A vertical alignment detection system for construction engineering

Abstract

The application discloses a vertical calibration degree detection system for building engineering and relates to the field of building engineering detection. A plurality of laser beams are emitted from a calibrated original point to a surface to be detected, the coordinates and distances of detection points where the laser beams intersect the surface to be detected are acquired, interference factors when the laser beams are emitted are collected in real time, the acquired interference factors are taken as inputs of a pre-trained neural network unit, error values of measured distances are output, the measured distances are compensated by using the error values, compensated measured distances are acquired, the coordinates of the detection points are recalculated by using the compensated measured distances, the surface to be detected is fitted by using a least square method, a plane equation and a normal vector of the surface to be detected are determined, and an included angle between the normal vector and a theoretical vertical direction is calculated as a representation of the perpendicularity of the surface to be detected, so that the perpendicularity detection with high precision, high efficiency, automation and real-time monitoring is realized, and an innovative solution is provided for the field of building engineering.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of building engineering detection, in particular to a vertical calibration degree detection system for building engineering. BACKGROUND

[0002] In the field of building engineering, ensuring the verticality of the structure is one of the key factors to guarantee the quality and safety of the building. Traditional verticality detection methods mainly rely on manual operation, such as using tools such as level, theodolite, etc. for measurement. Although these methods can meet the measurement needs to some extent, they also have many limitations.

[0003] Firstly, manual measurement method is inefficient, requiring a large amount of manpower and time cost. Secondly, the accuracy of manual measurement is significantly affected by the technical level of the operator and environmental factors. For example, the weather conditions, light intensity, and experience and fatigue of the operator during measurement can affect the accuracy of the measurement results. In addition, manual measurement method is difficult to realize automation and real-time monitoring, which cannot timely find the verticality deviation in the construction process, thereby increasing the risk of quality problems of the building structure.

[0004] With the development of technology, laser measurement technology has been gradually introduced into the field of building engineering. Laser measurement equipment can quickly and accurately measure distance and angle, greatly improving the measurement efficiency and accuracy. However, the existing laser measurement equipment is easily affected by environmental factors such as temperature, humidity, air flow speed, etc. during measurement. These environmental factors may cause the deflection and attenuation of the laser beam, thereby affecting the accuracy of the measurement results. In addition, the roughness and vibration of the wall surface to be detected also interfere with the laser measurement, further reducing the measurement accuracy. Therefore, there is an urgent need for a verticality detection system that can adapt to the complex conditions of building engineering site, has high precision and high efficiency. The system should be able to compensate for the influence of environmental factors and wall surface characteristics on the measurement results in real time, and have the functions of automatic measurement and real-time monitoring to meet the strict requirements of modern building engineering on quality and safety. Therefore, a vertical calibration degree detection system for building engineering is proposed. SUMMARY

[0005] The main purpose of the present application is to provide a vertical calibration degree detection system for building engineering, which realizes high-precision and high-efficiency detection of verticality by integrating laser measurement technology, edge computing module and pre-trained artificial neural network unit, and can compensate for the influence of environmental factors and wall surface characteristics on the measurement results in real time, which can effectively solve the problems in the background technology.

[0006] To achieve the above purpose, the technical scheme adopted by the present application is,

[0007] A vertical calibration degree detection system for building engineering, comprising:

[0008] a calibration module, configured to calibrate a coordinate point as an origin point;

[0009] a laser emission module, configured to emit a plurality of laser beams from the origin point to a surface to be detected;

[0010] a distance measurement module, configured to measure a distance between each detection point on the surface to be detected and the origin point through the laser beams;

[0011] a data acquisition module, configured to acquire interference factors when the laser beams are emitted, including environmental parameters, roughness of the surface to be detected, vibration parameters of the laser emission module, and laser beam emission angles;

[0012] an edge computing module, including a pre-trained neural network unit, configured to compensate for errors of the measured distances according to the interference factors;

[0013] a perpendicularity calculation module, configured to determine perpendicularity of the surface to be detected according to the measured distances after error compensation.

[0014] Further, a distance between the origin point and the surface to be detected satisfies a first constraint model as follows:

[0015] ;

[0016] wherein, is a first constraint condition; is a distance between the origin point and the surface to be detected; , are minimum and maximum effective distances of the laser emission module, respectively; is a change in laser wavelength caused by temperature change during measurement; is an initial wavelength of the laser during measurement; is a maximum allowable error caused by temperature change during measurement; is a change in laser attenuation coefficient caused by humidity change during measurement; is an initial attenuation coefficient of the laser during measurement; is a maximum allowable error caused by humidity change during measurement; is a change in laser beam offset angle caused by airflow speed change during measurement; is an initial laser beam offset angle of the laser during measurement; is a maximum allowable error caused by airflow speed change.

[0017] Further, a number of the laser beams emitted from the origin point to the surface to be detected satisfies a second constraint model as follows:

[0018] ;

[0019] in, This is the second constraint condition; The number of laser beams emitted; This represents the maximum number of laser beams under the system's maximum processing capacity. This is a characteristic correlation constant between the laser emitting module and the surface to be detected; To ensure the accuracy of the measurement target; The coverage density of the laser beam on the surface to be inspected; The area is the surface to be inspected.

[0020] Furthermore, the environmental parameters include one or more combinations of temperature, humidity, and airflow velocity.

[0021] Furthermore, the edge computing module also includes a feature engineering unit for extracting polynomial features and interaction features from the interference factors.

[0022] Furthermore, the edge computing module also includes a model training unit for training a neural network unit using the polynomial features and interaction features extracted by the feature engineering unit.

[0023] Furthermore, the edge computing module also includes an error prediction unit, which is used to predict the measurement error of the measured distance using the pre-trained neural network unit, and to compensate the measured distance based on the measurement error.

[0024] Furthermore, the verticality calculation module includes a plane fitting unit, which is used to fit the plane equation of the surface to be detected using the least squares method based on the measured distance after error compensation, and to calculate the normal vector of the surface to be detected.

[0025] Furthermore, the perpendicularity calculation module also includes an angle calculation unit, used to calculate the angle between the normal vector of the surface to be tested and the theoretical vertical direction, so as to determine the perpendicularity of the surface to be tested.

[0026] Furthermore, the implementation process of the system includes the following steps:

[0027] a) Define a coordinate point as the origin;

[0028] b) Emit several laser beams from the origin toward the surface to be tested, and obtain the coordinates of the detection points where each laser beam intersects with the surface to be tested. and measuring distance ,in, = , This refers to the number of the testing point;

[0029] c) Real-time acquisition of the first Interference factors during laser beam emission;

[0030] d) Using the obtained interference factors as input to the pre-trained neural network unit, and using the pre-trained neural network unit to output the measured distance. error value ;

[0031] e) Utilizing the error value For the measured distance Perform compensation and obtain the compensated measurement distance. ,in, = - ;

[0032] f) Using the compensated measurement distance Recalculate the first The coordinates of the detection point ,in, = ; = ; = ;

[0033] g) Based on the recalculation of the The coordinates of the detection point The least squares method is used to fit the surface to be detected, and the plane equation of the surface to be detected is determined. and normal vector = ;

[0034] h) Calculate the normal vector Angle with the theoretical perpendicular direction The included angle serves as a representation of the perpendicularity of the surface to be tested. The calculation method is as follows: = .

[0035] The present invention has the following beneficial effects:

[0036] Compared with existing technologies, this solution introduces pre-trained artificial neural network units, enabling the system to compensate in real time for the effects of environmental factors (such as temperature, humidity, and airflow speed) and wall characteristics (such as roughness and vibration) on the measurement results, thereby significantly improving the accuracy and reliability of the measurement.

[0037] Compared with existing technologies, this solution utilizes an edge computing module, enabling the system to process data quickly on-site, reducing data transmission and processing delays, and further improving measurement accuracy.

[0038] Compared with existing technologies, this solution significantly improves measurement efficiency by adopting automated measurement and real-time monitoring functions, reducing the complexity and time cost of manual operation.

[0039] Compared with existing technologies, this solution optimizes the number and distribution of laser beams, enabling the system to reduce unnecessary measurement points while ensuring measurement accuracy and further improving measurement speed.

[0040] Compared with existing technologies, this solution can operate stably in complex construction site environments, adapt to different environmental conditions and wall characteristics, and has strong environmental adaptability.

[0041] Compared with existing technologies, this solution significantly reduces the manpower and time costs required for measurement by optimizing the measurement process and reducing manual intervention. It can provide measurement results and verticality analysis in real time, helping construction personnel to adjust construction plans in a timely manner, ensuring construction quality and improving construction efficiency. Attached Figure Description

[0042] Figure 1 This is a schematic diagram of the vertical calibration detection system for building engineering according to the present invention.

[0043] Figure 2 This is a schematic diagram of the vertical calibration detection system for building engineering according to the present invention. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0045] Example 1

[0046] refer to Figure 1 The schematic diagram shown illustrates the implementation process of a vertical calibration detection system for building engineering according to the present invention, which includes the following steps:

[0047] a) Define a coordinate point as the origin;

[0048] It should be noted that, to ensure the accuracy and reliability of the measurement, the following constraints must be met:

[0049] The distance between the origin and the surface to be inspected should be within a reasonable range;

[0050] The distance between the origin and the surface to be inspected should meet the measurement accuracy requirements;

[0051] The distance between the origin and the surface to be inspected should take into account the influence of environmental factors, specifically:

[0052] The effects of temperature changes on laser wavelength and the thermal expansion and contraction of materials should be controlled within an acceptable range.

[0053] The impact of humidity changes on laser propagation characteristics should be controlled within an acceptable range.

[0054] The effect of airflow velocity on laser beam deflection should be controlled within an acceptable range.

[0055] Based on the above constraints, the distance between the origin and the surface to be detected can be determined to satisfy the following first constraint model:

[0056] ;

[0057] in, This is the first constraint condition; The distance between the origin and the surface to be detected; , These are the minimum and maximum effective distances of the laser emission module, respectively. This refers to the change in laser wavelength caused by temperature variations during the measurement process. The initial wavelength of the laser during the measurement process; This represents the maximum permissible error caused by temperature changes during the measurement process. This refers to the change in laser attenuation coefficient caused by humidity variations during the measurement process. The initial attenuation coefficient of the laser during the measurement process; This represents the maximum permissible error caused by humidity changes during the measurement process. The change in laser beam offset angle caused by changes in airflow velocity during the measurement process; This represents the initial laser beam offset angle during the measurement process. This represents the maximum permissible error caused by changes in airflow velocity.

[0058] b) Emit several laser beams from the origin toward the surface to be inspected, and obtain the coordinates of the detection points where each laser beam intersects with the surface to be inspected. and distance ,in, = , This refers to the number of the testing point;

[0059] It should be noted that, to ensure the accuracy and reliability of the measurement, the number of emitted laser beams also needs to meet certain constraints:

[0060] The number of emitted laser beams should be sufficient to reduce the impact of random and systematic errors, cover the key areas of the surface to be inspected, and provide enough data points for plane fitting and perpendicularity calculation. Specifically:

[0061] The number of emitted laser beams should at least meet the minimum data point requirement for plane fitting;

[0062] The emitted laser beam should uniformly cover the surface to be tested to ensure the representativeness of the measurement results;

[0063] To avoid excessive computational complexity that could affect the system's real-time performance and efficiency, and to ensure that operators can easily set up and adjust the measuring equipment, the number of emitted laser beams should be moderate.

[0064] Based on the above constraints, the number of laser beams emitted from the origin to the surface to be detected can be determined to satisfy the following second constraint model:

[0065] ;

[0066] in, This is the second constraint condition; The number of laser beams emitted; This represents the maximum number of laser beams under the system's maximum processing capacity. This is a characteristic correlation constant between the laser emitting module and the surface to be detected; To ensure the accuracy of the measurement target; The coverage density of the laser beam on the surface to be inspected; The area is the surface to be inspected.

[0067] c) Real-time acquisition of the first Interference factors during laser beam emission;

[0068] Specifically, interference factors include environmental parameters, surface roughness of the detection point, vibration parameters of the laser emission module, and laser beam emission angle. Among these, environmental parameters include temperature, humidity, and airflow velocity.

[0069] It should be noted that the influence mechanism of interference factors on measurement results is reflected in the following aspects:

[0070] 1) Temperature

[0071] Laser wavelength variation: Temperature changes affect the wavelength of the laser. Laser measurement equipment typically uses lasers of specific wavelengths; increases or decreases in temperature can cause slight changes in the laser wavelength, thus affecting measurement accuracy.

[0072] Material thermal expansion and contraction: The material of the surface being tested (such as concrete, steel, etc.) will expand and contract due to temperature changes. This physical change will cause the actual position of the measurement point to change, thus affecting the distance measurement result.

[0073] Thermal deformation of equipment: Laser measurement equipment itself can also undergo thermal deformation due to temperature changes, affecting its measurement accuracy and stability.

[0074] 2) Humidity

[0075] Laser propagation characteristics: Changes in humidity affect the propagation characteristics of lasers in the air. In high humidity environments, the number of water molecules in the air increases, causing the laser to be subject to more scattering and absorption during propagation, resulting in a weakened measurement signal and affecting measurement accuracy.

[0076] Equipment performance: High humidity may cause the optical and electronic components inside the laser measurement equipment to become damp, affecting their performance and stability.

[0077] 3) Airflow velocity

[0078] Laser beam deflection: Airflow velocity affects the propagation direction and stability of the laser beam. Strong airflow can cause the laser beam to deflect, affecting the accuracy of the measurement point.

[0079] Interference with measurement signals: Particles in the airflow (such as dust, water mist, etc.) can interfere with the laser signal, leading to increased measurement errors.

[0080] 4) The effect of roughness

[0081] Laser reflection characteristics

[0082] Reflected light intensity: The roughness of the detection surface affects the reflection characteristics of the laser. A rough surface causes changes in the intensity and direction of the reflected laser light, making the signal received by the receiver unstable and affecting the measurement accuracy.

[0083] Scattered light effect: Rough surfaces produce more scattered light, which can interfere with the measurement signal and lead to measurement errors.

[0084] Determinism of measurement points

[0085] Measurement point position deviation: Rough surfaces may cause the laser beam to reflect at an inconsistent position, resulting in a deviation in the measurement point position and affecting the distance calculation.

[0086] Repeatability issues: The irregularity of rough surfaces can lead to poor repeatability of measurement results. Even under the same measurement conditions, the results of multiple measurements may vary significantly.

[0087] 5) Overall Impact

[0088] The combined effects of environmental factors and the roughness of the detection surface can further complicate distance measurement results. For example:

[0089] The combined effect of temperature and humidity: Under high temperature and high humidity conditions, the combined effects of changes in laser wavelength and thermal expansion and contraction of materials can lead to greater measurement errors.

[0090] Synergistic effect of airflow and roughness: The combination of strong airflow and rough surface can cause laser beam deflection and unstable reflected signals, further increasing measurement errors.

[0091] d) Using the acquired interference factors as input to the pre-trained neural network units, and utilizing the output of the pre-trained neural network units according to the... Distance measured by laser beam error value ;

[0092] The training process for pre-trained neural network units includes the following steps:

[0093] 1) Collect historical measurement data and preprocess it:

[0094] Collect the coordinates of the measurement points and interference factors, including temperature. ,humidity airflow speed Surface roughness at the test point Vibration parameters of the laser emitting module (Taking vibration frequency as an example) and laser beam emission angle and the corresponding actual distance value ,in, Number the number of measurements; normalize the collected data to the range [0,1].

[0095] 2) Feature engineering:

[0096] Extract the polynomial and interaction features of interfering factors.

[0097] In one possible implementation, the extracted feature parameters may include the following types:

[0098] 2.1) Original features

[0099] Including: temperature ,humidity airflow speed Surface roughness at the test point Vibration frequency of the laser emitting module Laser beam emission angle and the The distance measured :

[0100] 2.2) Polynomial characteristics

[0101] To capture nonlinear relationships, polynomial features can be generated:

[0102] include:

[0103] Polynomial characteristics of temperature: , wait;

[0104] Polynomial characteristics of humidity: , wait;

[0105] Polynomial characteristics of airflow velocity: , wait;

[0106] Polynomial characteristics for detecting surface roughness: , wait;

[0107] Polynomial characteristics of vibration frequency: , wait;

[0108] Polynomial characteristics of laser beam emission angle: , wait;

[0109] 2.3) Interaction Features

[0110] To capture the interactions between different features, interactive features can be generated:

[0111] include:

[0112] The interaction between temperature and humidity: ;

[0113] The interaction between temperature and airflow velocity: ;

[0114] The interaction between temperature and roughness: ;

[0115] The interaction between temperature and vibration frequency: ;

[0116] The interaction between temperature and laser beam emission angle: ;

[0117] The interaction between humidity and airflow velocity: ;

[0118] The interaction between humidity and roughness: ;

[0119] The interaction between humidity and vibration frequency: ;

[0120] The interaction between humidity and laser beam emission angle: ;

[0121] The interaction between airflow velocity and roughness: ;

[0122] The interaction between airflow velocity and vibration frequency: ;

[0123] The interaction between airflow velocity and laser beam emission angle: ;

[0124] The interaction between roughness and vibration frequency: ;

[0125] The interaction between surface roughness and laser beam emission angle: ;

[0126] The interaction between vibration frequency and laser beam emission angle: ;

[0127] 2.4) Combination characteristics

[0128] Multiple features can be combined to generate more complex features:

[0129] Combination of temperature, humidity, and airflow speed: ;

[0130] Combination of temperature, humidity, and roughness: ;

[0131] Combination of temperature, humidity, and vibration frequency: ;

[0132] Combination of temperature, humidity, and laser beam emission angle: ;

[0133] And other similar ternary or multi-element combinations.

[0134] It should be further explained that after constructing a large number of features, it is necessary to select features that significantly contribute to the model performance. Collectively, this can be done using common feature selection algorithms, including feature selection based on statistical tests, feature selection based on models, feature selection based on iterations, or feature selection based on embedded methods, which will not be elaborated on here.

[0135] 3) Model building:

[0136] Choose an appropriate artificial intelligence model, such as a neural network, SVR, or random forest.

[0137] In one possible implementation, a neural network can be chosen as the artificial intelligence model, as follows:

[0138] = - = ;

[0139] in, For the first Error of the measurement; For the first The actual distance measured in this instance; It is a neural network model; The input data for the neural network is the feature dataset constructed by feature engineering; These are the parameters of the neural network model.

[0140] 4) Training the model:

[0141] The model is trained using the collected data to minimize the difference between the prediction error and the actual error. Commonly used loss functions include mean squared error (MSE) and root mean square error (RMSE).

[0142] e) Utilizing error values Distance Perform compensation and obtain the compensated measurement distance. ,in, = - ;

[0143] f) Using the compensated measurement distance Recalculate the first Coordinates of the detection point ,in, = ; = ; = ;

[0144] g) Based on the recalculation of the Coordinates of the detection point The least squares method is used to fit the surface to be detected, and the plane equation of the surface to be detected is determined. and normal vector = ;

[0145] The specific process includes the following steps:

[0146] g-1) Define matrix sum vector

[0147] matrix Each row corresponds to the coordinates of the compensated detection point and constant term 1:

[0148] = ;

[0149] = ;

[0150] in, The number of detection points;

[0151] g-2) Define parameter vector

[0152] = ;

[0153] g-3) Solving for the parameter vector using the least squares method The calculation method is as follows: = Because of vector Since it is a zero vector, the above equation can be simplified to: =0; the simplified calculation formula is a homogeneous linear system of equations, whose nontrivial solutions can be obtained by solving for eigenvalues ​​and eigenvectors. Specifically, we need to find the matrix The eigenvector corresponding to the smallest eigenvalue is used as the parameter vector. This allows us to solve for the parameters of the plane equation of the surface to be inspected. , , , ;

[0154] g-3) from the solved parameter vector Extract the normal vector of the surface to be detected. = .

[0155] h) Calculate the normal vector Angle with the theoretical perpendicular direction The included angle serves as a characterization of the perpendicularity of the surface to be inspected. The calculation method is as follows: = .

[0156] Example 2

[0157] See Figure 2 The schematic diagram shown below illustrates a vertical calibration detection system for building engineering according to the present invention, comprising:

[0158] The calibration module is used to calibrate a coordinate point as the origin;

[0159] The laser emitting module is used to emit several laser beams from the origin toward the surface to be inspected;

[0160] The ranging module is used to measure the distance between each detection point on the surface to be tested and the origin using a laser beam;

[0161] The data acquisition module is used to collect interference factors during laser beam emission, including environmental parameters, surface roughness of the detection point, vibration parameters of the laser emission module, and laser beam emission angle.

[0162] The edge computing module includes pre-trained neural network units for error compensation of the measured distance based on interference factors;

[0163] The verticality calculation module is used to determine the verticality of the surface to be inspected based on the measured distance after error compensation.

[0164] The edge computing module also includes a feature engineering unit for extracting polynomial features and interaction features from interference factors.

[0165] The edge computing module also includes a model training unit, which is used to train neural network units using polynomial features and interaction features extracted by the feature engineering unit.

[0166] The edge computing module also includes an error prediction unit, which uses a pre-trained neural network unit to predict the measurement error of the measured distance and compensate for the measured distance based on the measurement error.

[0167] The verticality calculation module includes a plane fitting unit, which uses the least squares method to fit the plane equation of the surface to be tested based on the measured distance after error compensation, and calculates the normal vector of the surface to be tested.

[0168] The perpendicularity calculation module also includes an angle calculation unit, which is used to calculate the angle between the normal vector of the surface to be inspected and the theoretical vertical direction, so as to determine the perpendicularity of the surface to be inspected.

[0169] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A vertical calibration detection system for building engineering, characterized in that, include: The calibration module is used to calibrate a coordinate point as the origin; The laser emitting module is used to emit several laser beams from the origin toward the surface to be detected; The ranging module is used to measure the distance between each detection point on the surface to be detected and the origin using the laser beam; The data acquisition module is used to collect interference factors during the laser beam emission, including environmental parameters, surface roughness of the detection point, vibration parameters of the laser emission module, and laser beam emission angle. An edge computing module includes pre-trained neural network units for error compensation of the measured distance based on the interference factors; The verticality calculation module is used to determine the verticality of the surface to be tested based on the measured distance after error compensation.

2. The vertical calibration detection system for building engineering according to claim 1, characterized in that, The distance between the origin and the surface to be detected satisfies the following first constraint model: ； in, This is the first constraint condition; The distance between the origin and the surface to be detected; , These are the minimum and maximum effective distances of the laser emission module, respectively. This refers to the change in laser wavelength caused by temperature variations during the measurement process. The initial wavelength of the laser during the measurement process; This represents the maximum permissible error caused by temperature changes during the measurement process. This refers to the change in laser attenuation coefficient caused by humidity variations during the measurement process. The initial attenuation coefficient of the laser during the measurement process; This represents the maximum permissible error caused by humidity changes during the measurement process. The change in laser beam offset angle caused by changes in airflow velocity during the measurement process; This represents the initial laser beam offset angle during the measurement process. This represents the maximum permissible error caused by changes in airflow velocity.

3. The vertical calibration detection system for building engineering according to claim 1, characterized in that, The number of laser beams emitted from the origin toward the surface to be detected satisfies the following second constraint model: ； in, This is the second constraint condition; The number of laser beams emitted; This represents the maximum number of laser beams under the system's maximum processing capacity. This is a characteristic correlation constant between the laser emitting module and the surface to be detected; To ensure the accuracy of the measurement target; The coverage density of the laser beam on the surface to be inspected; The area is the surface to be inspected.

4. The vertical calibration detection system for building engineering according to claim 1, characterized in that, The environmental parameters include one or more of temperature, humidity, and airflow velocity.

5. A vertical calibration detection system for building engineering according to claim 1, characterized in that, The edge computing module also includes a feature engineering unit for extracting polynomial features and interaction features from the interference factors.

6. A vertical calibration detection system for building engineering according to claim 5, characterized in that, The edge computing module also includes a model training unit, which is used to train a neural network unit using the polynomial features and interaction features extracted by the feature engineering unit.

7. A vertical calibration detection system for building engineering according to claim 6, characterized in that, The edge computing module further includes an error prediction unit, which is used to predict the measurement error of the measured distance using the pre-trained neural network unit, and to compensate the measured distance based on the measurement error.

8. A vertical calibration detection system for building engineering according to claim 1, characterized in that, The verticality calculation module includes a plane fitting unit, which is used to fit the plane equation of the surface to be detected using the least squares method based on the measured distance after error compensation, and to calculate the normal vector of the surface to be detected.

9. A vertical calibration detection system for building engineering according to claim 8, characterized in that, The perpendicularity calculation module also includes an angle calculation unit, which is used to calculate the angle between the normal vector of the surface to be tested and the theoretical vertical direction, so as to determine the perpendicularity of the surface to be tested.

10. A verticality calibration detection system for building engineering according to any one of claims 1-9, characterized in that, The implementation process of the system includes the following steps: a) Define a coordinate point as the origin; b) Emit several laser beams from the origin toward the surface to be tested, and obtain the coordinates of the detection points where each laser beam intersects with the surface to be tested. and distance ,in, = , This refers to the number of the testing point; c) Real-time acquisition of the first Interference factors during laser beam emission; d) Using the obtained interference factors as input to the pre-trained neural network unit, and utilizing the output of the pre-trained neural network unit according to the... The laser beam measurement distance error value ; e) Utilizing the error value Distance Perform compensation and obtain the compensated measurement distance. ,in, = - ; f) Using the compensated measurement distance Recalculate the first The coordinates of the detection point ,in, = ; = ; = ; g) Based on the recalculation of the The coordinates of the detection point The least squares method is used to fit the surface to be detected, and the plane equation of the surface to be detected is determined. and normal vector = ; h) Calculate the normal vector Angle with the theoretical perpendicular direction The included angle serves as a representation of the perpendicularity of the surface to be tested. The calculation method is as follows: = .

Images