Converter station valve hall steel structure deviation and deformation detection method, system, equipment and medium

Abstract

The invention relates to a deviation and deformation detection method, system and device for a converter station valve hall steel structure and a medium. The method comprises the steps that on-site three-dimensional point cloud data of the converter station valve hall steel structure are collected, a steel structure point cloud model is generated, point cloud segmentation is conducted on the steel structure point cloud model, and end cross section point cloud of each component is obtained; according to principal component analysis, plane point cloud projection and a parameterized shape fitting method of the cross section of the steel structural member, extracting vectors of the end cross section normal direction, centroid direction and symmetry axis direction of the steel structural member from the point cloud of the end cross section, and carrying out direction, position deviation and torsional deformation detection; and extracting the central axis of the steel structural member according to a progressive fitting shape point cloud slicing method and a parameterized shape fitting method of the cross section of the steel structural member, and carrying out flexural deflection detection. Compared with the prior art, the detection precision is higher, the detection is more comprehensive, and the detection efficiency is higher.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering structure detection, and in particular to a method, system, device and medium for detecting the deviation and deformation of the steel structure in the valve hall of a converter station. Background Art

[0002] In the construction and operation of large converter stations, the detection of the deviation and deformation of the steel structure in the valve hall is an important link to ensure the structural safety and normal function. Traditional detection methods often rely on manual measurement or two-dimensional drawing comparison, which is not only time-consuming and laborious, but also may have large errors.

[0003] With the development of three-dimensional laser scanning technology, the point cloud processing method based on terrestrial three-dimensional laser scanning has gradually become an effective means for steel structure detection. However, there is still much room for improvement in the accuracy, comprehensiveness and detection efficiency of the existing steel structure deviation and deformation detection based on three-dimensional point clouds. Summary of the Invention

[0004] The purpose of the present invention is to overcome the above-mentioned defects existing in the prior art, and provide a method, system, device and medium for detecting the deviation and deformation of the steel structure in the valve hall of a converter station with higher detection accuracy, more comprehensive detection and higher detection efficiency.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] According to the first aspect of the present invention, a method for detecting the deviation and deformation of the steel structure in the valve hall of a converter station is provided, including:

[0007] Collecting the on-site three-dimensional point cloud data of the steel structure in the valve hall of the converter station, generating a steel structure point cloud model, performing point cloud segmentation on the steel structure point cloud model to obtain the point cloud of each individual steel structure member, and performing boundary extraction on the point cloud of the steel structure member to obtain the end cross-sectional point cloud of each steel structure member;

[0008] Respectively extracting the end cross-sectional normal direction, centroid and symmetry axis direction vector of the steel structure member from the end cross-sectional point cloud according to the principal component analysis, plane point cloud projection and parametric shape fitting method of the steel structure member cross-section, and performing direction, position deviation and torsional deformation detection;

[0009] Extracting the central axis of the steel structure member from the point cloud of the steel structure member according to the progressive fitting shape point cloud slicing method and the parametric shape fitting method of the steel structure member cross-section, and performing flexural deformation detection.

[0010] Preferably, the performing point cloud segmentation on the steel structure point cloud model to obtain the point cloud of each individual steel structure member, and performing boundary extraction on the point cloud of the steel structure member to obtain the end cross-sectional point cloud of each steel structure member is specifically:

[0011] The three-dimensional point cloud of the steel structure is scanned by a terrestrial three-dimensional laser scanner, and multiple measuring stations are set up to splice each measuring station through a target to generate a point cloud model of the steel structure.

[0012] Preferably, the point cloud of the steel structure model is segmented to obtain the point cloud of each individual steel structure member, and the boundary of the point cloud of the steel structure member is extracted to obtain the end cross-sectional point cloud of each steel structure member. Specifically:

[0013] The point cloud of the steel structure model is segmented according to the difference of the point cloud normal vector by the normal differential point cloud segmentation method, and the point cloud of each individual steel structure member is extracted;

[0014] The alpha-shape algorithm is used for boundary extraction to obtain the boundary point cloud of the point cloud of each steel structure member, and the end cross-sectional point cloud of each member is obtained after intercepting.

[0015] Preferably, the end cross-sectional normal direction, centroid and symmetry axis direction vector of the steel structure member are respectively extracted from the end cross-sectional point cloud according to the principal component analysis, plane point cloud projection and parametric shape fitting method of the steel structure member cross-section, and the direction, position deviation and torsional deformation are detected. Specifically include:

[0016] Perform principal component analysis on the end cross-sectional point cloud of the steel structure member, obtain the three principal components of the end cross-sectional point cloud, and use the third principal component n3 as the normal vector of the end cross-section to calculate the direction deviation of the steel structure member;

[0017] Set the plane equation as a(x - x0)+b(y - y0)+c(z - z0) = 0, take the root mean square distance value from the points in the end cross-sectional point cloud to the plane as the objective function, and use the least squares method to solve the optimal parameter group (x0, y0, z0) to fit the plane where the end cross-sectional point cloud of the steel structure member is located;

[0018] Project the end cross-sectional point cloud onto the fitted plane, and create a local coordinate system with the centroid of the plane projection point cloud as the origin O of the coordinate axis, the projection vector of the first principal component n1 on the fitted plane as the X axis, the cross product of the X axis vector and the third principal component n3 as the Y axis, and the third principal component n3 as the Z axis;

[0019] Construct a parametric shape fitting model of the steel structure cross-section based on the local coordinate system to detect the direction, position deviation and torsional deformation.

[0020] Preferably, constructing a parametric shape fitting model of the steel structure cross-section based on the local coordinate system specifically includes:

[0021] 1) Point cloud input module: Read the end cross-sectional point cloud of the steel structure member;

[0022] 2) Parametric shape modeling module:

[0023] For steel structure members with rectangular cross-sections: The rectangular size is controlled by the starting position parameter x of the X-axis dimension range ds and the ending position parameter x of the X-axis dimension range de as well as the starting position parameter y of the Y-axis dimension range ds and the ending position parameter y of the Y-axis dimension range de and the orientation of the rectangle is controlled by the angle parameter θ between the axis of symmetry and the X-axis r ;

[0024] For steel structure members with circular cross-sections: The shape of the circle is controlled by the parameter Δx c of the deviation of the center of the circle from the origin of the local coordinate system and Δy c , and the radius parameter r;

[0025] For steel structure members with I-shaped cross-sections: The shape of the I-shape is controlled by the parameter Δx h of the deviation of the centroid from the origin of the local coordinate system and Δy h , the cross-section height parameter h, the cross-section width parameter b, the flange thickness parameter t f , the web thickness parameter t w and the angle parameter θ between the axis of symmetry and the X-axis h ;

[0026] 3) Parameter optimization fitting module:

[0027] Taking the root mean square distance value of the closest distance cp i from n points p i in the end cross-sectional point cloud of the steel structure member to the edge of the parametric shape as the objective function, parameter optimization fitting is carried out;

[0028] 4) Shape feature calculation module:

[0029] Calculate the centroid point and the axis direction vector of the end cross-sectional shape of steel structure members with rectangular, circular, and I-shaped cross-sections, and calculate the position deviation and cross-sectional torsional deformation amount of the steel structure member.

[0030] Preferably, in the parameter optimization fitting module, the parameter update of the parametric shape is driven by using the RBFOpt optimization algorithm through an optimization solver to minimize the objective function value, and parameter optimization fitting is carried out.

[0031] Preferably, according to the progressive fitting shape point cloud slicing method and the parametric shape fitting of the cross-section of the steel structure member, the central axis of the steel structure member is extracted for flexural deformation detection, specifically including:

[0032] Taking the centroid C and the normal N of the end cross-section as the starting point and the starting direction of the point cloud slice;

[0033] According to the centroid c of the cross-section of the first two point cloud slices i-2 、c i-1 The vector formed is the normal d of the new slice plane i ;

[0034] The centroid c of the cross-section of the previous point cloud slice i-1 Translate a certain distance D along the normal d of the new slice plane i The obtained point is a point p on the new slice plane i ;

[0035] Through the normal d of the new slice plane i And a point p on the slice plane i Construct the new slice plane SP i The points whose distance from the new slice plane is less than half of the slice thickness w are intercepted as the new slice point cloud S i ;

[0036] For the new slice point cloud S i Calculate the centroid c of the cross-section where the new slice point cloud is located by the parametric shape fitting method of the steel structure cross-section i Until all the point clouds of the components are sliced and the centroids of the cross-sections are obtained;

[0037] The centroids of all cross-sections characterize the central axis of the component, and the flexural deformation is calculated.

[0038] According to the second aspect of the present invention, there is provided a system applying the method for detecting the deviation and deformation of the steel structure in the valve hall of a converter station, including:

[0039] A point cloud generation module, configured to collect the on-site three-dimensional point cloud data of the steel structure in the valve hall of the converter station, generate a steel structure point cloud model, perform point cloud segmentation on the steel structure point cloud model to obtain the point cloud of each individual steel structure component, and perform boundary extraction on the point cloud of the steel structure component to obtain the end cross-section point cloud of each steel structure component;

[0040] A first detection module, configured to respectively extract the end cross-section normal, centroid and symmetry axis direction vector of the steel structure component from the end cross-section point cloud according to the principal component analysis, plane point cloud projection and parametric shape fitting method of the steel structure component cross-section, and perform direction, position deviation and torsional deformation detection;

[0041] A second detection module, configured to extract the central axis of the steel structure component from the point cloud of the steel structure component according to the progressive fitting shape point cloud slicing method and the parametric shape fitting method of the steel structure component cross-section, and perform flexural deformation detection.

[0042] According to the third aspect of the present invention, there is provided an electronic device, including a memory and a processor, where a computer program is stored on the memory, and when the processor executes the program, the method described in any one of the above is implemented.

[0043] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium having stored thereon a computer program, which when executed by a processor implements the method according to any one of the above.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] (1) Based on the on-site three-dimensional point cloud data of the steel structure in the converter station valve hall, the present invention extracts the end cross-section point cloud of the steel structure member through point cloud segmentation, and then extracts the normal direction, centroid and symmetry axis direction vector of the end cross-section from the end cross-section point cloud through principal component analysis, planar point cloud projection and parametric shape fitting method of the steel structure member cross-section, so as to realize the detection of direction, position deviation and torsional deformation. At the same time, according to the progressive fitting shape point cloud slicing method and the parametric shape fitting method of the steel structure member cross-section, the central axis of the steel structure member is extracted to realize the flexural deformation detection, and it can obtain the deviation and deformation of the large converter station valve hall steel structure member more quickly and comprehensively, taking into account the requirements of high efficiency and high precision.

[0046] (2) The present invention scans the three-dimensional point cloud of the steel structure through a ground three-dimensional laser scanner, and the three-dimensional laser scanning can quickly obtain high-precision three-dimensional point cloud data of the valve hall steel structure; the normal differential segmentation is used to segment the point cloud of the member, and the segmentation is carried out by calculating the normal vector of each point in the point cloud and its change rate. The segmentation based on geometric features can accurately capture the shape change of the surface of the steel structure point cloud, and the segmentation result is more accurate; the alpha-shape algorithm is used to extract the end cross-section point cloud of the member, which can adapt to the steel structure point cloud data with different shape complexities, so that the end cross-section point cloud of each steel structure member can be extracted more accurately and efficiently, providing a basis for the subsequent quantitative analysis of structural deviation and deformation.

[0047] (3) Through principal component analysis of the end cross-section point cloud of the steel structure member, the third principal component is directly used as the normal vector of the end cross-section to calculate the direction deviation of the steel structure member. A local coordinate system is created with the centroid of the planar projected point cloud as the origin of the coordinate axis, the projection vector of the first principal component on the fitting plane as the X-axis, the cross product of the X-axis vector and the third principal component as the Y-axis, and the third principal component as the Z-axis, and a parametric shape fitting model of the steel structure cross-section is constructed, which can realize more accurate detection of direction, position deviation and torsional deformation. Description of the Drawings

[0048] Figure 1 is a flowchart of a method for detecting deviation and deformation of a large converter station valve hall steel structure based on point cloud processing provided according to the content of the present invention;

[0049] Figure 2It is a schematic diagram of extracting the cross-section normal direction by the main component analysis of the end cross-section provided according to the content of the present invention;

[0050] Figure 3 It is a schematic diagram of the point cloud plane projection and the local coordinate system provided according to the content of the present invention;

[0051] Figure 4 It is a schematic diagram of the parametric representation of a rectangular cross-section provided according to the content of the present invention;

[0052] Figure 5 It is a schematic diagram of the parametric representation of a circular cross-section provided according to the content of the present invention;

[0053] Figure 6 It is a schematic diagram of the parametric representation of an I-shaped cross-section provided according to the content of the present invention;

[0054] Figure 7 It is a schematic diagram of extracting the centroid and the axis of symmetry of the cross-section shape by parametric shape fitting of the cross-section of a rectangular steel structure provided according to the content of the present invention;

[0055] Figure 8 It is a schematic diagram of the progressive fitting shape point cloud slicing method provided according to the content of the present invention;

[0056] Figure 9 It is a schematic diagram of the calculation result of the centroid of the cross-section point cloud slice provided according to the content of the present invention;

[0057] Figure 10 It is a schematic diagram of the extraction result of the flexural deformation of the component provided according to the content of the present invention. Specific Embodiments

[0058] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0059] Embodiment 1

[0060] As Figure 1 shown, this embodiment provides a method for detecting the deviation and deformation of the steel structure in the converter station valve hall. This method uses point cloud processing technology to detect the structural deviation and deformation of the large converter station valve hall steel structure. Its main contents include:

[0061] S1. Collect the on-site three-dimensional point cloud data of the steel structure in the converter station valve hall, generate a steel structure point cloud model and perform point cloud segmentation to obtain the end cross-section point cloud of each component;

[0062] S2. Extract the normal direction, centroid, and axis of symmetry direction vector of the end cross-section of the steel structure member based on principal component analysis, planar point cloud projection, and parametric shape fitting of the cross-section of the steel structure member, and perform direction, position deviation, and torsional deformation detection;

[0063] S3. Extract the central axis of the steel structure member according to the progressive fitting shape point cloud slicing method and parametric shape fitting of the cross-section of the steel structure member, and perform flexural deformation detection.

[0064] This embodiment also provides a converter station valve hall steel structure detection system based on point cloud processing, including:

[0065] A point cloud generation module, configured to collect on-site three-dimensional point cloud data of the converter station valve hall steel structure, generate a steel structure point cloud model, and perform point cloud segmentation;

[0066] A first detection module, configured to extract the normal direction, centroid, and axis of symmetry direction vector of the end cross-section of the steel structure member based on principal component analysis, planar point cloud projection, and parametric shape fitting of the cross-section of the steel structure member, and perform direction, position deviation, and torsional deformation detection;

[0067] A second detection module, configured to extract the central axis of the steel structure member according to the progressive fitting shape point cloud slicing method and parametric shape fitting of the cross-section of the steel structure member, and perform flexural deformation detection.

[0068] The electronic device of the present invention includes a central processing unit (CPU), which can execute various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) or computer program instructions loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for device operation can also be stored. The CPU, ROM, and RAM are connected to each other through a bus. An input / output (I / O) interface is also connected to the bus.

[0069] Multiple components in the device are connected to the I / O interface, including: an input unit, such as a keyboard, a mouse, etc.; an output unit, such as various types of displays, speakers, etc.; a storage unit, such as a disk, an optical disc, etc.; and a communication unit, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit allows the device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0070] The processing unit executes the various methods and processes described above, such as methods S1 to S3. For example, in some embodiments, methods S1 to S3 may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed onto the device via the ROM and / or the communication unit. When the computer program is loaded into the RAM and executed by the CPU, one or more steps of methods S1 to S3 described above may be executed. Alternatively, in other embodiments, the CPU may be configured to execute methods S1 to S3 by any other suitable means (such as, by means of firmware).

[0071] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. By way of example, and without limitation, the types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0072] The program code for implementing the methods of the present invention may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, a special purpose computer, or other programmable data processing device, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on the remote machine or server.

[0073] In the context of the present invention, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0074] Embodiment 2

[0075] This embodiment provides a method for detecting the deviation and deformation of the steel structure in the converter valve hall based on point cloud processing. The method includes the following steps:

[0076] S1: Collect on-site three-dimensional point cloud data, generate a steel structure point cloud model and perform point cloud segmentation to obtain the end cross-sectional point cloud of each component. Specifically, it includes the following sub-steps

[0077] S1-1: Use a ground three-dimensional laser scanner to scan the three-dimensional point cloud of the steel structure, set multiple measurement stations, and splice each measurement station through a target to generate a steel structure point cloud model;

[0078] S1-2: Based on the segmentation method of normal differential, segment the point cloud model according to the difference of point cloud normal vectors, and extract the point cloud of each individual steel structure component;

[0079] S1-3: Use the alpha-shape algorithm to extract the boundary point cloud of each steel structure component point cloud, and intercept to obtain the end cross-sectional point cloud of each component.

[0080] S2. Extract the normal direction, centroid and symmetry axis direction vector of the end cross-section of the steel structure component according to principal component analysis, plane point cloud projection and parametric shape fitting of the steel structure component cross-section, and perform direction, position deviation and torsional deformation detection. Specifically, it includes the following sub-steps:

[0081] S2-1: As Figure 2 , perform principal component analysis on the end cross-sectional point cloud of the steel structure component to obtain three principal components n1, n2 and n3 of the end cross-sectional point cloud. The third principal component n3(a, b, c) of the principal component analysis is the normal vector of the end cross-section, which is used to calculate the direction deviation of the steel structure component;

[0082] S2-2: Assume that the plane equation is a(x - x0) + b(y - y0) + c(z - z0) = 0, take the root mean square distance value from the points in the end cross-sectional point cloud to the plane as the objective function, and use the least squares method to solve the optimal parameter group (x0, y0, z0) to fit the plane where the end cross-sectional point cloud of the steel structure component is located;

[0083] S2-3: As Figure 3 , project the end cross-sectional point cloud onto the fitted plane, and create a local coordinate system with the centroid of the plane projection point cloud as the origin O of the coordinate axis, the projection vector of the first principal component n1 on the fitted plane as the X-axis, the cross product of the X-axis vector and the third principal component n3 as the Y-axis, and the third principal component n3 as the Z-axis;

[0084] S2-4: Compile the parametric shape fitting of the steel structure cross-section according to the local coordinate system. Specifically, it includes:

[0085] 1) Point cloud input module, read the end cross-sectional point cloud of the steel structure component;

[0086] 2) Parametric shape modeling module, as Figure 4 shown, for steel structure members with rectangular cross-sections: The dimensions of the rectangle are controlled by the starting position parameter x of the X-axis dimension range ds , the ending position parameter x of the X-axis dimension range de , the starting position parameter y of the Y-axis dimension range ds and the ending position parameter y of the Y-axis dimension range de ; the orientation of the rectangle is controlled by the angle parameter θ between the axis of symmetry and the X-axis r ; as Figure 5 shown, for steel structure members with circular cross-sections: The shape of the circle is controlled by the parameters Δx c and Δy c of the deviation of the center of the circle from the origin of the local coordinate system, and the radius parameter r; as Figure 6 shown, for steel structure members with I-shaped cross-sections: The shape of the I-shape is controlled by the parameters Δx h and Δy h of the deviation of the centroid from the origin of the local coordinate system, the cross-section height parameter h, the cross-section width parameter b, the flange thickness parameter t f , the web thickness parameter t w and the angle parameter θ between the axis of symmetry and the X-axis h ; 3) Parameter optimization and fitting module, with the root mean square distance value of the closest distance cp i from n points p i in the end cross-sectional point cloud of the steel structure member to the edge of the parametric shape as the objective function, and using the RBFOpt optimization algorithm to drive the parameter update of the parametric shape by the optimization solver to minimize the objective function value. For steel structure members with rectangular cross-sections: The fitting process is expressed as For steel structure members with circular cross-sections: The fitting process is expressed as For steel structure members with I-shaped cross-sections: The fitting process is expressed as 4) Shape feature calculation module, which calculates the centroid point and the axis direction vector of the end cross-sectional shape of steel structure members with rectangular, circular, and I-shaped cross-sections, and is used to calculate the position deviation and cross-sectional torsional deformation of the steel structure member. Taking the rectangular steel structure as an example, its cross-sectional parametric shape fitting process is as Figure 7 shown, and the position deviation and cross-sectional torsional deformation of the member are calculated based on the extraction results of the cross-section centroid and axis of symmetry.

[0087] S3. According to the progressive fitting shape point cloud slicing method and the parametric shape fitting of the steel structure member cross-section, extract the central axis of the steel structure member and perform flexural deformation detection, which specifically includes the following sub-steps:

[0088] S3-1: As Figure 8, with the centroid C of the end cross-section and the normal N as the starting point and starting direction of the point cloud slice;

[0089] S3-2: As Figure 8 , according to the centroids c i-2 、c i-1 of the cross-sections of the first two point cloud slices, the vector formed is the normal d i of the new slice plane;

[0090] S3-3: As Figure 8 , the centroid c i-1 of the cross-section of the previous point cloud slice is translated a certain distance D along the normal d i of the new slice plane to obtain a point p i on the new slice plane;

[0091] S3-4: As Figure 8 , through the normal d i of the new slice plane and a point p i on the slice plane to construct the new slice plane SP i , the points whose distance from the new slice plane is less than half of the slice thickness w are intercepted as the new slice point cloud S i ;

[0092] S3-5: As Figure 9 , for the new slice point cloud S i , use the steel structure cross-section parameterization shape fitting method in S2-4 to calculate the centroid c i of the cross-section where the new slice point cloud is located until all the component point clouds are sliced and the cross-section centroids are obtained;

[0093] S3-6: As Figure 10 , all the cross-section centroids represent the center axis of the component, and the flexural deformation is calculated.

[0094] Based on the point cloud processing method, the present invention can quickly and comprehensively obtain the deviations and deformations of the steel structure components of large converter station valve halls, improving the steel structure detection efficiency.

[0095] Other settings in this embodiment are the same as those in Embodiment 1.

[0096] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for detecting the deviation and deformation of the valve hall steel structure of a converter station, characterized in that, Including: Collecting the on-site three-dimensional point cloud data of the valve hall steel structure of the converter station, generating a steel structure point cloud model, performing point cloud segmentation on the steel structure point cloud model to obtain the point cloud of each individual steel structure member, and performing boundary extraction on the point cloud of the steel structure member to obtain the end cross-sectional point cloud of each steel structure member; Extracting the normal direction, centroid, and symmetry axis direction vector of the end cross-section of the steel structure member from the end cross-sectional point cloud respectively according to principal component analysis, plane point cloud projection, and parametric shape fitting method of the steel structure member cross-section, and performing direction, position deviation, and torsional deformation detection; Extracting the central axis of the steel structure member from the steel structure member point cloud according to the progressive fitting shape point cloud slicing method and the parametric shape fitting method of the steel structure member cross-section, and performing flexural deformation detection.

2. The method for detecting the deviation and deformation of the steel structure of the converter station valve hall according to claim 1, wherein The step of performing point cloud segmentation on the steel structure point cloud model to obtain the point cloud of each individual steel structure member, and performing boundary extraction on the point cloud of the steel structure member to obtain the end cross-sectional point cloud of each steel structure member is specifically as follows: Scanning the three-dimensional point cloud of the steel structure with a ground three-dimensional laser scanner, and setting multiple measurement stations to splice each measurement station through a target to generate a steel structure point cloud model.

3. A method for detecting the deviation and deformation of the steel structure in the converter station valve hall according to claim 1, characterized in that The step of performing point cloud segmentation on the steel structure point cloud model to obtain the point cloud of each individual steel structure member, and performing boundary extraction on the point cloud of the steel structure member to obtain the end cross-sectional point cloud of each steel structure member is specifically as follows: Using the normal differential point cloud segmentation method to segment the steel structure point cloud model according to the difference of the point cloud normal vectors, and extracting the point cloud of each individual steel structure member; Using the alpha-shape algorithm to perform boundary extraction to obtain the boundary point cloud of the point cloud of each steel structure member, and intercepting to obtain the end cross-sectional point cloud of each member.

4. A method for detecting the deviation and deformation of the steel structure of a converter station valve hall according to claim 1, characterized in that The step of extracting the normal direction, centroid, and symmetry axis direction vector of the end cross-section of the steel structure member from the end cross-sectional point cloud respectively according to principal component analysis, plane point cloud projection, and parametric shape fitting method of the steel structure member cross-section, and performing direction, position deviation, and torsional deformation detection specifically includes: Performing principal component analysis on the end cross-sectional point cloud of the steel structure member, obtaining three principal components of the end cross-sectional point cloud, and taking the third principal component n3 as the normal vector of the end cross-section for calculating the direction deviation of the steel structure member; Setting the plane equation as a(x - x0) + b(y - y0) + c(z - z0) = 0, taking the root mean square distance value from the points in the end cross-sectional point cloud to the plane as the objective function, and using the least squares method to solve the optimal parameter group (x0, y0, z0) to fit the plane where the end cross-sectional point cloud of the steel structure member is located; Projecting the end cross-sectional point cloud onto the fitted plane, creating a local coordinate system with the centroid of the plane projection point cloud as the coordinate origin O, the projection vector of the first principal component n1 on the fitted plane as the X-axis, the cross product of the X-axis vector and the third principal component n3 as the Y-axis, and the third principal component n3 as the Z-axis; Constructing a parametric shape fitting model of the steel structure cross-section based on the local coordinate system, and performing direction, position deviation, and torsional deformation detection.

5. A method for detecting the deviation and deformation of the steel structure of a converter station valve hall according to claim 4, characterized in that, Constructing a parametric shape fitting model of the steel structure cross-section based on the local coordinate system specifically includes: 1) Point cloud input module: Reading the end cross-sectional point cloud of the steel structure member; 2) Parametric Shape Modeling Module: For steel structure members with rectangular cross-sections: the starting position parameter x of the X-axis dimension range ds , the ending position parameter x of the X-axis dimension range de , the starting position parameter y of the Y-axis dimension range ds and the ending position parameter y of the Y-axis dimension range de control the rectangular dimensions, and the angle parameter θ between the axis of symmetry and the X-axis r controls the rectangular orientation; For steel structural members with circular cross-sections: the shape of the circle is controlled by the parameters Δx c and Δy c that deviate the center of the circle from the origin of the local coordinate system, as well as the radius parameter r; For the I-shaped cross-section steel structure members: By the parameters of the centroid deviation from the origin of the local coordinate system Δx h and Δy h , the cross-section height parameter h, the cross-section width parameter b, the flange thickness parameter t f , the web thickness parameter t w and the angle parameter θ between the axis of symmetry and the X-axis h to control the shape of the I-shape; 3) Parameter Optimization Fitting Module: Taking the root mean square distance value of the nearest distances cp i from n points p in the end cross-sectional point cloud of the steel structure member to the edges of the parametric shape i as the objective function, parameter optimization fitting is carried out; i to the edges of the parametric shape i as the objective function, parameter optimization fitting is carried out; 4) Shape Feature Calculation Module: Calculate the centroid point and the direction vector of the axis of symmetry of the end cross-sectional shape of steel structure members with rectangular, circular, and I-shaped cross-sections, and calculate the position deviation and cross-sectional torsional deformation of the steel structure members.

6. A method for detecting the deviation and deformation of the steel structure of a converter station valve hall according to claim 5, characterized in that In the Parameter Optimization Fitting Module, the parameter update of the parametric shape is driven by the RBFOpt optimization algorithm using an optimization solver to minimize the objective function value for parameter optimization fitting.

7. A method for detecting the deviation and deformation of the steel structure in the converter station valve hall according to claim 1, characterized in that, Extract the central axis of the steel structure member according to the progressive fitting shape point cloud slicing method and the parametric shape fitting of the cross-section of the steel structure member, and perform flexural deformation detection, specifically including: Use the centroid C and normal N of the end cross-section as the starting point and starting direction of the point cloud slice; According to the centroids c i-2 and c i-1 of the cross-sections of the first two point cloud slices, the vector formed is the normal d i of the new slice plane; The centroid c of the cross-section of the previous point cloud slice i-1 The normal d along the new slice plane i The point obtained by translating a certain distance D is a point p on the new slice plane i ; Normal d of the new slice plane i and a point p on the slice plane i Construct a new slice plane SP i Points whose distance from the new slice plane is less than half of the slice thickness w are the new slice point cloud S i ; For the new sliced point cloud S i Calculate the centroid c of the cross-section where the new sliced point cloud is located by using the parametric shape fitting method of the steel structure cross-section i , until all the point clouds of the component are sliced and the centroids of the cross-sections are obtained; The centroids of all cross-sections represent the central axis of the member, and the flexural deformation is calculated.

8. A system applying the method for detecting the deviation and deformation of the steel structure of a converter station valve hall according to claim 1, characterized in that, Including: Point Cloud Generation Module, which is used to collect the on-site three-dimensional point cloud data of the steel structure in the converter valve hall, generate a steel structure point cloud model, perform point cloud segmentation on the steel structure point cloud model to obtain the point cloud of each individual steel structure member, and perform boundary extraction on the point cloud of the steel structure member to obtain the point cloud of the end cross-section of each steel structure member; First Detection Module, which is used to extract the normal direction, centroid, and direction vector of the axis of symmetry of the end cross-section of the steel structure member from the end cross-section point cloud respectively according to the principal component analysis, plane point cloud projection, and parametric shape fitting method of the steel structure member cross-section, and perform direction, position deviation, and torsional deformation detection; Second Detection Module, which is used to extract the central axis of the steel structure member from the steel structure member point cloud according to the progressive fitting shape point cloud slicing method and the parametric shape fitting of the cross-section of the steel structure member, and perform flexural deformation detection.

9. An electronic device, comprising a memory and a processor, wherein a computer program is stored on the memory, characterized in that, When the processor executes the program, it implements the method described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method described in any one of claims 1 to 7.

Images