Intelligent calibration method based on steel structure assembly precision

Abstract

The invention provides an intelligent calibration method based on steel structure assembly precision, and relates to the technical field of intelligent calibration, and the method comprises the steps: collecting spatial position data of a joint of an I-shaped steel beam flange and an H-shaped steel column flange, converting the spatial position data into a verticality deviation value, and obtaining stress distribution data of a beam column connection node; calculating the deformation compensation amount of the I-shaped steel beam flange based on the perpendicularity deviation value and the stress distribution data, and calculating a calibration force distribution curve according to the change rule of the inertia moment of the section of the I-shaped steel beam flange; and the welding sequence and the welding bead spacing are optimized based on the calibration force distribution curve, and welding parameters are controlled through the thermal field distribution gradient, so that the perpendicularity deviation between the flange of the I-shaped steel beam and the flange of the H-shaped steel column is controlled. In this way, the problem that the assembly precision is insufficient due to the fact that perpendicularity deviation is difficult to calculate accurately and welding heat input distribution is uneven can be solved, the steel structure assembly precision and efficiency are improved, and the structural stability is enhanced.

Description

Technical Field

[0001] This invention relates to the field of intelligent calibration technology, and more specifically, to an intelligent calibration method based on the assembly accuracy of steel structures. Background Technology

[0002] With the continuous development of modern architecture and industrial engineering, steel structures have become the mainstream structural form for high-rise buildings, bridges, and industrial plants due to their high strength, light weight, short construction period, and excellent seismic performance. In the assembly process of steel structures, beam-column joints, as key connection points, directly affect the stability, load-bearing capacity, and service life of the entire steel structure. Therefore, improving the accuracy of beam-column joint connections to meet the increasingly stringent requirements for assembly precision in complex projects has become an important direction for research in steel structure assembly technology. However, in actual construction, due to the large size of I-beams and H-columns, the complex installation environment, and limitations of construction techniques, beam-column connection joints are prone to displacement deviations and thermal deformations during hoisting and welding, especially verticality deviations. Currently, traditional assembly calibration methods mainly rely on manual measurement and experience-based adjustments, which are insufficient to meet the high requirements of modern steel structure assembly in terms of accuracy and efficiency. In recent years, calibration technologies based on digital measurement and automated control have made some progress, but existing technologies still have limitations in achieving high-precision calibration of verticality deviations caused by hoisting deviations and welding thermal deformation.

[0003] Existing steel structure assembly technologies have several shortcomings in addressing the verticality deviation of beam-column joints: First, traditional techniques rely on rudimentary methods for acquiring and processing spatial location data of beam-column connections, failing to accurately and in real-time obtain the verticality deviation between the flanges of I-beams and H-beam columns. This results in lag in deviation calibration and error accumulation. Second, current calibration methods lack effective control over thermal deformation during welding and fail to optimize welding heat input by incorporating the variation of the beam flange's moment of inertia. Welding thermal deformation often exacerbates verticality deviation. Furthermore, existing technologies do not adequately consider the impact of verticality deviation on stress distribution at beam-column joints when adjusting them, potentially leading to localized stress concentration and weakening the overall stability of the connection. Particularly in practical engineering, verticality deviations exceeding 3mm significantly impact the structural performance of beam-column connections, thereby jeopardizing the safety of the entire steel structure system. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention is proposed. This invention provides an intelligent calibration method for steel structure assembly accuracy, which can, to some extent, solve the problems of inaccurate calculation of verticality deviation due to the inability to accurately collect spatial position data and stress distribution data at the connection between the flanges of I-beams and H-shaped columns, as well as uneven welding heat input distribution and the inability to optimize calibration force distribution, thereby affecting the assembly accuracy and structural stability of steel structures.

[0005] According to one aspect of the present invention, an intelligent calibration method based on the assembly accuracy of steel structures is provided, comprising:

[0006] Spatial position data of the connection between the flange of the I-beam and the flange of the H-beam column are collected, the spatial position data are converted into verticality deviation values, and stress distribution data of the beam-column connection node are obtained.

[0007] Based on the verticality deviation value and the stress distribution data, the deformation compensation amount of the I-beam flange is calculated.

[0008] Based on the aforementioned deformation compensation amount, and according to the variation law of the moment of inertia of the flange section of the I-beam, the calibration force distribution curve along the flange circumference is calculated;

[0009] Based on the calibration force distribution curve, the welding sequence and weld spacing are determined. The welding parameters are adjusted by the gradient control principle of the thermal field distribution to control the perpendicularity deviation between the flanges of the I-beam and the H-beam column.

[0010] Furthermore, based on the verticality deviation value and the stress distribution data, by calculating the stress concentration factor and introducing the influence of the verticality deviation, the deformation compensation amount of each measurement point is determined by using the nominal stress formula combined with the optimization objective function.

[0011] Furthermore, the calculation of the stress concentration factor is based on the traditional von Mises equivalent stress, but introduces the influence of a quadratic term of perpendicularity deviation, as expressed by the formula:

[0012]

[0013] in, The stress concentration factor is... This is the stress amplification factor caused by verticality deviation; The normal stress in the radial direction of the flange of the I-beam is... For nominal stress, Tangential stress in the circumferential direction of the flange of the I-beam This refers to the shear stress in the 45° direction of the flange of the I-beam.

[0014] Furthermore, the optimization objective function is constructed by fitting a nonlinear relationship between the stress concentration coefficient and the perpendicularity deviation value using the least squares method after obtaining the stress concentration coefficient at each measurement reference point, and based on this relationship, the following formula is used:

[0015]

[0016] in, These are the weighting coefficients; The coordinates are along the circumferential direction of the flange of the I-beam.

[0017] Furthermore, based on the aforementioned optimization objective function, the deformation compensation amount for each measurement reference point is calculated. A new model for calculating deformation compensation is established, expressed as:

[0018] in, For the first Deformation compensation at each measurement reference point The deformation compensation coefficient is... For the first The distance from each reference point to the center. The distance from the outermost reference point to the center is measured. Radial influence index, This is a stress level correction factor. The yield strength of the material.

[0019] Furthermore, based on the variation law of the moment of inertia of the flange section of the I-beam, the relationship between the load and the radial displacement is established using the fourth-order differential equation based on the theory of variable cross-section beams. The radial displacement is determined by the calibration force distribution function, the elastic modulus of the material, and the moment of inertia of the variable cross-section.

[0020] Furthermore, based on the deformation compensation amount and moment of inertia distribution, the calibration force distribution required to restore the flange to its ideal state is solved in reverse according to the current radial deviation, i.e., radial displacement. By transforming the fourth-order differential equation, the target deformation is converted into the calibration force distribution, and the calibration force required to eliminate the deviation under specific load conditions is determined.

[0021] Furthermore, based on the obtained calibration force distribution, a continuous calibration force distribution curve is established using the same cubic spline interpolation method as that used to process the deformation data.

[0022] Furthermore, based on the calibration force distribution curve, it is transformed into a welding heat input distribution. Through the principle of welding deformation compensation, the relationship between the welding heat input per unit length and the calibration force distribution is established. Then, through the welding heat input formula, the required heat input is transformed into welding process parameters, including welding thermal efficiency, voltage, current, and speed.

[0023] Furthermore, based on the welding process parameters, a deformation prediction model is established to control the perpendicularity deviation, describing the perpendicularity deviation angle at the location, expressed as:

[0024]

[0025] in, For position The perpendicularity deviation angle at point n, where n is the total number of welds. The deformation coefficient is... For the thickness of the workpiece plate, The coefficient of linear expansion is 1 / 3. For welding temperature, For ambient temperature, For the material's Poisson's ratio, This is the decay function.

[0026] Compared with existing technologies, this invention can effectively control verticality deviation by accurately collecting spatial position data and stress distribution data at the connection between the flange of the I-beam and the flange of the H-beam column, calculating the deformation compensation amount by combining the verticality deviation, and optimizing the calibration force distribution curve and welding heat input parameters based on the variation law of the moment of inertia of the beam flange section. This significantly improves the accuracy and efficiency of steel structure assembly, while reducing the adverse effects of welding thermal deformation on structural stability. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0028] Figure 1 This is a flowchart of an intelligent calibration method for steel structure assembly accuracy according to an embodiment of the present invention. Detailed Implementation

[0029] Hereinafter, exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0030] As mentioned in the background section, existing technologies suffer from two main problems: first, due to the inability to accurately determine the real-time population distribution in each area, uniformly broadcast evacuation instructions can easily lead to congestion in some areas while underutilizing resources in others; second, poor indoor positioning signals result in some areas failing to receive evacuation information in a timely manner. Our invention addresses these technical pain points by proposing an intelligent calibration method based on the assembly accuracy of steel structures.

[0031] Figure 1 This is a system block diagram of an intelligent calibration method for steel structure assembly accuracy according to an embodiment of the present invention. Figure 1 As shown, the intelligent calibration method based on steel structure assembly accuracy includes:

[0032] S1: Collect spatial position data at the connection between the flange of the I-beam and the flange of the H-beam column, convert the spatial position data into a verticality deviation value, and obtain the stress distribution data of the beam-column connection node;

[0033] At the connection point between the flange of the I-beam and the flange of the H-section steel column, 36 measurement reference points are arranged at equal intervals of 50mm along the edge of the I-beam flange. These reference points form a complete circular array. An additional, denser measurement reference point is added at each of the four corners of the I-beam flange, with a spacing of 25mm between the denser reference points. High-precision displacement sensors and strain sensors are installed at these reference points, with the displacement sensors having a measurement accuracy of 0.01mm and the strain sensors having a sensitivity of 1με.

[0034] A rectangular coordinate system is established on the surface of the H-shaped steel column flange with the connection center as the origin. 36 reference targets are fixed in the rectangular coordinate system, and each reference target corresponds one-to-one with the measurement reference point on the H-beam flange. The three-dimensional spatial coordinate data of the measurement reference point of the H-beam flange relative to the reference target of the H-shaped steel column flange is collected by displacement sensors. The three-dimensional spatial coordinate data includes the planar displacement component in the X-axis direction, the lateral displacement component in the Y-axis direction, and the vertical displacement component in the Z-axis direction.

[0035] The three-dimensional spatial coordinate data is transformed into the perpendicularity deviation value between the flanges of the I-beam and the H-section steel column using a homogeneous coordinate transformation matrix consisting of a 3×3 rotation matrix and a 3×1 translation vector. The perpendicularity deviation value is expressed as the angle between the normal vectors of the two flange planes. It means that among them = arccos(n1·n2), where n1 and n2 are the unit normal vectors of the I-beam flange and the H-beam column flange, respectively. If θ is positive, it means that the I-beam flange is deflected in the positive direction relative to the H-beam column flange; if θ is negative, it means that the I-beam flange is deflected in the negative direction relative to the H-beam column flange.

[0036] Simultaneously, stress distribution data of the beam-column connection nodes were collected by strain sensors deployed at various measurement reference points. The stress distribution data included the normal stress along the radial direction of the I-beam flange. Tangential stress along the circumferential direction of the flange of the I-beam and shear stress in the 45° direction The stress components in these three directions fully characterize the stress state at each measurement reference point of the connection node;

[0037] The stress distribution data was collected at a frequency of 10Hz. After continuous collection for 60 seconds at each measurement reference point, the average value was taken as the effective stress value at that point.

[0038] S2: Based on the verticality deviation value and the stress distribution data, calculate the deformation compensation amount of the I-beam flange, wherein the deformation compensation amount is determined by minimizing the nodal stress concentration factor.

[0039] Based on the obtained verticality deviation values ​​and stress distribution data, the deformation compensation of the I-beam flange is calculated, including:

[0040] Stress concentration factors were calculated at 36 measurement reference points. Considering that perpendicularity deviation can lead to non-uniform stress distribution, a perpendicularity deviation is introduced into the traditional von Mises equivalent stress. The effect of the quadratic term is expressed by the formula:

[0041]

[0042] in, This is the stress amplification factor caused by perpendicularity deviation, with a value ranging from 1.15 to 1.25. For normal stress, This is the nominal stress.

[0043] Nominal stress The calculation formula is expressed as:

[0044]

[0045] in, The bending moment of the I-beam. The section modulus of the I-beam. This is the shear deformation correction factor, with a value ranging from 0.05 to 0.15; The cross-sectional height of the I-beam. This is the calculated span of the I-beam.

[0046] After obtaining the stress concentration coefficients at each measurement reference point, establish the stress concentration coefficients. Verticality deviation value The nonlinear functional relationship between them:

[0047]

[0048]

[0049] in, ~ The fitting coefficients are determined based on measured data using the least squares method.

[0050] Based on this functional relationship, an optimization objective function considering the stress gradient is constructed, expressed as:

[0051]

[0052] in, This is a weighting coefficient, with a value ranging from 0.1 to 0.3, used to balance maximum control and gradient control; The coordinates are along the circumferential direction of the flange.

[0053] Based on the optimization objective function, the deformation compensation amount of each measurement benchmark point is calculated. A new model for calculating deformation compensation is established, expressed as:

[0054] in, For the first Deformation compensation at each measurement reference point The deformation compensation coefficient is... For the first The distance from each reference point to the center. The distance from the outermost reference point to the center is measured. The radial influence index ranges from 1.5 to 2.0. This is a stress level correction factor, with a value ranging from 0.2 to 0.4. The yield strength of the material.

[0055] To ensure the consistency of deformation, the deformation compensation between adjacent measurement reference points must meet the following requirements:

[0056]

[0057] in, This is the deformation compatibility factor, with a value ranging from 0.6 to 0.8. The distance between adjacent measurement reference points. It is the elastic modulus.

[0058] S3: Based on the deformation compensation amount, and according to the variation law of the moment of inertia of the flange section of the I-beam, calculate the calibration force distribution curve along the flange circumference, wherein the calibration force distribution curve satisfies the elastic mechanical equilibrium equation of flange deformation.

[0059] During the deformation adjustment process of the flange of an I-beam, since the flange is essentially a thin-walled annular structure with varying curvature, its deformation behavior needs to be described using the theory of elasticity. Therefore, a fourth-order differential equation based on the theory of variable cross-section beams is established to describe the relationship between load and deformation, expressed as:

[0060]

[0061] in, This represents the radial displacement of the flange under load. Where is the radius of curvature of the flange. For calibrating the force distribution function, The elastic modulus of the material. For variable cross-section moment of inertia.

[0062] Based on the circumferential variation characteristics of the moment of inertia of the flange section of the I-beam, a moment of inertia distribution function is established. , represented as:

[0063]

[0064] in, The moment of inertia of the reference section, This is the circumferential variation coefficient, with a value range of 0.1 to 0.2; For the wing circumference, For any position radius, As the reference radius, The radial influence index has a value range of 1.2 to 1.5.

[0065] Deformation compensation amount based on calculation By establishing a continuous deformation function through spline interpolation, discrete measurement data are transformed into a continuous deformation field, expressed as:

[0066]

[0067] in, Represents any position Deformation at that location For the first The cubic spline basis functions corresponding to each measurement point.

[0068] Based on the deformation compensation amount and moment of inertia distribution, an inverse problem needs to be solved: given the current flange deviation, calculate the calibration force required to restore it to its ideal state. By transforming the above basic control equations, the target deformation is converted into the required calibration force distribution, expressed as:

[0069]

[0070] Among them, at this time This indicates the radial deviation of the flange currently measured.

[0071] To ensure calculation accuracy, a correction term is introduced to eliminate nonlinear factors in engineering, including the influence of stress level on material behavior and the influence of cross-sectional changes on force transmission, expressed as:

[0072]

[0073] in, This represents the stress correction factor, with a value ranging from 0.2 to 0.3. Indicates the yield strength of the material. This represents the stress influence index, with a value ranging from 1.5 to 2.0. This represents the influence coefficient of cross-sectional variation, with a value range of 0.1 to 0.15.

[0074] The calibration force distribution also needs to meet the overall equilibrium conditions, including:

[0075]

[0076]

[0077] By setting equilibrium conditions, the calibration process is ensured to avoid introducing additional overall displacement and rotation, thus maintaining the stability of the structure.

[0078] Based on the obtained calibration force distribution, a continuous calibration force distribution curve is established using the same cubic spline interpolation method as that used to process the deformation data.

[0079] S4: Determine the welding sequence and weld spacing based on the calibration force distribution curve, and adjust the welding parameters through the gradient control principle of thermal field distribution to control the perpendicularity deviation between the flange of the I-beam and the flange of the H-beam column.

[0080] Based on the obtained calibration force distribution curve, it is converted into a welding heat input distribution. According to the welding deformation compensation principle, the welding heat input per unit length... The relationship with the calibration force distribution can be expressed as:

[0081]

[0082] in, For welding heat input per unit length, The force-heat conversion coefficient, For the thickness of the flange, This is the elastic modulus of the material.

[0083] The required heat input is further converted into specific welding process parameters, expressed as follows:

[0084]

[0085] in, For welding thermal efficiency, For welding voltage, For welding current, This refers to the welding speed.

[0086] By adjusting the voltage, current, and welding speed, the magnitude and distribution of heat input can be precisely controlled. However, simply controlling the heat input is not enough; it is also necessary to consider how heat is transferred and distributed within the material.

[0087] Considering the overlapping effect of the heat-affected zone, the spacing between adjacent weld passes must be strictly controlled. Spacing between adjacent weld beads Must meet:

[0088]

[0089] in, The thermal diffusivity of the material, Characteristic cooling time, The highest welding temperature, For ambient temperature, This is the critical temperature.

[0090] Once reasonable heat input and heat distribution are ensured, a deformation prediction model is established to control verticality deviation:

[0091]

[0092] in, For position The perpendicularity deviation angle at point n, where n is the total number of welds. The deformation coefficient is... For the thickness of the workpiece plate, The coefficient of linear expansion is 1 / 3. For welding temperature, For ambient temperature, For the material's Poisson's ratio, As a decay function, the degree of influence decreases exponentially with the increase of the distance between the observation point and the heat source.

[0093] This relationship allows for accurate prediction of deformation effects under given thermal input conditions, thereby achieving precise control over deformation. Specifically:

[0094] If the verticality deviation angle is greater than 2mm, a larger correction effect is required. At this time, the heat input should be controlled within the range of 1.2-1.5kJ / mm. The welding current should be selected between 280 and 320A to ensure sufficient penetration. At the same time, the arc voltage should be set between 28 and 30V to ensure good arc stability. The welding speed should be controlled between 4 and 5mm / s to ensure sufficient heat accumulation.

[0095] If the verticality deviation is within the range of 1 to 2 mm, a medium heat input of 0.8-1.2 kJ / mm should be used. At this time, the welding current should be set at 240 to 280 A to provide a moderate penetration depth, the arc voltage should be maintained at 26 to 28 V to ensure stable droplet transfer, and the welding speed should be maintained at 5 to 6 mm / s to achieve uniform heat distribution.

[0096] If the verticality deviation is less than 1mm, use a smaller heat input of 0.6-0.8kJ / mm to avoid excessive deformation. Specifically, reduce the welding current to 200-240A to reduce the penetration depth, control the arc voltage at 24-26V to reduce heat input, and increase the welding speed to 6-7mm / s to reduce heat input per unit length.

[0097] In practice, a segmented welding strategy is adopted, with the length of each weld segment strictly controlled within the range of 150–200 mm. The welding interval between adjacent weld segments must meet the following formula:

[0098]

[0099] in, This indicates the minimum time interval required between adjacent weld sections. The maximum permissible interlayer temperature, The thickness of the plate representing the workpiece. The thermal diffusivity of the material, This refers to the peak temperature reached during the welding process. The initial ambient temperature.

[0100] This waiting time ensures that the heat generated by the previous weld can dissipate sufficiently, allowing the workpiece temperature to drop to within acceptable limits before proceeding to the next weld. Simultaneously, the waiting time ensures that the deformation from the previous weld reaches a relatively stable state, effectively preventing the cumulative effect of deformation from exceeding expectations and ultimately ensuring that the geometric accuracy of the entire welded workpiece meets design requirements.

[0101] In summary, the intelligent calibration method for steel structure assembly accuracy based on the embodiments of the present invention has been clarified. It accurately collects spatial position data and stress distribution data at the connection between the flange of the I-beam and the flange of the H-beam column, calculates the deformation compensation amount by combining the verticality deviation, and optimizes the calibration force distribution curve and welding heat input parameters based on the variation law of the moment of inertia of the beam flange section. It can effectively control the verticality deviation, significantly improve the accuracy and efficiency of steel structure assembly, and reduce the adverse effects of welding thermal deformation on structural stability.

Claims

1. A method for intelligent calibration of steel structure assembly accuracy, characterized in that, include: Spatial position data of the connection between the flange of the I-beam and the flange of the H-beam column are collected, the spatial position data are converted into verticality deviation values, and stress distribution data of the beam-column connection node are obtained. Based on the verticality deviation value and the stress distribution data, the deformation compensation amount of the I-beam flange is calculated. Based on the aforementioned deformation compensation amount, and according to the variation law of the moment of inertia of the flange section of the I-beam, the calibration force distribution curve along the flange circumference is calculated; Based on the calibration force distribution curve, the welding sequence and weld spacing are determined. The welding parameters are adjusted by the gradient control principle of the thermal field distribution to control the perpendicularity deviation between the flanges of the I-beam and the H-beam column.

2. The intelligent calibration method for steel structure assembly accuracy according to claim 1, characterized in that, Based on the verticality deviation value and the stress distribution data, the deformation compensation amount at each measurement point is determined by calculating the stress concentration factor and introducing the influence of the verticality deviation, using the nominal stress formula combined with the optimization objective function.

3. The intelligent calibration method for steel structure assembly accuracy according to claim 2, characterized in that, The stress concentration factor is calculated by introducing a quadratic term of perpendicularity deviation based on the traditional von Mises equivalent stress. The formula is as follows: in, The stress concentration factor is... This is the stress amplification factor caused by verticality deviation; The normal stress in the radial direction of the flange of the I-beam is... For nominal stress, Tangential stress in the circumferential direction of the flange of the I-beam This refers to the shear stress in the 45° direction of the flange of the I-beam.

4. The intelligent calibration method for steel structure assembly accuracy according to claim 2, characterized in that, The optimization objective function is derived by fitting a nonlinear relationship between the stress concentration coefficient and the perpendicularity deviation value using the least squares method after obtaining the stress concentration coefficient at each measurement reference point. The formula is expressed as follows: in, These are the weighting coefficients; The coordinates are along the circumferential direction of the flange of the I-beam.

5. The intelligent calibration method for steel structure assembly accuracy according to claim 4, characterized in that, Based on the aforementioned optimization objective function, the deformation compensation amount for each measurement reference point is calculated. A new model for calculating deformation compensation is established, expressed as: in, For the first Deformation compensation at each measurement reference point The deformation compensation coefficient is... For the first The distance from each reference point to the center. The distance from the outermost reference point to the center is measured. Radial influence index, This is a stress level correction factor. The yield strength of the material.

6. The intelligent calibration method for steel structure assembly accuracy according to claim 1, characterized in that, Based on the variation law of the moment of inertia of the flange section of the I-beam, the relationship between the load and the radial displacement is established using the fourth-order differential equation based on the theory of variable cross-section beams. The radial displacement is determined by the calibration force distribution function, the elastic modulus of the material, and the moment of inertia of the variable cross-section.

7. The intelligent calibration method for steel structure assembly accuracy according to claim 6, characterized in that, Based on the deformation compensation amount and moment of inertia distribution, the calibration force distribution required to restore the flange to its ideal state is solved in reverse by considering the current radial deviation, i.e., radial displacement. By transforming the fourth-order differential equation, the target deformation is converted into a calibration force distribution, and the calibration force required to eliminate the deviation under specific load conditions is determined.

8. The intelligent calibration method for steel structure assembly accuracy according to claim 7, characterized in that, Based on the obtained calibration force distribution, a continuous calibration force distribution curve is established using the same cubic spline interpolation method as that used to process the deformation data.

9. The intelligent calibration method for steel structure assembly accuracy according to claim 8, characterized in that, Based on the calibration force distribution curve, it is transformed into a welding heat input distribution. Through the principle of welding deformation compensation, the relationship between the welding heat input per unit length and the calibration force distribution is established. Then, through the welding heat input formula, the required heat input is transformed into welding process parameters, including welding thermal efficiency, voltage, current, and speed.

10. The intelligent calibration method for steel structure assembly accuracy according to claim 9, characterized in that, Based on the welding process parameters, a deformation prediction model is established to control the perpendicularity deviation, describing the perpendicularity deviation angle at the location, expressed as: in, For position The perpendicularity deviation angle at point n, where n is the total number of welds. The deformation coefficient is... For the thickness of the workpiece plate, The coefficient of linear expansion is 1 / 3. For welding temperature, For ambient temperature, For the material's Poisson's ratio, This is the decay function.

Images