Cable tray selection method and device, electronic equipment and storage medium

Abstract

The present application relates to the technical field of intelligent modeling, and discloses a cable tray selection method and device, electronic equipment and a storage medium. The method comprises the following steps: obtaining a task description text corresponding to a cable tray laying task, the task description text comprising a cable list corresponding to the cable tray laying task; determining a total outer diameter cross-sectional area of the cable to be laid based on cable type and quantity information of the cable to be laid obtained by analyzing the cable list; determining a minimum theoretical cross-sectional area of the required tray based on the total outer diameter cross-sectional area; determining a recommended tray type corresponding to the corresponding type of cable from a pre-constructed knowledge graph according to the cable type required to be accommodated by the tray to be laid; and selecting a target specification tray from the pre-constructed knowledge graph data based on the minimum theoretical cross-sectional area and the type information of the recommended tray, wherein the effective cross-sectional area of the target specification tray is greater than and closest to the minimum theoretical cross-sectional area.

Description

Technical Field

[0001] This invention relates to the field of intelligent modeling technology, specifically to a cable tray selection method, device, electronic equipment, and storage medium. Background Technology

[0002] The cable tray system in a nuclear power plant is the backbone laying channel for power, control, instrumentation, and safety-related cables, and its design is extremely complex. First, it carries a wide variety of cables, including Class 1E safety cables, medium-voltage power cables, control cables, and instrumentation cables, each with different requirements for laying spacing, isolation, fire protection, and seismic resistance. Second, the route environment is complex, requiring passage through containment buildings, electrical rooms, auxiliary rooms, and other rooms, while avoiding high-temperature pipelines, high-radiation areas, vibrating equipment, and various process pipelines. Finally, the regulatory system is extensive, requiring simultaneous compliance with multiple dimensions of engineering design specifications, including electrical safety, fire protection, seismic assessment, electromagnetic compatibility, and maintainability, often with trade-offs involved.

[0003] In related technologies, the selection of nuclear power cable trays mainly relies on manual methods, which results in low design efficiency, high labor costs, and selection results that depend on personal experience, leading to poor consistency and insufficient intelligence. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a cable tray selection method, device, electronic device and storage medium to solve the problems that the selection of nuclear power cable trays mainly relies on manual labor, resulting in low design efficiency, high labor costs and selection results that depend on personal experience, leading to poor consistency and insufficient intelligence.

[0005] According to a first aspect, embodiments of the present invention provide a cable tray selection method, comprising: obtaining a task description text corresponding to a cable tray laying task, the task description text including a cable list corresponding to the cable tray laying task, the cable list including cable type, cable specification, and quantity information to be accommodated by the tray to be laid; determining the total outer diameter cross-sectional area of ​​the cables to be laid based on the cable specification and quantity information to be accommodated by the tray to be laid obtained by parsing the cable list; determining the minimum theoretical cross-sectional area of ​​the required tray based on the total outer diameter cross-sectional area; determining a recommended tray type corresponding to the corresponding type of cable from a pre-constructed knowledge graph according to the parsed cable type to be accommodated by the tray to be laid; and selecting a target specification tray from the pre-constructed knowledge graph data based on the minimum theoretical cross-sectional area and the type information of the recommended tray, wherein the effective cross-sectional area of ​​the target specification tray is greater than and closest to the minimum theoretical cross-sectional area. According to a second aspect, embodiments of the present invention provide a cable tray selection device, comprising: a first acquisition module, configured to acquire task description text corresponding to a cable tray laying task, the task description text including a cable list corresponding to the cable tray laying task, the cable list including cable type, cable specification, and quantity information to be accommodated by the tray to be laid; a first determination module, configured to determine the total outer diameter cross-sectional area of ​​the cable to be laid based on the cable specification and quantity information to be accommodated by the tray to be laid obtained by parsing the cable list; a second determination module, configured to determine the minimum theoretical cross-sectional area of ​​the required tray based on the total outer diameter cross-sectional area; a third determination module, configured to determine the recommended tray type corresponding to the corresponding type of cable from a pre-constructed knowledge graph based on the parsed cable type to be accommodated by the tray to be laid; and a first filtering module, configured to filter out target specification trays from the pre-constructed knowledge graph data based on the minimum theoretical cross-sectional area and the type information of the recommended trays, wherein the effective cross-sectional area of ​​the target specification tray is greater than and closest to the minimum theoretical cross-sectional area. According to a third aspect, an embodiment of the present invention provides an electronic device, including: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the cable tray selection method described in the first aspect or any optional embodiment of the first aspect.

[0006] According to a fourth aspect, embodiments of the present invention provide a computer-readable storage medium storing computer instructions for causing a computer to perform the cable tray selection method described in the first aspect or any optional embodiment of the first aspect.

[0007] According to a fifth aspect, embodiments of the present invention provide a computer program product, including computer instructions for causing a computer to execute the cable tray selection method of the first aspect or any corresponding embodiment described above.

[0008] The cable tray selection method provided in this invention obtains the task description text of the cable list corresponding to the cable tray laying task. Based on the cable specifications and quantity information of the cables to be laid contained in the cable list, the total outer diameter cross-sectional area of ​​the cables to be laid is determined. Then, based on the total outer diameter cross-sectional area, the minimum theoretical cross-sectional area of ​​the required tray is determined. According to the parsed cable types to be laid, the recommended tray types corresponding to the corresponding cable types are determined from a pre-built knowledge graph. Based on the minimum theoretical cross-sectional area and the type information of the recommended trays, the target specification trays with effective cross-sectional areas greater than and closest to the minimum theoretical cross-sectional area are selected from the pre-built knowledge graph data. By intelligently parsing the cable list to obtain the corresponding cable parameters to determine the minimum theoretical cross-sectional area of ​​the trays required for laying the cables, and determining the recommended tray types corresponding to the corresponding cable types based on the knowledge graph, and combining the specification information of the recommended type trays to determine the target specification trays with effective cross-sectional areas greater than and closest to the minimum theoretical cross-sectional area, intelligent tray selection is achieved while improving design efficiency and design consistency. Attached Figure Description

[0009] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0010] Figure 1 This is a flowchart of a cable tray selection method according to an embodiment of the present invention; Figure 2 This is a structural block diagram of a cable tray selection device according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0012] According to an embodiment of the present invention, an embodiment of a cable tray selection method 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.

[0013] This embodiment provides a cable tray selection method, which can be used by an intelligent modeling system to execute the method. This intelligent modeling system can act as a server to issue modeling instructions. Figure 1 This is a flowchart of a cable tray selection method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps: 101. Obtain the task description text corresponding to the cable tray laying task. The task description text includes the cable list corresponding to the cable tray laying task. The cable list includes the cable type, cable specifications and quantity information to be accommodated by the tray to be laid.

[0014] For example, the task description text is used to provide descriptive information related to the cable laying task to be performed. In this embodiment of the application, the cable list included in the task description text can be uploaded together with the cable tray laying task. The cable type information included in the cable list can be pre-determined according to the scenario of the cable to be laid. For example, if the scenario of the cable to be laid requires power cables and control cables, then the cable type information in the cable list is power cables and control cables. At the same time, the cable list also records the quantity of the corresponding type of cable (e.g., 3 power cables and 9 control cables are required) and specification information (e.g., cable diameter information). The cable list is usually a structured table and can contain information such as cable number, type, specification, length, start point, end point, rated current, voltage level, and safety level. The corresponding parameter information of the cable to be laid can be clearly obtained through the cable list.

[0015] 102. Based on the cable specifications and quantity information to be accommodated in the laying tray obtained by parsing the cable list, the total outer diameter cross-sectional area of ​​the cables to be laid is determined.

[0016] For example, in an embodiment of this application, the total outer diameter cross-sectional area can be calculated according to the following formula:

[0017] in, Let i be the number of the i-th type of cable. Let be the outer diameter of the i-th type of cable. The estimated value for the reserved expansion area is not limited in the embodiments of this application. Those skilled in the art can set it according to actual needs, such as taking 20% ​​of the actual cable outer diameter area as the estimated value for the reserved expansion area; n is the type and quantity of cables to be laid. 103. Determine the minimum theoretical cross-sectional area of ​​the required tray based on the total outer diameter cross-sectional area.

[0018] By way of example, embodiments of this application determine the minimum theoretical cross-sectional area of ​​the required pallet according to the following. :

[0019] 104. Based on the cable types that the tray to be laid needs to accommodate, as obtained from the analysis, determine the recommended tray type corresponding to the corresponding cable type from the pre-built knowledge graph.

[0020] For example, a knowledge graph is pre-constructed based on the target core entities and the relationships between entities in the field of cable laying. In this embodiment, the target core entities include: cable entities, tray entities, and standard and specification entities. Specifically, the attributes of cable entities may include cable type, cross-sectional area, outer diameter, weight, rated current, insulation type, voltage rating, safety level, etc.; the attributes of tray entities may include width (W), height (H), material (e.g., steel, aluminum, fiberglass), type (e.g., ladder type, trough type, tray type), protection level (IP), fire rating, weight per unit length, load-bearing capacity curve, heat dissipation coefficient, and reference current carrying capacity, etc.; standard and specification entities may include technical clauses corresponding to various cable laying operations; entity relationships may include: "Recommended tray type X for cable A", "Allowable fill rate η for tray specification S", "Specification C requires cables with safety level K1 to use metal-enclosed trays", and other similar relationships. By deeply integrating electrical engineering calculations with specification clause reasoning in the construction of this knowledge graph, the safety and economy of cable laying design can be ensured. Based on the analysis, the type of cable to be laid is obtained, and the recommended tray type corresponding to the corresponding cable type is obtained by querying the pre-built knowledge graph.

[0021] 105. Based on the minimum theoretical cross-sectional area and the recommended pallet type information, select target specification pallets from the pre-built knowledge graph data. The effective cross-sectional area of ​​the target specification pallets is greater than and closest to the minimum theoretical cross-sectional area.

[0022] For example, the recommended pallet type may include multiple specifications due to differences in parameters such as width and height. The effective cross-sectional area of ​​the recommended pallet of different specifications is different. The effective cross-sectional area of ​​the various specifications corresponding to the recommended pallet type can be found from a pre-built knowledge graph. Then, based on the determined minimum theoretical cross-sectional area, the pallet that is larger than the minimum theoretical cross-sectional area and closest to the minimum theoretical cross-sectional area is determined as the target specification pallet. For example, if the minimum theoretical cross-sectional area is 85000 mm², the pallet is selected as the target specification pallet. 2 The recommended pallet types with effective cross-sectional areas greater than this minimum theoretical cross-sectional area are 90000 mm². 2 and 91000mm 2 Then choose 90000mm 2 The corresponding pallet is selected as the target specification pallet for this type, ensuring that the selected target specification pallet occupies the minimum three-dimensional space while meeting cable laying requirements. For example, if the final selected target specification pallet is: "a steel trough type pallet with dimensions of 600mm(W) x 150mm(H)", then the required laying information, such as the protection level (e.g., IP55) and fire resistance level (F120), can be further determined based on a knowledge graph.

[0023] The cable tray selection method provided in this embodiment intelligently analyzes the cable list to obtain the corresponding cable parameters, determines the minimum theoretical cross-sectional area of ​​the tray required for laying the cable, and determines the recommended tray type corresponding to the corresponding type of cable based on a knowledge graph. Combining the specification information of the recommended type of tray, the method determines the target specification tray with an effective cross-sectional area that is greater than and closest to the minimum theoretical cross-sectional area, thereby achieving intelligent tray selection while improving design efficiency and design consistency.

[0024] As an optional implementation of this invention, the task description text further includes a laying scenario description text and a laying operation precautions description text. In this embodiment, the laying scenario description text can be obtained by the user through text input, and may include scenario location information and laying position information. The laying operation precautions description text may include anti-collision information, interval information, etc. For example, the task description text received by natural language instructions is: "In room EL-102 of the electrical workshop, lay a tray from the low-voltage distribution cabinet MCC-A-01 (elevation +10.500m) to the emergency lighting distribution box ELB-05 (elevation +3.200m) located in the northwest corner of the room. The tray needs to accommodate all 12 cables in the cable list 'List-C-202', including 3 power cables and 9 control cables. Path requirements: avoid the main air conditioning duct in the center of the room, maintain a distance of at least 300mm from the existing communication tray, and consider the expansion capacity of adding 5 similar cables in the future." The method also includes: The task description data is subjected to target entity and entity relationship extraction operations. For example, a domain fine-tuning LLM can be used as the parsing hub, and target entity identification and entity relationship extraction can be performed through prompt word engineering. For example, key entities such as "starting device", "ending device", "cable list identifier", "avoidance object", "spacing requirement", "expansion requirement" and their relationships can be identified from natural language instructions.

[0025] Based on the task description text, the technical specification document corresponding to the cable tray laying operation is parsed to obtain the operation specification data. For example, the technical specification document is generally an unstructured PDF or Word document, covering electrical design specifications, fire protection requirements, seismic assessment criteria, material standards, installation requirements, etc. Regarding the association and extraction of relevant specification clauses in the technical specification document, the vertical model extracts specific clauses related to the current cable laying task through question-and-answer and summarization methods. For example, regarding the requirement of "distance from communication trays," the vertical model locates and extracts the specific clause from the electrical specifications: "When cable trays of different voltage levels or types are laid in parallel, their spacing should not be less than 300mm; this can be appropriately reduced when there is a fireproof board for isolation."

[0026] Obtain the three-dimensional spatial information of the cable tray laying scenario; for example, the corresponding spatial information and coordinates, including room boundaries, main equipment outlines, and existing pipes and cable trays, can be extracted from the existing three-dimensional model corresponding to the laying scenario through API to construct a data map.

[0027] The extracted information can be integrated with the cable inventory data to generate a unified, structured JSON output, which serves as the input source for all subsequent modules. For example, the cable tray laying task "TRAY-EL-102-001" aims to lay a cable tray from distribution cabinet "MCC-A-01" to distribution box "ELB-05". The task needs to accommodate three 185mm² cables. 2 Main wire core + 1 95mm 2 The power cable has a neutral / grounded core (each with a rated current of 350A) and contains 24 cores with a cross-sectional area of ​​2.5mm². 2The control cables with independent cores (each rated at 10A) all come from cable list "C-202", and future expansion space for 5 more similar control cables is reserved. Regarding laying path constraints, crossing "air conditioning main ducts" is strictly prohibited; flexibility requires maintaining a distance of at least 0.3 meters from "communication trays"; "exposed laying" and "along walls or ceilings" are preferred. The path starts at the bottom outlet of "MCC-A-01" (approximately represented by coordinates [x1, y1, z1]) and ends at the top inlet of "ELB-05" (approximately represented by coordinates [x2, y2, z2]). Furthermore, two key specifications were extracted from the technical specifications: first, the fill rate of power cable trays should not exceed 50%, and that of control cables should not exceed 40%; second, when crossing fire compartments, the trays must be sealed with fire-resistant sealing material at the crossing point.

[0028] The structured output example in this application is as follows: json { "task_meta": { "task_id": "TRAY-EL-102-001", "description": "MCC-A-01 to ELB-05 Cable Tray Laying" }, "cable_bundle": { "source_list_id": "List-C-202", "cables": [ {"id": "PWR-001", "type": "power", "spec": "3x185+95", "rated_current": 350, "qty": 3}, {"id": "CTL-001", "type": "control", "spec": "24x2.5", "rated_current":10, "qty": 9}, ], "future_expansion": {"cable_count": 5, "type_similar_to": "control"} }, "routing_constraints": { "hard_avoidance": ["Air conditioning main duct"], "soft_avoidance": [ {"object_type": "communication tray", "min_distance": 0.3, "unit": "m"} ], "preference": ["open application", "along the wall or ceiling"], }, "end_points": { "start": {"component_id": "MCC-A-01", "interface": "bottom line out", "coordinate_approx": [x1, y1, z1]}, "end": {"component_id": "ELB-05", "interface": "top entry line", "coordinate_approx": [x2, y2, z2]}, }, "extracted_codes": [ {"code_id": "Electrical Code-5.2.1", "content": "Cable tray filling rate: power cables should not exceed 50%, control cables should not exceed 40%."}, {"code_id": "Fire Protection Code-3.4.5", "content": "Cable trays that pass through fire compartments shall be sealed with fire-resistant sealing material at the point of entry."} ]; }

[0029] The extraction results corresponding to the task description data, the operation specification data, and the three-dimensional spatial information are subjected to feature encoding processing to obtain the laying intention vector expression corresponding to the cable tray laying task.

[0030] For example, the extracted structured description information, work specification data, and three-dimensional spatial information are processed by feature encoding and then embedded together into a high-dimensional design intent vector. middle.

[0031] ; in, This represents vector concatenation and feature fusion operations. It is the encoder part of the large language model. Encapsulating all semantic and constraint information of the current laying task, it serves as the core input driving subsequent intelligent decisions. It receives and integrates natural language design instructions from users, electronic cable lists, multiple relevant technical specification documents, and three-dimensional spatial context information about building structures and process equipment. Utilizing an industry-vertical model fine-tuned for nuclear power electrical fields, it extracts key entities, relationships, and constraints from unstructured natural language and specification texts, and associates structured data such as cable lists with them, outputting a standardized, structured laying task description and its associated composite constraint rule base. The structured JSON output, extracted specification clause summaries, and spatial context feature encodings are all embedded into a high-dimensional design intent vector, serving as the core input driving subsequent intelligent decisions.

[0032] As an optional embodiment of the present invention, the method further includes: discretizing the three-dimensional building space corresponding to the cable tray laying scenario into a uniform three-dimensional voxel grid; inputting the laying intention vector expression into a pre-trained virtual route generation model to obtain multiple virtual routes; and determining the lowest cost path between the starting point and the ending point based on the cost of the three-dimensional voxel grid on each virtual route, and using the lowest cost path as the planned target path.

[0033] For example, the three-dimensional architectural space is discretized into a uniform three-dimensional voxel mesh. Each voxel Link a basic cost And a series of soft-constraint cost increments.

[0034] The total cost per voxel is determined by combining the basic cost with multiple soft-constraint cost increments. As shown in the following formula:

[0035] in: The basic cost of unobstructed passage can be set to "1", meaning that when the route passes through 100 voxels, the basic passage cost is "100". It is the set of all soft constraints that need to be considered. In the embodiments of this application, the soft constraints can be collision constraints, heat source constraints, radiation zone avoidance constraints, etc. The embodiments of this application do not limit the specific type of soft constraints. It is a voxel Quantify the cost of violating the m-th type of soft constraint; This refers to the weight of the m-th constraint. This weight can be set according to the importance level of each soft constraint for a specific cable laying scenario. For example, if the primary consideration for cable laying is heat source constraint, then the weight corresponding to the heat source constraint is set higher; if the secondary consideration is collision constraint, then the weight corresponding to the collision constraint is set relatively lower, to ensure that the planned route prioritizes meeting constraints with higher importance levels. This application does not limit the specific weight values; those skilled in the art can set them according to actual needs. Regarding the costs corresponding to different soft constraints, those skilled in the art can set them according to actual conditions. This application takes heat source constraint and collision constraint as examples, and their corresponding constraint costs can be shown in the table below:

[0036] By inputting the laying intention vector into a pre-trained virtual route generation model, the starting point, ending point, and spatial layout of the cable tray laying task can be analyzed based on the task description text of the large language model. For example, for a laying task scenario obtained by parsing the large language model as "the starting point is in the southeast corner of the room, the ending point is in the northwest corner, and there is a large air duct blocking the way in between," the pre-trained virtual route generation model, combined with the guidance of the large language model and the input laying intention vector, can generate multiple virtual routes that meet the requirements, such as "first rise vertically from the starting point to the ceiling space, then cross horizontally to the west to the top of the ending point, and then descend vertically to the ending point."

[0037] The improved A* algorithm (a classic heuristic optimal path search algorithm) is used, and its evaluation function... In the embodiments of this application, the Not geometric distance, but distance from the starting point to the node. Accumulation of voxels The cost is shown in the following formula. The algorithm uses a dynamic cost map. Search for the lowest cost path connecting the origin, virtual waypoints, and destination. It is a classic heuristic function, using Euclidean distance.

[0038]

[0039] Based on the total cumulative cost of the three-dimensional voxel mesh on each virtual route obtained through search calculation, the lowest cost path between the starting point and the ending point is determined, and this lowest cost path is used as the planned target path.

[0040] As an optional implementation of this invention, the method further includes: The target path is sampled according to a preset step size to obtain multiple sampling points; for example, the planned target path in continuous space can be... Sampling is performed at intervals according to the target step size to obtain multiple sampling points, and the target path is then... Parameterized according to the time series before and after the sampling points ,,in, These are the coordinates of the corresponding sampling points.

[0041] The direction change of the target path is determined based on the coordinates of each sampling point; the corresponding angle of the connector is determined based on the direction change. For example, the target path is identified based on the coordinates of the corresponding sampling points, following the preceding and following relationships of the sampling points. The direction of change; specifically, when there is a straight line between two adjacent sampling points, for the straight line segment, a "straight-through tray" component is generated, with a length of , direction vector For each adjacent sampling point, a turning point is determined based on its coordinates. For the turning point, the entrance direction is calculated. and export direction Then the turning angle Then, based on the plane where the turn is located, calculations are performed. Determine the normal vector to identify whether it is a horizontal bend or a vertical bend. Then, select the standard component with the closest angle (e.g., 30°, 45°, 90°) from the standard bend library. If the same coordinate point is found to be in multiple paths, it contains a branch point. Insert a tee or cross component, the direction of which is determined by the direction of the branch path.

[0042] The location of the support points on the target path is determined based on the load per meter of the target type of pallet, the maximum allowable span, and the target support reinforcement points. For example, support design is a crucial aspect of ensuring the long-term safe and reliable operation of the cable tray system. In this embodiment, the load per meter of tray... The calculation method for (N / m) is shown in the following formula:

[0043] in, It is the acceleration due to gravity. The weight per unit length of pallet. This refers to the total weight of the cable per unit length.

[0044] The maximum allowable span can be determined using a large language model based on pallet specifications and load. Based on the seismic resistance category and support type, the maximum allowable span can be obtained by querying the "Support Span Table" stored in the knowledge graph. .

[0045] Initial support points can be laid out based on the load per meter and the maximum allowable span, specifically along the target path. Starting from the starting point, positions are arranged using support points. (generally Support points are arranged at intervals.

[0046] Based on the identification of the target path, target support reinforcement points are forcibly added at the target location, with a spacing of less than [missing information]. In this embodiment of the application, the location of the forced addition of target support reinforcement points may include: both sides of the center point of each non-straight-through component such as elbows, tees, and crosses, and at a distance from the center of the component. Locations where the slope of the path changes significantly, and locations where it intersects with other pipelines or requires rigid fixation.

[0047] Based on the load conditions between adjacent support points, the support span, the location of the support points, and seismic requirements, the model of the support component corresponding to each support point is determined. For example, based on the load... Based on the support span, installation location, and seismic requirements, a suitable support model is assigned to each support point from the standard support library, taking into account the performance parameters of the corresponding support components. Specifically, the support model can be selected from the standard support library using a pre-trained large model.

[0048] As an optional implementation of this application, the method further includes: sending modeling instruction information to a target protocol client plugin running in 3D modeling software, the modeling instruction information including the determined attribute information of the target tray, target path information, connector information, support point layout information, and support model information, so that the target protocol client plugin calls the 3D modeling software to perform modeling operations based on the modeling instruction information; obtaining modeling result-related information; and when the modeling result-related information contains error information, adjusting the corresponding modeling data according to the error information.

[0049] Exemplary, this application embodiment does not limit the type of 3D modeling software, as long as it can be equipped with a corresponding protocol type plugin and meets the modeling requirements. In this application embodiment, the target protocol is selected as the MCP protocol (Model Coordination Protocol). The MCP protocol is a standardized protocol in the style of a language server protocol, which allows external tools and 3D design software to communicate in a structured manner via JSON-RPC. In this application embodiment, the intelligent modeling system that performs cable tray laying modeling is used as the MCP server, and the plugin installed in the 3D design software is used as the MCP client plugin. The instructions are sent to the MCP client plugin running inside the 3D design software through the established MCP communication link. The plugin parses the instructions and calls the native application programming interface of the 3D design software to automatically create, locate, and assemble all tray components and support components in the software scene, build an accurate 3D model in real time, and feed the operation results back to the intelligent modeling system.

[0050] Specifically, the intelligent modeling system converts the design data contained in the modeling instruction information into a set of atomic operation instructions, for example: [ {"method": "create_tray_run", "params": {"run_id": "T1", "spec": "600x150", "material": "Steel", "type": "Ladder"}}, {"method": "add_straight", "params": {"run_id": "T1", "length": 2500,"start": [1000,2000,3500], "end": [3500,2000,3500]}}, {"method": "add_horizontal_elbow", "params": {"run_id": "T1", "angle": 90, "radius": 900, "center": [3500,2000,3500]}}, {"method": "create_support", "params": {"type": "Hanger", "location":[1200,2000,3450], "size": "M12_Double", "attached_to": "T1"}}, {"method": "assign_cables", "params": {"run_id": "T1", "cable_ids":["PWR-001", "CTL-001", ...]}}, {"method": "set_parameter", "params": {"object_id": "T1", "parameter": "FireRating", "value": "F120"}}, ].

[0051] The meanings of the above atomic operation instructions are as follows: Create a pallet trunk line: Create a new pallet trunk line with the code "T1", with specifications of 600mm wide and 150mm high, made of steel, and of type ladder pallet.

[0052] Add a straight section: Add a 2500mm long straight tray to the T1 trunk line, with the starting coordinates at (1000,2000,3500) and the ending coordinates at (3500,2000,3500), that is, lay it horizontally along the positive X-axis direction.

[0053] Add a horizontal bend: Add a 90° horizontal bend at the end of the previous straight section (3500, 2000, 3500). The centerline radius of the bend is 900mm, which will change the direction of the pallet.

[0054] Create a support hanger: Create a hanger-type support for the T1 trunk line at location (1200,2000,3450), with specifications of double M12 hangers, for securing the pallet.

[0055] Cable distribution: Associate the two cables (numbered PWR-001 and CTL-001) with the T1 tray and record their affiliation for subsequent fill rate calculation and material statistics.

[0056] Setting parameters: Set the fire rating parameter for the T1 pallet to "F120", which means a fire resistance time of 120 minutes.

[0057] The MCP client plugin receives the corresponding modeling instructions and calls the API of the 3D modeling software to execute the modeling operation. The corresponding modeling execution results and any error information can be returned to the server via the MCP protocol. The entire intelligent modeling system, equipped with Domain Fine-tuning Large Model (LLM), completes the entire process of input parsing, tray selection, path planning, support design, MCP instruction generation, and compliance verification optimization. Simultaneously, this intelligent modeling system can perform fault-tolerant processing or design adjustments based on feedback. The intelligent modeling system, acting as an agent, receives modeling anomaly information from the MCP client plugin. Its built-in large language model identifies the fault type. For minor parameter errors, the agent directly corrects the command parameters for fault-tolerant re-issuance. For design flaws, it retraces the tray selection, path, or support design stages for recalculation, updates the design data, and generates new modeling commands. Specifically, the client sends the modeling failure code, failure location, and error reason back to the server-side agent via JSON-RPC. The agent uses LLM to parse the error type and handles it in two ways: fault-tolerant handling (minor local corrections, without changing the tray selection / overall path) involves only fine-tuning the command parameters and re-issuing the MCP commands for secondary modeling; design adjustment (major errors) involves retracing upstream design steps for recalculation, recalculating the selection, path, and support layout, updating the modeling data across the entire chain, and generating new commands. As an optional implementation of this application, the method further includes: querying parameter information of the generated model through a target protocol; obtaining key modeling data based on the parameter information, wherein the key modeling data is used to verify the compliance of the generated model; generating a model self-inspection report based on the key modeling data; comparing the model self-inspection report with data related to the original cable laying requirements; issuing an alarm for inconsistent comparison results and initiating a local optimization procedure.

[0058] For example, the intelligent modeling system queries the parameter information of the generated model through a target protocol (such as TCP protocol), and obtains key modeling data based on the extracted model parameter information. In this embodiment, the key modeling data may include, but is not limited to, the following data, which can be set by those skilled in the art according to actual compliance inspection needs: (1) Actual fill rate: ,in, This refers to the total outer cross-sectional area of ​​the cable to be laid. The effective cross-sectional area of ​​the target type tray.

[0059] (2) Shortest distance: Calculate the minimum spatial distance between the tray path and each object to be avoided (heat source, other pipelines). Specifically, it can be obtained by spatial geometric calculation based on the three-dimensional coordinates of the tray, heat source and corresponding pipeline.

[0060] (3) Support span statistics: List the distances between all adjacent support points and find the maximum value. Specifically, the maximum support span can be obtained by traversing and statistically calculating based on the three-dimensional coordinates of the center points of all support components and then using distance formulas (such as Euclidean distance).

[0061] (4) Compliance with regulations: Check whether fire-stopping components have been automatically added at the fire compartment crossings. Specifically, based on the location information of fire-stopping components in the model, the pallet crossing sections that cross fire compartments can be selected, and the fire-stopping components can be checked at the crossing locations to complete the compliance with regulations.

[0062] The intelligent modeling system utilizes its built-in large language model to organize key modeling data into natural language reports. For example, it can generate a self-inspection report stating: "Model 'TRAY-EL-102-001' self-inspection complete: actual fill rate 38.5% (meets ≤40% requirement); minimum distance to air conditioning duct 0.85m (meets >0.5m requirement); maximum support span 2.1m (less than the allowable value of 2.4m); fireproof sealing added at the point where it passes through the east wall of the room; no obvious compliance issues found." The large language model then compares this self-inspection report with the original design intent and extracted regulatory clauses. If inconsistencies are found, for example, if the report shows a path segment is only 0.25m from the communication tray, violating the 0.3m requirement, an alert can be directly issued to the user, indicating the problem location. A local optimization process can be automatically initiated, such as increasing the weight of isolation constraints during tray path planning for the problematic section. The path segment is replanned, and the model is locally modified using MCP instructions to achieve self-repair, forming an autonomous closed loop of "design-verification-optimization". As a specific implementation of this application, the scenario for designing power cable trays in the conventional island building of a nuclear power plant is described as follows: "In the turbine hall on the ground floor of the conventional island building, power cable trays need to be laid for the motor power cabinets of two circulating water pumps (CWP-A / B)." The input natural language command is: "Lay two independent power cable trays from switchgear CB-A01 and CB-B01 in the 6.6kV switch room (elevation +0.000m) of the CI building to the CWP-A and CWP-B motor junction boxes located in the pump room (elevation -6.500m). Each tray accommodates three single-core 400mm² cables." 2High-voltage cables (rated current 550A). The route must avoid the high-temperature area beneath the main steam pipe (marked on the layout diagram) and should be laid along the cable tunnel on the west side of the plant as much as possible to facilitate heat dissipation and maintenance. Two cable trays can be laid side by side in the cable tunnel, but the spacing must meet heat dissipation requirements. The cable inventory is used to confirm parameters such as cable type, specifications, outer diameter, and weight. The technical specifications include electrical design codes, cable laying codes, and fire protection codes. The three-dimensional context information includes: plant structure model, main steam pipe model, and planned cable tunnel model.

[0063] The intelligent modeling system performs the following steps: The S100 uses a large language model to parse instructions and identify two independent tasks (path A and path B). The key constraints are "avoid high-temperature areas", "prioritize cable tunnels", and "lay cables in parallel for heat dissipation".

[0064] S200, calculate 3 400mm rods 2 The total outer diameter cross-sectional area of ​​the high-voltage cable is determined based on a fill rate of ≤50% for power cables. A knowledge graph query indicates that "non-magnetic material" trays are recommended for high-voltage single-core cables to reduce eddy current losses. Based on this, LLM prioritizes aluminum alloy trays among the candidate specifications. According to the various specifications and minimum theoretical cross-sectional area of ​​the aluminum alloy trays, the target tray specification selected is "aluminum alloy ladder tray, with dimensions of (500x150) mm".

[0065] S300 constructs a cost map. The area below the main steam pipe can be designated as an extremely high-cost zone, while the cable tunnel area is designated as a negative-cost zone (strong preference). The path search algorithm plans specific paths for routes A and B on the cost map, ensuring that the center-to-center distance between the two paths within the cable tunnel meets the 600mm requirement for heat dissipation calculations. After analyzing the spatial layout, LLM proposes a high-rise strategy: "Both paths start from the switch room, first vertically downwards into the common cable mezzanine at the -3,000m level, then horizontally westwards into the cable tunnel, laid parallel within the tunnel to above the pump house, and finally vertically downwards to the target motor."

[0066] The S400 system automatically generates sequences containing components such as straight sections, vertical bends, and horizontal bends. Based on the specifications of the aluminum alloy tray (500x150), the weight of the high-voltage cable, and the seismic requirements of the conventional island, it automatically calculates the maximum support span as 3.0m. Heavy-duty seismic-resistant hangers are automatically deployed along the path, especially on vertical sections and at bends.

[0067] S500 generates the MCP command, which automatically creates two blue aluminum alloy ladder tray models in Revit, placed side by side inside the cable tunnel. The model properties already include information such as specifications, materials, and links to current carrying capacity calculation sheets.

[0068] S600, the system extracts model parameter data and generates a report: "The A / B road pallet filling rate is approximately 45%; the minimum horizontal distance from the main steam pipe is 4.5m, and the vertical distance is 2.0m (safe); the parallel spacing within the tunnel is 600mm (meets heat dissipation requirements); the maximum support span is 2.7m. Verification passed."

[0069] The solution provided in this application allows a design task that originally required several hours of collaborative work between electrical and layout professionals to be completed in half an hour, resulting in a high-quality initial model that has passed compliance verification.

[0070] As another specific embodiment of this application, in an existing containment cable tray model, due to equipment layout adjustments, a new Class 1E instrument cable tray needs to be added, running from the reactor pressure vessel instrument outlet to the containment penetration. The input natural language modification command is: "In the existing model area, add a new tray connecting RPV instrument 'IC-202' to the penetration 'PEN-101'. The cables are Class 1E, Category K3, totaling 15. The path must maintain a physical isolation distance of at least 500mm from existing non-Class 1E trays (ID: TRAY-NC-01), or employ physical isolation measures." The system loads the current complete 3D model inside the containment as the context.

[0071] The intelligent modeling system performs the following steps: S100, the large language model understands "physical isolation" as a key constraint, and derives a specific clause from the fire protection code: "When the distance cannot be met, fireproof partitions may be used for separation."

[0072] For S200, the selected model must use a "stainless steel enclosed metal tray with a cover" to meet the fire protection and safety requirements of Class 1E cables.

[0073] S300, when planning the path, the algorithm found that in a certain narrow area, no matter how it detoured, the minimum distance between the new pallet and TRAY-NC-01 could only reach 300mm, which could not meet the 500mm requirement.

[0074] Domain-specific vertical model intervention in decision-making: The system feeds this conflict back to the larger model. Based on knowledge graphs and specifications, the larger model proposes two solutions: Recommendation 1: In this narrow section of the path, add a fireproof metal partition to the new pallet or the existing TRAY-NC-01 pallet to achieve physical isolation, thereby allowing the spacing to be reduced to 300mm. Recommendation 2: Modify a small section of the existing 'TRAY-NC-01' pallet path to make room for it. Based on the preset principle of "minimizing the impact on existing design," the system prioritizes Recommendation 1 and adds a "fireproof partition required" mark to this section in the constraint library.

[0075] For S400 / S500, components and supports are generated normally, and after the pallet model for this section is generated, it is automatically marked in its properties as "Fireproof partition needs to be installed, distance from TRAY-NC-01 300mm".

[0076] S600, the verification report states: "In the coordinate [X, Y, Z] area, the spacing is 300mm. A fireproof partition has been adopted as an alternative to meet the physical isolation requirements, which complies with the corresponding fire protection specifications."

[0077] The intelligent modeling system provided in this application not only automates the execution of changes, but also, when encountering specification conflicts, imitates expert thinking to propose innovative solutions that conform to the specifications and automatically completes the solution marking, greatly improving the intelligence level of handling complex changes.

[0078] The intelligent modeling method provided in this application takes design requirements expressed in natural language, unstructured technical specifications, and structured cable data as input. Through an intelligent agent centered on an industry vertical model, it performs deep understanding, knowledge retrieval, multi-objective reasoning, and decision-making. It automatically completes the specification selection and verification of cable trays, global optimal path planning, and automated layout of components and support systems. Furthermore, it drives 3D design software through a standardized model coordination protocol to generate a high-quality 3D digital model that fully complies with all relevant specifications and takes into account both economy and constructability. This method can liberate designers from repetitive and low-level drawing work while improving modeling efficiency and convenience.

[0079] This application also provides an intelligent modeling system for nuclear power cable trays based on an industry vertical model. The system includes: (1) an input parsing and intent generation module for performing multimodal design input parsing and structured intent generation steps; (2) an intelligent selection module for performing intelligent tray selection steps that integrate electrical calculation and normative reasoning; (3) a path planning module for performing global path automatic planning steps driven by multiple constraints; (4) a component and support design module for performing component serialization generation and support system collaborative automated design steps; (5) a modeling instruction generation and driving module for performing executable modeling instruction generation and execution steps based on model coordination protocols; and (6) a compliance verification and optimization module for performing compliance intelligent verification and adaptive optimization steps of the generated model. The system also includes a database storing a domain knowledge graph and a finely tuned industry vertical model.

[0080] For cable laying design in the complex environment of nuclear power plants, it can automatically select cable tray systems, intelligently plan paths, arrange support systems and verify compliance based on natural language design instructions, multi-source technical specifications, cable lists and three-dimensional spatial context. Finally, it generates accurate, compliant and constructable digital models in three-dimensional design software through standardized interfaces.

[0081] This embodiment also provides a cable tray selection device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. The term "module" as used below can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0082] This embodiment provides a cable tray selection device, such as... Figure 2 As shown, it includes: The first acquisition module 201 is used to acquire the task description text corresponding to the cable tray laying task. The task description text includes the cable list corresponding to the cable tray laying task. The cable list includes the cable type, cable specifications and quantity information to be accommodated by the tray to be laid. The first determining module 202 is used to determine the total outer diameter cross-sectional area of ​​the cable to be laid based on the cable specifications and quantity information to be accommodated by the tray to be laid obtained by parsing the cable list. The second determining module 203 is used to determine the minimum theoretical cross-sectional area of ​​the required tray based on the total outer diameter cross-sectional area; The third determining module 204 is used to determine the recommended tray type corresponding to the corresponding type of cable from a pre-built knowledge graph based on the type of cable that the tray to be laid needs to accommodate, obtained from the parsing. The first filtering module 205 is used to filter target specification pallets from pre-constructed knowledge graph data based on the minimum theoretical cross-sectional area and the type information of the recommended pallets. The effective cross-sectional area of ​​the target specification pallets is greater than and closest to the minimum theoretical cross-sectional area. For detailed explanations, please refer to the relevant descriptions in the above method embodiments, which will not be repeated here.

[0083] In this embodiment, the cable tray selection device is presented in the form of a functional unit. Here, a unit refers to an ASIC circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0084] The cable tray selection device provided in this embodiment intelligently analyzes the cable list to obtain the corresponding cable parameters, determines the minimum theoretical cross-sectional area of ​​the tray required for laying the cable, and determines the recommended tray type corresponding to the corresponding type of cable based on a knowledge graph. Combining the specification information of the recommended type of tray, it determines the target specification tray with an effective cross-sectional area that is greater than and closest to the minimum theoretical cross-sectional area, thereby achieving intelligent selection of trays while improving design efficiency and design consistency.

[0085] As an optional embodiment of this application, the task description text further includes a laying scene description text and a laying operation precautions description text; the device further includes: an extraction module, used to extract target entities and entity relationships from the task description data; a first parsing module, used to parse the technical specification document corresponding to the cable tray laying operation based on the task description text to obtain operation specification data; a third acquisition module, used to acquire the three-dimensional spatial information of the cable tray laying scene to be carried out; and an encoding module, used to perform feature encoding processing on the extraction result corresponding to the task description data, the operation specification data, and the three-dimensional spatial information to obtain the laying intention vector expression corresponding to the cable tray laying task. As an optional embodiment of this application, the device further includes: a discretization module, used to discretize the three-dimensional building space corresponding to the cable tray laying scene into a uniform three-dimensional voxel grid; a fourth acquisition module, used to input the laying intention vector expression into a pre-trained virtual route generation model to obtain multiple virtual routes; and a fourth determination module, used to determine the lowest cost path between the starting point and the ending point based on the cost of the three-dimensional voxel grid on each virtual route and use the lowest cost path as the planned target path. As an optional embodiment of this application, the device further includes: a sampling module, used to sample the target path according to a preset step size to obtain multiple sampling points; a fifth determining module, used to determine the direction change of the target path based on the coordinates of each sampling point; a sixth determining module, used to determine the connecting member with the corresponding angle based on the direction change; a seventh determining module, used to determine the arrangement position of the support points on the target path based on the load per meter of the target type pallet, the maximum allowable span, and the target support reinforcement points; and an eighth determining module, used to determine the support member model corresponding to each support point based on the load between adjacent support points, the support span, the arrangement position of the support points, and the seismic requirements. As an optional embodiment of this application, the device further includes: a sending module, configured to send modeling instruction information to a target protocol client plugin running in 3D modeling software, the modeling instruction information including the determined attribute information of the target tray, target path information, connector information, support point layout information, and support model information, so that the target protocol client plugin calls the 3D modeling software to perform modeling operations based on the modeling instruction information; a fifth acquisition module, configured to acquire modeling result-related information; and an adjustment module, configured to adjust the corresponding modeling data according to the error information when the modeling result-related information contains error information. As an optional embodiment of this application, the device further includes: a query module for querying parameter information of the generated model through a target protocol; a sixth acquisition module for obtaining key modeling data based on the parameter information, wherein the key modeling data is used to verify the compliance of the generated model; a generation module for generating a model self-inspection report based on the key modeling data; a comparison module for comparing the model self-inspection report with data related to the original cable laying requirements; and an optimization module for issuing an alarm for inconsistent comparison results and initiating a local optimization procedure. Further functional descriptions of the above modules are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0086] This invention also provides an electronic device having the above-described features. Figure 2 The cable tray selection device shown.

[0087] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of a device provided in an optional embodiment of the present invention, such as... Figure 3 As shown, the device may include: at least one processor 601, such as a central processing unit (CPU), at least one communication interface 603, memory 604, and at least one communication bus 602. The communication bus 602 is used to enable communication between these components. The communication interface 603 may include a display screen or a keyboard; optionally, the communication interface 603 may also include a standard wired interface or a wireless interface. The memory 604 may be high-speed volatile random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory 604 may also be at least one storage device located remotely from the aforementioned processor 601. The processor 601 may be combined with... Figure 2The described apparatus has an application program stored in memory 604, and a processor 601 calls the program code stored in memory 604 to perform any of the above method steps.

[0088] The communication bus 602 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 602 can be divided into an address bus, a data bus, and a control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0089] The memory 604 may include volatile memory, such as random-access memory (RAM); the memory may also include non-volatile memory, such as flash memory, hard disk drive (HDD) or solid-state drive (SSD); the memory 604 may also include a combination of the above types of memory.

[0090] The processor 601 can be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP.

[0091] The processor 601 may further include a hardware chip. This hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0092] Optionally, memory 604 is also used to store program instructions. Processor 601 can call the program instructions to implement the functions described in this application. Figure 1The cable tray selection method shown in the embodiment.

[0093] This disclosure also provides a computer-readable storage medium in which the methods described in this disclosure can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium may also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the multi-source knowledge graph construction method shown in the above embodiments is implemented.

[0094] A portion of this disclosure can be applied to computer program products, such as computer program instructions, which, when executed by a computer, can invoke or provide methods and / or technical solutions according to this disclosure through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, and installation package files. Accordingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions; the computer compiling the instructions and then executing the corresponding compiled program; the computer reading and executing the instructions; or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0095] Although embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for selecting cable trays, characterized in that, include: Obtain the task description text corresponding to the cable tray laying task. The task description text includes the cable list corresponding to the cable tray laying task. The cable list includes the cable type, cable specifications and quantity information to be accommodated by the tray to be laid. Based on the cable specifications and quantity information to be accommodated in the laying tray obtained by parsing the cable list, the total outer cross-sectional area of ​​the cables to be laid is determined. The minimum theoretical cross-sectional area of ​​the required tray is determined based on the total outer diameter cross-sectional area; Based on the cable types that the tray to be laid needs to accommodate, as determined by the analysis, the recommended tray type for the corresponding cable type is determined from the pre-built knowledge graph. Based on the minimum theoretical cross-sectional area and the recommended pallet type information, target specification pallets are selected from pre-built knowledge graph data. The effective cross-sectional area of ​​the target specification pallets is greater than and closest to the minimum theoretical cross-sectional area.

2. The method according to claim 1, characterized in that, The task description text also includes a laying scenario description text and a laying operation precautions description text; the method further includes: The task description data is subjected to an extraction operation to extract target entities and entity relationships. Based on the task description text, the technical specification document corresponding to the cable tray laying operation is parsed to obtain the operation specification data; Obtain the three-dimensional spatial information of the scene where cable trays are to be laid; The extraction results corresponding to the task description data, the operation specification data, and the three-dimensional spatial information are subjected to feature encoding processing to obtain the laying intention vector expression corresponding to the cable tray laying task.

3. The method according to claim 2, characterized in that, The method further includes: The three-dimensional building space corresponding to the cable tray laying scene is discretized into a uniform three-dimensional voxel mesh. The laying intention vector is input into a pre-trained virtual route generation model to obtain multiple virtual routes; Based on the cost of the 3D voxel mesh on each virtual route, the lowest cost path between the starting point and the ending point is determined, and the lowest cost path is used as the planned target path.

4. The method according to claim 3, characterized in that, The method further includes: The target path is sampled according to a preset step size to obtain multiple sampling points; The direction change of the target path is determined based on the coordinates of each sampling point; Determine the corresponding angle of the connector based on the change in direction; The location of the support points on the target path is determined based on the load per meter of the target type of pallet, the maximum allowable span, and the target support reinforcement points. Based on the load conditions between adjacent support points, the support span, the location of the support points, and the seismic requirements, the model of the support component corresponding to each support point is determined.

5. The method according to claim 4, characterized in that, The method further includes: The modeling instruction information is sent to the target protocol client plugin running in the 3D modeling software. The modeling instruction information includes the determined attribute information of the target tray, the target path information, the connector information, the support point layout information, and the support model information, so that the target protocol client plugin calls the 3D modeling software to perform modeling operations based on the modeling instruction information. Obtain information related to the modeling results; If the modeling results contain error information, the corresponding modeling data shall be adjusted and processed according to the error information.

6. The method according to claim 5, characterized in that, The method further includes: Query the parameter information of the generated model using the target protocol; Based on the parameter information, key modeling data is obtained, which is used to verify the compliance of the generated model. A model self-inspection report is generated based on the key modeling data; The model self-inspection report is compared with the original cable laying requirements data; Issue an alert for inconsistent comparison results and initiate a local optimization procedure.

7. A cable tray selection device, characterized in that, include: The first acquisition module is used to acquire the task description text corresponding to the cable tray laying task. The task description text includes the cable list corresponding to the cable tray laying task. The cable list includes the cable type, cable specifications and quantity information to be accommodated by the tray to be laid. The first determining module is used to determine the total outer diameter cross-sectional area of ​​the cable to be laid based on the cable specifications and quantity information to be accommodated by the laying tray obtained by parsing the cable list. The second determining module is used to determine the minimum theoretical cross-sectional area of ​​the required tray based on the total outer diameter cross-sectional area; The third determination module is used to determine the recommended tray type for the corresponding type of cable from a pre-built knowledge graph based on the type of cable that the tray to be laid needs to accommodate, as obtained from the parsing. The first filtering module is used to filter out target specification pallets from pre-built knowledge graph data based on the minimum theoretical cross-sectional area and the type information of the recommended pallets. The effective cross-sectional area of ​​the target specification pallets is greater than and closest to the minimum theoretical cross-sectional area.

8. An electronic device, characterized in that, include: A memory and a processor are interconnected, the memory storing computer instructions, and the processor executing the computer instructions to perform the cable tray selection method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to execute the cable tray selection method according to any one of claims 1-6.

10. A computer program product, characterized in that, Includes computer instructions for causing a computer to execute the cable tray selection method according to any one of claims 1 to 6.

Images