Multi-stage adjusting method and system for steel structure welding deformation control

Abstract

The invention relates to the technical field of welding deformation control, and discloses a multi-stage adjusting method and system for steel structure welding deformation control. The method comprises the steps that steel member parameters are measured, a welding deformation prediction model is established, and pre-deformation data are obtained; performing accurate pre-deformation processing according to the data; executing segmented welding and recording a temperature field and a deformation amount; performing local heat treatment on the high-stress area to obtain stress distribution; correcting a deformation area by using multi-point force; and performing precision detection and quality evaluation according to the corrected data to form a control file. According to the method, high-precision control over welding deformation of the complex steel structure is achieved through data transmission and feedback adjustment of all stages.

Description

Technical Field

[0001] The present application relates to the technical field of welding deformation control, and in particular to a multi-stage adjustment method and system for controlling welding deformation of steel structures. Background Art

[0002] In the field of large-scale engineering structures, controlling welding deformation of steel structures such as bridges, high-rise buildings, and offshore platforms has always been a key technical challenge in engineering construction. Traditional methods for controlling welding deformation of steel structures mainly include pre-deformation, rigid constraint, reasonable welding sequence, and thermal processing. The pre-deformation method applies deformation opposite to the expected welding deformation to the structure before welding to offset the deformation caused by welding; the rigid constraint method uses external clamps to limit the free deformation of the structure during the welding process; the reasonable welding sequence method optimizes the welding path and sequence so that the deformation caused by each weld offsets each other; and the thermal processing process adjusts the existing deformation through local heating and cooling. These methods have been widely used in actual engineering and have formed relatively mature technical specifications and operating standards.

[0003] However, existing technologies still have obvious shortcomings when dealing with welding deformation control of large and complex steel structures. First, the effect of a single control method is limited, and it is difficult to cope with the various deformation modes in complex structures; second, traditional methods mostly rely on experience and judgment, lack accurate quantitative analysis and prediction capabilities, resulting in low control accuracy; third, welding deformation control is often carried out in isolation, failing to form an organic connection with the entire manufacturing process, and lacking data sharing and feedback mechanisms between various links; fourth, existing methods for deformation control are mostly concentrated before or during welding, and lack systematic and effective correction methods for residual deformation after welding; fifth, there is a lack of a scientific evaluation system for control effects, making it difficult to provide reliable technical references for subsequent similar structures. These shortcomings make deformation control of large steel structures during welding difficult, with low accuracy and low efficiency, affecting the assembly accuracy and service performance of the structure. Summary of the Invention

[0004] The present application provides a multi-stage adjustment method and system for controlling welding deformation of steel structures, which is used to achieve high-precision control of welding deformation of complex steel structures through data transmission and feedback adjustment at each stage.

[0005] In the first aspect, the present application provides a multi-stage adjustment method for controlling welding deformation of steel structures, which includes: establishing a welding deformation prediction model by measuring the geometric parameters of steel structure parts and combining them with welding process parameters to obtain a pre-deformation data set; performing precise pre-deformation treatment on specified positions of steel structure parts according to the pre-deformation data set to obtain pre-treated steel components; performing segmented welding operations on the pre-treated steel components, recording the temperature field distribution and real-time deformation during the welding process, and obtaining a welding deformation record table; based on the welding deformation record table, performing local heat treatment on high stress areas of the welded steel components to obtain a stress distribution map; based on the stress distribution map, applying correction force to the deformed area through multi-point mechanical correction equipment to obtain morphological correction data; using the morphological correction data, performing final precision inspection and quality assessment on the steel structure to form a deformation control file.

[0006] In a second aspect, the present application provides a multi-stage adjustment system for controlling deformation of steel structure welding, the multi-stage adjustment system for controlling deformation of steel structure welding comprising: The measurement module is used to establish a welding deformation prediction model by measuring the geometric parameters of the steel structure and combining them with the welding process parameters to obtain a pre-deformation data set; a processing module, configured to perform precise pre-deformation processing on a designated position of a steel structure according to the pre-deformation data set to obtain a pre-processed steel member; a recording module, configured to perform a segmented welding operation on the pretreated steel component, record the temperature field distribution and real-time deformation during the welding process, and obtain a welding deformation record table; an implementation module, configured to perform local heat treatment on a high stress area of the welded steel component according to the welding deformation record table to obtain a stress distribution diagram; an applying module, configured to apply a correction force to the deformed area through a multi-point mechanical correction device according to the stress distribution diagram to obtain morphological correction data; The evaluation module is used to use the morphological correction data to perform final accuracy detection and quality evaluation on the steel structure to form a deformation control file.

[0007] The third aspect of the present invention provides a computer device comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the computer device executes the above-mentioned multi-stage adjustment method for controlling steel structure welding deformation.

[0008] A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored therein, which, when executed on a computer, enables the computer to execute the above-mentioned multi-stage adjustment method for controlling welding deformation of a steel structure.

[0009] In the technical solution provided by this application, a welding deformation prediction model is established by measuring the geometric parameters of steel structures and combining them with welding process parameters. This transforms traditional empirical predictions into data-driven precise calculations, significantly improving the accuracy of pre-deformation calculations and avoiding over-compensation or under-compensation. At the same time, the generation of a pre-deformation data set provides precise guidance for subsequent processes. Based on the pre-deformation data set, precise pre-deformation treatment is performed on designated locations of steel structures. Combining the composite technology of laser heating and mechanical preloading, precise control of deformation amount and direction is achieved. The acquisition of pre-treated steel components lays a good foundation for subsequent welding work. Segmented welding operations are performed on pre-treated steel components. The symmetrical segmented staggered welding method effectively balances the heat input distribution, significantly reducing the overall deformation trend. At the same time, the temperature field distribution and deformation amount are recorded in real time. The resulting welding deformation record table provides accurate data support for subsequent heat treatment. Based on the welding deformation record table, local heat treatment is performed on high-stress areas. By precisely controlling the heating temperature and cooling rate, residual stress is effectively released. The resulting stress distribution diagram intuitively reflects the stress release effect. Based on the stress distribution diagram, a correction force is applied to the deformed area using multi-point mechanical correction equipment. Using a progressive loading strategy and real-time stress monitoring, deformation correction is achieved safely and efficiently. The resulting morphological correction data comprehensively records the correction process and results. The morphological correction data is used to conduct final precision testing and quality assessment of the steel structure, forming a systematic and complete deformation control archive. This not only verifies the deformation control effect, but also provides valuable experience reference for subsequent similar structures. In particular, the data mining algorithms used in the welding deformation prediction and control process can extract deformation patterns from historical cases, establish a correlation model between process parameters and deformation results, and continuously optimize prediction accuracy through deep learning methods, so that the prediction results can adapt to different structural forms and welding conditions, greatly improving the pertinence and effectiveness of deformation control. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic diagram of an embodiment of a multi-stage adjustment method for controlling welding deformation of a steel structure in an embodiment of the present application; Figure 2 This is a schematic diagram of an embodiment of a multi-stage adjustment system for controlling steel structure welding deformation in an embodiment of the present application; Figure 3 It is a schematic block diagram of the structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0012] The embodiments of the present application provide a multi-stage adjustment method and system for controlling deformation of steel structure welding. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or apparatus that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or that are inherent to these processes, methods, products or apparatus.

[0013] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In one embodiment of the present application, a multi-stage adjustment method for controlling steel structure welding deformation includes: Step S101: Establish a welding deformation prediction model by measuring the geometric parameters of the steel structure and combining them with the welding process parameters to obtain a pre-deformation data set; Step S102: performing precise pre-deformation processing on a designated position of the steel structure according to the pre-deformation data set to obtain a pre-processed steel component; Step S103: performing a segmented welding operation on the pretreated steel component, recording the temperature field distribution and real-time deformation during the welding process, and obtaining a welding deformation record table; Step S104: performing local heat treatment on the high stress area of the welded steel component according to the welding deformation record table to obtain a stress distribution map; Step S105: applying a correction force to the deformed area using a multi-point mechanical correction device according to the stress distribution diagram to obtain morphological correction data; Step S106: Using the morphological correction data, perform final precision inspection and quality assessment on the steel structure to form a deformation control file.

[0014] It is understandable that the execution subject of this application can be a multi-stage adjustment system for steel structure welding deformation control, or a terminal or a server, which is not limited here. The embodiment of this application is described by taking the server as the execution subject as an example.

[0015] Specifically, a welding deformation prediction model is established by measuring the geometric parameters of steel components and combining them with welding process parameters. A 3D laser scanner is used to scan the bridge steel components, acquiring coordinates and geometric dimensions of key nodes. These geometric parameters include girder length, web height, flange width, and weld length and location. Welding process parameters such as welding current, voltage, speed, and heat input are also collected. These parameters are then input into a thermodynamic analysis system to establish a welding deformation prediction model. This model analyzes the heat distribution and transfer during welding using thermodynamic principles to calculate the expected deformation direction and magnitude. For example, for a 50-meter span steel box girder, after measuring its key geometric parameters and combining them with process parameters such as 800A welding current and 30V voltage, the welding heat input is calculated to be 24kJ / cm. Thermodynamic analysis predicts a maximum deflection of 18mm in the middle of the girder and approximately 5mm warping at the flange. These predictions, along with the deformation direction, form a pre-deformation dataset.

[0016] Precise pre-deformation is performed on designated locations of steel components based on the pre-deformation dataset. First, key points requiring pre-deformation are identified based on the dataset, such as the center of the main beam and the support connections. A high-power fiber laser is used to heat these locations in a controlled temperature range of 600-800°C, creating a controllable temperature gradient. Simultaneously, a mechanical loading system applies a force opposite the expected deformation direction to induce pre-deformation. For example, for a predicted 18mm downward deflection in the center of the main beam, an upward pre-deformation of approximately 22mm is applied (accounting for elastic rebound). Infrared thermal imaging is used to monitor the temperature distribution in the heated area in real time to ensure that the temperature remains within the set range and to prevent overheating that could alter material properties. After pre-deformation is complete, a 3D laser scanner is used to measure the actual pre-deformation and compare it to the pre-deformation dataset, ensuring an error within ±1mm. The pre-deformed steel component is then welded in sections. The welding area is first divided into multiple sections based on structural characteristics, and a welding sequence plan is developed. Pulse welding technology is used, with a pulse frequency controlled between 80-120 Hz and a duty cycle of 40%-60%, to minimize heat input and reduce thermal stress concentration. Based on the symmetry of the bridge steel structure, a symmetrical segmented staggered welding method is used, with welding proceeding synchronously from the center to the sides. The length of each weld segment is controlled to be 300-500 mm. During the welding process, a temperature sensor array monitors the temperature distribution in the weld area. When the temperature exceeds 550°C, welding is paused to allow cooling. Simultaneously, a laser interferometer deformation monitoring system tracks structural deformation in real time and records deformation values. For example, during the welding of the box girder web and flange connection weld, the flange deformation after welding was detected to be 3.2 mm, less than the 5 mm predicted in the pre-deformation data. Based on this information, the welding parameters of subsequent welds were adjusted, reducing the welding current to 220 A. The temperature field data and deformation values are integrated into time-series data to form a welding deformation record table.

[0017] Based on the welding deformation record, localized heat treatment is performed on high-stress areas of welded steel components. By analyzing the welding deformation record, stress concentration areas, such as the main beam-crossbeam joints and support connections, are identified. Residual stress in these areas often exceeds 70% of the material's yield strength. These areas are graded and marked, and a high-frequency induction heating system is installed, controlling the heating temperature between 550°C and 650°C for 15-30 minutes. A gradient heating method is used, with the temperature highest at the center and gradually decreasing outward, creating a temperature gradient of 30-50°C / cm. Acoustic emission detection technology is used to monitor stress release within the metal. When the AE signal intensity drops below 30% of the initial value, stress release is sufficient. The cooling rate is then controlled within a range of 15-25°C / min to avoid the generation of new stresses. Finally, X-ray diffraction is used to measure the residual stress distribution in the heat-treated areas, generating a stress map. Based on the stress map, a multi-point mechanical correction device applies correction forces to the deformed areas. First, a high-precision 3D laser scanning system is used to fully scan the heat-treated structure, acquiring point cloud data of the actual deformation with an accuracy of ±0.1mm. The actual deformation data was compared with the design model to generate a deformation vector diagram, identifying key points requiring correction. A multi-point synchronous correction system was designed, consisting of multiple sets of hydraulic servo actuators, each providing a correction force ranging from 10 to 50 tons. The correction force was applied using a progressive loading pattern, initially at 50% of the target force and then increasing in increments of 10%. For example, for a 12mm deformation in the center of the main beam, an initial correction force of 20 tons was applied, gradually increasing to 40 tons until the deformation returned to the design tolerance. During the correction process, a strain monitoring system monitored stress changes in real time to ensure that no new excessive stresses were introduced. After correction, morphological correction data was generated, including comparisons of deformation before and after correction. The morphological correction data was used to conduct final accuracy inspection and quality assessment of the steel structure. High-precision 3D laser scanning technology was used to measure the corrected structure in full scale, generating a measured geometric model. Overrun analysis was performed against the original design model, and dimensional deviations at key locations were calculated to ensure that the linear deviation of the bridge main beam was within 2mm / m. At the same time, a portable X-ray diffractometer is used to measure the residual stress of key welds and heat-affected zones to ensure that the residual stress is reduced to less than 30% of the material's yield strength. The internal quality of the welds is inspected using ultrasonic phased array testing, and the weld quality data is recorded. Vibration modal testing is performed on the bridge steel structure to obtain the first five natural frequencies, which are compared with the predicted values of the finite element model to ensure that the deviation is controlled within ±5%. Static load tests are performed on key connection nodes, applying 1.2 times the design load to monitor deformation recovery performance. The technical parameters of the entire process and the measured data are integrated to form a deformation control file.

[0018] In the embodiment of the present application, a welding deformation prediction model is established by measuring the geometric parameters of the steel structure and combining them with the welding process parameters. The traditional empirical prediction is transformed into a data-driven precise calculation, which greatly improves the accuracy of the pre-deformation calculation and avoids over-compensation or under-compensation. At the same time, the generation of the pre-deformation data set provides accurate guidance for subsequent processes. According to the pre-deformation data set, the specified position of the steel structure is precisely pre-deformed. Combining the composite technology of laser heating and mechanical preloading, the deformation amount and deformation direction are precisely controlled. The acquisition of the pre-treated steel component lays a good foundation for subsequent welding work. The pre-treated steel component is subjected to segmented welding operations. The heat input distribution is effectively balanced through the symmetrical segmented staggered welding method, which significantly reduces the overall deformation trend. At the same time, the temperature field distribution and deformation amount are recorded in real time. The resulting welding deformation record table provides accurate data support for subsequent heat treatment. According to the welding deformation record table, local heat treatment is performed on the high stress area. By precisely controlling the heating temperature and cooling rate, the residual stress is effectively released. The obtained stress distribution diagram intuitively reflects the stress release effect. Based on the stress distribution diagram, a correction force is applied to the deformed area using multi-point mechanical correction equipment. Using a progressive loading strategy and real-time stress monitoring, deformation correction is achieved safely and efficiently. The resulting morphological correction data comprehensively records the correction process and results. The morphological correction data is used to conduct final precision testing and quality assessment of the steel structure, forming a systematic and complete deformation control archive. This not only verifies the deformation control effect, but also provides valuable experience reference for subsequent similar structures. In particular, the data mining algorithms used in the welding deformation prediction and control process can extract deformation patterns from historical cases, establish a correlation model between process parameters and deformation results, and continuously optimize prediction accuracy through deep learning methods, so that the prediction results can adapt to different structural forms and welding conditions, greatly improving the pertinence and effectiveness of deformation control.

[0019] In a specific embodiment, the process of executing step S101 may specifically include the following steps: Perform 3D scanning on bridge steel structures to obtain the geometric parameters and key node coordinates of the structures; The geometric parameters and welding process parameters are input into the processing system to build a welding deformation prediction model; The welding deformation prediction model is divided into grid units, and the grid of the weld area is encrypted to obtain a fine grid in the welding area; Thermal cycle analysis of the steel structure welding process is performed based on fine mesh in the welding area to obtain temperature field distribution data; Calculate welding stress and deformation using a welding deformation prediction model based on temperature field distribution data to generate deformation prediction data; Correct the deformation prediction data under bridge load conditions, taking into account the effects of the structure's deadweight and service loads, and obtain the corrected deformation value; Determine the pre-deformation compensation amount based on the corrected deformation value and calculate the pre-deformation position parameters of each node; The pre-deformation position parameters are compared and analyzed with the original parameters to generate a pre-deformation data set including deformation direction, deformation amount and implementation position.

[0020] Specifically, bridge steel components are 3D scanned to obtain their geometric parameters and key node coordinates. A high-precision 3D laser scanner is used to comprehensively scan the steel structure. The spatial coordinates of the laser reflection points are determined through triangulation, generating point cloud data. The point cloud data density typically reaches 50-100 points per square centimeter, ensuring sufficient measurement accuracy. For bridge steel structures, geometric information is primarily collected for key components such as main beams, crossbeams, and connection nodes. This includes parameters such as dimensions, thickness, and angles, as well as the location and length of welds. These geometric parameters form the basis of a digital model of the steel structure and provide input data for subsequent analysis. These geometric parameters and welding process parameters are input into a processing system to construct a welding deformation prediction model. Welding process parameters include welding current, voltage, speed, heat input, and welding sequence. The processing system integrates this data to develop a welding thermodynamic analysis model. This model, based on thermoelastic theory, considers the temperature-dependent changes in material physical properties at high temperatures, such as the coefficient of thermal expansion, elastic modulus, and yield strength. The process of establishing the welding deformation prediction model integrates experimental data and theoretical calculations. Through the analysis of historical cases, the corresponding relationship between key parameters and deformation is established to form a prediction algorithm.

[0021] The welding deformation prediction model is divided into grid cells, and the mesh of the weld area is encrypted to obtain a fine mesh in the weld area. The mesh division adopts adaptive mesh technology, which automatically adjusts the mesh density according to the structural geometric characteristics and stress gradient. For the weld and its heat-affected zone, the mesh size is usually controlled at 1-3mm, while the mesh size of the area away from the weld can be relaxed to 10-20mm. This differentiated mesh division strategy greatly improves the calculation efficiency while ensuring the calculation accuracy of the weld area. The mesh quality is evaluated by indicators such as distortion rate and aspect ratio to ensure that the mesh quality meets the requirements of numerical calculation.

[0022] Based on the fine mesh of the welding area, a thermal cycle analysis of the steel structure welding process is performed to obtain temperature field distribution data. The thermal cycle analysis uses a moving heat source model to simulate the movement of the welding arc on the weld. The heat source model uses a double ellipsoid heat source or a Gaussian heat source distribution to consider the distribution characteristics of heat in the depth and plane directions. By solving the heat conduction equation, the temperature values of each point in the structure that change with time during the welding process are calculated. The thermal cycle analysis takes into account the changes in the thermophysical parameters of the material with temperature, such as thermal conductivity, specific heat capacity, etc., while also considering convection and radiation heat dissipation. The analysis results include temperature time history curves and temperature spatial distribution, which provide input for subsequent stress analysis.

[0023] The welding stress and deformation are calculated based on the temperature field distribution data through the welding deformation prediction model to generate deformation prediction data. This calculation uses the thermoelastic-plastic finite element method. Based on the temperature field data, the thermal expansion, phase change and elastic-plastic deformation of the material are considered to calculate the stress field during the welding process and the final residual stress distribution. It can be calculated by the following formula: ; in, represents the elastic modulus at the tth time step, represents the thermal expansion coefficient at the tth time step, represents the temperature at the tth time step, represents the reference temperature, represents the stress increment caused by plastic strain, and T is the total number of time steps. The welding deformation is obtained by calculating the node displacement, taking into account the combined effects of elastic deformation, plastic deformation and thermal expansion deformation.

[0024] The deformation prediction data is corrected under bridge load conditions, taking into account the effects of the structure's deadweight and service loads to obtain a corrected deformation value. The loads borne by the bridge in service include deadweight, vehicle loads, wind loads, etc. These loads will have a superimposed or offsetting effect on welding deformation. The correction process first establishes a structural mechanics model, applies the corresponding loads, and calculates the deformation under the action of the load. The load deformation and welding deformation are then superimposed and analyzed to obtain a comprehensive deformation value. The correction method takes into account the linear characteristics of load deformation and the nonlinear characteristics of welding deformation, and calculates the final deformation state through the superposition principle.

[0025] The pre-deformation compensation amount is determined based on the corrected deformation value, and the pre-deformation position parameters of each node are calculated. The pre-deformation compensation adopts the reverse deformation method, that is, before welding, a deformation opposite to the expected welding deformation direction is applied to the structure. The compensation amount is not a simple equal compensation, but takes into account the elastic rebound performance of the material and the structural stiffness distribution, and is adjusted by the compensation coefficient K. The pre-deformation position parameters include the pre-deformation direction vector and the pre-deformation amount. The new coordinates of each node after pre-deformation are obtained by coordinate transformation calculation. The pre-deformation position parameters are compared and analyzed with the original parameters to generate a pre-deformation data set containing the deformation direction, deformation amount and implementation position. During the comparative analysis process, the displacement difference and direction difference of each node are calculated to evaluate the effectiveness and accuracy of the pre-deformation. The pre-deformation data set is recorded in the form of a data table and a three-dimensional model, and contains specific operation instructions, such as the position of the pre-deformation point, heating temperature, mechanical loading force and other parameters.

[0026] Taking a steel box girder bridge as an example, the pre-deformation control process for the central section of the main girder is described. First, the box girder geometric parameters, including a 2.5m top plate width, a 1.8m web height, and a 25mm steel plate thickness, are acquired through 3D scanning. Combined with welding process parameters of 800A current and 30V voltage, these parameters are input into a processing system to construct a welding deformation prediction model. The model is meshed with a 2mm mesh size in the weld region, gradually increasing to 15mm away from the weld, for a total of approximately 110,000 mesh elements. Thermal cycle analysis reveals that the maximum temperature in the weld region reaches 1450°C, with a temperature gradient of approximately 300°C / cm in the heat-affected zone. The expected deflection of the central section of the main girder is calculated to be 18mm. After accounting for the 7mm camber caused by the structure's deadweight, the corrected deflection is 11mm. Taking into account material elastic rebound, the pre-deformation compensation is determined to be 13mm camber. Finally, a pre-deformation dataset is generated, containing 11 pre-deformation points along the main girder, the pre-deformation direction and magnitude at each point, as well as specific heating parameters and mechanical loading forces.

[0027] In a specific embodiment, the process of executing step S102 may specifically include the following steps: Determine the key points of pre-deformation of the bridge steel structure based on the pre-deformation data set and generate a pre-deformation operation guide; Configure a high-power fiber laser based on the pre-deformation operating instructions and set the laser heating parameters; Laser directional heating is performed on the designated position of the steel structure to form a temperature gradient area; Setting a mechanical preloading system according to the pre-deformation amount in the pre-deformation data set and determining the loading force value; An external force consistent with the pre-deformation direction is applied to the heating area through a mechanical preloading system to produce initial deformation; Use infrared thermal imaging equipment to monitor the temperature of the laser heating area in real time and obtain temperature distribution data; Adjust laser power and scanning speed based on temperature distribution data to control pre-deformation progress; The pre-deformed structure was measured using a 3D laser scanner and compared with the pre-deformed data set to obtain the pre-treated steel component.

[0028] Specifically, the pre-deformation key points of the bridge steel structure are determined based on the pre-deformation data set, and the process of generating the pre-deformation operation guide begins with data analysis. The pre-deformation data set contains information on deformation direction, deformation amount, and implementation location. The locations where the deformation exceeds the critical value are extracted as key points through a data screening algorithm. The key point screening uses a gradient analysis method to determine the areas with the largest deformation gradient and set pre-deformation operation points in these areas. For bridge steel structures, the main key points are usually distributed in the mid-span area of the main beam, the connection nodes of the main and secondary beams, and the support connection area. The generation of the operation guide adopts a parametric method, integrating the position coordinates, pre-deformation direction, pre-deformation amount, and required operation methods of each key point into a structured data table, including parameters such as the heating point position, heating temperature, heating time, and mechanical loading force value and direction.

[0029] When configuring a high-power fiber laser based on the pre-deformation operating guide and setting the laser heating parameters, heat calculations are required. First, the heat input required to reach the desired temperature is calculated based on the physical properties of the steel (such as specific heat capacity, thermal conductivity, density, etc.). Laser heating parameters include laser power, spot size, scanning speed, and scanning path. For typical steel used in bridge structures, such as Q345 steel, the laser power is usually set in the range of 5-10 kilowatts, and the spot diameter is adjusted between 10-30 mm according to the size of the heating area. The scanning speed setting is based on the heat input calculation, usually in the range of 5-15 mm / s to ensure sufficient heat deposition without causing overheating. Scanning path planning takes into account the heat conduction law in the structure, and usually adopts a spiral or raster path to ensure uniform heat distribution.

[0030] Laser-directed heating is performed on designated locations of steel structures to form temperature gradient areas. The laser beam is precisely positioned at the key points of pre-deformation through the optical path system. During the heating process, laser energy is converted into thermal energy, forming a high-temperature area on the surface of the steel. The heat is conducted to the inside and the surroundings, forming a temperature gradient. The formation of the temperature gradient area is the key to pre-deformation, because the uneven temperature distribution leads to uneven thermal expansion of the material, which generates internal stress. These internal stresses are converted into residual stress and plastic deformation after cooling. The heating control adopts a closed-loop method. The laser parameters are adjusted through real-time temperature monitoring to ensure that the temperature is controlled within the set range, usually below the phase transition temperature of the steel (about 700-800℃), to avoid changes in the material structure affecting the structural performance.

[0031] The mechanical preloading system is set according to the pre-deformation amount in the pre-deformation data set, and the process of determining the loading force value involves mechanical calculations. Based on the elastic-plastic properties of the material and the temperature-related yield strength, the external force required to produce the expected deformation under high temperature conditions is calculated. The mechanical preloading system consists of a hydraulic actuator and a control unit. The force value setting takes into account the reduction in the high-temperature strength of the material and is usually 50-70% of the force required at room temperature. The direction of application of the loading force is opposite to the expected welding deformation direction to achieve a compensation effect. The calculation of the loading force value also takes into account the distribution of structural stiffness. For areas with greater stiffness, the loading force is appropriately increased to ensure that the deformation meets the requirements.

[0032] An external force consistent with the pre-deformation direction is applied to the heated area through a mechanical preloading system. Precise force and heat synergistic control is performed during initial deformation. The application of mechanical force is synchronized with the formation of the temperature field. When the material reaches its optimal plastic state (temperature is usually in the range of 500-600°C), the maximum mechanical force is applied to achieve plastic deformation. The application of mechanical force adopts a progressive loading strategy, initially at 50% of the target force, and gradually increases to the set value as the temperature rises to avoid local damage caused by sudden force increases. Under the synergistic effect of force and heat, the steel structure undergoes plastic deformation at the key points of pre-deformation. This deformation is retained after cooling, forming a pre-deformed state.

[0033] Using infrared thermal imaging equipment to monitor the laser-heated area in real time and obtain temperature distribution data is a key step in precise control. Infrared thermal imagers capture infrared radiation from the steel surface, convert it into a temperature image, and display the temperature distribution. The data acquisition frequency is typically 10-20 Hz, ensuring timely capture of temperature changes. Temperature data is recorded in a matrix format, with each pixel corresponding to a temperature value, forming a temperature distribution map. Data processing, including noise filtering, emissivity correction, and background temperature elimination, improves temperature measurement accuracy. For large bridge structures, multiple thermal imagers are often required to work together, using data fusion technology to generate a complete temperature distribution map. An intelligent control algorithm is used to adjust laser power and scanning speed based on temperature distribution data to control the pre-deformation progress. The control algorithm first analyzes the temperature distribution data in real time, calculating the deviation between the current temperature and the target temperature, as well as the temperature change rate. Based on the deviation size and trend, the laser power and scanning speed are adjusted to achieve precise temperature control. The adjustment strategy uses the PID (proportional-integral-derivative) control principle, calculating the control variable based on the temperature deviation, the integral of the deviation, and the rate of change of the deviation to ensure that the temperature remains stable within the target range. When the temperature is detected approaching the preset upper limit, the laser power is automatically reduced or the scanning speed is increased; when the temperature is below the lower limit, the power is increased or the speed is reduced. This closed-loop control ensures that the temperature field distribution during the pre-deformation process meets the expected level, thus achieving precise pre-deformation control.

[0034] The key to quality verification is to use a 3D laser scanner to measure the pre-deformed structure and compare and analyze it with the pre-deformation data set to obtain the process of pre-treated steel components. The 3D laser scanner emits lasers and receives reflected signals to measure the spatial coordinates of points on the surface of the structure, forming point cloud data of the pre-deformed structure. The point cloud data is filtered, aligned, and reconstructed to generate a pre-deformed 3D model. During the comparison and analysis process, the actual pre-deformed model is compared with the target model in the pre-deformation data set, and the positional deviation and directional deviation of each key point are calculated. The deviation analysis results are used to evaluate the quality of the pre-deformation. When the deviation exceeds the allowable range, secondary adjustments are required until the requirements are met. The final confirmed pre-treated steel components become the basis for the next stage of welding operations.

[0035] In a specific embodiment, the process of executing step S103 may specifically include the following steps: Divide the welding area of the pre-treated steel components into sections and generate a welding sequence planning table; Set pulse welding current parameters according to the welding sequence planning table and adjust the pulse frequency and duty cycle; The bridge steel structure is welded using a symmetrical segmented staggered welding method to form the initial welds; Real-time temperature monitoring of the welding area is performed through a temperature sensor array to obtain dynamic temperature field data; Determine the thermal cycle threshold based on the dynamic data of the temperature field and control the cooling time of the welding gap; The laser interferometer deformation monitoring system is used to track the structural deformation during welding in real time and record the deformation value; Dynamically adjust the welding parameters of subsequent welds according to the deformation value and perform compensation welding; The temperature field dynamic data and deformation values are integrated into time-series correlation data to generate a welding deformation record table.

[0036] Specifically, segmentation is based on structural stress distribution and deformation sensitivity analysis, dividing the weld into several sections of similar length. For bridge steel structures, the segment length is typically controlled between 300-500 mm to avoid excessive heat input in a single section, which could lead to concentrated local deformation. Welding sequence planning utilizes the principle of thermal balance, calculating the heat input and cooling time for each weld section and arranging the welding sequence to achieve a balanced heat distribution across the entire structure. The welding sequence planning table contains the weld number, location, length, welding parameters, and welding sequence for each weld section, providing detailed instructions for the welding operation. Pulse welding current parameters are set according to the welding sequence planning table, and the pulse frequency and duty cycle are optimized based on the characteristics of each weld section. Pulse welding is a welding technique that uses a periodically varying current. The pulse frequency is defined as the number of pulses per second (in Hertz), while the duty cycle is the percentage of the pulse duration over the entire cycle. For bridge steel welding, the pulse frequency is typically set between 80-120 Hz, with a duty cycle between 40% and 60%. The parameter setting takes into account factors such as weld position, plate thickness, and gap size. For key stress-bearing parts such as the connection nodes between the main beam and the cross beam, a lower pulse frequency and duty cycle are used to reduce heat input and residual stress; for non-critical parts, the frequency and duty cycle can be appropriately increased to improve welding efficiency.

[0037] The symmetrical segmented staggered welding method is used to weld bridge steel structures. The initial weld formation adheres to the principle of thermal balance. Symmetrical segmented staggered welding involves welding the welds on both sides of the structure's symmetrical plane simultaneously in symmetrical positions, with adjacent weld segments welded in staggered patterns. The welding process begins in the center of the structure and then progresses symmetrically to both sides. After completing each weld segment, the welder moves to the corresponding position on the other side of the structure to weld the next segment. This welding method effectively balances welding heat input and minimizes overall deformation. During staggered welding, adjacent weld segments are kept a certain distance apart to avoid heat concentration. The welding direction of each weld segment also considers stress distribution, typically welding from less constrained areas to more constrained areas. Real-time temperature monitoring of the weld area using a temperature sensor array and obtaining dynamic temperature field data are critical for controlling welding quality. This temperature sensor array consists of multiple high-precision thermocouples or infrared temperature sensors, arranged along the weld and surrounding areas to form a monitoring network. The sensor data acquisition frequency is typically 5-10 Hz, ensuring timely capture of temperature changes. Dynamic temperature field data consists of three dimensions: timestamp, spatial coordinates, and temperature values, forming a spatiotemporal temperature field matrix. Data processing includes noise filtering, outlier removal, and interpolation calculations to generate a continuous temperature field distribution map. Real-time monitoring of temperature changes in the weld area and heat-affected zone allows for the determination of thermal cycle status and provides a basis for subsequent welding parameter adjustments.

[0038] The process of determining the thermal cycle threshold and controlling the cooling time of the weld gap based on dynamic temperature field data involves thermodynamic analysis. The thermal cycle threshold refers to the critical point at which the temperature in the weld zone drops to a safe value, typically set at 300-350°C. At this temperature, the plastic deformation capacity of the steel material decreases significantly, and continued welding will not cause excessive cumulative deformation. Cooling time control is based on the rate of change analysis of temperature field data. By calculating the rate of temperature drop, the time required to reach the threshold temperature is predicted. If the temperature in the previous weld zone is still above the threshold, the next weld is delayed until the temperature drops. Precise control of the cooling time prevents excessive heat accumulation in the structure, minimizing thermal stress concentration and plastic deformation. The core technology of deformation control is to use a laser interferometer deformation monitoring system to track structural deformation during welding in real time and record deformation values. The laser interferometer deformation monitoring system consists of a laser transmitter, a reflector, and an interferometer signal receiver. By measuring tiny changes in the laser path length, it achieves submicron deformation monitoring accuracy. Monitoring points are set at key locations in the structure, such as the mid-span of the main beam, the end of the cantilever, and the support area. Deformation data is recorded as a time series, including the displacement values of each monitoring point at different times. Data processing includes interferometric signal demodulation, baseline drift correction, and temperature compensation to obtain the true structural deformation curve. By comparing the actual deformation with the predicted deformation, the deformation control effect of the welding process can be evaluated.

[0039] The welding parameters of subsequent welds are dynamically adjusted according to the deformation value. The process of performing compensation welding embodies the principle of adaptive control. When the deformation of a certain area is detected to exceed expectations, the welding parameters of subsequent related welds are adjusted, including reducing the welding current, reducing the welding speed, or changing the welding sequence. The adjustment strategy is based on the correlation model between deformation and welding parameters. By analyzing historical data, a parameter sensitivity matrix is established to quantify the impact of parameter changes on deformation. For example, for areas where the deformation exceeds expectations by 10%, the welding current of subsequent welds is reduced by 5-8%, or the pulse frequency is increased by 10-15% to reduce heat input. Compensation welding also includes adding cooling measures in deformation-sensitive areas, such as local compressed air cooling or CO2 refrigeration, to accelerate heat dissipation and reduce the heat accumulation effect.

[0040] The process of integrating temperature field dynamic data and deformation values into time-series correlation data and generating a welding deformation record table is a key step in data fusion and mining. Time-series correlation data links temperature data and deformation data through timestamps to establish a temperature field-deformation relationship model. Data integration uses multi-source data synchronization technology to ensure the temporal consistency of data from different sources. Correlation analysis includes the calculation of time lag effects, that is, the delay time of deformation response relative to temperature change. This parameter is crucial for understanding the thermal-deformation coupling mechanism. The welding deformation record table is stored in a structured format and contains multi-dimensional information such as weld information, welding parameters, temperature field data, deformation data, and parameter adjustment records. The record table becomes an important basis for subsequent heat treatment and deformation correction, and also provides reference data for welding deformation control of similar structures.

[0041] In a specific embodiment, the process of executing step S104 may specifically include the following steps: By analyzing the temperature field distribution and deformation data in the welding deformation record table, the residual stress concentration area in the bridge steel component is determined; Mark the residual stress concentration area in grades and generate the heat treatment area division map; Configure high-frequency induction heating equipment according to the heat treatment area division diagram and set the heating power and frequency parameters; Based on the heat treatment area division map, gradient heating is performed on the marked area to form a temperature gradient field; Use infrared thermal imaging system to monitor the heating process in real time and obtain the heat treatment temperature curve; Monitor the stress release process inside steel components through acoustic emission detection equipment and record stress release signals; Adjust cooling system parameters according to stress release signals to control cooling rate; An X-ray diffraction device is used to measure the residual stress of the steel component after heat treatment and generate a stress distribution map.

[0042] Specifically, identifying residual stress concentration areas in bridge steel components by analyzing the temperature field distribution and deformation data from welding deformation records is a prerequisite for accurate stress release. The welding deformation record contains temperature field data for each weld segment and deformation data at the corresponding locations. Data mining techniques are used to extract temperature-deformation correlations and identify residual stress distribution characteristics. Data analysis utilizes a gradient screening method. The deformation gradient, defined as the rate of change of deformation per unit length, is first calculated. Regions with large deformation gradients typically correspond to areas of residual stress concentration. Combined with the temperature field data, the maximum temperature and cooling rate during welding are analyzed, as these two parameters are closely related to residual stress formation. The specific method involves extracting the cooling rate from the temperature-time curve and converting it into an estimated residual stress value using an empirical formula. For bridge steel structures, residual stress concentration areas are primarily located at weld intersections, areas of sudden stiffness changes, and the edges of the heat-affected zone. Stress levels in these areas often approach or even exceed the material's yield strength. Residual stress concentration areas are graded and labeled, and the process of generating a heat treatment zone partitioning map involves region clustering and prioritization. Based on the calculated residual stress estimate, a three-level classification standard is adopted: the first-level area is a high-risk area where the residual stress exceeds 80% of the material's yield strength, the second-level area is a medium-risk area where the residual stress is between 50% and 80% of the yield strength, and the third-level area is a low-risk area where the residual stress is between 30% and 50% of the yield strength. Regional clustering uses spatial correlation analysis to merge points with similar stress values and adjacent positions into one heat treatment area to avoid excessive fragmentation. At the same time, considering the importance of the structure, the stress area of the key load-bearing parts is upgraded. The heat treatment area division map intuitively displays the stress level and boundaries of each area in the form of color coding. The first-level area is marked in red, the second-level area is yellow, and the third-level area is green, forming an intuitive guide map for heat treatment operations.

[0043] High-frequency induction heating equipment is configured according to the heat treatment zone division diagram. The process of setting heating power and frequency parameters must take into account material properties and zone geometry. High-frequency induction heating utilizes the principle of electromagnetic induction, generating induced currents and eddy current losses in metals through high-frequency alternating current, achieving contactless heating. Different heating parameters are set for different levels of heat treatment zones: the primary zone utilizes higher power (30-40kW) and longer hold times (20-30 minutes); the secondary zone utilizes medium power (20-30kW) and medium hold times (15-20 minutes); and the tertiary zone utilizes lower power (10-20kW) and shorter hold times (10-15 minutes). The frequency parameter selection takes into account the skin effect of the induced current. For thicker plate areas, a lower frequency (8-12kHz) is used to increase heating depth, while for thinner plate areas, a higher frequency (20-30kHz) is used to improve heating efficiency. The shape and size of the induction coil are customized to the geometric characteristics of the heat treatment zone to ensure heating uniformity. Based on the heat treatment area division map, gradient heating is applied to the marked area to form a temperature gradient field, which is the core link of stress release. Gradient heating refers to the formation of a temperature distribution that decreases from the center to the outside inside the heat treatment area, rather than uniform heating. In specific operations, the center of the first-level area is first heated to the target temperature (550-650°C), and then the heating range is expanded outward to form a temperature gradient of 30-50°C / cm. This gradient heating method can generate internal stress during the heating process and guide the redistribution and release of residual stress in the softened state of the material. The heating rate is strictly controlled during the heating process, usually 150-200°C / minute, to avoid new thermal stress caused by excessive heating. For multiple adjacent heat treatment areas, multi-point synchronous heating technology is adopted, and the optimal heating point position and heating sequence are designed according to the structural symmetry and stiffness distribution to ensure that the overall structure is heated evenly and avoid new deformation during the heating process.

[0044] Using an infrared thermal imaging system to monitor the heating process in real time and obtain the heat treatment temperature curve is a key technology for temperature control. The infrared thermal imaging system captures the infrared radiation emitted by the surface of the object and converts it into a temperature distribution image. During the monitoring process, the thermal imager collects images at a frequency of 5-10 frames per second, covering the entire heat treatment area. The temperature data is stored in a matrix format, with each pixel corresponding to a temperature value. Data processing includes emissivity correction, background temperature compensation, and noise filtering to improve temperature measurement accuracy. The heat treatment temperature curve records the temperature changes of each monitoring point over time, including the heating section, the holding section, and the cooling section. The temperature curve analysis focuses on several key parameters: heating rate, maximum temperature, holding time, and cooling rate. These parameters directly affect the stress release effect. When the temperature curve is detected to deviate from the preset target, the heating power is dynamically adjusted through the closed-loop control system to ensure that the temperature is controlled within the set range.

[0045] Acoustic emission testing equipment is used to monitor the stress release process within steel components and record the stress release signal, providing a direct method for determining the adequacy of stress release. Acoustic emission testing utilizes transient elastic waves generated by the release of elastic energy under stress for nondestructive testing. During heat treatment, as temperature increases and holding time increases, residual stresses gradually release, causing tiny dislocation slips and microcrack closures. These microscopic changes generate acoustic emission signals. Acoustic emission sensors are attached around the heat treatment area and collect acoustic signals in real time, typically at a sampling frequency of 1-2 MHz. The acoustic signals undergo pre-amplification, filtering, and feature extraction to extract characteristic parameters such as amplitude, frequency, energy, and duration. During the stress release process, the intensity and frequency of the acoustic emission signal decrease as the degree of stress release increases. When the signal intensity drops to 20-30% of the initial value and the signal frequency continues to decrease, stress release is essentially complete and the cooling phase can begin.

[0046] Adjusting the cooling system parameters according to the stress release signal and controlling the cooling rate are key links in preventing the generation of new stress. The cooling control adopts a segmented speed change strategy. A slower cooling rate (10-15°C / minute) is adopted in the high temperature section (650-450°C), and the cooling rate is appropriately increased (15-25°C / minute) in the medium temperature section (450-300°C). Natural cooling can be used in the low temperature section (below 300°C). The cooling system includes air cooling and water cooling devices, and the cooling rate is controlled by adjusting the flow and temperature of the cooling medium. The adjustment of cooling parameters is based on the trend of changes in the acoustic emission signal. When a sudden increase in the intensity of the acoustic emission signal is detected, it indicates that new stress concentration has occurred during the cooling process. The cooling rate needs to be reduced immediately, and reheating is required if necessary to eliminate the newly generated stress. Continuously monitor the structural deformation during the cooling process to ensure that the deformation caused by cooling is within a controllable range.

[0047] Using an X-ray diffraction device to measure the residual stress of steel components after heat treatment and generate a stress distribution map is a quantitative means of evaluating the stress release effect. The X-ray diffraction method uses the principle of crystal diffraction to calculate the stress state inside the material by measuring the change in the interplanar spacing. During measurement, the X-ray beam is irradiated onto the surface of the material, generating a diffraction pattern according to Bragg's law. The lattice strain is calculated by analyzing the change in the diffraction angle and then converted into a stress value. The arrangement of the residual stress measurement points adopts the grid method. Multiple measuring points are arranged in and around the heat treatment area. Usually 5-10 measuring points are set in each heat treatment area to form a measurement network. Each measuring point measures the stress components along different directions to obtain the stress tensor. The measured data is corrected and interpolated to generate a continuous stress distribution map, which intuitively displays the stress magnitude and direction. The stress distribution map is represented in the form of colored contour lines, with different colors corresponding to different stress levels, which facilitates intuitive judgment of the stress release effect.

[0048] The heat treatment process for the main girder-crossbeam connection of a steel box girder bridge is illustrated by analyzing the welding deformation log. The peak temperature in the joint region reached 1480°C, with a cooling rate of 45°C / second, corresponding to a deformation of 5.8 mm, significantly higher than the average for other regions. Data analysis revealed an estimated residual stress of 345 MPa in this region, approaching 95% of the yield strength of Q345 steel. This region was designated as a primary stress concentration zone. Secondary and tertiary zones were then delineated around the joint to create a heat treatment zone map. Based on this map, a 35kW high-frequency induction heating system was deployed, with frequencies set to 10kHz for the primary zone, 15kHz for the secondary zone, and 25kHz for the tertiary zone. Gradient heating was implemented, initially heating the center of the primary zone to 600°C and then gradually expanding outward, creating a temperature gradient field with a center temperature of 600°C and an edge temperature of 450°C. An infrared thermal imaging system monitored the temperature distribution throughout the process, recording a heating rate of 180°C / minute and a stable temperature of 595-605°C during the holding phase. At the same time, the acoustic emission sensor detected that the signal intensity began to decrease significantly after 8 minutes of heating, and dropped to 25% of the initial value after 15 minutes, indicating that the stress was fully released. According to the changes in the acoustic emission signal, the cooling rate was controlled at 12°C / minute, and after cooling to 300°C, it was switched to natural cooling. Finally, the residual stress was measured by X-ray diffraction. It was found that the maximum residual stress in the node area after heat treatment dropped to 125MPa, which is about 36% of the yield strength of the material. The average stress reduction in the heat-treated area reached 68%. The generated stress distribution diagram showed that the stress distribution was more uniform, the high stress area was significantly reduced, and the heat treatment achieved the expected effect.

[0049] In a specific embodiment, the process of executing step S105 may specifically include the following steps: A high-precision 3D laser scanning system is used to comprehensively scan the heat-treated bridge steel structure to obtain actual deformation point cloud data; Compare the actual deformed point cloud data with the design model to generate a deformed vector diagram; Determine the key points of correction based on the deformation vector diagram and stress distribution diagram, and form a correction point distribution table; Design a multi-point synchronous correction scheme based on the correction point distribution table to determine the magnitude and direction of the correction force; Configure parameters for the multi-point mechanical correction equipment and set the loading sequence and loading rate of the hydraulic servo actuator; Implement progressive loading on the deformed area through multi-point mechanical correction equipment to form a preliminary correction state; Use the strain monitoring system to monitor the stress changes during the calibration process in real time and record the stress change curve; The correction process is adjusted based on the stress change curve until the deformation returns to the design tolerance range and the morphological correction data is generated.

[0050] Specifically, a high-precision 3D laser scanning system was used to comprehensively scan the heat-treated bridge steel structure, acquiring actual deformation point cloud data, which is essential for accurate calibration. This high-precision 3D laser scanning system utilizes the phase-based ranging principle. By emitting laser light and receiving reflected signals, the system calculates the laser propagation time and phase differences to measure the 3D coordinates of spatial points. During the scanning process, the laser emitter moves along a pre-set path, forming a scanning grid and capturing a spatial point cloud of the structure's surface. The point cloud data density typically ranges from 5,000 to 10,000 points per square meter, with a measurement accuracy of ±0.1 mm. After data acquisition, preliminary processing is performed, including noise point filtering, outlier removal, and coordinate system conversion. Noise point filtering utilizes statistical outlier analysis to calculate the average distance between each point and its neighbors. Points that deviate from the average distance by more than three standard deviations are identified as noise points and removed. Coordinate system conversion converts the local coordinate data obtained from the scans to the bridge's design coordinate system, facilitating subsequent comparative analysis.

[0051] The process of comparing the actual deformed point cloud data with the design model and generating a deformation vector diagram is a key step in deformation quantification. The design model usually exists in the form of a three-dimensional CAD model or a finite element model, which contains the ideal geometric shape and size information of the structure. The comparative analysis first aligns the point cloud with the model. The iterative closest point (ICP) algorithm is used to achieve precise alignment between the point cloud data and the design model surface by minimizing the distance and normal deviation between the point cloud data and the design model surface. After the alignment is completed, the distance and direction from each point in the point cloud to the corresponding position of the design model are calculated to form the deformation amount and deformation direction data. The deformation vector diagram intuitively displays the deformation status of each part of the structure in a color-coded manner. Red indicates severe deformation areas that exceed the tolerance, yellow indicates critical deformation areas, and green indicates areas within the tolerance range. The length of the deformation vector arrow indicates the magnitude of the deformation, and the direction of the arrow indicates the deformation direction, which intuitively displays the deformation distribution characteristics of the structure.

[0052] Identifying key correction points based on the deformation vector diagram and stress distribution diagram and generating a correction point distribution table involves a multi-criteria decision analysis. The selection of key correction points requires considering three factors: deformation, stress level, and structural importance. First, extreme value analysis is performed on the deformation vector diagram to identify candidate regions where deformation exceeds the design tolerance. Then, combined with the stress distribution diagram, regions with low stress levels (typically below 50% of the material's yield strength) are selected. These regions are less likely to undergo new plastic deformation during the correction process. Finally, considering the structural mechanical properties, correction points are selected at locations with moderate structural stiffness and clear force paths, avoiding the application of correction forces in areas with sudden changes in stiffness. The density of correction points is related to the deformation gradient; areas with large deformation gradients require more correction points. The correction point distribution table records the coordinates of each correction point, the corresponding deformation, the deformation direction, and the local stiffness of the structure, providing a data foundation for subsequent correction plan design. Designing a multi-point simultaneous correction plan based on the correction point distribution table and determining the magnitude and direction of the correction force are key techniques in the correction process. The correction plan design utilizes a structural mechanics inverse algorithm, taking the target deformation as a known condition and inferring the external forces required to produce these deformations. The calculation process takes into account the stiffness matrix and deformation influence matrix of the structure, and establishes a mapping relationship between external force and deformation. The magnitude of the correction force is determined by taking into account the elastic-plastic properties of the material, and is usually controlled near the critical value of slight plastic deformation. For Q345 steel, this value is approximately 90% of the yield strength. The direction of the correction force is opposite to the direction of deformation, but the connection constraints and overall stiffness distribution of the structure need to be considered. Sometimes, non-direct antagonistic forces need to be applied to achieve deformation correction. The multi-point synchronous correction scheme also includes the grouping and loading sequence of correction points. The correction points are usually divided into several groups according to the symmetry and stiffness distribution of the structure, and synchronous or sequential loading strategies are designed to ensure that the structure is balanced during the correction process and to avoid local stress concentration.

[0053] Configuring the parameters of the multi-point mechanical correction equipment and setting the loading sequence and loading rate of the hydraulic servo actuators is the technical basis for precise correction. The multi-point mechanical correction equipment consists of multiple hydraulic servo actuators, force sensors, displacement sensors, and a control unit, providing precisely controllable correction force. Parameter configuration includes setting the actuator's maximum force, selecting the force control mode, setting the loading rate, and setting safety limits. The hydraulic servo actuator force is typically set at 1.1-1.2 times the theoretically calculated value to allow for any deviations between the actual structural stiffness and the calculated stiffness. The loading sequence follows the principles of "global first, then local," "primary first, then secondary," and "symmetric first, then asymmetric" to ensure balanced structural forces during the correction process. Controlling the loading rate is crucial for precise correction. A low loading rate (typically 2-5% of the maximum force per minute) is used initially. This rate is gradually reduced as the correction progresses, reaching an extremely low rate (0.5-1% of the maximum force per minute) near the target deformation to achieve precise control.

[0054] The process of applying progressive loading to the deformed area through multi-point mechanical correction equipment to form a preliminary correction state embodies the concept of precise control. Progressive loading refers to a loading method that gradually increases the correction force in multiple steps rather than applying the full force value at one time. Usually 5-8 loading steps are used, with the initial load being 30-50% of the target force, and then increasing by 10-15% in each subsequent step until the calculated correction force value is reached. After each loading step, the force value is kept stable for a period of time (3-5 minutes), and the structural deformation response is observed to verify the consistency between the actual deformation and the expected value. Progressive loading avoids structural vibration and local stress concentration caused by sudden force increases, while providing the structure with adaptation time to make the stress distribution more uniform. When implementing multi-point synchronous correction, the loading progress of each actuator needs to be coordinated to ensure that the structure is always in a force balance state during the correction process. This is usually achieved by adjusting the loading rate of each actuator in real time through the central control unit.

[0055] Using a strain monitoring system to monitor stress changes during the correction process in real time and recording stress change curves is an important means to prevent over-correction. The strain monitoring system consists of multiple strain gauges, signal conditioning modules and data acquisition units, and can measure strain changes on the surface of the structure in real time. Strain gauges are arranged around key correction points and stress-sensitive areas of the structure, usually in a three-axis rosette arrangement, to measure strain components in different directions. The strain data acquisition frequency is usually 5-10Hz to ensure that subtle stress changes are captured. After filtering, temperature compensation and zero-point correction, the raw strain data is converted into stress data. The stress change curve records the stress change trend of each monitoring point over time and loading force during the correction process, reflecting the response characteristics of the structure to the correction force. The key parameters of stress monitoring include maximum stress value, stress change rate and stress distribution uniformity. These parameters directly reflect the safety status of the structure during the correction process.

[0056] The correction process is adjusted based on the stress curve until the deformation returns to the design tolerance. This process of generating morphological correction data embodies the principle of closed-loop control. This correction employs a real-time feedback control strategy, dynamically adjusting the magnitude and direction of the correction force by comparing the actual deformation with the target deformation. When the monitored stress in a certain area approaches the material's yield strength, the correction force increment rate is reduced or stopped to prevent excessive plastic deformation. Simultaneously, based on the deformation monitoring data, when the deformation approaches 80-90% of the target value, a fine-tuning phase begins, employing a lower loading rate and smaller loading increments to precisely control the final deformation. The correction process is terminated when the structural deformation returns to the design tolerance and the stress level falls below 70% of the material's yield strength. After correction is complete, the correction force is maintained stable for a period of time (typically 2-4 hours) to allow for sufficient stress redistribution within the structure, followed by a slow unloading process to avoid rebound deformation. The morphological correction data records the deformation comparison before and after correction, the stress evolution, and the correction force parameters, providing a reference for subsequent deformation correction of similar structures.

[0057] The entire process of correcting the deformation of the main girder of a steel box girder bridge is illustrated by an example. First, a high-precision 3D laser scanning system was used to fully scan the heat-treated main girder, generating point cloud data containing approximately 2 million points. Data processing revealed the actual geometry of the main girder. Comparison with the design model revealed a downward deflection of 32 mm in the center of the girder, exceeding the design tolerance of 10 mm. Based on the deformation vector diagram and stress distribution diagram, seven key correction points were identified, including three at the midspan and two at each quarter-span. A correction point distribution table was then created. A multi-point simultaneous correction scheme was designed based on this distribution table. Calculations determined that an upward correction force of 40 tons was required at the midspan and 25 tons at each of the quarter-span points on either side. Hydraulic servo actuators were configured according to the correction scheme, with a maximum force set at 1.15 times the calculated value and a loading rate of 3% of the maximum force per minute. The correction process employed a six-step progressive loading process, with an initial load of 40% of the target force and an increase of 12% with each step. A strain monitoring system monitored stress changes during the correction process in real time. During the fourth loading step, the stress in a certain area of the main beam reached 320 MPa (close to the yield strength of Q345 steel). The rate of increase in the correction force in that area was immediately reduced to one-third of its original value. After careful adjustments, the deflection in the middle of the main beam was restored to 9 mm, within the design tolerance. After maintaining the correction force for three hours and then slowly unloading it, the final shape was measured, and the main beam deformation stabilized at 8 mm.

[0058] In a specific embodiment, the process of executing step S106 may specifically include the following steps: Use high-precision 3D laser scanning technology to measure the full size of the corrected bridge steel structure and obtain the measured geometric model; Conduct overrun analysis on the measured geometric model and the original design model to calculate the dimensional deviation values of key parts; Draw the deformation contour map of the bridge steel structure based on the dimensional deviation value to determine the deformation distribution state; Use a portable X-ray diffractometer to measure residual stress in key welds and heat-affected zones and generate stress distribution reports; Use ultrasonic phased array testing equipment to perform non-destructive testing on the inside of the weld and record weld quality data; Conduct vibration modal testing on bridge steel structures to obtain structural dynamic characteristic parameters; Conduct static load tests on key connection nodes based on structural dynamic characteristic parameters to measure deformation recovery performance; Integrate the morphological correction data with the technical parameters of the entire process to establish a digital twin model and form a deformation control file.

[0059] Specifically, full-scale measurements of the corrected bridge steel structure are performed using high-precision 3D laser scanning technology. Obtaining a measured geometric model is the primary step in quality inspection. High-precision 3D laser scanning is a non-contact measurement method based on the principle of laser ranging, characterized by fast measurement speed, high accuracy, and wide coverage. During the scanning process, the laser measuring device moves along a preset trajectory, collecting spatial point cloud data from the structure's surface. For large bridge steel structures, multiple measuring stations are typically required for scanning. The data from each station is then stitched together into a complete point cloud model using common target points. Point cloud processing involves three steps: denoising, streamlining, and reconstruction. Denoising utilizes statistical outlier analysis to calculate the average distance between each point and its neighbors, removing points with excessively large outliers. Point cloud streamlining employs uniform sampling or curvature sampling algorithms to reduce redundant points while preserving geometric features. 3D reconstruction utilizes point cloud-to-surface conversion technology to convert the discrete point cloud into a continuous surface model, forming the measured geometric model. The measured model is stored as a triangulated mesh or NURBS surface, accurately depicting the structure's actual form.

[0060] The measured geometric model and the original design model are subjected to over-limit analysis, and the dimensional deviation values of key parts are calculated to quantitatively evaluate the effectiveness of deformation control. The over-limit analysis first performs accurate registration of the two models, using the reference point registration method or the iterative nearest point algorithm to ensure that the two models are compared in the same coordinate system. After the registration is completed, the difference between the measured value and the design value is calculated for the key control points of the bridge (such as the mid-span point of the main beam, the support area, the node connection, etc.) to obtain the dimensional deviation value. The deviation calculation adopts the normal distance method, that is, the distance from the measured point to the design surface is measured along the normal direction of the design model surface. This method can more accurately reflect the actual situation of structural deformation. For bridge steel structures, key control indicators include main beam linear deviation, lateral inclination, node position offset, etc. The over-limit analysis results are presented in numerical tables and color-coded visual images, which intuitively display the deviation status of various parts of the structure.

[0061] Deformation contour maps of bridge steel structures are created based on dimensional deviation values to determine the deformation distribution, providing a visual representation of the deformation pattern. A deformation contour map is a curve formed by connecting points with identical deviation values, similar to the contour lines on a topographic map. The creation process first spatially interpolates the deviation data to generate a continuous deviation field distribution. Contour lines are then extracted according to a preset contour interval. The interpolation algorithm typically employs kriging or radial basis functions, which produce smooth transitions between discrete sampling points. The contour interval is set based on the structure dimensions and deformation magnitude, typically 1 / 5 to 1 / 3 of the design tolerance. Deformation contour maps are color-coded for enhanced visual appeal: red indicates positive deviation (measured values greater than the design value) and blue indicates negative deviation (measured values less than the design value). The color depth indicates the magnitude of the deviation. Deformation contour maps clearly identify concentrated areas of deformation, the direction of the deformation gradient, and the overall deformation pattern, providing a valuable reference for final acceptance and future maintenance of the structure.

[0062] Using a portable X-ray diffractometer to measure residual stress in critical welds and heat-affected zones (HAZs) and generate stress distribution reports is an important tool for internal quality assessment. X-ray diffraction, based on Bragg's law, calculates the internal stress state of a material by measuring changes in lattice spacing. During measurement, an X-ray beam strikes the material surface. Changes in the diffraction angle reflect the degree of lattice distortion, which is then used to calculate the stress value. The portable X-ray diffractometer's compact design enables non-destructive measurement of structures on-site. Measurement points are arranged using a combination of a grid and keypoint method, forming a measurement network at the weld center, the edge of the HAZ, and the substrate. At each location, stress components are measured in multiple directions to obtain stress tensor information. The measured data undergoes statistical processing and spatial interpolation to generate a continuous stress distribution map. The stress distribution report, which includes numerical data, distribution images, and statistical analysis results, assesses the absolute level of residual stress, its uniformity, and its ratio to the material's yield strength, thereby determining the effectiveness of stress relief.

[0063] Ultrasonic phased array testing equipment is used to perform nondestructive testing of welds and record weld quality data, verifying the quality of the welding process. Ultrasonic phased array testing is an advanced nondestructive testing technology that controls the transmission and reception timing of multiple piezoelectric elements to form a controllable ultrasonic beam, enabling the detection of internal defects in materials. Compared to traditional ultrasonic testing, phased array technology offers advantages such as faster scanning speed, intuitive defect imaging, and precise defect location. The testing process begins with equipment calibration using a standard test block to determine sound velocity, sensitivity, and resolution. The ultrasonic echo signal is then scanned along the weld, and the echo signal is recorded. Signal processing, including filtering, gain adjustment, and deconvolution, improves the signal-to-noise ratio and resolution. Data analysis utilizes a defect feature extraction algorithm to identify defect types such as porosity, slag inclusions, and lack of fusion based on the amplitude, duration, and phase characteristics of the echo signal. Weld quality data is presented as B-scan and C-scan images, visually displaying the location, size, and distribution of defects. The weld quality grade is then assessed in accordance with relevant standards.

[0064] Conducting vibration modal testing on steel bridge structures to obtain dynamic structural parameters is a scientific method for overall performance evaluation. Vibration modal testing measures the structure's vibration response under excitation and identifies dynamic parameters such as the structure's natural frequency, mode shape, and damping ratio. Testing utilizes either environmental or artificial excitation. Environmental excitation utilizes natural sources such as wind loads and traffic loads, while artificial excitation uses a hammer or vibration exciter to apply a known input. The measurement equipment includes accelerometers, a data acquisition system, and a signal analyzer. Sensor placement follows the principle of dense node density, with sensors placed at key locations within the structure to capture the primary vibration modes. Data processing utilizes fast Fourier transforms to convert time-domain signals into the frequency domain. Natural frequencies and mode shapes are extracted through peak identification and modal parameter fitting algorithms. Dynamic characteristic parameters reflect the structure's stiffness distribution, mass distribution, and boundary conditions. By comparing these dynamic characteristic parameters with predicted values from the finite element model, the overall structural performance and connection stiffness are evaluated, and the effects of welding and deformation control on the structural dynamic characteristics are verified.

[0065] Static load tests are conducted on key connection nodes based on the dynamic characteristic parameters of the structure. Measuring the deformation recovery performance is a direct test of structural reliability. Static load tests apply a known load to the structure, measure the deformation response of the structure, and evaluate the structure's bearing capacity and deformation characteristics. The test load is usually set to 1.2 times the design load and is applied using weights, water tanks, or jacks. Deformation measurement uses displacement sensors or high-precision levels to record the deformation curve during loading and the residual deformation after unloading. Data analysis focuses on three key indicators: maximum deformation, deformation recovery rate, and linearity of the load-deformation curve. The deformation recovery rate is defined as the ratio of rebound deformation to total deformation after unloading and reflects the elastic working state of the structure. The linearity of the load-deformation curve is evaluated by the correlation coefficient and the root mean square error of deviation from linearity. By comparing the static load test results before and after welding deformation control, the improvement effect of deformation control on the service performance of the structure is quantitatively evaluated.

[0066] Integrating morphological correction data with full-process technical parameters to create a digital twin model and form a deformation control archive is a crucial step in knowledge accumulation and experience transfer. A digital twin model is a virtual representation of a physical object in the digital world, encompassing geometric models, physical properties, and behavioral characteristics. Model construction begins by integrating data from the entire process, including pre-deformation design data, welding process records, heat treatment parameters, calibration process data, and final inspection results. Data integration utilizes time series correlation and spatial position mapping to establish correlations between data from each stage. The modeling process employs a parametric approach, mapping key process parameters with deformation control results to form a parameter sensitivity model. The digital twin model not only records the current state of the structure but also encompasses the technical parameters and control strategies for the entire deformation control process, enabling retrospective analysis and predictive deduction capabilities. The deformation control archive, stored as a database and knowledge base, contains multidimensional information such as structural characteristics, process parameters, control methods, and quality assessments, providing a scientific basis and empirical reference for subsequent deformation control of similar structures.

[0067] The final acceptance of the main girder of a steel box girder bridge is used as an example to illustrate the entire process: First, a high-precision 3D laser scanner was used to measure the corrected main girder in full size, collecting approximately 3 million points of point cloud data. This data was then processed to generate a measured geometric model with an accuracy of ±0.2 mm. An over-limit analysis of the measured and designed models revealed that the maximum deflection at the center of the main girder was 7 mm, within the design tolerance (±10 mm). The maximum torsion deviation of the main girder was 0.08 degrees, which was below the specification limit (0.1 degrees). Deformation contour maps based on the deviation data showed that deformation was primarily concentrated to one side of the center of the main girder, exhibiting an asymmetric distribution. Residual stresses in eight welds at the connection between the main girder and the crossbeam were then measured using a portable X-ray diffractometer. The results showed an average residual stress of 112 MPa, approximately 32% of the yield strength of Q345 steel and significantly lower than the measured value before deformation control (315 MPa). Ultrasonic phased array testing of the internal weld quality revealed no defects above Level II that could impact structural safety. Vibration modal testing obtained the first six natural frequencies of the main beam, with an average deviation of 4.2% from the finite element analysis results, indicating that the overall stiffness of the structure meets the design requirements. Static load tests at 1.2 times the design load were conducted on the main beam connection nodes. The maximum deformation was 92% of the design value, and the residual deformation after unloading was only 3.5% of the total deformation, indicating good deformation recovery performance. Ultimately, the technical parameters and test data of the entire deformation control process were integrated to establish a digital twin model, recording complete information on process parameters, control strategies, and effect evaluation, forming a systematic deformation control archive, which provides a valuable technical reference for subsequent deformation control of bridge steel structure welding.

[0068] The above describes the multi-stage adjustment method for controlling the deformation of steel structure welding in the embodiment of the present application. The following describes the multi-stage adjustment system for controlling the deformation of steel structure welding in the embodiment of the present application. Figure 2 In one embodiment of the present application, a multi-stage adjustment system for controlling steel structure welding deformation includes: The measurement module is used to establish a welding deformation prediction model by measuring the geometric parameters of the steel structure and combining them with the welding process parameters to obtain a pre-deformation data set; a processing module, configured to perform precise pre-deformation processing on a designated position of a steel structure according to the pre-deformation data set to obtain a pre-processed steel member; a recording module, configured to perform a segmented welding operation on the pretreated steel component, record the temperature field distribution and real-time deformation during the welding process, and obtain a welding deformation record table; an implementation module, configured to perform local heat treatment on a high stress area of the welded steel component according to the welding deformation record table to obtain a stress distribution diagram; an applying module, configured to apply a correction force to the deformed area through a multi-point mechanical correction device according to the stress distribution diagram to obtain morphological correction data; The evaluation module is used to use the morphological correction data to perform final accuracy detection and quality evaluation on the steel structure to form a deformation control file.

[0069] Through the collaborative efforts of these components, a welding deformation prediction model was established by measuring the geometric parameters of the steel structure and integrating them with the welding process parameters. This model transforms traditional empirical predictions into precise, data-driven calculations, significantly improving the accuracy of pre-deformation calculations and avoiding over- or under-compensation. The generated pre-deformation dataset also provides precise guidance for subsequent processes. Based on the pre-deformation dataset, precise pre-deformation treatment was performed at designated locations on the steel structure. A hybrid technique combining laser heating and mechanical preloading achieved precise control of the deformation amount and direction, creating a pre-treated steel component that laid a solid foundation for subsequent welding. Segmented welding was performed on the pre-treated steel component. A symmetrical, staggered welding method effectively balanced the heat input distribution, significantly reducing the overall deformation trend. The temperature field distribution and deformation were simultaneously recorded in real time, generating a weld deformation record that provided accurate data support for subsequent heat treatment. Based on the weld deformation record, localized heat treatment was applied to high-stress areas. By precisely controlling the heating temperature and cooling rate, residual stresses were effectively released. The resulting stress distribution map intuitively reflects the stress relief effect. Based on the stress distribution diagram, a correction force is applied to the deformed area using multi-point mechanical correction equipment. Using a progressive loading strategy and real-time stress monitoring, deformation correction is achieved safely and efficiently. The resulting morphological correction data comprehensively records the correction process and results. The morphological correction data is used to conduct final precision testing and quality assessment of the steel structure, forming a systematic and complete deformation control archive. This not only verifies the deformation control effect, but also provides valuable experience reference for subsequent similar structures. In particular, the data mining algorithms used in the welding deformation prediction and control process can extract deformation patterns from historical cases, establish a correlation model between process parameters and deformation results, and continuously optimize prediction accuracy through deep learning methods, so that the prediction results can adapt to different structural forms and welding conditions, greatly improving the pertinence and effectiveness of deformation control.

[0070] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3As shown. The computer device includes a processor, memory, display screen, input device, network interface and database connected via a system bus. The processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0071] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0072] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-described method when executed by a processor. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0073] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media provided herein and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM.

[0074] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0075] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0076] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A multi-stage adjustment method for controlling steel structure welding deformation, characterized in that: The multi-stage adjustment method for controlling steel structure welding deformation includes: By measuring the geometric parameters of steel structures and combining them with welding process parameters, a welding deformation prediction model is established to obtain a pre-deformation data set; According to the pre-deformation data set, precise pre-deformation processing is performed on the designated position of the steel structure to obtain a pre-treated steel component; Performing segmented welding operations on the pretreated steel component, recording the temperature field distribution and real-time deformation during the welding process, and obtaining a welding deformation record table; According to the welding deformation record table, local heat treatment is performed on the high stress area of the welded steel component to obtain a stress distribution map; According to the stress distribution diagram, a correction force is applied to the deformed area by a multi-point mechanical correction device to obtain morphological correction data; The morphological correction data is used to conduct final precision inspection and quality assessment on the steel structure to form a deformation control file.

2. The multi-stage adjustment method for controlling steel structure welding deformation according to claim 1, characterized in that: The method measures the geometric parameters of the steel structure and combines them with the welding process parameters to establish a welding deformation prediction model to obtain a pre-deformation data set, including: Perform 3D scanning on bridge steel structures to obtain the geometric parameters and key node coordinates of the structures; Inputting the geometric parameters and welding process parameters into a processing system to construct a welding deformation prediction model; Dividing the welding deformation prediction model into grid units, performing grid encryption processing on the weld area, and obtaining a fine grid of the welding area; Performing thermal cycle analysis on the steel structure welding process based on the fine grid of the welding area to obtain temperature field distribution data; Calculating welding stress and deformation using a welding deformation prediction model based on the temperature field distribution data to generate deformation prediction data; Correcting the deformation prediction data under bridge load conditions, taking into account the effects of the structure's deadweight and service load, to obtain a corrected deformation value; Determining a pre-deformation compensation amount based on the corrected deformation value, and calculating pre-deformation position parameters of each node; The pre-deformation position parameters are compared and analyzed with the original parameters to generate a pre-deformation data set including deformation direction, deformation amount and implementation position.

3. The multi-stage adjustment method for controlling steel structure welding deformation according to claim 1, characterized in that: The method of performing precise pre-deformation processing on a designated position of a steel structure according to the pre-deformation data set to obtain a pre-processed steel member includes: Determine the key points of pre-deformation of the bridge steel structure based on the pre-deformation data set and generate a pre-deformation operation guide; Configure a high-power fiber laser based on the pre-deformation operation guide and set the laser heating parameters; Performing laser directional heating on a designated position of the steel structure to form a temperature gradient area; Setting a mechanical preloading system according to the pre-deformation amount in the pre-deformation data set and determining a loading force value; Applying an external force consistent with the pre-deformation direction to the heating area through the mechanical preloading system to generate initial deformation; Use infrared thermal imaging equipment to monitor the temperature of the laser heating area in real time and obtain temperature distribution data; Adjusting the laser power and scanning speed based on the temperature distribution data to control the pre-deformation progress; The pre-deformed structure was measured using a 3D laser scanner and compared with the pre-deformed data set to obtain the pre-treated steel component.

4. The multi-stage adjustment method for controlling steel structure welding deformation according to claim 1, characterized in that: The step of performing segmented welding on the pretreated steel component and recording the temperature field distribution and real-time deformation during the welding process to obtain a welding deformation record table includes: Divide the welding area of the pre-treated steel components into sections and generate a welding sequence planning table; Setting pulse welding current parameters and adjusting pulse frequency and duty cycle according to the welding sequence planning table; The bridge steel structure is welded using a symmetrical segmented staggered welding method to form the initial welds; Real-time temperature monitoring of the welding area is performed through a temperature sensor array to obtain dynamic temperature field data; Determine the thermal cycle threshold based on the temperature field dynamic data and control the welding gap cooling time; The laser interferometer deformation monitoring system is used to track the structural deformation during welding in real time and record the deformation value; Dynamically adjusting welding parameters of subsequent welds according to the deformation value to perform compensation welding; The temperature field dynamic data and deformation values are integrated into time-series correlation data to generate a welding deformation record table.

5. The multi-stage adjustment method for controlling steel structure welding deformation according to claim 1, characterized in that: The method of performing local heat treatment on the high stress area of the welded steel component according to the welding deformation record table to obtain a stress distribution diagram includes: By analyzing the temperature field distribution and deformation data in the welding deformation record table, the residual stress concentration area in the bridge steel structure is determined; Marking the residual stress concentration areas in a graded manner to generate a heat treatment area division diagram; Configure high-frequency induction heating equipment according to the heat treatment area division diagram, and set heating power and frequency parameters; Performing gradient heating on the marked area based on the heat treatment area division map to form a temperature gradient field; Use infrared thermal imaging system to monitor the heating process in real time and obtain the heat treatment temperature curve; Monitor the stress release process inside steel components through acoustic emission detection equipment and record stress release signals; Adjusting cooling system parameters according to the stress release signal to control the cooling rate; An X-ray diffraction device is used to measure the residual stress of the steel component after heat treatment and generate a stress distribution map.

6. The multi-stage adjustment method for controlling steel structure welding deformation according to claim 1, characterized in that: The method of applying a correction force to the deformed area by a multi-point mechanical correction device according to the stress distribution diagram to obtain morphological correction data includes: A high-precision 3D laser scanning system is used to comprehensively scan the heat-treated bridge steel structure to obtain actual deformation point cloud data; Comparing the actual deformation point cloud data with the design model to generate a deformation vector diagram; Determine the key points of correction according to the deformation vector diagram and the stress distribution diagram, and form a correction point distribution table; Design a multi-point synchronous correction scheme based on the correction point distribution table to determine the magnitude and direction of the correction force; Configuring parameters of the multi-point mechanical correction device to set the loading sequence and loading rate of the hydraulic servo actuator; Applying progressive loading to the deformed area through the multi-point mechanical correction device to form a preliminary correction state; Use the strain monitoring system to monitor the stress changes during the calibration process in real time and record the stress change curve; The correction process is adjusted based on the stress change curve until the deformation is restored to within the design tolerance range, and morphological correction data is generated.

7. The multi-stage adjustment method for controlling steel structure welding deformation according to claim 1, characterized in that: The morphological correction data is used to conduct final precision testing and quality assessment on the steel structure to form a deformation control file, including: Use high-precision 3D laser scanning technology to measure the full size of the corrected bridge steel structure and obtain the measured geometric model; Perform overrun analysis on the measured geometric model and the original design model to calculate the dimensional deviation values of key parts; Drawing a deformation contour map of the bridge steel structure based on the dimensional deviation value to determine the deformation distribution state; Use a portable X-ray diffractometer to measure residual stress in key welds and heat-affected zones and generate stress distribution reports; Use ultrasonic phased array testing equipment to perform non-destructive testing on the inside of the weld and record weld quality data; Conduct vibration modal testing on bridge steel structures to obtain structural dynamic characteristic parameters; Performing static load tests on key connection nodes based on the structural dynamic characteristic parameters to measure deformation recovery performance; The morphological correction data is integrated with the technical parameters of the entire process to establish a digital twin model and form a deformation control file.

8. A multi-stage adjustment system for controlling welding deformation of a steel structure, used to implement the multi-stage adjustment method for controlling welding deformation of a steel structure according to any one of claims 1 to 7, characterized in that: The multi-stage adjustment system for steel structure welding deformation control includes: The measurement module is used to establish a welding deformation prediction model by measuring the geometric parameters of the steel structure and combining them with the welding process parameters to obtain a pre-deformation data set; a processing module, configured to perform precise pre-deformation processing on a designated position of a steel structure according to the pre-deformation data set to obtain a pre-processed steel member; a recording module, configured to perform a segmented welding operation on the pretreated steel component, record the temperature field distribution and real-time deformation during the welding process, and obtain a welding deformation record table; an implementation module, configured to perform local heat treatment on a high stress area of the welded steel component according to the welding deformation record table to obtain a stress distribution diagram; an applying module, configured to apply a correction force to the deformed area through a multi-point mechanical correction device according to the stress distribution diagram to obtain morphological correction data; The evaluation module is used to use the morphological correction data to perform final accuracy detection and quality evaluation on the steel structure to form a deformation control file.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and is characterized in that when the processor executes the computer program, the multi-stage adjustment method for controlling welding deformation of a steel structure according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the processor is caused to execute the multi-stage adjustment method for controlling welding deformation of a steel structure according to any one of claims 1 to 7.

Images