Artificial intelligence-based extradosed cable-stayed bridge construction control method and system

Abstract

The invention relates to the field of extradosed cable-stayed bridge construction, and particularly provides an extradosed cable-stayed bridge construction control method and system based on artificial intelligence, and the method comprises the steps: obtaining the construction indexes of an extradosed cable-stayed bridge; wherein the indexes comprise engineering technical indexes and three-dimensional arrangement indexes; geometric modeling of the extradosed cable-stayed bridge is carried out according to the three-dimensional arrangement indexes; dividing key construction periods of the extradosed cable-stayed bridge through geometric modeling, and determining a mechanical model of each key construction period; building a depth supervision model of the extradosed cable-stayed bridge through a mechanical model and engineering technical indexes; and performing construction process supervision through the deep supervision model, and judging whether to perform construction process optimization or not. Through the AI technology, real-time monitoring and automatic evaluation of the construction process can be realized, and problems can be quickly identified and optimized. Before construction and in the construction process, the future state of the structure needs to be predicted to assess the risk.

Description

Technical Field

[0001] The present invention relates to the field of cable-stayed bridge construction, and in particular to an artificial intelligence-based low-tower cable-stayed bridge construction control method and system. Background Art

[0002] At present, the low-tower cable-stayed bridge is a novel bridge type between the continuous beam bridge and the cable-stayed bridge. Its shape is similar to that of the cable-stayed bridge, and its main beam deck is similar to that of the continuous beam bridge. It has the characteristics of low tower, rigid beam and concentrated cables. Compared with the continuous beam, the low-tower cable-stayed bridge has the advantages of novel structure, large span capacity, simple construction and economy; compared with the cable-stayed bridge, it has the advantages of convenient construction, material saving and high main beam rigidity, which makes the low-tower cable-stayed bridge have broad development space.

[0003] In terms of construction supervision, traditional construction monitoring technology relies on sensors to collect data, manual data analysis, and expert systems to provide decision support. In terms of construction control, a large amount of computing resources are required, and the results depend on the accuracy of input parameters. It is mainly based on the digital technology of prison building information modeling, through image recognition and natural language processing, but it is unable to monitor the mechanical conditions of low-tower cable-stayed bridges. Summary of the invention

[0004] The present invention provides a construction control method and system for a low-tower cable-stayed bridge based on artificial intelligence, which can solve the problem that traditional construction monitoring technology relies on sensors to collect data, manually analyze data, and expert systems to provide decision support. In terms of construction control, a large amount of computing resources are required, and the results depend on the accuracy of input parameters, and mainly rely on the digital technology of prison building information model, through image recognition and natural language processing, but it is impossible to supervise the mechanical conditions of the low-tower cable-stayed bridge.

[0005] In a first aspect, the present invention proposes a construction control method for a low-tower cable-stayed bridge based on artificial intelligence, comprising:

[0006] Obtain construction indicators of low-tower cable-stayed bridges; construction indicators include: engineering technical indicators and three-dimensional layout indicators;

[0007] According to the three-dimensional layout indicators, geometric modeling of the low-tower cable-stayed bridge is carried out;

[0008] Through geometric modeling, the key construction period of the low-tower cable-stayed bridge is divided, and the mechanical model of each key construction period is determined;

[0009] Through mechanical models and engineering technical indicators, a deep supervision model of low-tower cable-stayed bridges is built;

[0010] The construction process is supervised through a deep supervision model to determine whether construction technology optimization is necessary.

[0011] In combination with the first aspect, the obtaining of the construction index of the low-tower cable-stayed bridge includes:

[0012] Obtain project index data for low-tower cable-stayed bridges, input the preset large-scale process model, and determine the construction process data and three-dimensional layout diagram;

[0013] Conduct cost accounting based on construction process data, determine the engineering process technology that meets cost requirements, and set engineering technology indicators;

[0014] According to the three-dimensional layout schematic diagram, carry out engineering quantity accounting and environmental adaptability calculation to determine the three-dimensional layout indicators that meet environmental requirements.

[0015] In combination with the first aspect, the geometric modeling of the low-tower cable-stayed bridge according to the three-dimensional arrangement index includes:

[0016] Import the three-dimensional layout index into the modeling software to obtain a realistic three-dimensional model of the low-tower cable-stayed bridge;

[0017] According to the real-life 3D model, geometric decomposition is performed to determine the geometric structure of the low-tower cable-stayed bridge; the geometric structure includes: bridge towers, main beams, cable stays, piers, foundations, supports, railings, and drainage channels;

[0018] Through geometric structure, geometric modeling of low-tower cable-stayed bridge is carried out.

[0019] In combination with the first aspect, the key construction period of the low-tower cable-stayed bridge is divided into the following by geometric modeling:

[0020] The geometric model is associated with engineering technical indicators to determine the construction process of the low-tower cable-stayed bridge; the construction process includes beam segment prestressing construction, hanging basket assembly, cantilever casting beam segment construction, side span closure segment construction, middle span closure segment construction and external prestressing construction;

[0021] According to the construction process, set quality indicators and testing measures for each construction cycle;

[0022] Empower the process of each construction cycle through testing measures and determine key construction indicators;

[0023] And through key construction indicators, determine the key construction period.

[0024] In combination with the first aspect, the detection measures include deformation monitoring and asynchronous hanging basket overturning monitoring throughout the construction process;

[0025] Deformation monitoring is carried out by presetting a linear test reference point on the bottom template of the hanging basket structure, and performing an inductance test. The inductance test data includes: measurement time, measurement point temperature (temperature type), absolute displacement value, relative displacement value, and zero point value;

[0026] The asynchronous basket overturning monitoring is carried out by pre-installing an inclinometer on the basket device for multi-directional testing, and the inclinometer is set with an alarm angle for basket overturning.

[0027] In combination with the first aspect, the mechanical model for each key construction period is determined, including:

[0028] According to the construction structure and mechanical indicators within the key construction period, the submechanical equations corresponding to the construction structure are established;

[0029] According to the submechanical equations, the overall geometric topological relationship of the low-tower cable-stayed bridge is established, and the mechanical transformation matrix between different construction structures of different low-tower cable-stayed bridges is generated;

[0030] Through the mechanical transformation matrix, the force characteristics and mechanical change laws of each construction structure are determined;

[0031] Based on the stress characteristics and laws of mechanical changes, a mechanical model for each key construction cycle is generated.

[0032] In combination with the first aspect, the deep supervision model of the low-tower cable-stayed bridge is constructed by using the mechanical model and engineering technical indicators, including:

[0033] According to the mechanical model and engineering technical indicators, a finite element model of a low-tower cable-stayed bridge is established; the finite element model is used to compare and verify the measured data and finite element analysis results during the construction process;

[0034] The finite element model is combined with a preset deep neural network to generate a deep supervision model; the deep neural network is used to identify the construction process of the low-tower cable-stayed bridge.

[0035] In combination with the first aspect, the construction process supervision by the deep supervision model and the determination of whether to optimize the construction process include:

[0036] Obtain measured data during the construction process and input it into the deep supervision model to model the construction process;

[0037] According to the construction process modeling, quality indicator supervision test and quality risk supervision test are carried out respectively;

[0038] Based on the quality index supervision test, determine whether process optimization can be carried out and output the process optimization control parameters;

[0039] The construction process is optimized through process optimization control parameters. When the target construction quality indicators cannot be achieved after multiple construction process optimizations, the construction process risks are determined through quality risk supervision tests.

[0040] In combination with the first aspect, the construction process optimization further includes:

[0041] According to the construction process modeling, the engineering detail model is built; the engineering detail model relies on the mechanical model construction and the correlation between different construction structures is marked;

[0042] Based on the engineering detail model, the construction process of each construction structure is scored, and the process optimization coefficient is determined by the quality score and the target process quality. The process optimization coefficient is associated with the process optimization control parameter.

[0043] In the second aspect, a construction control system for a low-tower cable-stayed bridge based on artificial intelligence comprises:

[0044] Construction index collection module: obtains the construction index of the low-tower cable-stayed bridge; the construction index includes: engineering technical index and three-dimensional layout index;

[0045] Geometric modeling module: geometric modeling of low-tower cable-stayed bridges based on three-dimensional layout indicators;

[0046] Mechanical model building module: Through geometric modeling, the key construction period of the low-tower cable-stayed bridge is divided and the mechanical model of each key construction period is determined;

[0047] Deep supervision module: Build a deep supervision model for low-tower cable-stayed bridges through mechanical models and engineering technical indicators;

[0048] Process optimization module: supervises the construction process through a deep supervision model to determine whether to optimize the construction process.

[0049] The beneficial effects of the present invention are:

[0050] The present invention uses AI technology to achieve real-time monitoring and automatic evaluation of the construction process, quickly identify problems and optimize them. Before and during construction, it is necessary to predict the future state of the structure to assess risks. AI models can make predictions based on historical data and existing conditions, helping managers make more accurate decisions.

[0051] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0053] Figure 1 A method flow chart of a construction control method for a low-tower cable-stayed bridge based on artificial intelligence in an embodiment of the present invention;

[0054] Figure 2 This is a longitudinal arrangement diagram of the deformation monitoring points of the hanging basket in an embodiment of the present invention;

[0055] Figure 3 This is a lateral arrangement diagram of the deformation monitoring points of the hanging basket in an embodiment of the present invention;

[0056] Figure 4 Schematic diagram of the principle of the inclinometer in an embodiment of the present invention;

[0057] Figure 5 A schematic diagram of sensor installation points for mechanical model testing in an embodiment of the present invention;

[0058] Figure 6 The system composition diagram of a low-tower cable-stayed bridge construction control system based on artificial intelligence in an embodiment of the present invention. DETAILED DESCRIPTION

[0059] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0060] In the prior art, the digital technology of prison building information model is mainly used, through image recognition and natural language processing, but it is impossible to supervise the mechanical conditions of the low-tower cable-stayed bridge. Therefore, the present invention proposes a construction control method of a low-tower cable-stayed bridge based on artificial intelligence, including:

[0061] Obtain construction indicators of low-tower cable-stayed bridges; the construction indicators include: engineering technical indicators and three-dimensional layout indicators;

[0062] According to the three-dimensional layout indicators, geometric modeling of the low-tower cable-stayed bridge is carried out;

[0063] Through geometric modeling, the key construction period of the low-tower cable-stayed bridge is divided, and the mechanical model of each key construction period is determined;

[0064] Through mechanical models and engineering technical indicators, a deep supervision model of low-tower cable-stayed bridges is built;

[0065] The construction process is supervised through a deep supervision model to determine whether construction technology optimization is necessary.

[0066] The principle of the above technical solution is:

[0067] As attached Figure 1As shown, in actual construction, the construction indicators obtained by the present invention usually require designers to provide a detailed set of construction standard data, including various engineering technologies and three-dimensional layout indicators. These indicators are engineering requirements and three-dimensional structures during the construction process, such as: road grade: first-class highway; vehicle load: highway-Ⅰ grade; design speed: 80Km / h; bridge deck width: 29m; seismic peak acceleration value 0.1g, basic intensity VII; design service life: 100 years; navigation grade: Class III waterway, navigation clearance is 165×10m; bridge deck pavement: 10cm asphalt concrete + waterproof layer + 6cmC40 waterproof concrete; safety level: first level; bridge deck transverse slope 2%, formed by the inclined top plate, the longitudinal section is symmetrical with the center of the bridge span, the slope change point is set at K13+477.2, the longitudinal slope of the bridge deck is 2.5% symmetrical slope, and the slope change point curve radius is 10000m. The three-dimensional layout indicators are the length and width of the entire bridge body and the geometric parameters of the main beam and other structures. When performing geometric modeling, 3D scanners, CAD software, etc. are required.

[0068] First, scan and identify all components on the construction drawings, then import these components into the corresponding modeling software and model them according to the size and position information on the drawings. Set constraints such as material strength, load specifications, etc. to ensure the feasibility and safety of the modeling results.

[0069] Based on geometric modeling, the construction process is divided and each critical construction period is determined. The critical construction period refers to the stage with the greatest impact and the most focus in the entire construction process. For example, for a steel structure bridge, the main construction stage may be the main beam casting, closing and welding.

[0070] For each key construction cycle, it is necessary to establish a corresponding mechanical model to monitor and control various parameters during the construction process. When implementing this application, the mechanical model is a mathematical model built on physical principles and a statistical model based on actual data. The deep supervision model is a model that uses artificial intelligence technology to comprehensively monitor and control the construction process. It can automatically detect abnormal situations during the construction process, and provide timely warnings and construction strategies, so that construction personnel can make timely adjustments and optimizations to specific construction optimization plans.

[0071] The beneficial effects of the above technical solution are:

[0072] The present invention uses AI technology to achieve real-time monitoring and automatic evaluation of the construction process, quickly identify problems and optimize them. Before and during construction, it is necessary to predict the future state of the structure to assess risks. The AI ​​model can make predictions based on historical data and existing conditions and generate decision-making opinions.

[0073] As an embodiment of the present invention, the step of obtaining the construction index of the low-tower cable-stayed bridge includes:

[0074] Obtain project index data for low-tower cable-stayed bridges, input the preset large-scale process model, and determine the construction process data and three-dimensional layout diagram;

[0075] Conduct cost accounting based on construction process data, determine the engineering process technology that meets cost requirements, and set engineering technology indicators;

[0076] According to the three-dimensional layout schematic diagram, carry out engineering quantity accounting and environmental adaptability calculation to determine the three-dimensional layout indicators that meet environmental requirements.

[0077] The principle of the above technical solution is:

[0078] In the actual construction process, it is necessary to obtain relevant project indicator data, such as budget, construction period, safety level and other information. In actual implementation, through design documents, bidding documents or other relevant materials. Then, these data are input into the preset process big data model. The process big data model is a big data model that includes multiple process solutions and is used to predict the cost, progress, safety risk and other aspects of different process solutions.

[0079] Through the process big data model, I determined the construction process data suitable for the current project and the corresponding engineering technical indicators. After determining the construction process data suitable for the current project, I performed cost accounting based on these data to determine the engineering process technology that meets the cost requirements.

[0080] In the process of cost accounting, it is necessary to analyze factors such as engineering quantity accounting, material procurement, and labor costs. In addition, it is necessary to set relevant engineering technical indicators, such as material strength, structural stability, and safety, based on the construction process data and cost accounting results. In addition to setting engineering technical indicators based on construction process data, it is also necessary to perform engineering quantity accounting and environmental adaptability calculations based on the three-dimensional layout schematic diagram to determine the three-dimensional layout indicators that meet environmental requirements.

[0081] The three-dimensional layout diagram contains a variety of possible layout schemes, such as changes in bridge span, changes in the direction of the main beam, adjustments to the position of the supports, etc. By calculating the engineering quantity and analyzing the environmental adaptability of these schemes, the optimal three-dimensional layout indicators are determined, and then construction adjustments are made.

[0082] The beneficial effects of the above technical solution are:

[0083] The present invention configures the process technology that best suits the real-time scenario and environment based on the process big model.

[0084] As an embodiment of the present invention, the geometric modeling of the low-tower cable-stayed bridge according to the three-dimensional layout index includes:

[0085] Import the three-dimensional layout index into the modeling software to obtain a realistic three-dimensional model of the low-tower cable-stayed bridge;

[0086] According to the real-life 3D model, geometric decomposition is performed to determine the geometric structure of the low-tower cable-stayed bridge; the geometric structure includes: bridge towers, main beams, cable stays, piers, foundations, supports, railings, and drainage channels;

[0087] Through geometric structure, geometric modeling of low-tower cable-stayed bridge is carried out.

[0088] The principle of the above technical solution is:

[0089] In the actual implementation of the present invention, geometric modeling of a low-tower cable-stayed bridge is performed according to the three-dimensional arrangement index.

[0090] In this process, first, the three-dimensional layout indicators are imported into the modeling software to obtain a real-life 3D model of a low-tower cable-stayed bridge containing all the necessary information. Determine different engineering structures, such as: Bridge tower: As the main structure supporting the entire bridge, its design and construction must be carried out strictly in accordance with the design requirements. Main beam: Connects the bridge tower and the cable, and is the part that bears most of the load. Cable: Used to connect the main beam and the bridge tower, and bears part of the load. Bridge pier: Used to bear all the loads of the bridge tower and the main beam, as well as part of the horizontal force. Foundation: Used to transfer all the vertical and horizontal forces of the bridge tower and the main beam to the ground. Support: Used to connect the bridge tower and the main beam, and is also the rotating joint of the bridge. Railing: Ensure personal safety and prevent accidental falls. Drainage channel: Ensure the drainage of rainwater and groundwater. Then model one by one according to different component structures.

[0091] The beneficial effects of the above technical solution are:

[0092] The present invention performs separate modeling for different component structures of a low-tower cable-stayed bridge, thereby ensuring the accuracy of modeling of the project.

[0093] As an embodiment of the present invention, the division of the key construction period of the low-tower cable-stayed bridge by geometric modeling includes:

[0094] The geometric model is associated with engineering technical indicators to determine the construction process of the low-tower cable-stayed bridge; the construction process includes beam segment prestressing construction, hanging basket assembly, cantilever casting beam segment construction, side span closure segment construction, middle span closure segment construction and external prestressing construction;

[0095] According to the construction process, set quality indicators and testing measures for each construction cycle;

[0096] Empower the process of each construction cycle through testing measures and determine key construction indicators;

[0097] And through key construction indicators, determine the key construction period.

[0098] The technical principle of the above technical solution is:

[0099] In the actual implementation process, by creating a geometric model of the low-tower cable-stayed bridge and correlating it with engineering technical indicators (such as structural strength, stability, material properties, etc.), we ensure that the design of the construction process is based on precise engineering requirements and technical standards;

[0100] In actual implementation, engineering requirements include: Functional requirements: functional requirements of the structure, such as bearing capacity, service life, wind and earthquake resistance, etc. Use space requirements, including the width, height, and traffic capacity of the bridge. Traffic flow design, such as vehicle flow, pedestrian flow, and traffic organization. Safety requirements: structural safety standards to ensure the safety of the structure under normal use and extreme conditions. Safety requirements such as fire prevention and evacuation. Environmental protection requirements, such as noise control and pollution treatment. Economic requirements: cost control, including construction costs and operation and maintenance costs. Resource optimization, rational use of materials and resources, and reduction of waste. Aesthetic requirements: structural appearance design and coordination with the surrounding environment. Aesthetic requirements such as lighting and landscaping, etc.

[0101] Technical standards include design standards, material standards, construction standards, safety standards, etc.

[0102] Then, according to the geometric model and engineering technical indicators, the various stages of the construction process are clarified, such as the prestressed construction of beam segments and the assembly of hanging baskets, so as to organize and manage the construction process. For each stage of the construction process, specific quality indicators (such as concrete strength, prestressing size, etc.) and corresponding detection measures (such as non-destructive testing, material testing, etc.) are set to ensure that the construction quality meets the design requirements. Process empowerment is to empower the process of each construction cycle through detection measures, that is, to quantify the importance and impact of the construction process according to the detection results, and determine which key processes. Determining key construction indicators is based on the results of process empowerment, identifying the key construction indicators that have the greatest impact on construction quality. Key construction indicators are the focus of construction control. Through key construction indicators, the key stages in the entire construction cycle are further determined. The key stages play a decisive role in the overall quality and progress of the project.

[0103] The beneficial effects of the above technical solution are:

[0104] This application can more effectively control construction quality and reduce construction errors through precise geometric modeling and quality indicator setting; confirm key construction periods and construction indicators, thereby optimizing the allocation and scheduling of construction resources. By monitoring key construction indicators, potential safety risks can be discovered in a timely manner and preventive measures can be taken.

[0105] As an embodiment of the present invention, the detection measures include deformation monitoring and asynchronous hanging basket overturning monitoring in the entire construction process;

[0106] Deformation monitoring is carried out by presetting a linear test reference point on the bottom template of the hanging basket structure, and performing an inductance test. The inductance test data includes: measurement time, measurement point temperature (temperature type), absolute displacement value, relative displacement value, and zero point value;

[0107] The asynchronous basket overturning monitoring is carried out by pre-installing an inclinometer on the basket device for multi-directional testing, and the inclinometer is set with an alarm angle for basket overturning.

[0108] The principle of the above technical solution is:

[0109] In the specific implementation of the present invention, the stress test element is selected from the JMZX-212HAT steel structure surface steel string strain sensor. The installation diagram of the sensor is as follows Figure 5 The testing instrument is a JMZX-3006 steel string reader. The actual strain of the material is converted through the strain-frequency calibration curve, and then the stress is calculated based on its elastic modulus. The stress monitoring of the hanging basket adopts an automated comprehensive testing system based on a cloud platform. Since the deformation of the bottom template of the hanging basket structure needs to find a linear test reference point when testing the deformation of the bottom template of the hanging basket structure manually, the JMDL-2220A intelligent digital displacement meter can be arranged at the lower crossbeam position of the outer web of the corrugated steel web for deformation monitoring. The intelligent digital displacement meter is designed and manufactured based on the principle of inductive frequency modulation. It has the advantages of high sensitivity, high precision, high stability, and temperature influence, and is suitable for long-term observation. The intelligent digital seam meter has a built-in storage chip with an intelligent memory function. The sensor model, number, calibration coefficient and other parameters are permanently stored in the sensor when it leaves the factory, and the required measurement results can be saved for multiple times, such as measurement time, measuring point temperature (temperature type), absolute displacement value, relative displacement value, zero point value, etc. In actual implementation, a single hanging basket is equipped with 4 deformation monitoring points, which are arranged at the lower cross beam of the outer web of the cantilever end of the corrugated steel web (2 monitoring points) and the cast end (2 monitoring points). Figure 2 and Figure 3 shown.

[0110] The overturning of the hanging basket device during construction is the main form of structural safety accidents. Therefore, it is necessary to install monitoring equipment on the truss of the hanging basket device to test the inclination of the front truss in the longitudinal and transverse directions of the bridge during construction. The fixed inclinometer installed on the surface of the hanging basket device structure can measure the inclination of the two mutually perpendicular directions of the structural components relative to the gravity axis. The geometric dimensions of the installation position can be used to calculate the deformation of the structural components in the X and Y directions, so as to monitor the inclination of the upper truss of the hanging basket and achieve the goal of monitoring whether the hanging basket equipment has the risk of overall overturning in the longitudinal and transverse directions of the bridge, and provide safety warnings when the structure overturns. Figure 4 shown.

[0111] The beneficial effects of the above technical solution are:

[0112] The present invention can detect the overall deformation of the bridge body and monitor the overturning of the asynchronous hanging basket during the construction process.

[0113] As an embodiment of the present invention, the determining of the mechanical model of each key construction period includes:

[0114] According to the construction structure and mechanical indicators within the key construction period, the submechanical equations corresponding to the construction structure are established;

[0115] According to the submechanical equations, the overall geometric topological relationship of the low-tower cable-stayed bridge is established, and the mechanical transformation matrix between different construction structures of different low-tower cable-stayed bridges is generated;

[0116] Through the mechanical transformation matrix, the force characteristics and mechanical change laws of each construction structure are determined;

[0117] Based on the stress characteristics and laws of mechanical changes, a mechanical model for each key construction cycle is generated.

[0118] The principle of the above technical solution is:

[0119] In the actual implementation process, first of all, the sub-mechanical equation corresponding to the construction structure is established according to the construction structure and mechanical indicators within the key construction period. The sub-mechanical equation established through the construction structure and mechanical indicators can accurately reflect the mechanical behavior during the construction process.

[0120] Secondly, based on the sub-mechanical equations, the overall geometric topological relationship of the low-tower cable-stayed bridge is established, and the mechanical transformation matrix between different construction structures of different low-tower cable-stayed bridges is generated. In the process of establishing the mechanical sub-equations, it is necessary to use tools such as computer simulation and numerical calculation to generate an accurate mechanical model.

[0121] Then, through this mechanical transformation matrix, the force characteristics and mechanical change laws of each construction structure are determined. This is done by analyzing the mechanical model to extract the force characteristics and mechanical change laws of each construction structure for monitoring and management during the construction process.

[0122] Finally, according to the force characteristics and mechanical change laws, the mechanical model of each key construction period can be generated. The mechanical model of the key construction period contains various construction information and mechanical data for real-time monitoring and management during the construction process.

[0123] The beneficial effects of the above technical solution are:

[0124] The present invention establishes a mechanical model of each construction structure according to each construction period and mechanical characteristics.

[0125] As an embodiment of the present invention, the deep supervision model of a low-tower cable-stayed bridge is constructed by using a mechanical model and engineering technical indicators, including:

[0126] According to the mechanical model and engineering technical indicators, a finite element model of a low-tower cable-stayed bridge is established; the finite element model is used to compare and verify the measured data and finite element analysis results during the construction process;

[0127] The finite element model is combined with a preset deep neural network to generate a deep supervision model; the deep neural network is used to identify the construction process of the low-tower cable-stayed bridge.

[0128] The principle of the above technical solution is:

[0129] In the actual implementation process, the present invention establishes a finite element model of a low-tower cable-stayed bridge according to the mechanical model and engineering technical indicators. The finite element model is a numerical analysis tool that can be implemented by discretizing entities and simplifying complex physical problems into a series of simple mathematical operations.

[0130] The finite element model is used to predict measured data, and the theoretical model is verified and improved. The finite element model is combined with the preset deep neural network to generate a deep supervision model.

[0131] In practical implementation, deep neural network is a machine learning algorithm that is suitable for adaptive learning and understanding of complex nonlinear problems.

[0132] Here, deep neural networks are used to identify and classify different construction processes and take targeted control strategies.

[0133] The beneficial effects of the above technical solution are:

[0134] The present invention can realize the verification and comparison of measured data and modeling data, and can also realize the accurate recognition of measured data by deep neural network and automatically perform verification and comparison.

[0135] As an embodiment of the present invention, the construction process supervision by the deep supervision model and the determination of whether to optimize the construction process include:

[0136] Obtain measured data during the construction process and input it into the deep supervision model to model the construction process;

[0137] According to the construction process modeling, quality indicator supervision test and quality risk supervision test are carried out respectively;

[0138] Based on the quality index supervision test, determine whether process optimization can be carried out and output the process optimization control parameters;

[0139] The construction process is optimized through process optimization control parameters. When the target construction quality indicators cannot be achieved after multiple construction process optimizations, the construction process risks are determined through quality risk supervision tests.

[0140] The principle of the above technical solution is:

[0141] In the actual implementation process, the present invention obtains measured data during the construction process and inputs it into a deep supervision model to model the construction process.

[0142] In this process, the construction process will be modeled through measured data, and the construction process modeling will be used as the input of the deep supervision model, so that the deep supervision model can learn the construction process more accurately and simulate the actual construction process.

[0143] According to the construction process modeling, quality indicator supervision test and quality risk supervision test are carried out respectively. Quality indicator supervision test and quality risk supervision test are used to evaluate the quality status of the construction process. Quality indicator supervision test is used to check whether the quality of the construction process has reached the expected goal, and quality risk supervision test is used to detect possible quality risks in the construction process.

[0144] Based on the quality index supervision test, determine whether the process can be optimized and output the process optimization control parameters. The goal of this step is to determine whether the process needs to be optimized by measuring quality indicators and risks. If optimization is required, the corresponding optimization control parameters will be output for application during the construction process.

[0145] The construction process is optimized through process optimization control parameters. If the target construction quality index cannot be achieved after multiple construction process optimizations, the construction process risk is determined through quality risk supervision tests. The core part of the construction process optimization is to optimize the construction process multiple times according to the optimization control parameters. If the expected quality index cannot be achieved after multiple optimizations, then it is necessary to determine whether there is a construction process risk through quality risk supervision tests.

[0146] The beneficial effects of the above technical solution are:

[0147] The present invention conducts a step-by-step test of construction quality and construction risk, thereby reducing mismeasurement of construction risk while accurately identifying construction risk and reducing construction cost.

[0148] As an embodiment of the present invention, the construction process optimization further includes:

[0149] According to the construction process modeling, the engineering detail model is built; the engineering detail model relies on the mechanical model construction and the correlation between different construction structures is marked;

[0150] Based on the engineering detail model, the construction process of each construction structure is scored, and the process optimization coefficient is determined by the quality score and the target process quality. The process optimization coefficient is associated with the process optimization control parameter.

[0151] The principle of the above technical solution is:

[0152] In the process of optimizing the construction process, the present invention first builds a detailed engineering model. The detailed engineering model is established based on the mechanical model, and the correlation between different construction structures is marked. The actual effects of different construction processes are predicted and evaluated, providing more accurate data support for process optimization.

[0153] When scoring the quality of the construction process of each construction structure, two factors, quality score and target process quality, are considered comprehensively. The quality score is mainly to evaluate the actual effect of each process, while the target process quality is the ideal state we hope to achieve through process optimization. The difference between the two is the process optimization coefficient, which reflects whether the required quality target is achieved during the process optimization.

[0154] The beneficial effects of the above technical solution are:

[0155] The present invention can score the construction process, and can ensure the accuracy of process optimization by associating the process optimization coefficient with the process optimization control coefficient.

[0156] In a second aspect, a construction control system for a low-tower cable-stayed bridge based on artificial intelligence includes: a construction index acquisition module: obtaining construction indicators of a low-tower cable-stayed bridge; wherein the construction indicators include: the construction indicators include engineering technical indicators and three-dimensional layout indicators;

[0157] Geometric modeling module: geometric modeling of low-tower cable-stayed bridges based on three-dimensional layout indicators;

[0158] Mechanical model building module: Through geometric modeling, the key construction period of the low-tower cable-stayed bridge is divided and the mechanical model of each key construction period is determined;

[0159] Deep supervision module: Build a deep supervision model for low-tower cable-stayed bridges through mechanical models and engineering technical indicators;

[0160] Process optimization module: supervises the construction process through a deep supervision model to determine whether to optimize the construction process.

[0161] The principle of the above technical solution is:

[0162] like Figure 6 As shown, the present invention obtains that in actual construction, the designer obtains the construction standard data in advance, wherein the construction standard data includes various engineering technologies and three-dimensional layout indicators. These indicators are the engineering requirements and three-dimensional structure of the construction process, for example: road grade: first-class highway; vehicle load: highway-Ⅰ grade; design driving speed: 80Km / h; bridge deck width: 29m; earthquake peak acceleration value 0.1g, basic intensity VII; design service life: 100 years; navigation grade: Ⅲ-class waterway, navigation clearance is 165×10m; bridge deck pavement: 10cm asphalt concrete + waterproof layer + 6cmC40 waterproof concrete; safety level: first level; bridge deck transverse slope 2%, formed by the inclined top plate, the longitudinal section is the symmetry line of the bridge span center, the slope change point is set at K13+477.2, the longitudinal slope of the bridge deck is 2.5% symmetrical slope, and the slope change point curve radius is 10000m. The three-dimensional layout indicators are the length and width of the entire bridge body and the geometric parameters of the main beam and other structures. When performing geometric modeling, 3D scanners, CAD software, etc. are required.

[0163] First, scan and identify all components on the construction drawings, then import these components into the corresponding modeling software and model them according to the size and position information on the drawings. Set constraints such as material strength, load specifications, etc. to ensure the feasibility and safety of the modeling results.

[0164] Based on geometric modeling, the construction process is divided and each critical construction period is determined. The critical construction period refers to the stage with the greatest impact and the most focus in the entire construction process. For example, for a steel structure bridge, the main construction stage may be the main beam casting, closing and welding.

[0165] For each key construction cycle, it is necessary to establish a corresponding mechanical model to monitor and control various parameters during the construction process. When implementing this application, the mechanical model is a mathematical model built on physical principles and a statistical model based on actual data. The deep supervision model is a model that uses artificial intelligence technology to comprehensively monitor and control the construction process. It can automatically detect abnormal situations during the construction process, and provide timely warnings and construction strategies, so that construction personnel can make timely adjustments and optimizations to specific construction optimization plans.

[0166] The beneficial effects of the above technical solution are:

[0167] The present invention uses AI technology to achieve real-time monitoring and automatic evaluation of the construction process, quickly identify problems and optimize them. Before and during construction, it is necessary to predict the future state of the structure to assess risks. The AI ​​model can make predictions based on historical data and existing conditions and generate decision-making opinions.

[0168] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A construction control method for a low-tower cable-stayed bridge based on artificial intelligence, characterized in that: include: Obtain construction indicators of low-tower cable-stayed bridges; the construction indicators include: engineering technical indicators and three-dimensional layout indicators; According to the three-dimensional layout indicators, geometric modeling of the low-tower cable-stayed bridge is carried out; Through geometric modeling, the key construction period of the low-tower cable-stayed bridge is divided, and the mechanical model of each key construction period is determined; Through mechanical models and engineering technical indicators, a deep supervision model of low-tower cable-stayed bridges is built; The construction process is supervised through a deep supervision model to determine whether construction technology optimization is necessary.

2. The artificial intelligence-based construction control method for a low-tower cable-stayed bridge according to claim 1, characterized in that: The obtaining of the construction index of the low-tower cable-stayed bridge includes: Obtain project index data for low-tower cable-stayed bridges, input the preset large-scale process model, and determine the construction process data and three-dimensional layout diagram; Conduct cost accounting based on construction process data, determine the engineering process technology that meets cost requirements, and set engineering technology indicators; According to the three-dimensional layout schematic diagram, carry out engineering quantity accounting and environmental adaptability calculation to determine the three-dimensional layout indicators that meet environmental requirements.

3. The artificial intelligence-based construction control method for a low-tower cable-stayed bridge according to claim 1, characterized in that: The geometric modeling of the low-tower cable-stayed bridge according to the three-dimensional layout index includes: Import the three-dimensional layout index into the modeling software to obtain a realistic three-dimensional model of the low-tower cable-stayed bridge; According to the real-life 3D model, geometric splitting is performed to determine the geometric structure of the low-tower cable-stayed bridge; the geometric structure includes: bridge towers, main beams, cable stays, piers, foundations, bearings, railings, and drainage channels; Through geometric structure, geometric modeling of low-tower cable-stayed bridge is carried out.

4. The artificial intelligence-based construction control method for a low-tower cable-stayed bridge according to claim 1, characterized in that: Through geometric modeling, the key construction period of the low-tower cable-stayed bridge is divided into: The geometric model is associated with engineering technical indicators to determine the construction process of the low-tower cable-stayed bridge; the construction process includes beam segment prestressing construction, hanging basket assembly, cantilever casting beam segment construction, side span closure segment construction, middle span closure segment construction and external prestressing construction; According to the construction process, set quality indicators and testing measures for each construction cycle; Empower the process of each construction cycle through testing measures and determine key construction indicators; Determine the critical construction period through key construction indicators.

5. The artificial intelligence-based construction control method for a low-tower cable-stayed bridge according to claim 4, characterized in that: The detection measures include deformation monitoring and asynchronous cradle overturning monitoring throughout the construction process; Deformation monitoring is carried out by presetting linear test reference points on the bottom template of the hanging basket structure, and performing inductance testing. The inductance test data includes: measurement time, temperature value of the measuring point, absolute displacement value, relative displacement value, and zero point value; The asynchronous basket capsizing monitoring is carried out by pre-installing an inclinometer on the basket device for multi-directional testing, and the inclinometer is set with an alarm angle for basket capsizing.

6. The artificial intelligence-based construction control method for a low-tower cable-stayed bridge according to claim 1, characterized in that: The mechanical model for each key construction period is determined, including: According to the construction structure and mechanical indicators within the key construction period, the submechanical equations corresponding to the construction structure are established; According to the submechanical equations, the overall geometric topological relationship of the low-tower cable-stayed bridge is established, and the mechanical transformation matrix between different construction structures of different low-tower cable-stayed bridges is generated; Through the mechanical transformation matrix, the force characteristics and mechanical change laws of each construction structure are determined; Based on the stress characteristics and laws of mechanical changes, a mechanical model for each key construction cycle is generated.

7. The artificial intelligence-based construction control method for a low-tower cable-stayed bridge according to claim 1, characterized in that: The deep supervision model of the low-tower cable-stayed bridge is constructed by using the mechanical model and engineering technical indicators, including: According to the mechanical model and engineering technical indicators, a finite element model of a low-tower cable-stayed bridge is established; the finite element model is used to compare and verify the measured data and finite element analysis results during the construction process; The finite element model is combined with a preset deep neural network to generate a deep supervision model; the deep neural network is used to identify the construction process of the low-tower cable-stayed bridge.

8. The artificial intelligence-based construction control method for a low-tower cable-stayed bridge according to claim 1, characterized in that: The construction process is supervised by the deep supervision model to determine whether to optimize the construction process, including: Obtain measured data during the construction process and input it into the deep supervision model to model the construction process; According to the construction process modeling, quality indicator supervision test and quality risk supervision test are carried out respectively; Based on the quality index supervision test, determine whether process optimization can be carried out and output the process optimization control parameters; The construction process is optimized through process optimization control parameters. When the target construction quality indicators cannot be achieved after multiple construction process optimizations, the construction process risks are determined through quality risk supervision tests.

9. The artificial intelligence-based construction control method for a low-tower cable-stayed bridge according to claim 8, characterized in that: The construction process optimization also includes: According to the construction process modeling, the engineering detail model is built; the engineering detail model relies on the mechanical model construction and the correlation between different construction structures is marked; Based on the engineering detail model, the construction process of each construction structure is scored, and the process optimization coefficient is determined by the quality score and the target process quality. The process optimization coefficient is associated with the process optimization control parameter.

10. A construction control system for a low-tower cable-stayed bridge based on artificial intelligence, characterized in that: include: Construction index collection module: obtains the construction index of the low-tower cable-stayed bridge; the construction index includes: engineering technical index and three-dimensional layout index; Geometric modeling module: geometric modeling of low-tower cable-stayed bridges based on three-dimensional layout indicators; Mechanical model building module: Through geometric modeling, the key construction period of the low-tower cable-stayed bridge is divided and the mechanical model of each key construction period is determined; Deep supervision module: Build a deep supervision model for low-tower cable-stayed bridges through mechanical models and engineering technical indicators; Process optimization module: supervises the construction process through a deep supervision model to determine whether to optimize the construction process.

Images