

[0091] The first component is connected to the second component through a replaceable component, that is, the first component is the previous component connected by the replaceable component, and the second component is the next component that can be replaced and connected. In this embodiment, the proxy model includes a load prediction proxy model and a stress prediction proxy model. The accuracy of the load prediction proxy model and the stress prediction proxy model are set according to actual needs and are not limited here. For ease of understanding, in the embodiments of the present application, the accuracy of the load prediction proxy model is within 5%, and the accuracy of the stress prediction proxy model is within 10%.

[0092] See also Figure 3 , Figure 3 An example diagram of a whole-machine proxy model according to an embodiment of the present application is schematically shown.

[0093] The load between the replaceable component and the first component is used as the input of the proxy model, and the load and stress between the replaceable component and the second component are used as the output of the proxy model to construct the proxy model of the replaceable component. When all the proxy models of the target components are assembled, the input of the load prediction proxy model is the load at the connection of the previous target component, and the output of the load prediction proxy model is the load at the connection with the next target component, thereby obtaining the whole machine proxy model of the engineering machinery. As shown in the figure, the whole machine proxy model is assembled by the proxy model of the crane arm 2, the proxy model of the crane arm 1, the proxy model of the balance arm 1, the proxy model of the tower head, the proxy model of the upper support, and the proxy model of the standard section.

[0094] The present application provides a model migration method, including: responding to a component configuration request of an engineering machinery, determining a component configuration set of the engineering machinery; selecting from a preset proxy model library according to the component configuration set to obtain corresponding proxy models of all target components; determining whether the accuracy of each target component proxy model is greater than the preset accuracy; when the accuracy of each target component proxy model is greater than the preset accuracy, assembling all target component proxy models according to the component connection relationship of the engineering machinery to obtain a whole-machine proxy model of the engineering machinery. A whole-machine proxy model of an engineering machinery that is based on components and can be assembled is constructed. When the component configuration of the engineering machinery changes, the whole-machine proxy model can be assembled flexibly and quickly, thereby realizing rapid migration of the proxy model. The efficiency of proxy model migration of engineering machinery with different configurations is improved, and there is no need to spend a lot of time to redeploy a new whole-machine proxy model, thereby improving the efficiency of proxy model deployment of engineering machinery.

[0095] The present application also provides a computing device, including:

[0096] a memory configured to store instructions;

[0097] The processor is configured to call instructions from the memory and implement the above-mentioned model migration method when executing the instructions.

[0098] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the problem of low efficiency in deploying the proxy model of engineering machinery can be solved by adjusting the kernel parameters.

[0099] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0100] An embodiment of the present application also provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute the above-mentioned model migration method.

[0101] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0102] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0103] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0105] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0106] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0107] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0108] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0109] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A model migration method, characterized in that: The model migration method comprises: In response to a component configuration request of an engineering machine, determining a component configuration set of the engineering machine; Selecting from a preset proxy model library according to the component configuration set to obtain corresponding proxy models of all target components, wherein the preset proxy model library stores component proxy models of the engineering machinery; Determining respectively whether the accuracy of each of the target component proxy models is greater than a preset accuracy; When the accuracy of each target component proxy model is greater than a preset accuracy, all the target component proxy models are assembled according to the component connection relationship of the engineering machinery to obtain a whole machine proxy model of the engineering machinery.

2. The method according to claim 1, characterized in that Each of the target component proxy models includes at least one sub-network; The model migration method further includes: In the case that the accuracy of at least one of the target component proxy models is less than or equal to the preset accuracy, for each target component proxy model whose accuracy is less than or equal to the preset accuracy, the target component proxy model is trained based on the accuracy error of each of the sub-networks in the target component proxy model until the accuracy of the target component proxy model is greater than the preset accuracy.

3. The method according to claim 2, characterized in that The step of training the target component proxy model based on the accuracy error of each sub-network in the target component proxy model comprises: Respectively obtaining the precision error of each of the sub-networks in the target component proxy model, and respectively determining whether the precision error of each of the sub-networks is greater than a preset error; When the precision error of each of the sub-networks is greater than a preset error, determining the deviation of the precision errors of all the sub-networks; The target component proxy model is trained according to the deviation.

4. The method according to claim 3, characterized in that Each of the target component proxy models also includes a summary network, and each of the sub-networks is connected to the summary network; The step of training the target component proxy model according to the deviation comprises: In the case where the deviation is a linear deviation, training the summing network; In the case where the deviation is not a linear deviation, all of the sub-networks are trained, and the summary network is trained.

5. The method according to claim 3, characterized in that: The step of training the target component proxy model based on the accuracy error of each sub-network in the target component proxy model comprises: When the precision error of at least one of the subnetworks is greater than or equal to the preset error, and the number of subnetworks with precision errors less than the preset error is greater than the number corresponding to a preset percentage, the subnetworks with precision errors greater than the preset error are trained, wherein the preset percentage is the percentage between the subnetworks with precision errors less than the preset error and the total number of subnetworks.

6. The method according to claim 1, characterized in that The preset proxy model library is obtained according to the following steps: Determine all replaceable parts corresponding to the construction machinery; Constructing a proxy model of each of the replaceable components respectively; Based on the proxy models of all the replaceable parts, a proxy model library is constructed.

7. The method according to claim 6, characterized in that The step of constructing a proxy model of each of the replaceable components comprises: The load between the replaceable component and the first component is used as the input of the proxy model, and the load and stress between the replaceable component and the second component are used as the output of the proxy model to construct a proxy model of the replaceable component, wherein the first component is connected to the second component through the replaceable component.

8. The method according to claim 1, characterized in that The method of selecting from a preset proxy model library according to the component configuration set to obtain corresponding proxy models of all target components includes: Acquire an initial component configuration set of the engineering machinery and an initial whole machine proxy model corresponding to the initial component configuration set; Determining components to be added and components to be subtracted according to the component configuration set and the initial component configuration set; A proxy model of the component to be added is selected from the proxy module library, and the proxy model of the component to be subtracted is subtracted from the initial whole machine proxy model to obtain all target component proxy models corresponding to the component configuration set.

9. A computing device, characterized in that include: a memory configured to store instructions; A processor is configured to call the instructions from the memory and implement the model migration method according to any one of claims 1 to 8 when executing the instructions.

10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions, which are used to enable a machine to execute the model migration method according to any one of claims 1 to 9.

Images