Intelligent steel structure bridge manufacturing method based on digital twinning technology

Abstract

The invention relates to the technical field of digital twinning application, in particular to a digital twinning technology-based intelligent manufacturing method for a steel structure bridge, which comprises the following steps of: S1, establishing a steel structure bridge design BIM (Building Information Modeling) model; s2, constructing a digital twin model, and mapping a physical manufacturing process in real time; s3, performing pilot run, and performing digital twinborn model optimization according to a pilot run result; s4, steel structure production supervision and optimization are carried out based on the optimized digital twinborn model; and S5, performing quality prediction and visual control guidance by using a BIM technology and a digital twinborn model. The advanced information technology is combined with the manufacturing process, so that the whole process optimization from design to manufacturing is realized. An accurate bridge design model is constructed by utilizing a BIM technology, detailed geometric information, material attributes, construction processes and the like are included, and accurate basic data are provided for subsequent manufacturing links. Meanwhile, the physical manufacturing process is mapped in real time by means of the digital twinning technology, precise monitoring and adjustment of production are achieved, and therefore it is guaranteed that manufacturing of the steel structure bridge can be completed efficiently with high quality.

Description

Technical Field

[0001] The present invention relates to the field of digital twin application technology, and in particular to an intelligent manufacturing method for a steel structure bridge based on digital twin technology. Background Art

[0002] In today's society, the demand for infrastructure construction is growing. As an important transportation hub, the quality and construction efficiency of steel structure bridges are of vital importance. It is in this context that the present invention came into being, aiming to solve the long-standing problems in the manufacturing process of steel structure bridges through innovative technical means, and significantly improve the efficiency and quality of manufacturing. There are many drawbacks in the traditional manufacturing method of steel structure bridges. For example, the information transmission between the design and manufacturing links is not smooth, resulting in the inability to accurately realize the design intent during the manufacturing process; the lack of real-time and effective monitoring of the production process makes it difficult to discover and solve problems in a timely manner; the quality control means are single and ineffective, making it difficult to ensure the stability and safety of the bridge. These problems not only affect the progress and quality of the project, but also increase costs and risks.

[0003] In the traditional steel structure bridge manufacturing, there are problems such as poor communication between design and manufacturing, difficulty in real-time monitoring of the production process, and difficulty in quality control, which lead to low efficiency and unstable quality. As an important part of modern transportation infrastructure, the manufacturing process of steel structure bridges involves multiple disciplines and complex process flows. In the past, the design department usually used independent design software to design the bridge structure, and the generated two-dimensional drawings were prone to information loss and misunderstanding when they were passed to the manufacturing department. When the manufacturing department produces according to the drawings, it often needs to communicate and confirm with the design department repeatedly, which not only consumes a lot of time and manpower, but also easily leads to delays in production progress. During the production process, due to the lack of effective real-time monitoring means, key data on the production line, such as processing accuracy and welding quality, cannot be obtained in time. This makes the problems not discovered until they accumulate to a certain extent, which seriously affects the quality and production efficiency of the products. In terms of quality control, traditional detection methods mainly rely on sampling detection and manual judgment, which makes it difficult to comprehensively and accurately evaluate the quality of products, resulting in unstable quality from time to time. The existence of these problems not only increases the production cost of enterprises, but also affects the delivery time and performance of steel structure bridges, and cannot meet the growing market demand and high-standard engineering requirements. Therefore, seeking an innovative solution to improve the efficiency and quality of steel structure bridge manufacturing has become an urgent need for the development of the industry.

[0004] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present invention, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art already known to those skilled in the art. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent manufacturing method for steel structure bridges based on digital twin technology to solve the technical problems existing in the prior art.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: The present invention provides a method for intelligent manufacturing of a steel structure bridge based on digital twin technology, which comprises: Step S1: Establishing a BIM model for steel structure bridge design; Step S2: Build a digital twin model to map the physical manufacturing process in real time; Step S3: trial operation, optimizing the digital twin model according to the trial operation results; Step S4: Supervise and optimize steel structure production based on the optimized digital twin model; Step S5: Use BIM technology and digital twin models for quality prediction and visual control guidance.

[0007] Preferably, step S1 is implemented by the following steps: Step S11: Build a WBS standard library. The work breakdown structure (WBS) breaks down the project into smaller, more manageable parts, and each WBS element has a unique identifier. Project decomposition includes breaking down the overall project into major tasks and subtasks, and adding detailed descriptions for each task, including time, resources, and responsible persons. Step S12: Select the corresponding WBS standard submodule as the construction plan template according to the type of the new project; Step S13: Establish a corresponding model according to the WBS decomposition module; Step S14: Use classification codes to identify model elements to ensure that each component can be associated with the corresponding task in the WBS; Step S15: According to the design requirements and construction plan, the model is gradually refined to add necessary details, material properties and construction information.

[0008] Preferably, step S2 is implemented by the following steps: Step S21: point cloud data collection, where the point cloud data is collected using laser radar and camera during the bridge manufacturing process. These data contain the spatial geometric information of the bridge structure; Step S22: reverse modeling, wherein the reverse modeling extracts geometric features from the point cloud data by using a graph convolution algorithm, thereby constructing a three-dimensional physical model of the bridge, and constructing a radiation field based on the features of the points, and improving the three-dimensional model by using a NERF algorithm; Step S23: creating a logical model, wherein the logical model is created by describing the components, organizational structure and operation mechanism of the logical model through graphical and formal methods; Step S24: digital-analog linkage, wherein the digital-analog linkage feeds back the attribute and behavior of the elements in the logical model to the physical model, and iterates and optimizes the physical model; Step S25: multi-objective optimization, wherein the multi-objective optimization is to combine multi-source data related to progress, quality, and safety, use a multi-objective optimization ant colony algorithm to train and optimize the simulation model, and feed back the simulation results to the physical model to continuously improve the accuracy and practicality of the model; Step S26: data fusion and conversion, wherein the data fusion and conversion is based on multi-source heterogeneous data fusion technology and neural network algorithm to achieve data cleaning conversion, sharing aggregation and iterative optimization of information flow, control flow, data flow and decision flow between physical space and virtual space; Step S27: Real-time mapping of the steel structure bridge manufacturing process, which is achieved through the data center to ensure real-time interaction and synchronous feedback between the digital twin and the physical entity.

[0009] Preferably, step S3 is implemented by the following steps: Step S31: Formulate a trial operation plan and clarify the trial operation objectives, including model accuracy verification, real-time data processing capability testing, and potential problem identification; Step S32: Conduct trial operation, including data collection, monitoring and recording, and troubleshooting; Step S33: Analyze the trial run data, compare the actual results with the model prediction results, and identify deviations and inconsistencies; Step S34: Evaluate the key performance indicators of the digital twin model, where the key performance indicators include response time, accuracy, real-time and reliability; Step S35: adjusting and optimizing the digital twin model according to the evaluation results; Step S36: Re-run the trial according to the optimization plan, repeat steps S31-S35, verify the optimization effect, and observe the improvement of the digital twin model until the optimized digital twin model reaches the trial operation target.

[0010] Preferably, step 4 is implemented by the following steps: Step S41: creating a visual representation of the construction plan; Step S42: Using the digital twin model to monitor key processes in real time, including using machine vision and sensor technology to automatically detect key processes such as welding and assembly; Step S43: Setting quality and safety thresholds, and once an abnormality is detected, issuing an alarm and taking corrective measures in a timely manner; Step S44: Feedback and continuous improvement.

[0011] Preferably, step S5 is implemented by the following steps: Step S51: creating a digital space, where the digital space is a model space mapped 1:1 to the real scene; Step S52: full process tracing and preview warning, the full process tracing is the full process of the completed work implementation based on the digital twin record; the preview is the future work implementation process deduced by the digital twin based on the completed work; the warning is the comparison and deviation warning of the cost, quality and progress targets according to the preview situation; Step S53: generating an adjustment construction strategy according to the preview warning result; Step S54: Generate a visual work instruction using the BIM model according to the adjusted construction strategy; Step S55: Continue to improve and repeat steps S51-S54 until manufacturing is completed.

[0012] By adopting the above technical solution, the present invention has the following beneficial effects: The present invention achieves full process optimization from design to manufacturing by combining advanced information technology with manufacturing technology. Using BIM technology to build an accurate bridge design model, including detailed geometric information, material properties and construction technology, provides accurate basic data for subsequent manufacturing links. At the same time, with the help of digital twin technology, the physical manufacturing process is mapped in real time to achieve accurate monitoring and adjustment of production, thereby ensuring that the manufacturing of steel structure bridges can be completed efficiently and with high quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0014] Figure 1 An intelligent manufacturing method for steel structure bridges based on digital twin technology is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0015] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0017] Combination Figure 1 As shown, this embodiment provides a method for intelligent manufacturing of steel structure bridges based on digital twin technology, aiming to improve the design, production and management efficiency of steel structure bridges. The specific steps of the method are as follows: Step 1: Create a BIM model for steel bridge design First, the steel structure bridge is designed and planned in detail by creating a building information model (BIM). The model will contain information such as the bridge's geometry, material properties, and structural loads, providing basic data for subsequent production.

[0018] Step 1 is implemented by the following steps: Step 1.1: Build a WBS standard library. Establish a work breakdown structure (WBS) standard library to break down the overall project into smaller, more manageable tasks. Each WBS element has a unique identifier and add detailed descriptions for each task, including time, resources, and responsible persons.

[0019] Step 1.2: Select the WBS standard submodule. Select the corresponding WBS standard submodule according to the type of the new project as the construction plan template.

[0020] Step 1.3: Establish the corresponding model. Establish the corresponding model according to the WBS decomposition module to ensure that the logical relationship between each module is clear.

[0021] Step 1.4: Use classification codes to identify model elements. Use classification codes to identify each component in the model so that it can be associated with the corresponding task in the WBS.

[0022] Step 1.5: Gradually refine the model Based on the design requirements and construction plan, gradually refine the model to add necessary details, material properties and construction information.

[0023] Step 2: Build a digital twin model to map the physical manufacturing process in real time After the BIM model is established, a corresponding digital twin model is constructed to reflect the various parameters and status of the physical manufacturing process in real time. Through data collection and processing, the digital twin model can be dynamically updated to ensure consistency with the actual production process.

[0024] Step 2 is implemented by the following steps: Step 2.1: Point cloud data collection The point cloud data during the bridge manufacturing process is collected using lidar and camera technology to obtain the spatial geometric information of the bridge structure.

[0025] Step 2.2: Reverse modeling: The geometric features in the point cloud data are extracted through the graph convolution algorithm, the three-dimensional physical model of the bridge is constructed, and the NERF algorithm is used to improve the three-dimensional model.

[0026] Step 2.3: Logical model creation Use graphical and formal methods to describe the components, organizational structure and operating mechanism of the logical model.

[0027] Step 2.4: The digital-analog linkage feeds back the attribute and behavior of the elements in the logical model to the physical model, realizing linkage and iterative optimization of the physical model.

[0028] Step 2.5: Multi-objective optimization combines multi-source data such as progress, quality and safety, and uses a multi-objective optimization ant colony algorithm to train and optimize the simulation model. The simulation results are fed back to the physical model to continuously improve the accuracy and practicality of the model.

[0029] Step 2.6: Data fusion and transformation Based on multi-source heterogeneous data fusion technology and neural network algorithms, data cleaning, transformation, sharing and iterative optimization of information flow, control flow and decision flow between physical space and virtual space are realized.

[0030] Step 2.7: Real-time mapping is carried out through the data center to ensure real-time interaction and synchronous feedback between the digital twin and the physical entity.

[0031] Step 3: Test run After the digital twin model is built, a trial run is conducted. This process will optimize the digital twin model based on the results of the trial run to ensure the accuracy and reliability of the model.

[0032] Step 3 is implemented by the following steps: Step 3.1: Develop a trial operation plan; Develop a detailed commissioning plan, including the commissioning objectives, scope, timeline, and personnel involved. Ensure that all relevant resources and equipment are ready.

[0033] Step 3.2: Perform a trial run; The trial run was carried out as planned within the specified time. The various parameters in the actual production process were monitored through the digital twin model to ensure that all indicators were consistent with expectations.

[0034] Step 3.3: Data collection and analysis; During the trial run, data is collected in real time, including information such as production speed, material usage, and equipment status. The collected data is analyzed to evaluate the effect of the trial run.

[0035] Step 3.4: Feedback and adjustment; Based on the data analysis results of the trial run, potential problems and room for improvement are identified, and the digital twin model is adjusted accordingly to improve the accuracy and applicability of the model.

[0036] Step 3.5: Model validation; Verify the degree of match between the adjusted digital twin model and actual production, ensure that the model can effectively reflect the real production process, and provide reliable support for subsequent production.

[0037] Step 4: Supervise and optimize steel structure production based on the optimized digital twin model By using the optimized digital twin model, the production process of the steel structure is monitored in real time. During this process, problems in production are discovered and solved in a timely manner to improve production efficiency and product quality.

[0038] Step 4 is implemented by the following steps: Step 4.1: Real-time monitoring of the production process; The production process can be monitored in real time through the digital twin model to ensure that each link is carried out according to the predetermined plan and abnormal situations are discovered in time.

[0039] Step 4.2: Data analysis and decision support; Use data analysis tools to conduct in-depth analysis of key data in the production process and provide decision support. Use data mining technology to predict possible problems and put forward improvement suggestions.

[0040] Step 4.3: Establishment of feedback mechanism; Establish an effective feedback mechanism to ensure that problems in the production process can be fed back to the design and management in a timely manner, and appropriate measures can be taken to make improvements.

[0041] Step 4.4: Production process optimization; Based on the results of real-time monitoring and data analysis, the production process is optimized to improve production efficiency and product quality, ensuring that the final product meets the design and quality standards.

[0042] Step 5: Use BIM technology and digital twin models for quality prediction and visual control guidance.

[0043] Step 5 is implemented by the following steps: Step 5.1: Quality prediction model construction; Build a quality prediction model based on historical data and current production data. Use machine learning algorithms to analyze key factors that affect product quality and predict possible quality problems.

[0044] Step 5.2: Visual control interface design; Develop a visual control interface to display key indicators and quality prediction results of the production process in a graphical way, which is convenient for managers to view and analyze in real time.

[0045] Step 5.3: Implement quality control guidance; Based on the results of the quality prediction model, formulate corresponding quality control guidance plans, including adjusting production parameters, optimizing material usage and other measures to ensure that product quality meets the standards.

[0046] Step 5.4: Feedback and continuous improvement; Feedback the implementation results of quality control guidance to the digital twin model for continuous optimization. Through continuous feedback and improvement, the overall production efficiency and product quality can be improved.

[0047] Finally, by combining BIM technology and digital twin models, quality prediction and visual control guidance are implemented. Effective management and control of quality is achieved through real-time monitoring and analysis of the production process.

[0048] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent manufacturing of steel structure bridges based on digital twin technology, characterized in that: include: Step S1: Establishing a BIM model for steel structure bridge design; Step S2: Build a digital twin model to map the physical manufacturing process in real time; Step S3: trial operation, optimizing the digital twin model according to the trial operation results; Step S4: Supervise and optimize steel structure production based on the optimized digital twin model; Step S5: Use BIM technology and digital twin models for quality prediction and visual control guidance.

2. The intelligent manufacturing method for steel structure bridges based on digital twin technology according to claim 1 is characterized in that: The step S1 is implemented by the following steps: Step S11: Build a WBS standard library. The work breakdown structure (WBS) breaks down the project into smaller, more manageable parts, and each WBS element has a unique identifier. Project decomposition includes breaking down the overall project into major tasks and subtasks, and adding detailed descriptions for each task, including time, resources, and responsible persons. Step S12: Select the corresponding WBS standard submodule as the construction plan template according to the type of the new project; Step S13: Establish a corresponding model according to the WBS decomposition module; Step S14: Use classification codes to identify model elements to ensure that each component can be associated with the corresponding task in the WBS; Step S15: According to the design requirements and construction plan, the model is gradually refined to add necessary details, material properties and construction information.

3. The intelligent manufacturing method for steel structure bridges based on digital twin technology according to claim 1 is characterized in that: The step S2 is implemented by the following steps: Step S21: point cloud data collection, where the point cloud data is collected using laser radar and camera during the bridge manufacturing process. These data contain the spatial geometric information of the bridge structure; Step S22: reverse modeling, wherein the reverse modeling extracts geometric features from the point cloud data by using a graph convolution algorithm, thereby constructing a three-dimensional physical model of the bridge, and constructing a radiation field based on the features of the points, and improving the three-dimensional model by using a NERF algorithm; Step S23: creating a logical model, wherein the logical model is created by describing the components, organizational structure and operation mechanism of the logical model through graphical and formal methods; Step S24: digital-analog linkage, wherein the digital-analog linkage feeds back the attribute and behavior of the elements in the logical model to the physical model, and iterates and optimizes the physical model; Step S25: multi-objective optimization, wherein the multi-objective optimization is to combine multi-source data related to progress, quality, and safety, use a multi-objective optimization ant colony algorithm to train and optimize the simulation model, and feed back the simulation results to the physical model to continuously improve the accuracy and practicality of the model; Step S26: data fusion and conversion, wherein the data fusion and conversion is based on multi-source heterogeneous data fusion technology and neural network algorithm to achieve data cleaning conversion, sharing aggregation and iterative optimization of information flow, control flow, data flow and decision flow between physical space and virtual space; Step S27: Real-time mapping of the steel structure bridge manufacturing process, which is achieved through the data center to ensure real-time interaction and synchronous feedback between the digital twin and the physical entity.

4. The intelligent manufacturing method for steel structure bridges based on digital twin technology according to claim 1 is characterized in that: The step S3 is implemented by the following steps: Step S31: Formulate a trial operation plan and clarify the trial operation objectives, including model accuracy verification, real-time data processing capability testing, and potential problem identification; Step S32: Conduct trial operation, including data collection, monitoring and recording, and troubleshooting; Step S33: Analyze the trial run data, compare the actual results with the model prediction results, and identify deviations and inconsistencies; Step S34: Evaluate the key performance indicators of the digital twin model, where the key performance indicators include response time, accuracy, real-time and reliability; Step S35: adjusting and optimizing the digital twin model according to the evaluation results; Step S36: Re-run the trial according to the optimization plan, repeat steps S31-S35, verify the optimization effect, and observe the improvement of the digital twin model until the optimized digital twin model reaches the trial operation target.

5. The intelligent manufacturing method for steel structure bridges based on digital twin technology according to claim 1 is characterized in that: The step 4 is implemented by the following steps: Step S41: creating a visual representation of the construction plan; Step S42: Using the digital twin model to monitor key processes in real time, including using machine vision and sensor technology to automatically detect key processes such as welding and assembly; Step S43: setting quality and safety thresholds, and once an abnormality is detected, issuing an alarm and taking corrective measures in a timely manner; Step S44: Feedback and continuous improvement.

6. The intelligent manufacturing method for steel structure bridges based on digital twin technology according to claim 1 is characterized in that: The step S5 is implemented by the following steps: Step S51: creating a digital space, where the digital space is a model space mapped 1:1 to the real scene; Step S52: whole process tracing and preview warning, the whole process tracing is the whole process of the completed work implementation based on the digital twin record; The preview is the future work implementation process deduced by the digital twin based on the completed work; the warning is the comparison and deviation warning of the cost, quality and progress targets based on the preview situation; Step S53: generating an adjustment construction strategy according to the preview warning result; Step S54: Generate a visual work instruction using the BIM model according to the adjusted construction strategy; Step S55: Continue to improve and repeat steps S51-S54 until manufacturing is completed.

Images