Engineering pipeline collision analysis method, electronic equipment and storage medium
By using pre-trained GCN model to perform pipeline collision analysis on CAD drawings, the problem of low efficiency of pipeline collision analysis in the prior art is solved, efficient and accurate pipeline collision detection is achieved, and cost and design cycles are reduced.
Patent Information
- Application Number
- CN202410883819.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-03
- Publication Date
- 2024-11-08
AI Technical Summary
In the prior art, pipeline collision analysis is inefficient, resulting in rework, economic losses and schedule delays. Both manual methods and BIM-based methods have problems of high cost, low efficiency and insufficient accuracy.
The CAD drawings are processed using a pre-trained GCN model. By converting the CAD drawings into dxf format, the categories and space vector information of pipelines and components are extracted, collision analysis and detection are performed, and detailed collision analysis reports are generated, and the pipeline layout principles are integrated. and specification requirements to improve analysis accuracy and efficiency.
Improves the efficiency and accuracy of pipeline collision analysis, saves manpower and material resources, reduces rework and economic losses, reduces costs, and improves the flexibility of the design cycle.
Smart Images

Figure CN118917170A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of construction engineering, and in particular to an engineering pipeline collision analysis method, electronic equipment and storage medium. Background Art
[0002] Construction projects generally include various pipelines, especially municipal projects and some building projects, mainly rainwater, sewage, gas, electricity, telecommunications, heat, water supply, fire protection, smoke exhaust, etc. Collisions between pipelines and between pipelines and structures caused by planning and design are very common, which will seriously affect construction operations, resulting in a lot of rework, economic losses, progress delays and other adverse consequences.
[0003] In order to avoid pipeline collision, pipeline collision analysis needs to be carried out before construction. At present, there are two main methods for pipeline collision analysis: 1. Manual review of drawings; 2. Modeling based on design drawings and BIM technology.
[0004] However, both methods require a lot of manpower, material resources and time costs. Not only is the efficiency of collision analysis low, but there are also problems such as insufficient modeling and subjective misjudgment. As a result, the collision analysis work is often not in place and it is impossible to provide efficient and comprehensive guidance on site. Summary of the invention
[0005] The purpose of this application is to provide an engineering pipeline collision analysis method, electronic equipment and storage medium to solve the problem of low efficiency of collision analysis.
[0006] The technical solution adopted by this application to solve its technical problem is:
[0007] In a first aspect, a method for collision analysis of engineering pipelines is provided, including: collecting CAD drawings of pipelines and pipeline-related components; converting the CAD drawings into dxf format; preprocessing the drawings in dxf format; using a pre-trained GCN model to extract the category and spatial vector information of the pipelines and pipeline-related components in the preprocessed drawings and perform collision analysis and detection; and generating a collision analysis report.
[0008] Furthermore, the training method of the GCN model includes: preparing drawing data of pipelines and pipeline-related components; constructing adjacency matrices and feature matrices; processing data in a coded manner according to pipeline layout principles and specification requirements; defining GCN layers and performing multi-layer GCN structure design; adapting the output layer to the task; training and optimizing the model in a coded manner according to pipeline layout principles and specification requirements; and conducting verification testing and performance evaluation in a coded manner according to pipeline layout principles and specification requirements.
[0009] Furthermore, the AutoCAD batch processing plug-in is used to batch convert CAD drawings into dxf format.
[0010] Further, AutoCAD batch processing plug-ins include CorelCAD or DWG FastView.
[0011] Furthermore, the method for preprocessing drawings in dxf format includes: removing redundant information, repairing errors, standardizing and opening frozen layers.
[0012] Furthermore, a preprocessing package written based on the ezdxf library in Python is used to preprocess the drawings in dxf format.
[0013] Furthermore, the collision analysis report includes: project overview, pipeline specialties, conflict point classification and location list and adjustment suggestions.
[0014] In a second aspect, an electronic device is provided, including: a drawing collection unit, used to collect CAD drawings of pipelines and pipeline-related components; a format conversion unit, used to convert CAD drawings into dxf format; a preprocessing unit, used to preprocess drawings in dxf format; a category and spatial vector information extraction and collision analysis detection unit, used to extract category and spatial vector information and collision analysis detection of pipelines and pipeline-related components in the preprocessed drawings using a pre-trained GCN model; and a report generation unit, used to generate a collision analysis report.
[0015] In a third aspect, an electronic device is provided, comprising a memory and a processor; the memory stores instructions executable by the processor; when the processor is configured to execute the instructions, the electronic device implements the engineering pipeline collision analysis method provided in the first aspect.
[0016] In a fourth aspect, a computer-readable storage medium is provided, comprising computer instructions, which, when executed on a computer, enable the computer to execute the engineering pipeline collision analysis method provided in the first aspect.
[0017] Beneficial effects of this application:
[0018] The engineering pipeline collision analysis method, electronic device and storage medium provided in the embodiments of the present application utilize the trained GCN model to perform collision analysis on the engineering pipeline, thereby improving the efficiency of collision analysis and saving a large amount of manpower and material resources; by integrating the coded pipeline layout principles and relevant specification requirements, the accuracy and efficiency of collision analysis are improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0020] Figure 1 is a flow chart of the engineering pipeline collision analysis method provided in an embodiment of the present application;
[0021] Figure 2 It is a schematic diagram of the composition of an electronic device provided in an embodiment of the present application;
[0022] Figure 3 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application.
[0023] Reference numerals:
[0024] 100- electronic equipment;
[0025] 101-drawing collection unit; 102-format conversion unit; 103-preprocessing unit; 104-category and space vector information extraction and collision analysis and detection unit; 105-report generation unit;
[0026] 200-Electronic equipment;
[0027] 201 - memory; 202 - processor; 203 - communication interface; 204 - bus. DETAILED DESCRIPTION
[0028] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.
[0029] It should be noted that similar numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. In addition, the embodiments and features in the embodiments of this application can be combined with each other without conflict.
[0030] In the description of the embodiments of the present application, the indicated orientation or positional relationship is based on the orientation or positional relationship shown in the accompanying drawings, or is the orientation or positional relationship in which the product of the application is usually placed when in use, or is the orientation or positional relationship commonly understood by those skilled in the art. The terms "disposed", "opened", "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, and an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal connection of two elements.
[0031] In construction projects, pipelines, as "blood vessels" and "nerves", occupy an extremely important position. They undertake key functions such as transmitting water resources, energy, and information, and are the "lifeline" for the normal operation of construction projects. Due to the wide variety of pipelines and complex functions, their layout is complex. In actual work, pipeline planning often lacks a strict and reasonable planning model, and most of the time it is based on the designer's knowledge, experience and design intent. This method is effective in solving small-scale and low-complexity optimization problems, but it is very weak for large-scale and highly complex optimization decision-making problems such as municipal public works such as integrated pipe corridors and underground spaces, and some construction projects such as commercial complexes and hospitals, which has brought many pipeline collision problems.
[0032] Among them, pipeline collision can be defined into three categories: 1. Physical contact and intersection occur between pipelines or between pipelines and structures; 2. The vertical or horizontal spacing between pipelines or between pipelines and structures does not meet the requirements of relevant specifications; 3. The pipeline layout violates relevant principles, such as small giving way to large, pressurized giving way to unpressurized, general giving way to dynamic, strong and weak separation, etc.; all of the above can be regarded as pipeline collision in a broad sense.
[0033] At present, pipeline collision analysis mainly relies on manual methods and methods based on BIM technology.
[0034] The manual method of pipeline collision analysis includes the following steps:
[0035] 1) Collect and prepare drawings: obtain drawings of different disciplines such as structure, electrical, piping, etc.
[0036] 2) Use overlay technology: overlay drawings of different disciplines using sulphuric acid paper or AutoCAD software.
[0037] 3) Check collision: The designer checks the superimposed drawings, identifies collision points and marks them.
[0038] 4) Modify the design and re-evaluate: Based on the results of the collision analysis, modify the original design. This may involve adjusting the pipeline direction, changing the equipment layout, adjusting the clearance, etc. The modified design needs to be subjected to collision analysis again to verify whether the problem has been solved.
[0039] The BIM-based method for pipeline collision analysis includes the following steps:
[0040] 1) Establish a preliminary model: technicians need to use professional BIM software such as Revit and Navisworks to perform 3D modeling based on the construction design drawings. At this stage, the pipe components involved need to be parameterized to ensure that the information in the model can be automatically updated as the parameters change.
[0041] 2) Classification of pipeline systems: Pipeline systems will be divided into several main categories, including: electrical systems such as low-voltage power distribution, integrated wiring, and fire alarm, HVAC systems such as ventilation, smoke exhaust, and air conditioning, and water supply, drainage, sprinkler, fire hydrant, and other water supply and drainage systems. Each system needs to be accurately set in the BIM model.
[0042] 3) Mark potential collisions: During the modeling process, if technicians find any potential pipeline collisions, they should be marked immediately.
[0043] 4) Simulate the pipeline system: Use specialized BIM software functions, such as Navisworks' Clash Detective, to perform collision detection and list a detailed collision report, including the location of the collision, the pipelines involved, and the severity of the collision.
[0044] 5) Optimize pipeline system: Re-layout and adjust conflicting pipelines according to the collision detection report. This may require modifying the direction, length or elevation of the pipeline to ensure that all pipelines are reasonably distributed in space and meet relevant specifications.
[0045] 6) Verify the final model: The adjusted model needs to be collided again to verify whether the collision has been resolved.
[0046] However, the existing manual methods and BIM-based methods for pipeline collision analysis have the following disadvantages:
[0047] 1. There is a large demand for professionals, high costs, heavy workload and low efficiency. The manual method requires a lot of manpower and time to collect drawings, overlay drawings and check collision points. BIM technology requires expensive software modeling, professional training and technical support. In addition, according to actual work experience, using BIM technology to establish a complete collision analysis model requires the same workload as redesigning the drawings.
[0048] 2. Limited accuracy. Manual methods rely on designers, who are limited by their knowledge and experience, and may not be able to accurately identify all collision points. BIM technology modeling requires multiple professionals to spend a lot of time on modeling, which is prone to inconsistency and disharmony, resulting in an incomplete model. The above problems are particularly evident in complex or large-scale projects.
[0049] 3. Difficulty in updating. Once the design plan changes, manual methods require re-overlaying of drawings, and BIM technology requires adjustment of the model to re-perform collision analysis, which further increases the workload and prolongs the design cycle.
[0050] To solve the above problems, see Figure 1 The present application embodiment provides a method for analyzing collision of engineering pipelines, comprising the following steps:
[0051] S1. Collect CAD drawings of pipelines and pipeline-related components.
[0052] Exemplarily, all CAD drawings of the project containing pipelines and spatial position information of components related to the pipelines are collected.
[0053] S2. Convert CAD drawings to dxf format.
[0054] Exemplarily, an AutoCAD batch processing plug-in is used to batch convert CAD drawings into a dxf format suitable for GCN algorithm recognition. The AutoCAD batch processing plug-in may include CorelCAD, DWG FastView, etc.
[0055] S3. Preprocess the drawings in dxf format.
[0056] Exemplarily, a preprocessing package written in the ezdxf library based on Python is used to preprocess the drawings in dxf format. The method for preprocessing the drawings in dxf format includes: removing redundant information, repairing errors, standardizing, and opening frozen layers.
[0057] S4. Use the pre-trained GCN model to extract the category and spatial vector information of pipelines and pipeline-related components in the pre-processed drawings and perform collision analysis and detection.
[0058] Exemplarily, the training method of the GCN model includes the following steps: preparing drawing data of pipelines and pipeline-related components; constructing an adjacency matrix and a feature matrix; processing the data in a coded manner according to pipeline layout principles and specification requirements; defining the GCN layer and performing a multi-layer GCN structure design; adapting the output layer to the task; training and optimizing the model in a coded manner according to pipeline layout principles and specification requirements; and conducting verification testing and performance evaluation in a coded manner according to pipeline layout principles and specification requirements.
[0059] S5. Generate a collision analysis report.
[0060] For example, a collision analysis report is generated based on the python docx library, wherein the collision analysis report includes: project overview, pipeline specialty, conflict point classification and location list and adjustment suggestions.
[0061] The engineering pipeline collision analysis method provided in the embodiment of the present application uses the trained GCN model to perform collision analysis on the engineering pipeline, thereby improving the efficiency of collision analysis and saving a lot of manpower and material resources. Compared with manual methods, it does not require a lot of manpower and time to overlay drawings and check collision points. Compared with BIM technology, it does not require expensive modeling software, professional training and technical support.
[0062] The engineering pipeline collision analysis method provided in the embodiment of the present application integrates the coded pipeline layout principles and relevant specification requirements into the graph convolutional neural network model developed based on Python, thereby improving the accuracy and efficiency of the collision analysis, avoiding rework and economic losses caused by inadequate collision analysis, and further reducing costs. Compared with the situation in the prior art where a large workload will be generated once the design scheme is changed, the method of the present application only needs to re-run the existing model, which is more flexible to update, reduces the workload and shortens the design cycle.
[0063] The embodiment of the present application can divide the functional modules of the electronic device and the server according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.
[0064] In the case of dividing each functional module into corresponding functional modules, Figure 2 A possible schematic diagram of the composition of the electronic device involved in the above embodiment is shown. Figure 2 The electronic device 100 may include a drawing collection unit 101, a format conversion unit 102, a preprocessing unit 103, a category and space vector information extraction and collision analysis detection unit 104 and a report generation unit 105.
[0065] Among them, the drawing collection unit 101 is used to collect CAD drawings of pipelines and pipeline-related components. The format conversion unit 102 is used to convert CAD drawings into dxf format. The preprocessing unit 103 is used to preprocess the drawings in dxf format. The category and spatial vector information extraction and collision analysis detection unit 104 is used to extract the category information and spatial vector information of pipelines and pipeline-related components in the preprocessed drawings and perform collision analysis detection using a pre-trained GCN model. The report generation unit 105 is used to generate a collision analysis report.
[0066] Figure 2 The units in can also be called modules, for example, the drawing collection unit can be called the drawing collection module. Figure 2 If each unit in the system is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium.
[0067] See also Figure 3 The embodiment of the present application also provides a hardware structure of an electronic device, the electronic device 200, includes a memory 201 and a processor 202; optionally, it also includes a communication interface 203 connected to the processor 202. The memory 201, the processor 202 and the communication interface 203 are connected via a bus 204.
[0068] The memory 201 may be a read-only memory or other types of static storage devices that can store static information and instructions, a random access memory or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory, a read-only optical disk or other optical disk storage, an optical disk storage, a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, and the embodiments of the present application do not impose any limitations on this.
[0069] The processor 202 may be a central processing unit, a general-purpose processor network processor, a digital signal processor, a microprocessor, a microcontroller, a programmable logic device, or any combination thereof. The processor 202 may also be any other device having a processing function, such as a circuit, a device, or a software module. The processor 202 may also include multiple CPUs, and the processor 202 may be a single-core processor or a multi-core processor. The processor 202 here may refer to one or more devices, circuits, or processing cores for processing data.
[0070] The memory 201 may exist independently or may be integrated with the processor 202. The memory 201 stores computer program codes, and the processor 202 is used to execute the computer program codes stored in the memory 201, thereby implementing the engineering pipeline collision analysis method provided in the embodiment of the present application.
[0071] The communication interface 203 may be used to communicate with other devices or a communication network, and the communication network may be Ethernet, a wireless access network, a wireless local area network, etc. The communication interface 203 may be a module, a circuit, a transceiver, or any device capable of implementing communication.
[0072] The bus 204 may be a peripheral component interconnection standard bus or an extended industry standard structure bus. The bus 204 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The fact that only one line is used in the diagram does not mean that there is only one bus or only one type of bus.
[0073] The embodiment of the present application also provides a computer-readable storage medium, including computer instructions, which, when executed on a computer, enable the computer to execute the engineering pipeline collision analysis method provided in the above embodiment. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more media integrated therein. For example, the available medium may be a magnetic medium, an optical medium, or a semiconductor medium.
[0074] The above is only a preferred embodiment of the present application and does not constitute any form of limitation to the present application. Based on the technical essence of the present application and within the spirit and principles of the present application, any simple modification, equivalent replacement and improvement of the above embodiments shall still fall within the protection scope of the technical solution of the present application.
Claims
1. A method for analyzing engineering pipeline collision. It is characterized in that include: Collect CAD drawings of pipelines and pipeline-related components; Convert CAD drawings to dxf format; Preprocess the drawings in dxf format; The pre-trained GCN model is used to extract the categories and spatial vector information of pipelines and pipeline-related components in the pre-processed drawings and to perform collision analysis and detection; Generate a collision analysis report.
2. The engineering pipeline collision analysis method according to claim 1, It is characterized in that The training method of the GCN model includes: Prepare drawings and data of pipelines and pipeline-related components; Construct adjacency matrix and feature matrix; Process the data in a coded manner according to pipeline layout principles and specification requirements; Define GCN layers and design multi-layer GCN structures; Adapt the output layer to the task; Encode the model training and optimization according to pipeline layout principles and specification requirements; Verification testing and performance evaluation are carried out in a coded manner according to pipeline layout principles and specification requirements.
3. The engineering pipeline collision analysis method according to claim 1, It is characterized in that Use AutoCAD batch processing plug-in to batch convert CAD drawings into dxf format.
4. The engineering pipeline collision analysis method according to claim 3, It is characterized in that AutoCAD batch processing plug-ins include CorelCAD or DWG FastView.
5. The engineering pipeline collision analysis method according to claim 1, It is characterized in that The method of preprocessing drawings in dxf format includes: removing redundant information, repairing errors, standardizing and opening frozen layers.
6. The engineering pipeline collision analysis method according to claim 1, It is characterized in that The dxf format drawings are preprocessed using a preprocessing package written in the ezdxf library based on Python.
7. The engineering pipeline collision analysis method according to claim 1, It is characterized in that The collision analysis report includes: project overview, pipeline specialty, conflict point classification and location list and adjustment suggestions.
8. An electronic device, It is characterized in that include: A drawing collection unit, used to collect CAD drawings of pipelines and pipeline-related components; Format conversion unit, used to convert CAD drawings into dxf format; A pre-processing unit is used to pre-process drawings in dxf format; Category and space vector information extraction and collision analysis and detection unit, used to extract category and space vector information and perform collision analysis and detection on pipelines and pipeline-related components in preprocessed drawings using a pre-trained GCN model; A report generation unit is used to generate a collision analysis report.
9. An electronic device, It is characterized in that including memory and processor; The memory stores instructions executable by the processor; When the processor is configured to execute the instructions, the electronic device implements the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, It is characterized in that The method comprises computer instructions, which, when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 7.
