Method and apparatus for automatically designing a pneumatic circuit based on ai

Abstract

This invention discloses an AI-based method and apparatus for automatically designing gas path diagrams. The method includes: generating a key point cloud of the 3D model using a point cloud processing algorithm based on feature points of the 3D model; identifying part categories using a neural network model based on the key point cloud; binding the identified part categories to preset 2D legend blocks to obtain part legend binding data; parsing the gas path schematic vector file, extracting its graphic metadata, and generating part connection relationship data based on the part legend binding data and the extracted graphic metadata; and connecting the corresponding 2D legend blocks and adding feature attributes based on the part connection relationship data to generate the gas path diagram. This invention solves the technical problems of inaccurate and inefficient gas path diagram generation in existing technologies.

Description

Technical Field

[0001] This invention relates to the field of intelligent automotive design, and more specifically, to a method and apparatus for automatically designing airflow diagrams based on AI. Background Technology

[0002] Competition in the automotive industry is becoming increasingly fierce, with emerging car companies springing up like mushrooms after rain. With the growth of automotive production lines and the development of numerous new models, the design and modification of tooling fixtures for different body parts assemblies and sub-assemblies are also underway. Designers need to illustrate the implementation principles of these fixtures in conjunction with product processes to guide on-site technicians in assembling the tooling fixtures according to pneumatic principles.

[0003] The design of the pneumatic circuit diagram requires the air source, valve block, solenoid valve, cylinder, suction cup, throttle valve, etc. According to the process documents, the designers classify different cylinders into a certain solenoid valve for control (collectively referred to as the action group), and then connect the diagrams of each part according to certain standards or rules.

[0004] When designing the pneumatic circuit, the number of cylinders in the actuation group is customized by the designer, which can easily lead to omissions or duplicates that are difficult to detect. The connection relationships between different parts require the designer to have a high degree of understanding of the pneumatic circuit principle of the entire fixture, which limits the designer's design experience to a certain extent.

[0005] There is currently no effective solution to the above problems. Summary of the Invention

[0006] This invention provides an AI-based method and apparatus for automatically designing gas path diagrams, which at least solves the technical problems of inaccurate and inefficient gas path diagram generation in the prior art.

[0007] According to one aspect of the present invention, an AI-based method for automatically designing gas path diagrams is provided, comprising: generating a key point cloud of the three-dimensional model based on feature points of the three-dimensional model using a point cloud processing algorithm, and identifying parts using a neural network model based on the key point cloud to obtain part categories; binding the identified parts in the three-dimensional model to corresponding two-dimensional legend blocks based on the part categories to obtain part legend binding data; parsing the gas path schematic vector file, extracting graphic metadata therein, and generating part connection relationship data based on the part legend binding data and the extracted graphic metadata; and connecting the corresponding two-dimensional legend blocks and adding feature attributes based on the part connection relationship data to generate a gas path diagram.

[0008] According to another aspect of the present invention, an AI-based automatic design apparatus for gas path diagrams is also provided, comprising: an identification module configured to generate a key point cloud of the three-dimensional model based on feature points of a three-dimensional model using a point cloud processing algorithm, and to identify parts based on the key point cloud using a neural network model to obtain part categories; a binding module configured to bind the parts identified in the three-dimensional model to corresponding two-dimensional legend blocks based on the part categories to obtain part legend binding data; a connection determination module configured to parse a gas path schematic vector file, extract graphic metadata therein, and generate part connection relationship data based on the part legend binding data and the extracted graphic metadata; and a generation module configured to connect the corresponding two-dimensional legend blocks and add feature attributes based on the part connection relationship data to generate a gas path diagram.

[0009] In this embodiment of the invention, based on the feature points of a 3D model, a point cloud processing algorithm is used to generate a key point cloud of the 3D model. Based on the key point cloud, a neural network model is used to identify parts and obtain part categories. Based on the part categories, the parts identified in the 3D model are bound to their corresponding 2D legend blocks to obtain part legend binding data. The gas path schematic vector file is parsed, and its graphic metadata is extracted. Based on the part legend binding data and the extracted graphic metadata, part connection relationship data is generated. Based on the part connection relationship data, the corresponding 2D legend blocks are connected and feature attributes are added to generate a gas path diagram. The above solution solves the technical problems of inaccurate and inefficient generation of gas path diagrams in the prior art. Attached Figure Description

[0010] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0011] Figure 1 This is a flowchart of an optional AI-based automatic gas path diagram design method according to an embodiment of the present invention;

[0012] Figure 2 This is a flowchart of another optional AI-based automatic gas path diagram design method according to an embodiment of the present invention;

[0013] Figure 3 This is a schematic diagram of key feature points of an optional cylinder according to an embodiment of the present invention;

[0014] Figure 4 This is an optional schematic diagram according to an embodiment of the present invention;

[0015] Figure 5 This is a schematic diagram illustrating two different optional connection relationships and styles according to an embodiment of the present invention;

[0016] Figure 6 This is a schematic diagram of an optional block name and variables according to an embodiment of the present invention;

[0017] Figure 7 This is an optional layer diagram according to an embodiment of the present invention;

[0018] Figure 8 This is a flowchart of another optional AI-based automatic gas path diagram design method according to an embodiment of the present invention;

[0019] Figure 9 This is a schematic diagram of an optional AI-based automatic gas path design according to an embodiment of the present invention;

[0020] Figure 10 A schematic diagram of the structure of a computer device suitable for implementing embodiments of the present disclosure is shown. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] According to an embodiment of the present invention, an embodiment of a method for automatically designing gas flow diagrams based on AI is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0024] Figure 1 This is an AI-based automatic gas path diagram design method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0025] Step S102: Based on the feature points of the 3D model, a point cloud of key points of the 3D model is generated using a point cloud processing algorithm. Based on the point cloud of key points, a neural network model is used to identify the parts and obtain the part category.

[0026] For example, the feature points of the three-dimensional model are extracted, including: the center of gravity, the maximum contour point, the protective cover mounting point, the pressure arm connection point, the air inlet / outlet mounting point, the cylinder assembly point, and the pressure arm rotation point; using the center of gravity as a reference point, the feature points are combined using the point cloud processing algorithm to form the key point cloud of the three-dimensional model; based on the key point cloud, feature learning is performed using the neural network model to obtain the spatial structure data of the three-dimensional model, and based on the spatial structure data, the part category of the three-dimensional model is determined.

[0027] Step S104: Based on the part category, bind the parts identified in the 3D model to the corresponding 2D legend blocks to obtain part legend binding data.

[0028] The part categories are matched with the mapping relationship table to determine the two-dimensional legend blocks corresponding to the part categories. The mapping relationship table stores the mapping relationship between parts and two-dimensional legend blocks. Based on the part categories and the corresponding two-dimensional legend blocks, a binding correspondence between parts and two-dimensional legend blocks is generated to obtain part binding mapping data. Based on the part binding mapping data and the parts in the three-dimensional model, the part legend binding data is obtained.

[0029] Step S106: Parse the gas path schematic vector file, extract the graphic metadata, and generate part connection relationship data based on the part legend binding data and the extracted graphic metadata.

[0030] The pneumatic circuit schematic vector file is parsed to extract the graphic metadata, which includes: legend blocks, layers, variable objects, connection relationships between different legend blocks, and text objects. Based on the layers, connection point information between legend blocks is determined. Based on the variable objects, annotation parameters related to the legend blocks are determined. Based on the text objects, text features associated with the legend blocks or variable objects are determined. According to preset action group configuration rules, multiple cylinders are categorized into the same solenoid valve for unified control, and action group configuration data is generated. Based on the part legend binding data, the connection point information, the annotation parameters, the text features, the action group configuration data, and the connection relationships between different legend blocks, the part connection relationship data is generated.

[0031] Step S108: Based on the component connection relationship data, connect the corresponding two-dimensional legend blocks and add feature attributes to generate an air path diagram.

[0032] First, based on the component connection relationship data, the line connection method between the two-dimensional legend blocks is determined; connecting lines are generated between the two-dimensional legend blocks, and connection topology data is formed based on the connection method. In some embodiments, the connection topology data can also be optimized. For example, the current layout corresponding to the connection topology data is divided into multiple grid cells, the line intersection density of the multiple grid cells is calculated, and conflict hotspot areas are determined based on the line intersection density; for the conflict hotspot areas, a set of candidate solutions is generated by adjusting node positions, inserting virtual inflection points, or exchanging the positions of nodes on the same layer, and the adaptive cost value of each candidate solution in the set of candidate solutions is calculated; based on the adaptive cost value, the optimal candidate solution is determined from the candidate solutions, and the connection topology data is optimized based on the optimal candidate solution.

[0033] Subsequently, based on the connection topology data, feature attributes are added to the connection lines and the two-dimensional legend blocks, wherein the feature attributes include at least one of the following: line type, color, font, and font size; based on the feature attributes, the two-dimensional legend blocks and the connection lines are rendered to generate the gas path diagram.

[0034] Figure 2This is another AI-based automatic pneumatic circuit schematic design method according to an embodiment of the present invention. This embodiment uses an AI model to intelligently identify the components included in various pneumatic circuit schematics under a certain category (or standard), such as air sources, solenoid valves, cylinders, etc., and the connection relationships between these components. Subsequently, the AI ​​model further identifies the number and type of three-dimensional models included in the fixture, such as cylinder models having open and closed states. Finally, the identified three-dimensional models are bound to corresponding legends in the pneumatic circuit schematics, thereby enabling the automatic generation of pneumatic circuit diagrams through the identification of three-dimensional models.

[0035] Specifically, such as Figure 2 As shown, the method includes the following steps:

[0036] Step S202: By creating a feature point cloud, an overall and local spatial structure is built to identify the category to which the part belongs.

[0037] In the design of the air circuit diagram, it is necessary to automatically identify specific types of parts, such as cylinders and suction cups.

[0038] First, based on the feature points of the 3D model, a key point cloud is generated. Figure 3 The diagram shows the key feature points of the cylinder's 3D model. (a) is the maximum contour point, (b) is the protective cover mounting point, (c) is the pressure arm connection point, (d) is the inlet / outlet mounting point, (e) is the cylinder assembly point, and (f) is the pressure arm rotation point. Using the 3D model's center of gravity as a reference point, point cloud processing algorithms, such as ISS or Harris3D algorithms, are used to integrate the points from these six categories, forming the key point cloud for the specific model.

[0039] Specifically, using Graph Neural Networks (GNNs) or the improved point cloud processing model PointNet++, feature points in the 3D model are generated and defined according to their categories. For example, CATIA automatically generates the centroid of the 3D model and then defines this point as the reference point. Points of the corresponding categories are created sequentially according to the six categories of feature points shown in the diagram above. The created feature points can include coordinates or the category features to which the feature point belongs. Using PointNet++ as the core network architecture, the feature points are connected to form the geometric contour and spatial structure data of this 3D model. The local structures of different categories are learned sequentially to obtain the part categories.

[0040] This embodiment further constructs the overall and local spatial structure by creating a key point cloud to identify the category to which the parts belong. After identifying the part category, the AI ​​model can automatically identify the 2D legend blocks corresponding to different 3D models through data feeding. In the subsequent automatic generation of gas path diagrams, the corresponding 2D legend blocks can be recommended based solely on the identification of the 3D models.

[0041] Step S204: The AI ​​model automatically identifies the features such as legend blocks, layers, and variables contained in the gas path schematic vector file, as well as the connection relationships between different legend blocks and the text that is related to the legend blocks.

[0042] Specifically, during the data learning phase, the AI ​​model analyzes the gas path schematic vector file from the feed to determine which symbols are used and the connection relationships between symbols under this drawing standard. The AI ​​model directly parses the gas path schematic vector file (DWG, DXF, etc.) designed by CAD software, which directly contains object information such as blocks, lines, layers, variables, and text. Blocks are connected by lines, layers are used to define connection points, variables define annotation content and their relative positions to blocks, and text can be parsed for features such as font, size, and color. The schematic diagram is shown below. Figure 4 As shown, (a) is a diagram of a solenoid valve, (b) is a label for a solenoid valve, (c) is a diagram of a cylinder, and (d) is a label for a cylinder. The connection relationships and styles are as follows. Figure 5 As shown, where, Figure 5 (a) represents the connection between different legends, and (b) represents the connection between different types of joints. The block names and variables are as follows: Figure 6 As shown, the layers are as follows Figure 7 As shown.

[0043] Step S206: Based on the 2D legend blocks corresponding to the identified 3D model, and combined with the parsed gas path principle vector file, connect the legend blocks according to the parsed rules, and add the corresponding features.

[0044] Compared with existing technologies, this application simplifies the operation steps, greatly reduces the workload of designers, improves work efficiency, and lowers design costs. Furthermore, compared with existing technologies, designers do not need to consider the 2D legends corresponding to the current model, the connection forms between different legends in the final gas path diagram, the line type and color, the font, size, and color of the text, etc. The design process does not require the full participation of designers, greatly improving design efficiency.

[0045] Figure 8 This is yet another AI-based method for automatically designing gas path diagrams according to embodiments of the present invention, such as... Figure 8 As shown, the method includes the following steps:

[0046] Step S802: Identify the part categories of the 3D model based on the neural network model.

[0047] In this embodiment, feature point information is first extracted from the 3D model file of the tooling fixture. The feature points include seven categories: center of gravity, maximum contour point, protective cover mounting point, pressure arm connection point, air inlet / outlet mounting point, cylinder assembly point, and pressure arm rotation point. A local coordinate system is established with the center of gravity of the 3D model as the origin. The normalized feature point set is input into the point cloud processing module, and a key point cloud is constructed through spatial clustering based on a KD tree.

[0048] In the feature recognition stage, this embodiment employs an improved multi-scale attention network, PointNet++-A. PointNet++-A introduces a spatial attention mechanism into the feature aggregation layer of the traditional PointNet++, adaptively weighting the importance of local point cloud clusters. Subsequently, through joint optimization using backpropagation and the cross-entropy loss function, the neural network model outputs the corresponding part category label. Furthermore, during the training phase, this embodiment incorporates a category hierarchy constraint term into the loss function to maintain a reasonable distance between similar parts (e.g., single-acting cylinders and double-acting cylinders) in the feature space, thereby reducing misclassification caused by category similarity.

[0049] Step S804: Bind the part category to the two-dimensional legend block.

[0050] To achieve automated matching, this embodiment establishes a mapping table between part categories and two-dimensional legend blocks. This table is stored in a database in JSON format, and each part category corresponds to at least one standard legend template. The corresponding two-dimensional legend block is automatically retrieved based on the category label.

[0051] When a certain category does not have a standard legend in the rule base, this embodiment uses a legend similarity calculation module based on graph convolutional network (GCN) to perform similarity matching on the candidate legend set and select the most similar legend for dynamic binding.

[0052] Step S806: Analyze the air circuit schematic vector file to generate component connection relationship data.

[0053] Parse the gas path schematic vector file (such as DWG, DXF, etc.), extract the legend blocks, layers, variable objects, text objects and their connection relationships, and construct the initial graphic topology.

[0054] To overcome the connection misjudgment problem caused by line segment offset, breakage, or overlapping in traditional CAD drawings, this embodiment adopts an adaptive connection recognition algorithm based on geometric-semantic dual-domain fusion. This algorithm includes three stages:

[0055] First, calculate the spatial coordinates of the endpoints connecting each node and establish a spatial hash table. When the distance between the endpoints of any two nodes is less than a dynamic threshold ε (adaptively adjusted based on the global average connection length and layer density), they are identified as potential connections.

[0056] Next, using the part semantic embedding module fine-tuned by the BERT model, the part category and attribute text are converted into semantic vectors, and the cosine similarity between nodes is calculated. When the similarity is higher than a set threshold and the connection direction conforms to the pneumatic control logic (such as solenoid valve → cylinder), it is confirmed as a semantically valid connection.

[0057] Finally, the identified connectivity relationships are input into a lightweight graph neural network (GNN) for self-supervised training to learn airway connection patterns under different standards. Topology rule transfer and adaptive learning are achieved by minimizing the topology consistency loss function. For example, the identified connectivity relationships are organized into a high-dimensional feature vector set, including geometric distance, connection angle, semantic similarity, and historical connection probability. The lightweight graph neural network is trained through a self-supervised learning mechanism to learn airway connection patterns under different design styles. During training, the topology consistency loss function is minimized.

[0058]

[0059] in, The connection features predicted by the current model. This is a standard template connection feature. For the current topology, For reference topology, For balance coefficients, i and j represent the node (part) numbers in the pneumatic circuit diagram, such as solenoid valves, cylinders, suction cups, etc. This represents the set of edges that connect all nodes. Using the method described above, the model can automatically learn the structural patterns of different pneumatic diagram templates, achieving adaptive topology analysis across projects. Ultimately, the output component connection relationship data not only includes connected node pairs but also includes the confidence coefficient, semantic weight, connection type, and topological level information for each edge. This data is stored as a JSON structured file as the component connection relationship data.

[0060] Compared with the traditional geometric matching method, this embodiment can accurately restore logical connections even if there are broken lines, offsets or overlaps in the CAD drawing through adaptive threshold and semantic embedding mechanism; the output confidence coefficient can be used for visualization prompts in subsequent graphics rendering; through the graph neural network self-learning stage, it can automatically adapt to the gas path standards of different manufacturers and realize cross-project model migration.

[0061] Step S808: Generate an air path diagram based on the component connection relationship data.

[0062] First, based on the component connection relationship data, the logical relationships between components such as the air source, solenoid valve, cylinder, suction cup, and sensor are analyzed. Combined with the action group configuration data, the connection attributes and directions of each pair of legend blocks are determined. To ensure logical consistency in the layout, the solenoid valve is used as the central node, serving as the core of the connection topology. The cylinder and suction cup connected to the solenoid valve are distributed on either side of it, and the sensor is placed on the extension line of the cylinder's output end. The initial placement positions of each component legend are obtained through spatial topology conversion of the 3D model, ensuring a correspondence between the 2D legend layout and the 3D physical structure.

[0063] Next, connecting lines are generated between the various 2D legend blocks, forming connection topology data. Specifically, an initial layout framework is first created. Based on the action group relationships, the corresponding legend templates are called, and solenoid valves, cylinders, suction cups, sensors, etc., are placed in the drawing coordinate system according to logical hierarchy. Constraints are established for all parts, including: they must remain connected to each other without any breaks; the boundary rectangles of any two legend blocks must not overlap and must maintain a safe distance; the length of a single air path must not exceed a set threshold; cylinders within the same action group must remain horizontally aligned, etc.

[0064] Next, the initial layout is scanned, and the number of line intersections, local area density, and total pipeline length are calculated. When the number or density of intersections exceeds a preset threshold, a conflict is identified, and the layout optimization process is automatically initiated. During the layout optimization phase, layered arrangement and topology adjustment operations are performed. Solenoid valves are uniformly assigned to the first layer, cylinders and suction cups are distributed in the second layer, and sensors are located in the third layer. The left and right positions are automatically adjusted according to the relationship between the air inlet and outlet directions to minimize cross-layer connections. This layered distribution concentrates the main air routes between layers, reducing invalid intersections.

[0065] In each layer, the centroid of each node is calculated, and its coordinates are determined by the average position of the connected nodes in the upper layer. The nodes are then sorted according to the centroid results. When the sorting still results in intersections, a dynamic swapping strategy is adopted, that is, adjacent nodes are tried to swap positions, and the new arrangement is only retained when the number of intersections decreases.

[0066] After determining the node order, the optimal routing method is selected for each connection path. Straight-line connections are preferred, and when a straight line causes an intersection, a polyline connection is used instead, but the polyline has no more than two inflection points. If a local area still has high-density intersections, that area is extracted as a local subgraph, and adaptive topology association and local iterative optimization are performed. Specifically, the entire current layout is divided into multiple grid cells, and the intersection density of each grid cell is calculated; if the density of a cell exceeds twice the global average, it is identified as a conflict hotspot. For hotspot areas, multiple candidate layouts are generated, and new feasible layout schemes are generated as a set of candidate solutions by adjusting node positions, inserting virtual inflection points, or exchanging the positions of nodes in the same layer. Each candidate solution is evaluated based on an adaptive cost function. In some embodiments, the adaptive cost function can be generated based on the number of intersections, total path length, total number of polyline inflection points, global average connection density, and local average connection density.

[0067]

[0068] Where C is the adaptive cost of the candidate layout. The number of intersections of the connecting lines. For the density of lines connecting local areas, The global average connection density. This is the total path length. This represents the total number of inflection points on the broken line. This serves as a reference threshold for the broken line graph. This is a global weight that can be dynamically adjusted. These are local weighting coefficients. In the early stages of optimization, the adaptive cost function reduces the weight of the number of intersections to minimize intersections and quickly eliminate major conflicts. In the middle stages, it gradually increases the weights of path smoothness and length to increase the total path length. In the later stages, it reduces the weight of the number of inflection points on the broken line and provides a weight for local density to optimize layout uniformity and overall aesthetics. If the cost of a candidate solution is less than 20% of the initial cost, it is directly accepted; otherwise, it is determined according to the probability function.

[0069]

[0070] The decision is made regarding whether to retain a candidate solution. In other words, if the adaptive cost of a candidate solution is lower than a preset cost threshold (20% of the initial cost), the candidate solution is retained; otherwise, the probability value of the candidate solution is calculated, and if the probability value is higher than a preset probability threshold (e.g., 0.3), the candidate solution is retained; if the probability value is lower than 0.3, the candidate solution is discarded. Here, T is the temperature parameter. Represents the local conflict factor. This represents the cost function. Using the above probability function, high-conflict regions... A larger value allows for the acceptance of suboptimal solutions during local searches to escape local minima. Finally, the optimal candidate solution is determined from the retained candidate solutions based on the adaptive cost value, and the connection topology data is optimized based on the optimal candidate solution.

[0071] Next, based on the generated connection topology data, feature attributes are added to the connection lines and each two-dimensional legend block. Feature attributes include parameters such as line type, color, font, and font size. For example, high-pressure gas paths are represented by solid red lines, low-pressure gas paths by thin green lines, control signal lines by dashed blue lines, and the font size is automatically adjusted proportionally. These feature attributes are not only used for graphic rendering but also serve as attribute labels for subsequent gas path control systems to support automatic identification and aerodynamic simulation.

[0072] Finally, based on the aforementioned features, rendering is performed on all 2D legend blocks and their connecting lines to generate the final gas path diagram. During rendering, lines are displayed as thick solid lines when the connections are determined by high-confidence data; when the connections are obtained through fuzzy matching inference, they are presented as light-colored dashed lines. This allows designers to intuitively identify the reliability of the AI-generated results. The final gas path diagram is output in vector format and can be exported as DWG, DXF, or SVG files.

[0073] In summary, this invention, by organically combining point cloud recognition, legend binding, and adaptive topology correlation analysis algorithms, achieves fully automated generation of gas path diagrams from three-dimensional structures. In particular, it can adaptively identify and correct connection relationships in complex, multi-layered gas path structures, providing a tool for intelligent gas path design.

[0074] This application also provides an AI-based device for automatically designing gas path diagrams, such as... Figure 9 As shown, it includes: an identification module 92, configured to generate a key point cloud of the 3D model based on feature points of the 3D model using a point cloud processing algorithm, and to identify the part category based on the key point cloud using a neural network model; a binding module 94, configured to bind the identified part category to a preset 2D legend block to obtain part legend binding data; a connection determination module 96, configured to parse the gas path schematic vector file, extract the graphic metadata therein, and generate part connection relationship data based on the part legend binding data and the extracted graphic metadata; and a generation module 98, configured to connect the corresponding 2D legend blocks and add feature attributes based on the part connection relationship data to generate a gas path diagram.

[0075] It should be noted that the AI-based automatic gas path diagram design device provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the AI-based automatic gas path diagram design device and the AI-based automatic gas path diagram design method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0076] Figure 10 A schematic diagram of a computer device suitable for implementing embodiments of the present disclosure is shown. It should be noted that... Figure 10 The computer device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0077] like Figure 10 As shown, the computer device includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage section 1008 into a random access memory (RAM) 1003. The RAM 1003 also stores various programs and data required for system operation. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0078] The following components are connected to I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to I / O interface 1005 as needed. A removable medium 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 1010 as needed so that computer programs read from it can be installed into storage section 1008 as needed.

[0079] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for automatically designing gas path diagrams based on AI, characterized in that, include: Based on the feature points of the 3D model, a point cloud of key points of the 3D model is generated using a point cloud processing algorithm, and based on the point cloud of key points, a neural network model is used to identify the part category. The identified part categories are bound to the corresponding two-dimensional legend blocks to obtain part legend binding data; Parse the gas path schematic vector file, extract the graphic metadata, and generate part connection relationship data based on the part legend binding data and the extracted graphic metadata; Based on the component connection relationship data, the corresponding two-dimensional legend blocks are connected and feature attributes are added to generate an air path diagram; Specifically, based on the feature points of the 3D model, a point cloud processing algorithm is used to generate a key point cloud of the 3D model, and based on the key point cloud, a neural network model is used to identify the part category, including: The feature points of the three-dimensional model are extracted, including: center of gravity, maximum contour point, protective cover mounting point, pressure arm connection point, air inlet and outlet mounting point, cylinder assembly point, and pressure arm rotation point. Using the centroid as a reference point, the feature points are combined using the point cloud processing algorithm to form the key point cloud of the three-dimensional model; Based on the key point cloud, feature recognition is performed using the neural network model to obtain the spatial structure data of the three-dimensional model, and based on the spatial structure data, the part category of the three-dimensional model is determined. Specifically, the identified part categories are bound to their corresponding two-dimensional legend blocks to obtain part legend binding data, including: The part categories are matched with the mapping table to determine the corresponding two-dimensional legend blocks, wherein the mapping table stores the mapping relationship between part categories and two-dimensional legend blocks; Based on the part category and the corresponding two-dimensional legend block, a binding relationship between the part category and the two-dimensional legend block is generated, which serves as the part legend binding data.

2. The method according to claim 1, characterized in that, The gas path schematic vector file is parsed, and its graphic metadata is extracted. Based on the component legend binding data and the extracted graphic metadata, component connection relationship data is generated, including: The gas path schematic vector file is parsed to extract the graphic metadata, which includes: legend blocks, layers, variable objects, connection relationships between different legend blocks, and text objects. Based on the layer, determine the connection point information between the legend blocks; based on the variable object, determine the annotation parameters related to the legend block; based on the text object, determine the text features associated with the legend block or the variable object. Based on the part legend binding data, the connection point information, the annotation parameters, the text features, and the connection relationships between different legend blocks, the part connection relationship data is generated.

3. The method according to claim 1, characterized in that, Based on the component connection relationship data, the corresponding two-dimensional legend blocks are connected and feature attributes are added to generate a gas path diagram, including: Based on the component connection relationship data, determine the line connection method between the corresponding two-dimensional legend blocks; Connecting lines are generated between the two-dimensional legend blocks, and connection topology data is formed based on the connection method; Based on the connection topology data, feature attributes are added to the connection lines and the corresponding two-dimensional legend blocks, wherein the feature attributes include at least one of the following: line type, color, font, and font size; Based on the aforementioned feature attributes, the corresponding two-dimensional legend block and the connecting lines are rendered to generate the gas path diagram.

4. The method according to claim 3, characterized in that, After forming connection topology data based on the connection method, the method further includes: The current layout corresponding to the connection topology data is divided into multiple grid cells, the line intersection density of the multiple grid cells is calculated, and conflict hotspot areas are determined based on the line intersection density. For the conflict hotspot area, a candidate solution set is generated by adjusting the node position, inserting virtual inflection points, or exchanging the positions of nodes at the same level, and the adaptive cost value of each candidate solution in the candidate solution set is calculated. Based on the adaptive cost, an optimal candidate solution is determined from the candidate solutions, and the connection topology data is optimized based on the optimal candidate solution.

5. An AI-based device for automatically designing gas path diagrams, characterized in that, include: The recognition module is configured to generate a key point cloud of the 3D model based on feature points of the 3D model using a point cloud processing algorithm, and to perform part category recognition based on the key point cloud using a neural network model. The binding module is configured to bind the identified part categories to the corresponding two-dimensional legend blocks to obtain part legend binding data; The connection determination module is configured to parse the gas path schematic vector file, extract the graphic metadata therein, and generate part connection relationship data based on the part legend binding data and the extracted graphic metadata; The generation module is configured to connect the corresponding two-dimensional legend blocks and add feature attributes based on the part connection relationship data to generate an air path diagram; The recognition module is further configured to: extract the feature points of the three-dimensional model, wherein the feature points include: center of gravity, maximum contour point, protective cover mounting point, pressure arm connection point, air inlet / outlet mounting point, cylinder assembly point, and pressure arm rotation point; using the center of gravity as a reference point, combine the feature points using the point cloud processing algorithm to form the key point cloud of the three-dimensional model; based on the key point cloud, use the neural network model to perform feature recognition to obtain the spatial structure data of the three-dimensional model, and based on the spatial structure data, determine the part category of the three-dimensional model; The binding module is further configured to: match the part category with the mapping relationship table to determine the corresponding two-dimensional legend block, wherein the mapping relationship table stores the mapping relationship between part categories and two-dimensional legend blocks; and generate a binding comparison relationship between part categories and two-dimensional legend blocks based on the part category and the corresponding two-dimensional legend block, as the part legend binding data.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 4.

7. A computer device, characterized in that, include: Memory and processor The memory stores computer programs; The processor is configured to execute a computer program stored in the memory, wherein when the computer program is executed, the processor performs the method according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images