Deflection calculation method and system for automatically identifying casing deformation

Abstract

The invention discloses a deflection calculation method and system for automatically identifying casing deformation, and relates to the technical field of engineering application. The method comprises the following steps: acquiring initial point cloud data of a sleeve, and preprocessing the initial point cloud data of the sleeve; constructing a casing deflection calculation model, wherein the casing deflection calculation model comprises a three-dimensional space straight line fitting module, a primary rotation module, a secondary rotation module, a deflection parameter adjustment module and a deflection calculation module; and performing casing deflection calculation on the preprocessed initial point cloud data of the casing by using a casing deflection calculation model, and outputting a calculation result. By means of the method and system, automatic recognition of the deformation end point and the datum reference point can be achieved in engineering casing deflection calculation, the casing deflection calculation efficiency is improved, the problem that point selection is difficult is solved, and input of manpower and material resources is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering applications, and in particular to a deflection calculation method and system for automatically identifying casing deformation. Background Art

[0002] Bushing is a widely used material in various projects (such as power and civil engineering). For example, through-the-wall bushing is large in size and heavy in weight. In actual operation, it only relies on the middle through-the-wall part as the only gravity support point, so that both ends of the bushing (outdoor side and indoor side) will inevitably have a certain degree of deflection deformation due to their own gravity, which will affect the connection of the current-carrying structure at the end of the bushing and cause failures (such as overheating of the bushing). At present, the only way to measure the deflection of the bushing is to disassemble it and measure it on the ground, which not only consumes a lot of manpower and material resources, but also has a large safety risk in crane operation, and is not completely consistent with the actual operating conditions.

[0003] In view of the above situation, the existing methods usually combine laser point cloud scanning equipment to scan the wall casing into point cloud data, and calculate the deflection based on the point cloud data. However, since the coordinate data of the point cloud is generally an independent coordinate system, lacking a reference system, and the method of processing the point cloud is mostly to manually select the deformation endpoints and the benchmark reference points, it is impossible to automatically identify and process the deformation endpoints and the benchmark reference points, resulting in low calculation efficiency and difficulty in point selection in the process of calculating the casing deflection based on the benchmark points, baselines and deformation endpoints, which consumes a lot of manpower and material resources. Summary of the invention

[0004] In order to overcome the problem that the existing casing deflection calculation technology is unable to automatically identify and process the deformation endpoints and benchmark reference points during the engineering casing deflection calculation, resulting in low casing deflection calculation efficiency and difficulty in point selection, the purpose of the present invention is to propose a deflection calculation method and system for automatically identifying casing deformation, which can realize automatic identification and data processing of deformation endpoints and benchmark reference points to improve the casing deflection calculation efficiency, effectively reduce the problem of difficulty in point selection, and reduce the investment of manpower and material resources.

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions: A deflection calculation method for automatically identifying casing deformation, the method comprising the following steps: Acquire initial point cloud data of the casing, and preprocess the initial point cloud data of the casing; Constructing a casing deflection calculation model, the casing deflection calculation model comprising a three-dimensional space straight line fitting module, a primary rotation module, a secondary rotation module, a deflection parameter adjustment module and a deflection calculation module; The casing deflection calculation model is used to calculate the casing deflection of the preprocessed initial point cloud data, and the calculation results are output.

[0006] In the above technical scheme, data preprocessing is performed on the acquired initial point cloud data of the casing, which can improve the practicability and reliability of the data and reduce data errors; by constructing a casing deflection calculation model that can effectively grasp the changes in casing point cloud data, automatic identification and data processing of deformation endpoints and benchmark reference points are realized to improve the efficiency of casing deflection calculation, effectively reduce the problem of point selection difficulties, and reduce the investment in manpower and material resources.

[0007] Furthermore, the process of preprocessing the initial point cloud data of the casing includes: The obtained initial point cloud data of the casing is cropped and denoised.

[0008] In the above technical solution, the acquired initial point cloud data of the casing is subjected to noise reduction processing, which can improve the practicality and reliability of the data, reduce data errors, and improve calculation efficiency.

[0009] The three-dimensional space straight line fitting module is used to perform three-dimensional fitting on the point cloud data to obtain the casing space straight line features of the casing point cloud data; The casing is rotated once according to the spatial linear features of the casing using a one-rotation module to extract the plane position features of the casing base; The secondary rotation module performs secondary rotation on the casing according to the extracted plane position features of the casing base, and extracts the point cloud features of the casing edge; The deflection parameter adjustment module selects point clouds according to the extracted point cloud features of the casing edge, and determines the deformation endpoint and the casing root point of the casing; The deflection calculation module determines the casing reference line according to the plane position characteristics of the casing base, calculates the deflection of the casing according to the casing deformation end point, the casing root point and the casing reference line, and outputs the calculation results.

[0010] In the above technical scheme, the constructed casing deflection calculation model is divided into modules according to different functions, and the three-dimensional space straight line fitting module is used to extract the casing space straight line features in the point cloud data. The one-rotation module extracts the casing base plane position features according to the casing space straight line features. The deflection parameter adjustment module determines the casing deformation end point and the casing root point according to the casing base plane position features. The deflection calculation module determines the casing baseline according to the casing base plane position features, and calculates the casing deflection according to the casing deformation end point, the casing root point and the casing baseline. Through the mutual cooperation of various modules, the casing deflection calculation model can effectively grasp the changes in the casing point cloud data, so that the casing deflection calculation model can realize the automatic identification and data processing of the casing deformation end point and the reference point, so as to improve the casing deflection calculation efficiency and effectively reduce the problem of point selection difficulties.

[0011] Furthermore, the process of performing three-dimensional fitting on the casing point cloud data using the three-dimensional space straight line fitting module includes: The decentralization and covariance matrix calculation method is used to perform three-dimensional fitting on the casing point cloud data and extract the casing space straight line features. The expression is: ; in, They represent the coordinates of the fitted straight line, They represent the centroid of the coordinates in the coordinate axis directions, Represent the direction vectors in the three directions of xyz respectively.

[0012] Furthermore, the process of performing three-dimensional fitting on the casing point cloud data by using the decentralization and covariance matrix calculation method includes: Calculate the centroid of the casing in the X, Y, and Z directions. The expression is: ; The centroid of the coordinates of the casing in the X, Y, and Z directions is decentralized, and the expression is: ; Calculate the covariance matrix of the casing and perform singular value decomposition. The expression is: ; ; in, represents the centroid, N represents the number of data points, represents coordinates, is the decentralized coordinate data, Represents the processed casing coordinate data, represents the matrix transpose, represents the covariance matrix of the data, represents the singular value decomposition process, represents the left singular vector, represents the right singular vectors.

[0013] In the above technical solution, the method of decentralization and calculation of covariance matrix is ​​adopted, which can effectively simplify the data processing process in the process of three-dimensional fitting of casing point cloud data to improve the efficiency of data calculation.

[0014] Furthermore, the process of extracting the plane position features of the casing base includes: According to the straight line characteristics of the casing space, the casing slope is calculated using the linear regression method. , the expression is: ; Calculate the rotation angle of the casing based on the casing slope , the expression is: ; According to the rotation angle The casing is rotated once to extract the plane position features of the casing base. The expression is: ; in, Indicates the number of points, represents coordinates, represents the coordinate mean, represents the rotation matrix around the Z axis, represents the matrix transpose, Represents the initial casing coordinate data.

[0015] Furthermore, the process of calculating the deflection of the casing according to the casing deformation end point, the casing root point and the casing reference line includes: The casing slope is obtained by fitting based on the position characteristics of the casing base plane to determine the reference line; The intercept of the reference line is located at the root point of the casing to calculate the deflection between the casing deformation endpoint and the reference line. The expression is: ; in, represents the deflection, are the parameters of the baseline. Respectively represent the X and Z coordinates of the deformation endpoints.

[0016] In the above technical solution, the linear regression method is used to calculate the casing slope, according to the rotation angle The casing is rotated once and the plane position features of the casing base are extracted, which can facilitate the subsequent identification of the casing head and tail and fitting, and improve the accuracy of automatic identification of the deformation endpoints and benchmark reference points of the casing. The optimizer Adam is used to optimize the parameters of the casing deflection calculation model, which can improve the calculation efficiency and accuracy of the casing deflection calculation model, thereby effectively reducing the investment of manpower and material resources.

[0017] A deflection calculation system for automatically identifying casing deformation, the system comprising: A data acquisition module is used to acquire initial point cloud data of the casing; A data processing module, used for preprocessing the initial point cloud data of the casing; A model building module, used to build a casing deflection calculation model, wherein the casing deflection calculation model includes a three-dimensional space straight line fitting module, a primary rotation module, a secondary rotation module, a deflection parameter adjustment module and a deflection calculation module; The casing deflection calculation module is used to calculate the casing deflection on the preprocessed initial point cloud data of the casing using the casing deflection calculation model, and output the calculation result.

[0018] An electronic device comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of a deflection calculation method for automatically identifying casing deformation are implemented.

[0019] Compared with the prior art, the present invention has the following beneficial effects: The present invention proposes a deflection calculation method and system for automatically identifying casing deformation. By preprocessing the acquired initial point cloud data of the casing, the practicability and reliability of the data can be improved and data errors can be reduced. By constructing a casing deflection calculation model that can effectively grasp the changes in casing point cloud data, automatic identification and data processing of deformation endpoints and benchmark reference points can be achieved to improve the calculation efficiency of casing deflection, effectively reduce the problem of point selection difficulties, and reduce the investment in manpower and material resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flowchart of the steps of a deflection calculation method for automatically identifying casing deformation provided in an embodiment of the present application; Figure 2 The initial image of the cannula obtained in the embodiment of the present application; Figure 3 The preprocessed initial image of the cannula provided in the embodiment of the present application; Figure 4 A casing spatial straight line feature map obtained by performing three-dimensional fitting on casing point cloud data provided in an embodiment of the present application; Figure 5 A comparison diagram of the sleeve before and after a rotation provided in an embodiment of the present application; Figure 6 The result of rotating the sleeve provided in the embodiment of the present application is projected onto the XZ plane; Figure 7 A comparison diagram of the sleeve before and after the second rotation provided in the embodiment of the present application; Figure 8 A schematic diagram of a slice after secondary rotation provided in an embodiment of the present application; Fig. 9 A schematic diagram of the distribution of the sleeve fitting area provided in the embodiment of the present application; Fig.10 A schematic diagram of point cloud parameter adjustment provided in an embodiment of the present application; Fig.11 A schematic diagram of the distribution of deformation endpoints and root points provided in an embodiment of the present application; Fig.12 A schematic diagram of the output casing deflection calculation result provided in an embodiment of the present application; Fig.13 A structural schematic diagram of a deflection calculation system for automatically identifying casing deformation provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Preferred embodiments of the present invention are provided in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present invention more thorough and comprehensive.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0023] Embodiment 1: This embodiment provides a method for calculating the deflection of the casing to automatically identify the deformation. Figure 1 , the method comprises the following steps: Step S1: acquiring initial point cloud data of the casing, and preprocessing the initial point cloud data of the casing; Step S2: constructing a casing deflection calculation model, wherein the casing deflection calculation model includes a three-dimensional space straight line fitting module, a primary rotation module, a secondary rotation module, a deflection parameter adjustment module and a deflection calculation module; Step S3: Calculate the casing deflection on the preprocessed initial point cloud data of the casing using the casing deflection calculation model, and output the calculation result.

[0024] In step S1, see Figure 2 and Figure 3 The process of preprocessing the initial point cloud data of the casing includes: After the initial point cloud data of the casing is cropped, it is exported to a coordinate file in txt format and subjected to noise reduction processing; It can be understood that denoising the acquired initial point cloud data of the casing can improve the practicability and reliability of the data, reduce data errors, and improve calculation efficiency.

[0025] Specifically, in step S2: S21: performing three-dimensional fitting on the casing point cloud data using a three-dimensional space straight line fitting module to obtain casing space straight line features of the casing point cloud data; S22: using a one-rotation module to rotate the casing once according to the spatial linear features of the casing, and extracting the plane position features of the casing base; S23: The secondary rotation module performs secondary rotation on the casing according to the extracted plane position features of the casing base, and extracts the point cloud features of the casing edge; S24: the deflection parameter adjustment module selects point clouds according to the extracted casing edge point cloud features, and determines the casing deformation endpoint and the casing root point; S25: The deflection calculation module determines the casing reference line according to the plane position characteristics of the casing base, calculates the deflection of the casing according to the casing deformation end point, the casing root point and the casing reference line, and outputs the calculation result; It can be understood that the constructed casing deflection calculation model is divided into modules according to different functions, and the three-dimensional space straight line fitting module is used to extract the casing space straight line features in the point cloud data. The one-rotation module extracts the casing base plane position features according to the casing space straight line features. The deflection parameter adjustment module determines the casing deformation end point and the casing root point according to the casing base plane position features. The deflection calculation module determines the casing baseline according to the casing base plane position features, and calculates the casing deflection according to the casing deformation end point, the casing root point and the casing baseline. Through the mutual cooperation of various modules, the casing deflection calculation model can effectively grasp the changes in the casing point cloud data, so that the casing deflection calculation model can realize the automatic identification and data processing of the casing deformation end point and the reference point, so as to improve the calculation efficiency of the casing deflection and effectively reduce the problem of point selection difficulties.

[0026] In step S21, see Figure 4 The process of using the three-dimensional space straight line fitting module to perform three-dimensional fitting on the casing point cloud data includes: The process of three-dimensional fitting of casing point cloud data using the decentralization and covariance matrix calculation method includes: Calculate the centroid of the casing in the X, Y, and Z directions. The expression is: ; The centroid of the coordinates of the casing in the X, Y, and Z directions is decentralized, and the expression is: ; Calculate the covariance matrix of the casing and perform singular value decomposition. The expression is: ; ; in, represents the centroid, N represents the number of data points, represents coordinates, is the decentralized coordinate data, Represents the processed casing coordinate data, represents the matrix transpose, represents the covariance matrix of the data, represents the singular value decomposition process, represents the left singular vector, represents the right singular vector, The first column is the direction vector .

[0027] The casing point cloud data is fitted in three dimensions by decentralization and calculation of the covariance matrix method to extract the casing spatial linear features. The expression is: ; in, They represent the coordinates of the fitted straight line, They represent the centroid of the coordinates in the coordinate axis directions, Represent the direction vectors in the three directions of xyz respectively.

[0028] It can be understood that the method of decentralization and calculation of the covariance matrix can effectively simplify the data processing process in the process of three-dimensional fitting of casing point cloud data to improve the efficiency of data calculation.

[0029] In step S22, the process of extracting the planar position features of the casing base includes: According to the straight line characteristics of the casing space, the casing slope is calculated using the linear regression method. , the expression is: ; Calculate the rotation angle of the casing based on the casing slope , the expression is: ; According to the rotation angle The casing is rotated once to extract the plane position features of the casing base. The expression is: ; in, Indicates the number of points, represents coordinates, represents the coordinate mean, represents the rotation matrix around the Z axis, represents the matrix transpose, Represents the initial casing coordinate data.

[0030] In some embodiments, based on the space straight line, the sleeve is rotated for the first time around the Z axis and the Y axis respectively. Since the initial coordinates do not have a fixed reference coordinate system, the spatial straight line feature obtained by fitting in step S22 is projected onto the XY plane, the slope is calculated to obtain the rotation angle, and it is "straightened", that is, roughly parallel to the X axis, to facilitate the subsequent identification of the head and tail and fitting. The rotation result is as follows Figure 5 , Figure 6 As shown, the linear regression formula is as follows.

[0031]

[0032] in, is the slope, is the intercept, For points, are coordinates, is the coordinate average. Then calculate the rotation angle :

[0033] Rotation matrix for rotation around the Z axis for:

[0034] The rotating casing for:

[0035] Here is the initial casing coordinate data, Represents matrix transpose; Similarly, project the three-dimensional coordinates onto the XZ plane and perform the same process to rotate the sleeve around the Y axis.

[0036] Exemplarily, in step S23, the head (deformation end) and tail (reference end) are identified, and the XY plane is rotated twice. Figure 7 and Figure 8 ( Figure 8 The red line in the middle represents the slice section, and the yellow dot represents the lowest point in the slice). Since there is no fixed criterion for the coordinate data, it is not possible to determine at which end of the X-axis the base is located, so the head and tail are identified. The identification method is: intercept 10% of the maximum value and 10% of the minimum value of the X-axis (10% is the ratio with better results obtained after testing), establish an index to find their Y and Z coordinates, and thus filter out the coordinate data of the head and tail; then find the maximum and minimum values ​​of the Y-axis corresponding to the two parts, and after making the difference, determine that the end with the larger difference is the chassis part.

[0037] The casing is projected onto the xy plane, random slices (i.e., cross sections) are taken within the casing, the points with the smallest y coordinates in each slice are selected, and they are used for linear regression fitting. Finally, the entire casing is strictly rotated around the z axis according to the slope of the fitting line.

[0038] Then the casing is projected onto the xz plane, and random slices (i.e., cross sections) are taken within the range of the base, and the slices are parallel to the xy plane. The points with the smallest x coordinates in each slice are selected and used for linear regression fitting. Finally, the entire casing is strictly rotated around the y axis according to the slope of the fitting line.

[0039] For example, in step S24, the deformation endpoint and the root point of the casing are determined. A portion of the chassis, the casing head and the root are cut off, and the point with the lowest elevation within a certain x-coordinate range is found to obtain the deformation endpoint and the root point to avoid the influence of individual noise points, such as Fig. 9 and Fig.10 ( Fig. 9 The dark gray area in the middle head is fitted to obtain the deformation endpoint, the light gray area is fitted to obtain the root point, and the gray area in the tail is reserved for the next step of fitting to solve the baseline; Fig.10 The round point is the deformation endpoint, and the square point is the root point). Fig.11 As shown, the fitting position of the root point and the baseline can be adjusted according to needs.

[0040] In step S25, the process of calculating the deflection of the casing according to the casing deformation end point, the casing root point and the casing reference line includes: The casing slope is obtained by fitting based on the position characteristics of the casing base plane to determine the reference line; The intercept of the reference line is located at the root point of the casing to calculate the deflection between the casing deformation endpoint and the reference line. The expression is: ; in, represents the deflection, are the parameters of the baseline. Respectively represent the X and Z coordinates of the deformation endpoints.

[0041] like Fig.12 The figure shows a schematic diagram of the calculation results of the casing deflection. The gray line in the figure is the reference line, and the black dot is the distance from the deformation point to the reference line, that is, the calculated deflection value.

[0042] In the embodiment of the present application, the optimizer Adam is used to perform parameter optimization on the casing deflection calculation model.

[0043] The method of the embodiment of the present application can be executed in the Cloud Compare software.

[0044] It can be understood that the linear regression method is used to calculate the casing slope according to the rotation angle The casing is rotated once and the plane position features of the casing base are extracted, which can facilitate the subsequent identification of the casing head and tail and fitting, and improve the accuracy of automatic identification of the deformation endpoints and benchmark reference points of the casing. The optimizer Adam is used to optimize the parameters of the casing deflection calculation model to improve the calculation efficiency and accuracy of the casing deflection calculation model, thereby effectively reducing the investment of manpower and material resources.

[0045] In this embodiment, data preprocessing is performed on the acquired initial point cloud data of the casing, which can improve the practicability and reliability of the data and reduce data errors. By constructing a casing deflection calculation model and using the preprocessed data to perform deflection calculation on the constructed casing deflection calculation model, automatic identification and data processing of deformation endpoints and benchmark reference points are achieved to improve the efficiency of casing deflection calculation, effectively reduce the problem of point selection difficulties, and reduce the investment in manpower and material resources.

[0046] Embodiment 2: This embodiment provides a deflection calculation system for automatically identifying casing deformation, see Fig.13 , the system comprising: A data acquisition module is used to acquire initial point cloud data of the casing; A data processing module, used for preprocessing the initial point cloud data of the casing; A model building module, used to build a casing deflection calculation model, wherein the casing deflection calculation model includes a three-dimensional space straight line fitting module, a primary rotation module, a secondary rotation module, a deflection parameter adjustment module and a deflection calculation module; The casing deflection calculation module is used to calculate the casing deflection on the preprocessed initial point cloud data of the casing using the casing deflection calculation model, and output the calculation result.

[0047] Embodiment three: This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of a deflection calculation method for automatically identifying casing deformation are implemented.

[0048] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A deflection calculation method for automatically identifying casing deformation, characterized in that: The method comprises the following steps: Acquire initial point cloud data of the casing, and preprocess the initial point cloud data of the casing; Constructing a casing deflection calculation model, the casing deflection calculation model comprising a three-dimensional space straight line fitting module, a primary rotation module, a secondary rotation module, a deflection parameter adjustment module and a deflection calculation module; The casing deflection calculation model is used to calculate the casing deflection of the preprocessed initial point cloud data, and the calculation results are output.

2. The deflection calculation method for automatically identifying casing deformation according to claim 1 is characterized in that: The process of preprocessing the initial point cloud data of the casing includes: The obtained initial point cloud data of the casing is cropped and denoised.

3. The deflection calculation method for automatically identifying casing deformation according to claim 2 is characterized in that: The three-dimensional space straight line fitting module is used to perform three-dimensional fitting on the point cloud data to obtain the casing space straight line features of the casing point cloud data; The casing is rotated once according to the spatial linear features of the casing using a one-rotation module to extract the plane position features of the casing base; The secondary rotation module performs secondary rotation on the casing according to the extracted plane position features of the casing base, and extracts the point cloud features of the casing edge; The deflection parameter adjustment module selects point clouds according to the extracted point cloud features of the casing edge, and determines the deformation endpoint and the casing root point of the casing; The deflection calculation module determines the casing reference line according to the plane position characteristics of the casing base, calculates the deflection of the casing according to the casing deformation end point, the casing root point and the casing reference line, and outputs the calculation results.

4. The deflection calculation method for automatically identifying casing deformation according to claim 3 is characterized in that: The process of three-dimensional fitting of casing point cloud data using the three-dimensional space straight line fitting module includes: The decentralization and covariance matrix calculation method is used to perform three-dimensional fitting on the casing point cloud data and extract the casing space straight line features. The expression is: ； in, They represent the coordinates of the fitted straight line, They represent the centroid of the coordinates in the coordinate axis directions, Represent the direction vectors in the three directions of xyz respectively.

5. The deflection calculation method for automatically identifying casing deformation according to claim 4 is characterized in that: The process of three-dimensional fitting of casing point cloud data using the decentralization and covariance matrix calculation method includes: Calculate the centroid of the casing in the X, Y, and Z directions. The expression is: ； The centroid of the coordinates of the casing in the X, Y, and Z directions is decentralized, and the expression is: ； Calculate the covariance matrix of the casing and perform singular value decomposition. The expression is: ； ； in, represents the centroid, N represents the number of data points, represents coordinates, is the decentralized coordinate data, Represents the processed casing coordinate data, represents the matrix transpose, represents the covariance matrix of the data, represents the singular value decomposition process, represents the left singular vector, represents the right singular vectors.

6. The deflection calculation method for automatically identifying casing deformation according to claim 4 is characterized in that: The process of extracting the plane position features of the casing base includes: According to the straight line characteristics of the casing space, the casing slope is calculated using the linear regression method. , the expression is: ； Calculate the rotation angle of the casing based on the casing slope , the expression is: ； According to the rotation angle The casing is rotated once to extract the plane position features of the casing base. The expression is: ； in, Indicates the number of points, represents coordinates, represents the coordinate mean, represents the rotation matrix around the Z axis, represents the matrix transpose, Represents the initial casing coordinate data.

7. The deflection calculation method for automatically identifying casing deformation according to claim 6 is characterized in that: The process of calculating the casing deflection based on the casing deformation end point, casing root point and casing reference line includes: The casing slope is obtained by fitting based on the position characteristics of the casing base plane to determine the reference line; The intercept of the reference line is located at the root point of the casing to calculate the deflection between the casing deformation endpoint and the reference line. The expression is: ； in, represents the deflection, are the parameters of the baseline. Respectively represent the X and Z coordinates of the deformation endpoints.

8. The deflection calculation method for automatically identifying casing deformation according to claim 3 is characterized in that: The optimizer Adam is used to optimize the parameters of the casing deflection calculation model.

9. A deflection calculation system for automatically identifying casing deformation, characterized in that: The system comprises: A data acquisition module is used to acquire initial point cloud data of the casing; A data processing module, used for preprocessing the initial point cloud data of the casing; A model building module, used to build a casing deflection calculation model, wherein the casing deflection calculation model includes a three-dimensional space straight line fitting module, a primary rotation module, a secondary rotation module, a deflection parameter adjustment module and a deflection calculation module; The casing deflection calculation module is used to calculate the casing deflection on the preprocessed initial point cloud data of the casing using the casing deflection calculation model, and output the calculation result.

10. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images