Method and system for constructing assembled environment-friendly cabinet by using aluminum-zinc plates with multiple folded edges

Abstract

The invention relates to the technical field of shell assembly, in particular to a method and system for constructing an assembled environment-friendly cabinet through aluminum-zinc plates with multiple folded edges, and the method comprises the steps that an obtained environment-friendly cabinet design scheme is subjected to image-text analysis, and an environment-friendly cabinet shell structure diagram and shell description information are obtained; carrying out feature extraction operation on the environment-friendly cabinet shell structure diagram, the aluminum-zinc plate information and the shell description information to respectively obtain a shell structure feature set, a plate feature set and a shell description feature set; analyzing according to the shell structure feature set to obtain a splicable region set; carrying out stress demand simulation analysis on the environment-friendly cabinet shell structure diagram to obtain a stress demand feature set; and according to the plate feature set, the shell description feature set and the stress demand feature set, carrying out flanging pattern recognition operation on the splicable area set to obtain flanging pattern results corresponding to each splicable area in the splicable area set, thereby carrying out production and installation. The plate consumption can be reduced, and the assembling quality of the environment-friendly cabinet shell is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of shell assembly, and in particular to a method and system for constructing an assembled environmental protection cabinet by using aluminum-zinc plates with multiple folded edges. Background Art

[0002] Environmental cabinet is the abbreviation of environmentally friendly gas insulated ring main unit. It uses environmentally friendly gas as the insulating medium to store electrical equipment. It has good insulation performance and environmental protection characteristics, and can improve the safety and service life of equipment. With the widespread application of environmental cabinets, environmental cabinets now adopt modular design, which can be customized according to different power requirements and application environments, provide personalized solutions, and can be easily expanded and upgraded when needed. The modular design can also facilitate transportation.

[0003] However, modular design also changes the environmental protection cabinet shell from the traditional integral structure to a spliced ​​structure of multiple panels. In order to ensure that the splicing of the panels can meet the national standard test, multiple folding is often used to increase the thickness of the panel joints, thereby improving the rigidity and stability of the panel joints. However, in the specific multiple folding process, there is no unified standard for the number of bends and the angle of the folding angle. The design depends entirely on the subjective experience of the technicians, which may result in wasted panels and failure to meet safety standards. Summary of the invention

[0004] The present invention provides a method for constructing an assembled environmental protection cabinet by using aluminum-zinc plates with multiple folded edges, the main purpose of which is to reduce the consumption of plates and improve the assembly quality of the environmental protection cabinet shell.

[0005] To achieve the above object, the present invention provides a method for constructing an assembled environmental protection cabinet using aluminum-zinc plates under multiple folded edges, comprising: Obtaining an environmental protection cabinet design scheme, performing image and text classification on the environmental protection cabinet design scheme, and obtaining image data and text data; Perform image recognition on the image data to obtain a structural diagram of the environmental protection cabinet shell, and perform text recognition operations on the text data based on preset shell dimensions, usage environment and function introduction to obtain shell description information, wherein the shell description information includes shell numerical parameters, usage environment parameters and shell function distribution; Using a pre-trained splicing structure recognition model, a feature extraction operation is performed on the environmental protection cabinet shell structure diagram and shell description information to obtain a shell structure feature set and a shell description feature set, and a to-be-spliced ​​position recognition operation is performed based on the shell structure feature set to obtain a splicable area set; Acquire aluminum-zinc plate material information, perform plate feature extraction operation on the aluminum-zinc plate material information, and obtain a plate feature set; According to the environmental protection cabinet shell structure diagram, a force demand simulation analysis is performed on the set of splicable areas to obtain a force demand feature set; According to the plate feature set, the shell description feature set and the force requirement feature set, a folding style recognition operation is performed on the set of splicable areas to obtain a folding style result corresponding to each splicable area in the set of splicable areas; According to the folding style results corresponding to each splicable area, the pre-constructed aluminum-zinc sheet is folded to obtain an assembled environmental protection cabinet shell.

[0006] Optionally, the image and text classification of the environmental protection cabinet design scheme to obtain image data and text data includes: Scan the environmental protection cabinet design scheme to obtain a long picture introducing the environmental protection cabinet; Performing a data cleaning operation based on a preset preprocessing strategy on the long image introducing the environmental protection cabinet to obtain a standardized image; Using a pre-built Canny operator to perform an edge detection operation on the normalized image to obtain an edge detection result, and cutting the normalized image according to the edge detection result to obtain a set of region blocks; An object classification and recognition operation is performed on each area block in the area block set to obtain text data and image data.

[0007] Optionally, performing image recognition on the image data to obtain a structure diagram of the environmental protection cabinet shell includes: Performing an object type classification operation on the image data to obtain an image object set, and filtering images of environmental protection cabinet type from the image object set to obtain an environmental protection cabinet image set; Performing an environmental protection cabinet structure recognition operation on each environmental protection cabinet image in the environmental protection cabinet image set to obtain the partial structure of the environmental protection cabinet corresponding to each environmental protection cabinet image; The key endpoints of each environmental protection cabinet partial structure are identified to obtain the key endpoint positions of each environmental protection cabinet partial structure, and according to each key endpoint position, the intersection and union operations are performed on each environmental protection cabinet partial structure to obtain the environmental protection cabinet shell structure diagram.

[0008] Optionally, performing a text recognition operation on the text data based on a preset shell size, usage environment and function introduction to obtain shell description information includes: Performing a text quantization operation based on self-attention configuration on the text data to obtain a context-enhanced text quantization sequence; Performing a text feature extraction operation on the context-enhanced text quantization sequence to obtain a text feature set, and performing a semantic recognition operation on the text feature set to obtain a semantic recognition result set; The semantic recognition result set is subjected to a text screening operation based on preset shell size, usage environment and function introduction to obtain shell description information.

[0009] Optionally, before using the pre-trained splicing structure recognition model, the method further includes: Extract one historical environmental protection cabinet from the pre-built historical environmental protection cabinet project set in turn, and obtain the historical structure diagram, splicing folding edge design, plate numerical parameters, application environment and function distribution of the historical environmental protection cabinet; Performing physical inspection on the historical environmental protection cabinet to obtain actual stress test data of the splicing and folding edge design; Using a pre-built finite element analysis service, based on the historical structural diagram and the plate numerical parameters, force measurement data of the splicing hem design is generated; According to the application environment and function distribution, the force measurement data is weighted calculated based on performance requirements to obtain force demand prediction data; Calculating the difference data between the actual force test data and the force demand prediction data, and calculating the ratio of the difference data to the force demand prediction data, to obtain the performance waste ratio of the splicing hem design; The historical structure diagram, plate numerical parameters, application environment and functional distribution are used as keys, and the splicing hem design and performance waste ratio are used as values ​​to construct a key-value pair sample; Summarize the key-value pair samples corresponding to all historical environmental protection cabinets in the historical environmental protection cabinet project set to obtain a training sample set; Using a pre-built splicing structure recognition model, and according to a pre-built regularized loss function, machine learning is performed on the training sample set to obtain a network parameter relationship based on environmental protection cabinet design-splicing structure design-performance waste; A minimization operation based on the performance waste ratio is performed on the network parameter relationship to obtain a splicing structure identification model based on environmental protection cabinet design-splicing structure design.

[0010] Optionally, the regularized loss function is expressed as: ; In the formula, represents the regularized loss function, represents the number of samples in the training sample set, Indicates The actual performance waste ratio of samples, Indicates The performance waste ratio of samples is Represents the network model parameters to be trained, Indicates the minimum value, represents the regularization parameter, Denotes the L2 regularization symbol.

[0011] Optionally, the step of performing a hemming style recognition operation on the set of joinable regions according to the plate feature set, the shell description feature set, and the force requirement feature set to obtain hemming style results corresponding to each joinable region in the set of joinable regions includes: Identify the plate folding patterns on the plate feature set and the force requirement feature set to obtain a primary available folding method set corresponding to each spliceable area in the spliceable area set; According to the shell description feature set, the performance requirement configuration of each spliceable area is identified, and according to the performance requirement configuration of each spliceable area, a style constraint is imposed on a primary available folding method set corresponding to each spliceable area to obtain an available folding method set of each spliceable area; According to the pre-constructed folding style cost table, the folding cost of each folding method in each available folding method set is calculated to obtain a folding cost set, and the folding cost set is screened for the lowest cost to obtain the folding style results corresponding to each splicable area.

[0012] Optionally, the pre-built aluminum-zinc sheet is folded according to the folding style results corresponding to each splicable area to obtain an assembled environmental protection cabinet shell, including: Extracting any one joinable area from the joinable area set, obtaining a folding pattern result of the joinable area, and calculating the folding consumables of the joinable area according to the folding pattern result; Using the folding consumables, adding consumable areas to the splicable area to obtain a cuttable aluminum-zinc plate area; According to the cuttable aluminum-zinc sheet area, a cutting operation is performed on the pre-constructed aluminum-zinc sheet to obtain a sheet to be folded; Summarizing the to-be-folded plates corresponding to all the joinable regions in the joinable region set to obtain a to-be-folded plate set; According to the folding style results corresponding to each splicable area, the set of plates to be folded is folded to obtain a set of plates to be assembled, and the set of plates to be assembled is assembled to obtain an assembled environmental protection cabinet shell.

[0013] Optionally, after obtaining the hemming style results corresponding to each joinable area in the joinable area set, the method further includes: Obtaining the distribution of each joinable area in the joinable area set on the environmental protection cabinet shell structure diagram to obtain an installation distribution diagram; The installation distribution diagram is visually marked using the folding edge style results corresponding to each splicable area to obtain an environmental protection cabinet shell assembly instruction diagram.

[0014] To achieve the above object, the present invention also provides an assembled environmental protection cabinet system constructed by using aluminum-zinc plates under multiple folded edges, comprising: An environmental protection cabinet design recognition module is used to obtain an environmental protection cabinet design scheme, perform image and text classification on the environmental protection cabinet design scheme to obtain image data and text data, perform image recognition on the image data to obtain an environmental protection cabinet shell structure diagram, and perform text recognition operations on the text data based on preset shell dimensions, usage environment and function introduction to obtain shell description information, wherein the shell description information includes shell numerical parameters, usage environment parameters and shell function distribution; A spliceable area recognition module is used to use a pre-trained splicing structure recognition model to perform feature extraction operations on the environmental protection cabinet shell structure diagram and shell description information, respectively obtain a shell structure feature set and a shell description feature set, and perform a to-be-spliced ​​position recognition operation based on the shell structure feature set to obtain a spliceable area set; A folding style recognition module is used to obtain aluminum-zinc plate material information, perform a plate feature extraction operation on the aluminum-zinc plate material information to obtain a plate feature set, and perform a force demand simulation analysis on the splicable area set according to the environmental protection cabinet shell structure diagram to obtain a force demand feature set, and perform a folding style recognition operation on the splicable area set according to the plate feature set, the shell description feature set and the force demand feature set to obtain a folding style result corresponding to each splicable area in the splicable area set; The folding production module is used to fold the pre-constructed aluminum-zinc sheet according to the folding style results corresponding to each splicable area to obtain an assembled environmental protection cabinet shell.

[0015] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising: A memory storing at least one instruction; The processor executes the instructions stored in the memory to implement the above-mentioned method of constructing an assembled environmental protection cabinet using aluminum-zinc plates with multiple folded edges.

[0016] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned method of constructing an assembled environmental protection cabinet using aluminum-zinc plates with multiple folded edges.

[0017] The present invention is to solve the problem described in the background technology. The present invention first scans the environmental protection cabinet design scheme passed by the enterprise to obtain text data and image data, then finds the environmental protection cabinet shell structure diagram from the image data, finds the shell description information from the text data, and then uses the pre-trained splicing structure recognition model to first identify the area to be spliced ​​in the environmental protection cabinet shell structure diagram, and then identifies the plate feature set according to the aluminum-zinc plate plate information, and identifies the force demand feature set according to the environmental protection cabinet shell structure diagram. Finally, the folding style is identified through the plate feature set, the force demand feature set and the shell description information to obtain the folding style result; wherein, the splicing structure recognition model is machine-learned to understand the mechanical analysis corresponding to each folding style in the environmental protection cabinet, thereby ensuring that the folding style is selected at the lowest consumable cost while meeting the customer's quality requirements. Therefore, the present invention can reduce the consumption of plates and improve the assembly quality of the environmental protection cabinet shell. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of a process for constructing an assembled environmental protection cabinet using aluminum-zinc plates with multiple folded edges provided in one embodiment of the present invention; Figure 2 A structural diagram of an assembled environmental protection cabinet shell according to a method for constructing an assembled environmental protection cabinet using aluminum-zinc plates under multiple folded edges provided by an embodiment of the present invention; Figure 3 A functional module diagram of a system for constructing an assembled environmental protection cabinet using aluminum-zinc plates under multiple folded edges provided by an embodiment of the present invention; Figure 4 A schematic structural diagram of an electronic device for implementing the method of constructing an assembled environmental protection cabinet using aluminum-zinc plates under multiple folded edges provided in one embodiment of the present invention.

[0019] Description of figure markings: 1. Electronic device; 10. Processor; 11. Memory; 12. Bus.

[0020] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0022] The embodiment of the present application provides a method for constructing an assembled environmental protection cabinet using aluminum-zinc plates under multiple folded edges. The execution subject of the method for constructing an assembled environmental protection cabinet using aluminum-zinc plates under multiple folded edges includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for constructing an assembled environmental protection cabinet using aluminum-zinc plates under multiple folded edges can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0023] Reference Figure 1 FIG. 1 is a flow chart of a method for constructing an assembled environmental protection cabinet using aluminum-zinc plates with multiple folded edges provided by an embodiment of the present invention. In this embodiment, the method for constructing an assembled environmental protection cabinet using aluminum-zinc plates with multiple folded edges includes: S1. Obtain an environmental protection cabinet design scheme, and perform image and text classification on the environmental protection cabinet design scheme to obtain image data and text data.

[0024] It should be known that environmental protection cabinets are designed to ensure the safety of electrical equipment and extend their service life. In order to adapt to different electrical equipment and different environments, most of them have personalized designs. Therefore, it is usually necessary to communicate through the environmental protection cabinet design plan. When the customer approves the design of the environmental protection cabinet, the company can start production according to the environmental protection cabinet design plan.

[0025] The contents of the environmental protection cabinet design plan generally include product overview, product features, shell size, usage environment, three-view drawing of the product, structural part drawing and other information.

[0026] In detail, in the embodiment of the present invention, the image and text classification of the environmental protection cabinet design scheme is performed to obtain image data and text data, including: Scan the environmental protection cabinet design scheme to obtain a long picture introducing the environmental protection cabinet; Performing a data cleaning operation based on a preset preprocessing strategy on the long image introducing the environmental protection cabinet to obtain a standardized image; Using a pre-built Canny operator to perform an edge detection operation on the normalized image to obtain an edge detection result, and cutting the normalized image according to the edge detection result to obtain a set of region blocks; An object classification and recognition operation is performed on each area block in the area block set to obtain text data and image data.

[0027] Among them, the preprocessing strategy includes image noise reduction and grayscale measurement, which is used to reduce the pixel magnitude of the long picture of the environmental protection cabinet introduction to obtain a standardized picture to facilitate subsequent calculations.

[0028] The Canny operator is an algorithm for image edge detection, which can effectively detect edges in an image while maintaining good noise suppression capabilities.

[0029] Specifically, in an embodiment of the present invention, the environmental protection cabinet design scheme is generally an electronic version or a paper version, and a long picture of the environmental protection cabinet introduction can be obtained by optical scanning or long picture screenshots. Then, the normalized picture is edge detected using the Canny operator to obtain an edge detection result, and then cut according to the edge detection result to obtain a set of area blocks, wherein the set of area blocks includes [POS: (1425, 1140) is a area block, POS: (574, 655) is a area block...]. Then, each area block is object classified (text and image) to obtain text data and image data, for example: POS: (574, 655) area block is image data, and POS: (1425, 1140) area block is text data.

[0030] S2. Perform image recognition on the image data to obtain a structural diagram of the environmental protection cabinet shell, and perform text recognition operations on the text data based on preset shell dimensions, usage environment and function introduction to obtain shell description information, wherein the shell description information includes shell numerical parameters, usage environment parameters and shell function distribution.

[0031] In the embodiment of the present invention, the specific contents of the environmental protection cabinet design are: 1) Product Introduction: This series of products has promotional terms such as...

[0032] 2) Product features: The gas box contains functional terms such as...

[0033] 3) Shell size: like Figure 2 The shell image shown; the specific parameters are shown in Table 1 below: ; Table 1 Table 1 shows the detailed shell size information.

[0034] 4) Usage environment: Ambient temperature: -10~40℃, humidity: daily average relative humidity 95%, monthly average relative humidity 90%, Altitude 1000m, Location: Indoor, low dust and no explosive and corrosive gas.

[0035] In detail, in an embodiment of the present invention, performing image recognition on the image data to obtain a structure diagram of the environmental protection cabinet shell includes: Performing an object type classification operation on the image data to obtain an image object set, and filtering images of environmental protection cabinet type from the image object set to obtain an environmental protection cabinet image set; Performing an environmental protection cabinet structure recognition operation on each environmental protection cabinet image in the environmental protection cabinet image set to obtain the partial structure of the environmental protection cabinet corresponding to each environmental protection cabinet image; The key endpoints of each environmental protection cabinet partial structure are identified to obtain the key endpoint positions of each environmental protection cabinet partial structure, and according to each key endpoint position, the intersection and union operations are performed on each environmental protection cabinet partial structure to obtain the environmental protection cabinet shell structure diagram.

[0036] The partial structure of the environmental protection cabinet refers to the structure of the environmental protection cabinet inferred from a single picture.

[0037] The intersection and union operation refers to retaining one repeated structure in each partial structure of the environmental protection cabinet and adding the non-repeated structure, so that the structure of the environmental protection cabinet becomes complete.

[0038] In an embodiment of the present invention, the image data is first classified into object types to obtain an image object set, such as [company logo, designer introduction pictures, factory introduction pictures, shell appearance pictures, shell structure pictures...], and the present invention needs to filter the environmental protection cabinet type in the image object set to obtain an environmental protection cabinet image set, such as [cabinet appearance pictures, shell structure pictures (three views)].

[0039] In an embodiment of the present invention, each shell surface image in the environmental protection cabinet image set is introduced from different angles, so partial structures of the environmental protection cabinet are obtained one by one. In order to construct a complete three-dimensional structure diagram, it is necessary to identify key endpoints and obtain key endpoint positions, such as landing points, vertices, corner positions, etc. After finding the common key endpoint positions, the intersection and union structures can be overlapped according to the positions of the key endpoints in the shell surface images to obtain the environmental protection cabinet shell structure diagram (three-dimensional structure).

[0040] In detail, in an embodiment of the present invention, the text data is subjected to a text recognition operation based on a preset shell size, usage environment and function introduction to obtain shell description information, including: Performing a text quantization operation based on self-attention configuration on the text data to obtain a context-enhanced text quantization sequence; Performing a text feature extraction operation on the context-enhanced text quantization sequence to obtain a text feature set, and performing a semantic recognition operation on the text feature set to obtain a semantic recognition result set; The semantic recognition result set is subjected to a text screening operation based on preset shell size, usage environment and function introduction to obtain shell description information.

[0041] Among them, the self-attention configuration (Text Self-Attention) is usually a mechanism used in natural language processing tasks to enhance the model's ability to understand the input text. The key is that it can capture the dependency between any two positions in the input sequence without relying on a fixed window size. In an embodiment of the present invention, due to the layout problem of the scheme, there is a position distance between each text data, but the content may be related, so it is necessary to use a self-attention mechanism to perform context enhancement within and between text data to obtain a context-enhanced text quantization sequence. Among them, the text quantization operation refers to converting text characters into vector-encoded characters, such as encoding through a one-hot algorithm or Word2Vec.

[0042] Then, the text features are extracted through the pre-built convolution layer and pooling layer to obtain a text feature set, and then semantic recognition is performed using a fully connected network to obtain a semantic recognition result set. Finally, the shell description information is obtained by classification extraction through preset data types, such as shell size, usage environment and function introduction. Among them, the function introduction is not a promotion of product quality, but a functional zoning of various areas of the environmental protection cabinet product, such as sealing area, grounding area, etc. Among them, the convolution layer, pooling layer and fully connected layer are common structures in the neural network text processing process, which will not be repeated here.

[0043] S3. Using a pre-trained splicing structure recognition model, perform feature extraction operations on the environmental protection cabinet shell structure diagram and shell description information to obtain a shell structure feature set and a shell description feature set, respectively, and perform a to-be-spliced ​​position recognition operation based on the shell structure feature set to obtain a splicable area set.

[0044] Among them, the splicing structure recognition model is a neural network model based on image and text binary data processing, which is used to analyze the folding styles that meet the quality standards and have the lowest folding consumables cost for each area to be spliced ​​according to the environmental protection cabinet shell structure diagram, aluminum-zinc plate material information and shell description information.

[0045] Among them, the folding styles are different types of multi-folding technology, such as folding once, folding twice, bending angle, etc. Different folding styles may be related to factors such as bearing capacity, sealing, and internal pressure of the shell.

[0046] In detail, in the embodiment of the present invention, before using the pre-trained splicing structure recognition model, the method further includes: Extract one historical environmental protection cabinet from the pre-built historical environmental protection cabinet project set in turn, and obtain the historical structure diagram, splicing folding edge design, plate numerical parameters, application environment and function distribution of the historical environmental protection cabinet; Performing physical inspection on the historical environmental protection cabinet to obtain actual stress test data of the splicing and folding edge design; Using a pre-built finite element analysis service, based on the historical structural diagram and the plate numerical parameters, force measurement data of the splicing hem design is generated; According to the application environment and function distribution, the force measurement data is weighted calculated based on performance requirements to obtain force demand prediction data; Calculating the difference data between the actual force test data and the force demand prediction data, and calculating the ratio of the difference data to the force demand prediction data, to obtain the performance waste ratio of the splicing hem design; The historical structure diagram, plate numerical parameters, application environment and functional distribution are used as keys, and the splicing hem design and performance waste ratio are used as values ​​to construct a key-value pair sample; Summarize the key-value pair samples corresponding to all historical environmental protection cabinets in the historical environmental protection cabinet project set to obtain a training sample set; Using a pre-built splicing structure recognition model, and according to a pre-built regularized loss function, machine learning is performed on the training sample set to obtain a network parameter relationship based on environmental protection cabinet design-splicing structure design-performance waste; A minimization operation based on the performance waste ratio is performed on the network parameter relationship to obtain a splicing structure identification model based on environmental protection cabinet design-splicing structure design.

[0047] Among them, the historical environmental protection cabinet project set refers to the data information of various types and models of environmental protection cabinets produced and tested by the enterprise in the past, including shell material, environment type, design structure, etc.

[0048] The physical inspection is different from software inspection, and the actual data is measured by inspection equipment such as a motor or a vibration machine.

[0049] Among them, Finite Element Analysis (FEA) is a numerical calculation technology used to simulate and analyze complex engineering and physical problems. The present invention can predict the minimum force measurement data required for the area to be spliced ​​through FEA service to maintain the product quality.

[0050] Among them, the regularized loss function refers to the loss function with the regularization parameter added, including the conventional loss function of regression prediction, the regularization term and the optimization term, wherein the regularization term can prevent overfitting, and the optimization term can effectively predict the performance waste ratio of the splicing hem design, so that the regularized loss function ensures that the model can accurately predict the performance waste ratio of the splicing structure of the environmental protection cabinet. In actual design, resources are used more effectively and waste is reduced. Through optimization algorithms such as back propagation and gradient descent, the model parameters can be gradually updated to minimize the loss function.

[0051] Specifically, in the embodiment of the present invention, the historical structure diagram, splicing folding design, plate numerical parameters, application environment and functional distribution of each historical environmental protection cabinet are obtained from the historical environmental protection cabinet project collection. Then the entity detection results of the historical environmental protection cabinet are obtained to obtain the actual force test data; and through the finite element analysis service, the performance of each area to be spliced ​​in the historical structure diagram that needs to bear at least is analyzed to obtain the force measurement data, wherein the force measurement data includes not only the bearing capacity, but also parameters such as bending strength.

[0052] Furthermore, in an embodiment of the present invention, according to the application environment and functional distribution, for example, if a certain area needs to be grounded, it is necessary to perform certain weighting on parameters such as corrosion resistance and bearing capacity, while if the function of a certain area is to store environmentally friendly gases, it is necessary to perform certain weighted calculation on the airtightness layer parameters, and finally obtain the force demand prediction data.

[0053] Furthermore, in an embodiment of the present invention, through the force demand prediction data and the actual force test data, it can be known whether the splicing folding design of the historical environmental protection cabinet in each area to be spliced ​​is appropriate. When the difference data is a positive value, it indicates good quality, and when the difference data is a negative value, it indicates unqualified quality, and the larger the difference data, the more wasteful the folding material. The present invention calculates the ratio of the difference data to the force demand prediction data to obtain the performance waste ratio of the splicing folding design, and then the performance waste ratio can be used as an evaluation label for the splicing folding design, to use the historical structure diagram, plate numerical parameters, application environment and functional distribution as keys, and the splicing folding design and performance waste ratio as values, to construct key-value pair samples, and then summarize to obtain a training sample set.

[0054] In detail, in the embodiment of the present invention, the regularized loss function is expressed as: ; In the formula, represents the regularized loss function, represents the number of samples in the training sample set, Indicates The actual performance waste ratio of samples, Indicates The performance waste ratio of samples is Represents the network model parameters to be trained, Indicates the minimum value, represents the regularization parameter, Denotes the L2 regularization symbol.

[0055] Specifically, in the embodiment of the present invention, the initialized splicing structure recognition model is used to perform machine learning on the training sample set. First, a splicing folding edge design is predicted through the design of historical environmental protection cabinets in the training samples. Then, it is checked whether the difference between the predicted splicing folding edge design and the actual splicing folding edge design is the performance waste ratio. The model is trained through conventional loss function and regularization term so that the model learns the network parameter relationship of environmental protection cabinet design-splicing structure design-performance waste. Then, the optimization term is used to perform minimization operation to obtain the splicing structure recognition model of environmental protection cabinet design-splicing structure design. Therefore, the splicing structure recognition model has the lowest plate waste rate according to the splicing structure design analyzed according to the environmental protection cabinet design.

[0056] Furthermore, in an embodiment of the present invention, a feature extraction operation is performed on the environmental protection cabinet shell structure diagram and shell description information through a neural network in a trained splicing structure recognition model, and a shell structure feature set and a shell description feature set are obtained respectively, and then a to-be-splice position recognition operation is performed according to the shell structure feature set to obtain a set of splicable areas. Among them, feature extraction and recognition are conventional functions of neural networks, and specific functions, such as the function of identifying the to-be-splice position, can be realized through simple training. Among them, the shell structure feature set includes, for example, the number of faces of the environmental protection cabinet, the height of each face, the number of shelves of the environmental protection cabinet, the number of spaces contained in the environmental protection cabinet, etc., and the shell description feature set is used to describe the upper layer use, middle layer use and lower layer use in the environmental protection cabinet, such as instrument access at the upper layer, and the middle layer is used to seal environmental protection gas, etc.

[0057] S4. Acquire the aluminum-zinc plate material information, perform a plate feature extraction operation on the aluminum-zinc plate material information, and obtain a plate feature set.

[0058] The aluminum-zinc sheet material information is a table recording the aluminum-zinc sheet information.

[0059] Specifically, in the embodiment of the present invention, the aluminum-zinc plate material information includes aluminum-zinc alloy ratio, plate hardness, bearing capacity, bending strength, corrosion resistance, plate thickness, etc.

[0060] In the embodiment of the present invention, the feature set of the aluminum-zinc sheet material is easily obtained by extracting the feature of the sheet material information through a neural network.

[0061] S5. According to the environmental protection cabinet shell structure diagram, a force demand simulation analysis is performed on the set of splicable areas to obtain a force demand feature set.

[0062] In an embodiment of the present invention, transfer learning is performed on some capabilities of the FEA service. Virtual modeling can be performed based on the environmental protection cabinet shell structure diagram to obtain an environmental protection cabinet model. Then, the force and direction that each area to be spliced ​​of the environmental protection cabinet model needs to withstand at least are predicted to obtain a set of force requirement characteristics.

[0063] S6. According to the plate feature set, the shell description feature set and the force requirement feature set, a folding style recognition operation is performed on the set of joinable areas to obtain a folding style result corresponding to each joinable area in the set of joinable areas.

[0064] In detail, in an embodiment of the present invention, the hemming style recognition operation is performed on the set of joinable areas according to the plate feature set, the shell description feature set and the force requirement feature set to obtain the hemming style results corresponding to each joinable area in the set of joinable areas, including: Identify the plate folding patterns on the plate feature set and the force requirement feature set to obtain a primary available folding method set corresponding to each spliceable area in the spliceable area set; According to the shell description feature set, the performance requirement configuration of each spliceable area is identified, and according to the performance requirement configuration of each spliceable area, a style constraint is imposed on a primary available folding method set corresponding to each spliceable area to obtain an available folding method set of each spliceable area; According to the pre-constructed folding style cost table, the folding cost of each folding method in each available folding method set is calculated to obtain a folding cost set, and the folding cost set is screened for the lowest cost to obtain the folding style results corresponding to each splicable area.

[0065] Among them, the performance requirement configuration refers to whether there are other performance requirements in addition to the load-bearing and bending strength performance required by the plate structure itself. For example, when pressurization is required in the environmental protection cabinet, higher pressure resistance is required; when sealing is required in the environmental protection cabinet, better sealing is required.

[0066] Specifically, in an embodiment of the present invention, the plate folding style is first identified based on the trained splicing structure recognition model. In the folding style identification process, the primary set of available folding methods corresponding to each splicing area in the splicing area set can be obtained first. If bending 90°, folding once, and folding twice represent 30 points, 60 points, and 90 points respectively, once the force demand prediction data identified by the model is 50 points, the style can only be constrained to folding once and folding twice. The performance waste ratio of folding twice is significantly greater than the performance waste ratio of folding once. Therefore, according to the training parameters that minimize the performance waste ratio, folding once is selected for output. The present invention can construct more levels, such as 30 points and 35 points, so as to more accurately locate the folding style.

[0067] In detail, in the embodiment of the present invention, after obtaining the hemming style results corresponding to each joinable area in the joinable area set, the method further includes: Obtaining the distribution of each joinable area in the joinable area set on the environmental protection cabinet shell structure diagram to obtain an installation distribution diagram; The installation distribution diagram is visually marked using the folding edge style results corresponding to each splicable area to obtain an environmental protection cabinet shell assembly instruction diagram.

[0068] The distribution of the various splicable areas on the environmental protection cabinet shell structure diagram can be marked with dark colors, and the installation distribution diagram can be visually marked with symbols such as welding and screws.

[0069] Specifically, in an embodiment of the present invention, the splicable area of ​​the environmental protection cabinet shell structure diagram can be calibrated to obtain an installation distribution diagram, and then each folding style result can be visually marked to obtain an environmental protection cabinet shell assembly instruction to facilitate installation by installation technicians.

[0070] S7. According to the folding style results corresponding to each splicable area, the pre-constructed aluminum-zinc sheet is folded to produce the assembled environmental protection cabinet.

[0071] In detail, in the embodiment of the present invention, the pre-constructed aluminum-zinc sheet is folded according to the folding style results corresponding to each splicable area to obtain an assembled environmental protection cabinet shell, including: Extracting any one joinable area from the joinable area set, obtaining a folding pattern result of the joinable area, and calculating the folding consumables of the joinable area according to the folding pattern result; Using the folding consumables, adding consumable areas to the splicable area to obtain a cuttable aluminum-zinc plate area; According to the cuttable aluminum-zinc sheet area, a cutting operation is performed on the pre-constructed aluminum-zinc sheet to obtain a sheet to be folded; Summarizing the to-be-folded plates corresponding to all the joinable regions in the joinable region set to obtain a to-be-folded plate set; According to the folding style results corresponding to each splicable area, the set of plates to be folded is folded to obtain a set of plates to be assembled, and the set of plates to be assembled is assembled to obtain an assembled environmental protection cabinet shell.

[0072] In the embodiment of the present invention, only seamlessly connected regular plates can be seen in the environmental protection cabinet shell structure diagram, and the specific splicing and folding pattern is not shown. Therefore, the plates cannot be cut according to the numerical values ​​in the environmental protection cabinet shell structure diagram, and a certain margin needs to be reserved for multiple folding operations according to the splicing and folding pattern.

[0073] The increase in the consumable area refers to the operation of adding some plates for folding outside the designed plate size range.

[0074] Specifically, in an embodiment of the present invention, the folding consumables are calculated through the folding style results, and then added at the corresponding position of the environmental protection cabinet shell structure diagram to obtain a cuttable aluminum-zinc plate area, and then the plate can be processed by a pre-built cutting machine, and then the folding machine is used to perform folding operations to obtain a set of spliced ​​plates to be assembled, and then it is installed according to the environmental protection cabinet assembly instruction diagram to obtain an assembled environmental protection cabinet.

[0075] The present invention is to solve the problem described in the background technology. The present invention first scans the environmental protection cabinet design scheme passed by the enterprise to obtain text data and image data, then finds the environmental protection cabinet shell structure diagram from the image data, finds the shell description information from the text data, and then uses the pre-trained splicing structure recognition model to first identify the area to be spliced ​​in the environmental protection cabinet shell structure diagram, and then identifies the plate feature set according to the aluminum-zinc plate plate information, and identifies the force demand feature set according to the environmental protection cabinet shell structure diagram. Finally, the folding style is identified through the plate feature set, the force demand feature set and the shell description information to obtain the folding style result; wherein, the splicing structure recognition model is machine-learned to understand the mechanical analysis corresponding to each folding style in the environmental protection cabinet, thereby ensuring that the folding style is selected at the lowest consumable cost while meeting the customer's quality requirements. Therefore, the present invention can reduce the consumption of plates and improve the assembly quality of environmental protection cabinets.

[0076] like Figure 3 As shown, it is a functional module diagram of a system for constructing an assembled environmental protection cabinet using aluminum-zinc plates under multiple folded edges provided by an embodiment of the present invention.

[0077] The system 100 for constructing an assembled environmental protection cabinet using aluminum-zinc plates under multiple folded edges of the present invention can be installed in an electronic device. According to the functions to be implemented, the system 100 for constructing an assembled environmental protection cabinet using aluminum-zinc plates under multiple folded edges can include an environmental protection cabinet design identification module 101, a splicable area identification module 102, a folded edge style identification module 103, and a folded edge production module 104. The module described in the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0078] The environmental protection cabinet design recognition module 101 is used to obtain an environmental protection cabinet design scheme, perform image text classification on the environmental protection cabinet design scheme to obtain image data and text data, perform image recognition on the image data to obtain an environmental protection cabinet shell structure diagram, and perform text recognition operations on the text data based on preset shell size, use environment and function introduction to obtain shell description information, wherein the shell description information includes shell numerical parameters, use environment parameters and shell function distribution; The spliceable region identification module 102 is used to perform feature extraction operations on the environmental protection cabinet shell structure diagram and shell description information using a pre-trained splicing structure identification model, obtain a shell structure feature set and a shell description feature set, and perform a to-be-spliced ​​position identification operation according to the shell structure feature set to obtain a spliceable region set; The folding style recognition module 103 is used to obtain aluminum-zinc plate material information, perform a plate feature extraction operation on the aluminum-zinc plate material information to obtain a plate feature set, and perform a force demand simulation analysis on the splicable area set according to the environmental protection cabinet shell structure diagram to obtain a force demand feature set, and perform a folding style recognition operation on the splicable area set according to the plate feature set, the shell description feature set and the force demand feature set to obtain a folding style result corresponding to each splicable area in the splicable area set; The folding production module 104 is used to perform folding production on the pre-constructed aluminum-zinc sheet according to the folding style results corresponding to each splicable area to obtain an assembled environmental protection cabinet shell.

[0079] In detail, the modules in the assembled environmental protection cabinet system 100 constructed by using aluminum-zinc plates under multiple folded edges in the embodiment of the present invention are used in the same manner as described above. Figure 1 The same technical means as described in the method of constructing an assembled environmental protection cabinet using aluminum-zinc plates under multiple folded edges can produce the same technical effects, so I will not go into details here.

[0080] like Figure 4, which is a schematic diagram of the structure of an electronic device for realizing a method for constructing an assembled environmental protection cabinet using aluminum-zinc plates under multiple folded edges provided by an embodiment of the present invention.

[0081] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a method program for constructing an assembled environmental protection cabinet using aluminum-zinc plates with multiple folded edges.

[0082] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the method program for constructing an assembled environmental protection cabinet using aluminum-zinc plates under multiple folded edges, but can also be used to temporarily store data that has been output or is to be output.

[0083] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (for example, a method program for constructing an assembled environmental protection cabinet using aluminum-zinc plates under multiple folded edges, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0084] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0085] Figure 4 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 4 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0086] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0087] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0088] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0089] The method program for constructing an assembled environmental protection cabinet using aluminum-zinc plates under multiple folded edges stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, the following can be achieved: Obtaining an environmental protection cabinet design scheme, performing image and text classification on the environmental protection cabinet design scheme, and obtaining image data and text data; Perform image recognition on the image data to obtain a structural diagram of the environmental protection cabinet shell, and perform text recognition operations on the text data based on preset shell dimensions, usage environment and function introduction to obtain shell description information, wherein the shell description information includes shell numerical parameters, usage environment parameters and shell function distribution; Using a pre-trained splicing structure recognition model, a feature extraction operation is performed on the environmental protection cabinet shell structure diagram and shell description information to obtain a shell structure feature set and a shell description feature set, and a to-be-spliced ​​position recognition operation is performed based on the shell structure feature set to obtain a splicable area set; Acquire aluminum-zinc plate material information, perform plate feature extraction operation on the aluminum-zinc plate material information, and obtain a plate feature set; According to the environmental protection cabinet shell structure diagram, a force demand simulation analysis is performed on the set of splicable areas to obtain a force demand feature set; According to the plate feature set, the shell description feature set and the force requirement feature set, a folding style recognition operation is performed on the set of splicable areas to obtain a folding style result corresponding to each splicable area in the set of splicable areas; According to the folding style results corresponding to each splicable area, the pre-constructed aluminum-zinc sheet is folded to obtain an assembled environmental protection cabinet shell.

[0090] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 4 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0091] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0092] The present invention further 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 of an electronic device, the computer program can implement: Obtaining an environmental protection cabinet design scheme, performing image and text classification on the environmental protection cabinet design scheme, and obtaining image data and text data; Perform image recognition on the image data to obtain a structural diagram of the environmental protection cabinet shell, and perform text recognition operations on the text data based on preset shell dimensions, usage environment and function introduction to obtain shell description information, wherein the shell description information includes shell numerical parameters, usage environment parameters and shell function distribution; Using a pre-trained splicing structure recognition model, a feature extraction operation is performed on the environmental protection cabinet shell structure diagram and shell description information to obtain a shell structure feature set and a shell description feature set, and a to-be-spliced ​​position recognition operation is performed based on the shell structure feature set to obtain a splicable area set; Acquire aluminum-zinc plate material information, perform plate feature extraction operation on the aluminum-zinc plate material information, and obtain a plate feature set; According to the environmental protection cabinet shell structure diagram, a force demand simulation analysis is performed on the set of splicable areas to obtain a force demand feature set; According to the plate feature set, the shell description feature set and the force requirement feature set, a folding style recognition operation is performed on the set of splicable areas to obtain a folding style result corresponding to each splicable area in the set of splicable areas; According to the folding style results corresponding to each splicable area, the pre-constructed aluminum-zinc sheet is folded to obtain an assembled environmental protection cabinet shell.

[0093] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and actual implementation may have other division methods.

[0094] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0095] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0096] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for constructing an assembled environmental protection cabinet using aluminum-zinc plates with multiple folded edges, characterized in that: The method comprises: Obtaining an environmental protection cabinet design plan, performing image and text classification on the environmental protection cabinet design plan, and obtaining image data and text data; Perform image recognition on the image data to obtain a structural diagram of the environmental protection cabinet shell, and perform text recognition operations on the text data based on preset shell dimensions, usage environment and function introduction to obtain shell description information, wherein the shell description information includes shell numerical parameters, usage environment parameters and shell function distribution; Using a pre-trained splicing structure recognition model, a feature extraction operation is performed on the environmental protection cabinet shell structure diagram and shell description information to obtain a shell structure feature set and a shell description feature set, and a to-be-spliced ​​position recognition operation is performed based on the shell structure feature set to obtain a splicable area set; Acquire aluminum-zinc plate material information, perform plate feature extraction operation on the aluminum-zinc plate material information, and obtain a plate feature set; According to the environmental protection cabinet shell structure diagram, a force demand simulation analysis is performed on the set of splicable areas to obtain a force demand feature set; According to the plate feature set, the shell description feature set and the force requirement feature set, a folding style recognition operation is performed on the set of splicable areas to obtain a folding style result corresponding to each splicable area in the set of splicable areas; According to the folding style results corresponding to each splicable area, the pre-constructed aluminum-zinc sheet is folded to obtain an assembled environmental protection cabinet shell.

2. The method for constructing an assembled environmental protection cabinet using aluminum-zinc plates with multiple folded edges as claimed in claim 1, characterized in that: The image and text classification of the environmental protection cabinet design scheme is performed to obtain image data and text data, including: Scan the environmental protection cabinet design scheme to obtain a long picture introducing the environmental protection cabinet; Performing a data cleaning operation based on a preset preprocessing strategy on the long image introducing the environmental protection cabinet to obtain a standardized image; Using a pre-built Canny operator to perform an edge detection operation on the normalized image to obtain an edge detection result, and cutting the normalized image according to the edge detection result to obtain a set of region blocks; An object classification and recognition operation is performed on each area block in the area block set to obtain text data and image data.

3. The method for constructing an assembled environmental protection cabinet using aluminum-zinc plates with multiple folded edges as claimed in claim 2, characterized in that: The image data is subjected to image recognition to obtain a structure diagram of the environmental protection cabinet housing, including: Performing an object type classification operation on the image data to obtain an image object set, and filtering images of environmental protection cabinet type from the image object set to obtain an environmental protection cabinet image set; Performing an environmental protection cabinet structure recognition operation on each environmental protection cabinet image in the environmental protection cabinet image set to obtain the partial structure of the environmental protection cabinet corresponding to each environmental protection cabinet image; The key endpoints of each environmental protection cabinet partial structure are identified to obtain the key endpoint positions of each environmental protection cabinet partial structure, and according to each key endpoint position, the intersection and union operations are performed on each environmental protection cabinet partial structure to obtain the environmental protection cabinet shell structure diagram.

4. The method for constructing an assembled environmental protection cabinet using aluminum-zinc plates with multiple folded edges as claimed in claim 3, characterized in that: The text data is subjected to a text recognition operation based on a preset shell size, usage environment and function introduction to obtain shell description information, including: Performing a text quantization operation based on self-attention configuration on the text data to obtain a context-enhanced text quantization sequence; Performing a text feature extraction operation on the context-enhanced text quantization sequence to obtain a text feature set, and performing a semantic recognition operation on the text feature set to obtain a semantic recognition result set; The semantic recognition result set is subjected to a text screening operation based on preset shell size, usage environment and function introduction to obtain shell description information.

5. The method for constructing an assembled environmental protection cabinet using aluminum-zinc plates with multiple folded edges as claimed in claim 4, characterized in that: Before using the pre-trained splicing structure recognition model, the method further includes: Extract one historical environmental protection cabinet from the pre-built historical environmental protection cabinet project set in turn, and obtain the historical structure diagram, splicing folding edge design, plate numerical parameters, application environment and function distribution of the historical environmental protection cabinet; Performing physical inspection on the historical environmental protection cabinet to obtain actual stress test data of the splicing and folding edge design; Using a pre-built finite element analysis service, based on the historical structural diagram and the plate numerical parameters, force measurement data of the splicing hem design is generated; According to the application environment and function distribution, the force measurement data is weighted calculated based on performance requirements to obtain force demand prediction data; Calculating the difference data between the actual force test data and the force demand prediction data, and calculating the ratio of the difference data to the force demand prediction data, to obtain the performance waste ratio of the splicing hem design; The historical structure diagram, plate numerical parameters, application environment and functional distribution are used as keys, and the splicing hem design and performance waste ratio are used as values ​​to construct a key-value pair sample; Summarize the key-value pair samples corresponding to all historical environmental protection cabinets in the historical environmental protection cabinet project set to obtain a training sample set; Using a pre-built splicing structure recognition model, and according to a pre-built regularized loss function, machine learning is performed on the training sample set to obtain a network parameter relationship based on environmental protection cabinet design-splicing structure design-performance waste; A minimization operation based on the performance waste ratio is performed on the network parameter relationship to obtain a splicing structure identification model based on the environmental protection cabinet design-splicing structure design.

6. The method for constructing an assembled environmental protection cabinet using aluminum-zinc plates with multiple folded edges as claimed in claim 5, characterized in that: The regularized loss function is expressed as: ； In the formula, represents the regularized loss function, represents the number of samples in the training sample set, Indicates The actual performance waste ratio of samples, Indicates The performance waste ratio of samples is Represents the network model parameters to be trained, Indicates the minimum value, represents the regularization parameter, Denotes the L2 regularization symbol.

7. The method for constructing an assembled environmental protection cabinet using aluminum-zinc plates with multiple folded edges as claimed in claim 6, characterized in that: The step of performing a folding style recognition operation on the set of joinable regions according to the plate feature set, the shell description feature set and the force requirement feature set to obtain a folding style result corresponding to each joinable region in the set of joinable regions includes: Identify the plate folding patterns on the plate feature set and the force requirement feature set to obtain a primary available folding method set corresponding to each spliceable area in the spliceable area set; According to the shell description feature set, the performance requirement configuration of each spliceable area is identified, and according to the performance requirement configuration of each spliceable area, a style constraint is imposed on a primary available folding method set corresponding to each spliceable area to obtain an available folding method set of each spliceable area; According to the pre-constructed folding style cost table, the folding cost of each folding method in each available folding method set is calculated to obtain a folding cost set, and the folding cost set is screened for the lowest cost to obtain the folding style results corresponding to each splicable area.

8. The method for constructing an assembled environmental protection cabinet using aluminum-zinc plates with multiple folded edges as claimed in claim 7, characterized in that: According to the folding pattern results corresponding to each splicable area, the pre-constructed aluminum-zinc sheet is folded to produce the assembled environmental protection cabinet shell, including: Extracting any one joinable area from the joinable area set, obtaining a folding pattern result of the joinable area, and calculating the folding consumables of the joinable area according to the folding pattern result; Using the folding consumables, adding consumable areas to the splicable area to obtain a cuttable aluminum-zinc plate area; According to the cuttable aluminum-zinc sheet area, a cutting operation is performed on the pre-constructed aluminum-zinc sheet to obtain a sheet to be folded; Summarize the to-be-folded plates corresponding to all the joinable regions in the joinable region set to obtain a to-be-folded plate set; According to the folding style results corresponding to each splicable area, the set of plates to be folded is folded to obtain a set of plates to be assembled, and the set of plates to be assembled is assembled to obtain an assembled environmental protection cabinet shell.

9. The method for constructing an assembled environmental protection cabinet using aluminum-zinc plates with multiple folded edges as claimed in claim 8, characterized in that: After obtaining the hemming style results corresponding to each joinable area in the joinable area set, the method further includes: Obtain the distribution of each spliceable area in the spliceable area set on the environmental protection cabinet shell structure diagram to obtain an installation distribution diagram; The installation distribution diagram is visually marked using the folding edge style results corresponding to each splicable area to obtain an environmental protection cabinet shell assembly instruction diagram.

10. An assembled environmental protection cabinet system constructed by using aluminum-zinc plates with multiple folded edges, characterized in that: The system comprises: An environmental protection cabinet design recognition module is used to obtain an environmental protection cabinet design scheme, perform image and text classification on the environmental protection cabinet design scheme to obtain image data and text data, perform image recognition on the image data to obtain an environmental protection cabinet shell structure diagram, and perform text recognition operations on the text data based on preset shell dimensions, usage environment and function introduction to obtain shell description information, wherein the shell description information includes shell numerical parameters, usage environment parameters and shell function distribution; A spliceable area recognition module is used to use a pre-trained splicing structure recognition model to perform feature extraction operations on the environmental protection cabinet shell structure diagram and shell description information, respectively obtain a shell structure feature set and a shell description feature set, and perform a to-be-spliced ​​position recognition operation based on the shell structure feature set to obtain a spliceable area set; A folding style recognition module is used to obtain aluminum-zinc plate material information, perform a plate feature extraction operation on the aluminum-zinc plate material information to obtain a plate feature set, and perform a force demand simulation analysis on the splicable area set according to the environmental protection cabinet shell structure diagram to obtain a force demand feature set, and perform a folding style recognition operation on the splicable area set according to the plate feature set, the shell description feature set and the force demand feature set to obtain a folding style result corresponding to each splicable area in the splicable area set; The folding production module is used to fold the pre-constructed aluminum-zinc sheet according to the folding style results corresponding to each splicable area to obtain an assembled environmental protection cabinet shell.

Images