Cable-stayed bridge cable tower digital monitoring method and related equipment

Abstract

The invention discloses a cable-stayed bridge cable bent tower digital monitoring method and related equipment, and relates to the technical field of bridge monitoring, the method comprises the following steps: obtaining initial data, the initial data comprising cable bent tower environment data and three-dimensional form information; positioning a skeleton position based on the magnetic coding data and the three-dimensional form information; adjusting a template posture based on the skeleton position so as to enable the template posture to be matched with the skeleton position, and obtaining correction data in the adjustment process; the pouring process is monitored based on an intelligent hydraulic control system, and dynamic data are obtained; analyzing feature points of the concrete surface image based on the concrete surface image, calculating a deviation error, and determining deviation data; multi-source data are integrated to monitor the cable bent tower structure, the health state of the cable bent tower structure is predicted, and the multi-source data comprise the initial data, the correction data, the dynamic data and the deviation data.

Description

Technical Field

[0001] The present application relates to the technical field of bridge monitoring, and in particular to a digital monitoring method for cable-stayed bridge towers and related equipment. Background Art

[0002] Existing cable-stayed bridge tower monitoring technology usually relies on manual regular inspections and local sensor monitoring. This traditional method has problems such as limited monitoring range, incomplete data collection, and poor real-time performance, and cannot provide a comprehensive and accurate assessment of the overall structural health of the tower.

[0003] In addition, due to the limitations of monitoring technology, existing monitoring methods are unable to provide dynamic monitoring of the cable tower during the pouring and construction process, which may result in potential structural deviations that cannot be corrected in a timely manner.

[0004] With the increasing requirements for structural safety in modern bridge engineering, there is an urgent need for a digital monitoring method that can monitor the health status of cable-stayed bridge towers in real time and comprehensively. Summary of the invention

[0005] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Description of the Invention section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0006] In a first aspect, the present application provides a digital monitoring method for a cable-stayed bridge tower, comprising:

[0007] Acquiring initial data, wherein the initial data includes tower environment data and three-dimensional morphology information;

[0008] Locating the skeleton based on the magnetically encoded data and the three-dimensional morphological information;

[0009] Adjusting the template posture based on the skeleton position so that the template posture matches the skeleton position, and obtaining correction data during the adjustment process;

[0010] Monitor the pouring process based on the intelligent hydraulic control system to obtain dynamic data;

[0011] Based on the concrete surface image, analyzing the characteristic points of the concrete surface image, calculating the deviation error, and determining the deviation data;

[0012] Integrate multi-source data to monitor the tower structure and predict the health status of the tower structure, wherein the multi-source data includes the initial data, the correction data, the dynamic data and the displacement data.

[0013] In a feasible implementation manner, the tower environmental data includes a sensor data matrix containing a time series, and the sensor data matrix includes temperature data, humidity data, stress data and vibration data;

[0014] The three-dimensional morphological information is point cloud data converted from a three-dimensional coordinate set, and the three-dimensional coordinate set is a set of three-dimensional coordinates of tower nodes obtained by scanning the tower with a laser radar.

[0015] In a feasible implementation, it also includes:

[0016] Determine the magnetic encoding data according to the coordinate information collected by the magnetic encoder;

[0017] The above skeleton positions are calculated based on the spatial positions and weights of the encoded points.

[0018] In a feasible implementation manner, adjusting the template posture based on the skeleton position so that the template posture matches the skeleton position includes:

[0019] Determining a target pose adjustment amount based on minimizing an error between a template position and the skeleton position;

[0020] Based on the above target posture adjustment amount, a posture adjustment signal is formed using a deep learning model optimization algorithm;

[0021] Based on the posture adjustment signal, the adjustment process of the template posture is controlled to make the template posture match the skeleton position.

[0022] In a feasible implementation, it also includes:

[0023] The above-mentioned intelligent hydraulic control system includes a hydraulic pump, a hydraulic cylinder, and a control system;

[0024] The control system monitors the working status of the hydraulic pump and the hydraulic cylinder and dynamically adjusts the working parameters of the hydraulic pump based on a PID control algorithm.

[0025] In a feasible implementation manner, the above-mentioned method of analyzing the feature points of the concrete surface image based on the concrete surface image and calculating the deviation error includes:

[0026] Performing preprocessing operations of denoising and illumination correction on the concrete surface image;

[0027] A convolutional neural network is used to extract feature points of the above concrete surface image;

[0028] The above feature points are compared with the preset positions of the template to calculate the above deviation errors.

[0029] In a feasible implementation, the above-mentioned integrated multi-source data monitoring of the cable tower structure and prediction of the health status of the cable tower structure include:

[0030] Based on the above multi-source data, the tilt state and damage degree of the tower column are evaluated based on big data analysis technology;

[0031] The multi-source data, the tilt state and the damage degree are input into a prediction model of time series analysis to obtain the health state of the tower structure.

[0032] In the second aspect, the present application proposes a digital monitoring device for a cable-stayed bridge tower, comprising:

[0033] An acquisition unit, used for acquiring initial data, wherein the initial data includes tower environment data and three-dimensional morphology information;

[0034] A positioning unit, used for positioning the skeleton based on the magnetic encoding data and the above three-dimensional morphological information;

[0035] A matching unit, used for adjusting the template posture based on the skeleton position so that the template posture matches the skeleton position, and obtaining correction data during the adjustment process;

[0036] A monitoring unit is used to monitor the pouring process based on an intelligent hydraulic control system and obtain dynamic data;

[0037] The recognition unit is used to analyze the characteristic points of the concrete surface image based on the concrete surface image, calculate the deviation error, and determine the deviation data;

[0038] A prediction unit is used to integrate multi-source data to monitor the tower structure and predict the health status of the tower structure, wherein the multi-source data includes the initial data, the correction data, the dynamic data and the offset data.

[0039] In a third aspect, an electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to implement the steps of the digital monitoring method for cable-stayed bridge towers as described in any one of the first aspects above when executing the computer program stored in the memory.

[0040] In a fourth aspect, the present application further proposes a computer-readable storage medium having a computer program stored thereon, characterized in that when the above-mentioned computer program is executed by a processor, the digital monitoring method for cable-stayed bridge towers of any one of the first aspects is implemented.

[0041] In summary, the embodiment of the present application can obtain the three-dimensional shape, skeleton position, template posture and environmental data (such as temperature, humidity, stress and vibration data) of the cable tower during the pouring process through the combination of laser radar scanning, magnetic encoder and multi-type environmental sensors. This multi-source data acquisition method enables the monitoring system to fully understand the structural state and construction progress of the cable tower from multiple dimensions, providing a more detailed data basis than a single sensor system. The present application adopts the technology of combining magnetic encoder and laser radar, which can determine the position of the cable tower skeleton with high precision, and automatically optimize the template posture using deep learning model and reinforcement learning algorithm. This intelligent correction method can ensure the precise matching of the template and the skeleton by minimizing the error between the template and the skeleton, thereby improving the accuracy of concrete pouring and avoiding structural problems caused by template misalignment. During the concrete pouring process, an intelligent hydraulic control system is used to monitor and adjust the template position in real time. Based on the PID control algorithm, the system can dynamically adjust the working parameters of the hydraulic pump to ensure that the template is always kept in the best position during the pouring process. This not only improves the pouring accuracy, but also avoids structural deviations caused by changes in the template position during construction. After the concrete is poured, the high-precision camera carried by the drone is used to obtain the concrete surface image, and the feature points of the concrete surface are analyzed through the convolutional neural network (CNN) to detect the surface deviation after the pouring. The present application can compare the deviation between the actual surface and the preset template in real time to ensure the pouring quality, and realize remote analysis and storage of data through cloud data processing. By integrating multi-source data (initial data, correction data, dynamic data and deviation data) during the construction process, the present application can use big data analysis technology to evaluate the overall health status of the cable tower, including the inclination angle and degree of damage of the tower column. At the same time, the long-term structural health status of the cable tower is predicted through the time series analysis model, which helps to discover potential structural problems in advance and perform preventive maintenance. The intelligent system of the present application can automatically monitor and adjust the pouring process, reducing the error of manual operation. All data are uploaded to the cloud in real time through wireless transmission, and construction personnel can view the health status and construction progress of the cable tower in real time through the remote monitoring platform, which significantly improves construction efficiency and safety.

[0042] The digital monitoring method for cable-stayed bridge towers proposed by the present invention, other advantages, objectives and features of the present invention will be partially reflected in the following description, and will also be understood by technicians in this field through research and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0044] Figure 1 A schematic flow chart of a digital monitoring method for a cable-stayed bridge tower provided in an embodiment of the present application;

[0045] Figure 2 A schematic structural diagram of a digital monitoring device for a cable-stayed bridge tower provided in an embodiment of the present application;

[0046] Figure 3 A schematic diagram of the structure of a digital monitoring electronic device for a cable-stayed bridge tower provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0048] See also Figure 1 , which is a flow chart of a digital monitoring method for a cable-stayed bridge tower provided in an embodiment of the present application, which may specifically include:

[0049] S110, obtaining initial data, wherein the initial data includes tower environment data and three-dimensional morphology information;

[0050] For example, during the construction or monitoring of the cable tower of a cable-stayed bridge, initial data must be obtained first. These initial data include the environmental data and three-dimensional morphological information of the cable tower, among which the environmental data collects environmental parameters in real time through sensors deployed at various key parts of the cable tower. Environmental data usually include temperature, humidity, stress, vibration, etc., all of which are collected in time series. These data not only reflect the external environmental conditions of the cable tower, but also help analyze the stress changes and responses of the structure under different conditions. The three-dimensional morphological information uses laser radar scanning technology to collect the geometric information of the cable tower by emitting a laser beam and receiving the reflected signal. The scanning results are presented in the form of a point cloud, that is, a set of three-dimensional coordinates of the cable tower structure. These three-dimensional point cloud data provide the precise geometry of the cable tower and provide a basis for the calculation of the skeleton position and the adjustment of the template posture in subsequent steps.

[0051] S120, locating the skeleton position based on the magnetic encoding data and the above three-dimensional morphological information;

[0052] Exemplarily, the spatial position of the skeleton inside the cable tower is accurately located using the three-dimensional morphological information obtained from the magnetic encoder and the laser radar. The magnetic encoder is installed at the key nodes of the cable tower skeleton to detect the precise position of these nodes. The magnetic encoder can generate coordinate information by monitoring the changes in the magnetic field to indicate the spatial position of each node of the skeleton. The point cloud data generated by the laser radar can provide a reference for the overall three-dimensional morphology of the skeleton. Combined with the coded point data collected by the magnetic encoder, the center position of the skeleton and its spatial posture can be located through weighted averaging or other calculation models. Accurate positioning of the skeleton is crucial for subsequent template correction.

[0053] S130, adjusting the template posture based on the skeleton position so that the template posture matches the skeleton position, and obtaining correction data during the adjustment process;

[0054] Exemplarily, the template is a temporary frame used to define the shape of concrete pouring, which must be precisely aligned with the skeleton to ensure the accuracy of the pouring process. In this step, the posture of the template is adjusted to match the positioned skeleton position, and correction data is obtained in the process. The position and angle of the template must be finely adjusted to keep it consistent with the position of the skeleton. Using a deep learning algorithm and a posture optimization model, the posture of the template is continuously adjusted according to the initial error between the skeleton and the template until the minimum error is achieved. This process relies on the precise position data provided by the previous magnetic encoder and lidar. During the posture adjustment process, the position information of the template and the error after each adjustment are recorded in real time. These data are stored as correction data for use in subsequent steps.

[0055] S140, monitoring the pouring process based on the intelligent hydraulic control system to obtain dynamic data;

[0056] During the concrete pouring process, the system uses an intelligent hydraulic control system to dynamically monitor the posture of the template to ensure that the template remains stable throughout the process. The hydraulic system consists of a hydraulic pump, a hydraulic cylinder, and a control system. By monitoring the deviation between the actual position of the template and the expected position, the hydraulic system can adjust the working parameters of the hydraulic pump (such as pressure, flow, etc.) in real time to maintain the stability of the template. The system relies on the PID (proportional, integral, differential) control algorithm for adjustment. By comparing the deviation between the actual position of the template and the target position, the operation of the hydraulic cylinder is continuously adjusted to ensure that the template position is consistent with the predetermined target. The dynamic monitoring data records every adjustment during the pouring process, forming a real-time dynamic data set.

[0057] S150, based on the concrete surface image, analyzing the characteristic points of the concrete surface image, calculating the deviation error, and determining the deviation data;

[0058] Exemplarily, after the concrete pouring is completed, the concrete surface is analyzed by image processing technology to detect whether there are pouring errors. Use drones or other high-precision camera equipment to obtain images of the concrete surface after pouring. In order to improve the image quality, the image needs to undergo preprocessing steps such as denoising and lighting correction before entering the deep learning model to ensure the clarity of the feature points. Feature points are extracted from the concrete surface image using a convolutional neural network (CNN). CNN can automatically identify key points on the concrete surface, such as edges, cracks, or uneven areas. The actual feature points in the image are compared with the preset positions of the template to calculate the deviation errors generated during the concrete pouring process. The error data can be used to evaluate the construction quality and provide a reference for subsequent adjustments.

[0059] S160. Integrate multi-source data to monitor the tower structure and predict the health status of the tower structure, wherein the multi-source data includes initial data, correction data, dynamic data and offset data.

[0060] Exemplarily, this step integrates all the data generated in the previous steps, and analyzes and predicts the health status of the cable tower based on these multi-source data. Through big data analysis technology, these data from different sources are integrated to form a comprehensive structural status monitoring system. The integrated data not only reflects the current geometry and construction status of the cable tower, but also contains information on possible deviations during the pouring process. Based on the integrated data, the use of big data analysis and time series prediction models can enable long-term monitoring and prediction of the health status of the cable tower. The model can evaluate the inclination degree, stress concentration areas and potential damage locations of the cable tower structure, help predict possible structural problems in the future, and thus provide data support for maintenance and repair.

[0061] In summary, the embodiment of the present application can obtain the three-dimensional shape, skeleton position, template posture and environmental data (such as temperature, humidity, stress and vibration data) of the cable tower during the pouring process through the combination of laser radar scanning, magnetic encoder and multi-type environmental sensors. This multi-source data acquisition method enables the monitoring system to fully understand the structural state and construction progress of the cable tower from multiple dimensions, providing a more detailed data basis than a single sensor system. The present application adopts the technology of combining magnetic encoder and laser radar, which can determine the position of the cable tower skeleton with high precision, and automatically optimize the template posture using deep learning model and reinforcement learning algorithm. This intelligent correction method can ensure the precise matching of the template and the skeleton by minimizing the error between the template and the skeleton, thereby improving the accuracy of concrete pouring and avoiding structural problems caused by template misalignment. During the concrete pouring process, an intelligent hydraulic control system is used to monitor and adjust the template position in real time. Based on the PID control algorithm, the system can dynamically adjust the working parameters of the hydraulic pump to ensure that the template is always kept in the best position during the pouring process. This not only improves the pouring accuracy, but also avoids structural deviations caused by changes in the template position during construction. After the concrete is poured, the high-precision camera carried by the drone is used to obtain the concrete surface image, and the feature points of the concrete surface are analyzed through the convolutional neural network (CNN) to detect the surface deviation after the pouring. The present application can compare the deviation between the actual surface and the preset template in real time to ensure the pouring quality, and realize remote analysis and storage of data through cloud data processing. By integrating multi-source data (initial data, correction data, dynamic data and deviation data) during the construction process, the present application can use big data analysis technology to evaluate the overall health status of the cable tower, including the inclination angle and degree of damage of the tower column. At the same time, the long-term structural health status of the cable tower is predicted through the time series analysis model, which helps to discover potential structural problems in advance and perform preventive maintenance. The intelligent system of the present application can automatically monitor and adjust the pouring process, reducing the error of manual operation. All data are uploaded to the cloud in real time through wireless transmission, and construction personnel can view the health status and construction progress of the cable tower in real time through the remote monitoring platform, which significantly improves construction efficiency and safety.

[0062] In some examples, the tower environmental data includes a sensor data matrix containing a time series, and the sensor data matrix includes temperature data, humidity data, stress data, and vibration data;

[0063] The three-dimensional morphological information is point cloud data converted from a three-dimensional coordinate set, and the three-dimensional coordinate set is a set of three-dimensional coordinates of tower nodes obtained by scanning the tower with a laser radar.

[0064] For example, the laser radar obtains the three-dimensional coordinate information of the key nodes of the tower by emitting a laser beam and detecting its reflected signal, and represents each node of the tower as a set of discrete point cloud data, and the three-dimensional coordinate of each point is represented as T i，j，k (x, y, z), i, j, k are the indexes of the tower nodes, and (x, y, z) are the coordinates of the node in three-dimensional space.

[0065] The distance of each beam of light emitted by the lidar is calculated using the time-of-flight principle, and the distances of multiple reflection points are sampled to obtain a three-dimensional point cloud data set for the entire tower. In order to more accurately reconstruct the three-dimensional shape of the tower, the lidar will repeatedly scan multiple angles and use the iterative closest point algorithm (ICP) for multiple alignments to ultimately obtain an accurate three-dimensional shape.

[0066] Multiple sensors are deployed at different locations on the tower to monitor different environmental parameters. The data matrix generated by the sensors can be expressed as:

[0067] S(t)=[T t ,H t ,E t ,V t ]

[0068] Among them, T t is the temperature data at time t; H t is humidity data; E t is stress data; V t is the vibration data; t is the time parameter.

[0069] The data collected by the sensor is considered as a function of time. These data are continuously updated as time changes, so each set of data can be regarded as a multidimensional data set of time series. All sensor data and the three-dimensional morphological data generated by the lidar are uploaded to the cloud in real time via wireless network to form a preliminary data set. The data set is represented as:

[0070] D1={S(t),T i，j，k (x,y,z)}

[0071] The set includes the sensor environment data matrix S(t) and the three-dimensional space coordinate point set T i，j，k (x, y, z) is a multidimensional dataset consisting of sensor data and 3D morphological data, which contains the geometric shape and structural health information of the tower. This dataset is the core input in subsequent steps for tasks such as template correction and hydraulic system control.

[0072] In some examples, this also includes:

[0073] Determine the magnetic encoding data according to the coordinate information collected by the magnetic encoder;

[0074] The above skeleton positions are calculated based on the spatial positions and weights of the encoded points.

[0075] For example, a magnetic encoder is a sensor that can detect changes in magnetic field strength and convert them into electrical signal outputs. The magnetic encoder is installed at key positions of the rigid skeleton (such as template interfaces, important nodes, etc.). The magnetic encoder is installed at key positions of the rigid skeleton to collect coordinate information of multiple points on the skeleton.

[0076] "Skeleton" usually refers to the internal structure that supports the bridge structure. During the construction of cable-stayed bridge towers, the skeleton generally refers to the structural frame or rigid skeleton used to support and fix the towers. These skeletons are responsible for bearing the loads during the construction process and during the use of the bridge, and ensuring that the shape and stiffness of the entire tower meet the design requirements. The spatial coordinate data of the skeleton is obtained through magnetic encoders and lidar, and it is accurately positioned to ensure that it is consistent with the designed position. "Formwork" is a temporary structure used to define the shape of concrete during concrete pouring. The formwork is an external frame that is installed around the skeleton to ensure that the concrete can solidify according to the predetermined shape and size when pouring. The installation posture of the formwork must be accurate to ensure that the shape of the structure after the concrete is poured is consistent with the design drawings. The precise positioning of the skeleton is used to ensure the stability of the structure, while the correction of the formwork ensures the accuracy of the concrete pouring. The two work closely together during construction.

[0077] The core purpose of the skeleton positioning part is to combine the three-dimensional shape data of the laser radar with the magnetic encoder. i，j，k (x, y, z ) , to accurately locate the frame of the tower. The coordinate points collected by the magnetic encoder are discrete, represented by P n (x n ,y n , z n ), where n is the number of the code point. In order to locate the rigid skeleton, the weight coefficient α n The weighted average of these discrete points is used to obtain the skeleton positioning model, which is expressed as:

[0078]

[0079] Among them, M(x, y, z) is the center position of the skeleton; α n is the weight coefficient for each code point; N is the total number of code points; P n (x n ,y n , z n ) is the position of the nth code point.

[0080] Weight coefficient α nThe data accuracy of each point measured by the magnetic encoder may be different, so different weight coefficients α are used. n To characterize the contribution of each code point to skeleton positioning, the weight coefficient satisfies the following conditions:

[0081]

[0082] Through the above conditions, it is ensured that the final skeleton position M(x, y, z) is the weighted average of all encoding points, and the spatial position P of each encoding point is n (x n ,y n , z n ) and weight α n , the skeleton position M(x, y, z) can be accurately calculated.

[0083] In some examples, adjusting the template pose based on the skeleton position so that the template pose matches the skeleton position includes:

[0084] Determining a target pose adjustment amount based on minimizing an error between a template position and the skeleton position;

[0085] Using a deep learning model optimization algorithm to form a posture adjustment signal based on the target posture adjustment amount;

[0086] Based on the posture adjustment signal, the adjustment process of the template posture is controlled to make the template posture match the skeleton position.

[0087] Exemplarily, the direction and magnitude of adjustment required are determined by calculating the error between the current position of the template and the target position of the skeleton. This error is obtained by comparing the actual position of the template in three-dimensional space with the designed position of the skeleton. By minimizing this error, the adjustment direction and size of the template posture, that is, the target posture adjustment amount, are obtained. A deep learning optimization algorithm is used to process the target posture adjustment amount calculated in the previous step. The deep learning model generates a posture adjustment signal based on the current posture of the template and the theoretical position of the skeleton. This signal guides the control system on how to adjust the posture of the template to reduce the error. Based on the adjustment signal generated in the previous step, the control system fine-tunes and optimizes the posture of the template according to this signal. This process is a dynamic feedback control. The system will continuously detect the position of the template and further optimize it according to the feedback signal until the template posture accurately matches the skeleton position.

[0088] Exemplarily, the posture correction of the template is achieved by minimizing the error between the template position and the skeleton positioning, and the deviation between the template posture and the skeleton position is described by the following objective function:

[0089]

[0090] Among them, A opt is the optimal posture matrix of the template; P n is the position of the code point; M n (A) is the theoretical position of the skeleton in posture A; N is the number of encoding points; ||·|| is the Euclidean distance.

[0091] The template posture matrix A describes the rotation and translation of the template in space. By adjusting A, the position of the template and the rigid skeleton are kept consistent. The optimal template installation posture is found by minimizing the error between the actual position of the template and the theoretical position of the skeleton. This process is achieved through a deep learning model. The model will continuously select and adjust the template posture until it reaches the optimal one, including:

[0092] The input of the deep learning model is the current posture of the template and the theoretical position of the skeleton, and the output is a new posture adjustment signal. By calculating the error each time and feeding it back to the model, the model will learn how to adjust the position of the template more accurately to reduce the error through continuous training.

[0093] Input the current template pose A and the theoretical skeleton position M (x, y, z) and the encoding point P n (x n ,y n , z n ).

[0094] The output deep learning model predicts a new posture adjustment vector ΔA, which is the next posture adjustment operation recommended by the model.

[0095] Error calculation, the error is the distance difference between the current position of the template and the theoretical position of the skeleton, expressed as:

[0096]

[0097] The goal of the deep learning model is to continuously reduce the error E(A) by adjusting the posture.

[0098] First, a training data set is prepared, which includes different template postures A and their corresponding error values; a training data set is formed through a large number of different posture adjustments and error feedback after each adjustment.

[0099] Deep learning models usually use multi-layer neural networks (for example, convolutional neural networks or fully connected networks) to process these inputs and outputs. The architecture of the model can be understood as follows: the input layer receives the posture A and skeleton position M (x, y, z) of the current template; the hidden layer learns how to adjust the suggestion based on the input posture through several layers of nonlinear activation functions; the output layer outputs the new posture adjustment vector ΔA.

[0100] In the training phase, a large amount of input data is provided, namely different template poses and their corresponding error values. The model continuously adjusts the weights and parameters of the network through the back-propagation algorithm, so that the predicted pose adjustment ΔA can better reduce the error between the template and the skeleton.

[0101] In practical applications, the trained deep learning model will input the current template pose A and skeleton position M (x, y, z) in each iteration, and then output a new pose adjustment ΔA. The system will update the template pose based on this adjustment and then calculate the error again; this process will continue to iterate until the error converges to the minimum value, and the optimal template pose A is obtained. opt .

[0102] During the template correction process, a reinforcement learning algorithm is used to optimize the installation posture of the template. Reinforcement learning continuously adjusts the strategy by interacting with the environment and calculating immediate rewards at each step.

[0103] The objective function L(θ) of reinforcement learning is expressed as:

[0104]

[0105] Among them, s is the current state (the position and posture of the template); a is the current action (adjusting the posture of the template); r t is the immediate reward (indicating the change in error after each posture adjustment); γ is the discount factor, which is used to indicate the importance of future rewards; Q(s, a; θ) is the state-action value function, which indicates the expected return of selecting an action in the current state.

[0106] The reinforcement learning process is:

[0107] State s, at each step, the system decides whether to adjust the pose based on the current template pose and skeleton position.

[0108] For action a, the system can choose to rotate or translate the template to adjust its pose.

[0109] Reward t After each adjustment, the system calculates the error between the template and the skeleton. If the error decreases, the system will receive a positive reward, otherwise it will receive a negative reward.

[0110] Strategy update,By continuously adjusting the posture, the system will find the optimal installation posture until the objective function L(θ) converges.

[0111] After completing skeleton positioning and template correction, the data will be uploaded to the cloud to form a new data set D2, which contains the skeleton position M (x, y, z) and the optimal posture matrix A of the template. opt, and combined with the data set D1 in step S110, it is expressed as:

[0112] D2={M(x,y,z),A opt , D1}

[0113] Based on the magnetic encoder and LiDAR point cloud data, the weighted average method is used to determine the position of the rigid skeleton. Through deep learning and reinforcement learning algorithms, the template posture is adjusted to minimize the deviation from the skeleton, and finally the optimal template installation posture matrix is ​​obtained. Aopt Dataset D2 It contains all the data for skeleton positioning and template correction, providing an important basis for subsequent steps.

[0114] In some examples, this also includes:

[0115] The above-mentioned intelligent hydraulic control system includes a hydraulic pump, a hydraulic cylinder, and a control system;

[0116] The control system monitors the working status of the hydraulic pump and the hydraulic cylinder and dynamically adjusts the working parameters of the hydraulic pump based on a PID control algorithm.

[0117] For example, hydraulic pumps and hydraulic cylinders are core components in a hydraulic control system. During the construction of cable-stayed bridge towers, the specific applications of hydraulic pumps and hydraulic cylinders are:

[0118] When the hydraulic pump is working, it generates high-pressure oil, which is transported to the hydraulic cylinder through the pipeline. The piston rod in the hydraulic cylinder extends under the action of the high-pressure oil, pushing the template up. When the template reaches the predetermined position, the control system detects the position change through the displacement sensor, adjusts the output of the hydraulic pump, and stops the action of the hydraulic cylinder. The control system instructs the hydraulic pump to work in the reverse direction, and the piston rod in the hydraulic cylinder contracts during the oil return process, and the template descends. After descending to the next pouring section, the template is fixed again and concrete is poured.

[0119] The hydraulic pump is usually installed in the hydraulic pump station at the construction site, which is the power center of the hydraulic system. The hydraulic pump delivers pressurized liquid to the hydraulic cylinder through a pipeline. The hydraulic cylinder is usually installed near the template or frame and is responsible for controlling the position and displacement of the template and frame. The piston of the hydraulic cylinder pushes the template or frame to the predetermined position according to the pressure provided by the hydraulic pump.

[0120] Based on the skeleton and template correction data of the previous step S130, the intelligent hydraulic control system dynamically adjusts the working parameters of the hydraulic pump (such as pressure and displacement, the control force of the hydraulic control system, the actual displacement of the template and the actual displacement of the skeleton) during the pouring process through the feedback control system. The hydraulic control system relies on the PID control algorithm to ensure the stability of the concrete pouring process so that the concrete can be accurately formed during the pouring process. By comparing the actual displacement X(t) with the reference displacement Xref , dynamically adjust the output of the hydraulic system according to the error.

[0121] The basic equation of hydraulic control is as follows:

[0122]

[0123] Where F(t) is the control force applied by the hydraulic system at time t; X(t) is the actual displacement of the template or skeleton position in the current hydraulic system; X ref is the reference displacement of the system, that is, the position that the template or skeleton should reach in an ideal state; K p is the proportional gain, which indicates the influence of the current displacement error on the control force; K d is the differential gain, which indicates the influence of the rate of change of displacement error on the control force; displacement error X(t)-X ref It is the difference between the current displacement of the system and the reference displacement, representing the deviation between the actual and ideal state. The goal of the control system is to minimize this error to 0; the proportional control term K p (X(t)-X ref ) is adjusted directly according to the current error. Proportional gain K p It determines the intensity of the system's response to the error. The larger the value, the faster the system responds. The differential control term takes into account the rate of change of the error, helping the system to foresee future error trends and make adjustments in advance. This helps to reduce system oscillations caused by rapid changes in errors.

[0124] At each moment t, the system collects the actual displacement X(t) of the template or skeleton and the control force F(t) of the hydraulic system in real time through sensors, and uploads these data to the cloud. At this time, the data set will be updated to:

[0125] D3={F(t),X(t),D2}

[0126] The data set D3 includes: F(t) is the control force of the hydraulic control system; X(t) is the actual displacement of the template or skeleton; D2 is the data set generated in step S130, including the data of skeleton positioning and template correction.

[0127] During the entire pouring process, the system will continuously adjust the parameters of the hydraulic pump according to the current template position X(t) and the skeleton position. The data after each adjustment will be fed back to the control system in real time to ensure that the next adjustment is more accurate. In this way, the system can dynamically respond to environmental changes and uncertainties in the pouring process to ensure that the position of the template and skeleton remains stable.

[0128] In some examples, the above-mentioned analyzing feature points of the concrete surface image based on the concrete surface image and calculating the deviation error includes:

[0129] Performing preprocessing operations of denoising and illumination correction on the concrete surface image;

[0130] A convolutional neural network is used to extract feature points of the above concrete surface image;

[0131] The above feature points are compared with the preset positions of the template to calculate the above deviation errors.

[0132] For example, the drone uses a high-precision camera to obtain images of the concrete surface after pouring. The image data contains the texture, shape and other visual features of the surface. These images are pre-processed (such as denoising, lighting correction, etc.) and then input into the deep learning model for further analysis.

[0133] The following image processing techniques are used during preprocessing:

[0134] Use non-local means or bilateral filtering to remove noise while preserving edge details, expressed as:

[0135]

[0136] Among them, I(p) is the gray value of pixel p; ω(p) is the weight, which indicates the similarity of the neighborhood pixels to the current pixel; ω(p) is the neighborhood range.

[0137] Use histogram equalization or adaptive histogram equalization to adjust the contrast of the image.

[0138] After image preprocessing, convolutional neural network is used to analyze the feature points in the image and perform feature point detection. CNN is a deep learning model commonly used for image classification and feature extraction. Its structure consists of convolutional layer, pooling layer and fully connected layer. After convolution and pooling operations, the network outputs a feature point set {f k}, these feature points represent important locations on the concrete surface, such as surface height differences, edges, etc.

[0139] The feature points f extracted by the deep learning model k , and the reference position X of the template ref Comparison is performed to detect the deviation between the actual casting surface and the reference template. The deviation calculation formula is:

[0140] AP=P actual -P ref

[0141] Among them, P actual is the position of the actual surface feature point obtained by feature point detection.

[0142] After the deviation data is calculated, the system uploads this data to the cloud and updates the data set D4:

[0143] D4={ΔP,D3}

[0144] Dataset D4 contains the deviation ΔP, the offset between the actual surface and the reference template; D3 in the previous step, namely the hydraulic system data, skeleton positioning and template correction data.

[0145] For example, the template installation posture adjusts the initial installation position and direction of the template to match it with the frame, with the focus on the template installation posture A opt The actual displacement of the template refers to the actual displacement of the template caused by external force (hydraulic control) during the pouring process, which is represented by X(t). The focus is on dynamically adjusting the position change of the template through the control system. The template reference position refers to the design reference position P of the template. ref , which is used for comparison with the actual casting surface to detect deviations.

[0146] In some examples, the above-mentioned integration of multi-source data to monitor the tower structure and predict the health status of the tower structure includes:

[0147] Based on the above multi-source data, the tilt state and damage degree of the tower column are evaluated based on big data analysis technology;

[0148] The multi-source data, the tilt state and the damage degree are input into a prediction model of time series analysis to obtain the health state of the tower structure.

[0149] For example, the tilt state of the tower column is evaluated by analyzing its lateral displacement at different time points. The tilt angle can reflect whether the tower column has structural deformation or instability. The tilt angle formula is expressed as:

[0150]

[0151] Among them, θ is the inclination angle of the tower column, Δy is the difference in lateral displacement between the top and bottom of the tower column, indicating the distance the tower column deviates from the vertical direction, and L is the height of the tower column; Δy is the lateral displacement data of the top of the tower column relative to the bottom collected by the sensor. The change in lateral displacement may be caused by environmental influences (such as wind, earthquake) or structural stress; the vertical height of the tower column, L, is used to normalize the lateral displacement to ensure the accuracy of the inclination angle calculation.

[0152] The core of long-term assessment of the structural health of the tower column is to analyze the changes in structural stress. The damage degree formula is expressed as:

[0153]

[0154] Among them, Dd is the overall damage degree, which is used to evaluate the health status of the tower column. By analyzing the stress changes at multiple stress monitoring points, the potential damage degree of the tower column can be estimated. If the Dd value is large, it means that there may be serious stress anomalies in the structure, and the health status needs further evaluation; Δσ sen is the stress change at the senth monitoring point. It is the difference between the actual stress value collected by the stress sensor and the reference stress at different monitoring points of the tower column. Stress change is one of the early signals of structural damage, which may be caused by external loads, material aging, etc.; ref is the reference stress value, representing the ideal stress state set during the tower column design, and indicating the load that the tower column should withstand under normal operating conditions; SEN is the total number of sensor monitoring points.

[0155] By integrating previously generated multi-source data, the tower's tilt status and damage level, this information is fed into a time series analysis prediction model to assess and predict the tower's future structural health. Time series analysis is used to detect tower trends over a period of time and predict possible structural problems in the future.

[0156] The long short-term memory network (LSTM) is used as a time series prediction model. LSTM can process data with time dependencies. Its input is a combination of multi-source data, tilt state and damage degree, and its output is a predicted future health state. The input of the LSTM model is a combination of multi-source data, tilt state and damage degree, and its output is a predicted future health state.

[0157] The input is represented as: (D4(T), Dd(t), θ(t)), and the output is represented as:

[0158] The LSTM model processes input through a recursive structure, expressed as:

[0159] h t =LSTM(h t-1 ,D4(t),Dd(t),θ(t))

[0160] Among them, h t is the hidden state at time t, indicating the current health information of the system; h t-1 is the hidden state at the previous time; D4(t) is the multi-source input data at the current moment.

[0161]

[0162] In the formula, To predict future health status.

[0163] The health status of a cable tower usually includes the overall stability of the structure, stress distribution, tilt status, material damage degree, etc. In practical applications, the health status of a cable tower can be divided into the following common situations:

[0164] Under normal conditions, the tower's inclination angle, stress distribution and material state are within the design range, with no obvious signs of damage, the inclination angle close to zero, the lateral displacement very small, and the structure remaining vertical; the degree of damage is close to zero; the material stress is stable, and the stress changes at all monitoring points are small. The tower is in a healthy state, can normally withstand the design load, has good structural stability, and the system does not require maintenance measures.

[0165] Local damage: local stress concentration or material micro-cracks occur in some parts of the cable tower, resulting in local damage. Common causes include long-term use of local material aging, stress concentration points or environmental stress. The tilt angle does not change much, but the stress changes at the local monitoring points are abnormal, and there may be slight structural deviations. The degree of damage has increased significantly, and the stress changes in specific areas are large, which may exceed the normal load-bearing range of the material. Local damage requires targeted maintenance measures, such as repairing damaged parts, enhancing local structural strength, and continuously monitoring the area to prevent the spread of damage.

[0166] Severe damage or structural instability: The structural health of the tower has seriously deteriorated, and there is a clear risk of material damage, stress overload or tilt instability; the tilt angle is very large, which may exceed the design limit, and the structure is at risk of collapse. The degree of damage is extremely high, and stress changes at multiple monitoring points are drastic, which may be accompanied by obvious material fractures, cracks or fatigue. At this time, the structure needs to be stopped immediately for emergency reinforcement or reconstruction. Severe damage or instability is a signal of the end of the life of the structure, and failure to repair it in time may lead to catastrophic consequences.

[0167] See also Figure 2 , which is a structural schematic diagram of a digital monitoring device for a cable-stayed bridge tower provided in an embodiment of the present application, comprising:

[0168] An acquisition unit 21 is used to acquire initial data, wherein the initial data includes tower environment data and three-dimensional morphology information;

[0169] A positioning unit 22, used to locate the skeleton based on the magnetic encoding data and the above three-dimensional morphological information;

[0170] A matching unit 23, used for adjusting the template posture based on the skeleton position so that the template posture matches the skeleton position, and obtaining correction data during the adjustment process;

[0171] A monitoring unit 24 is used to monitor the pouring process based on an intelligent hydraulic control system to obtain dynamic data;

[0172] The recognition unit 25 is used to analyze the characteristic points of the concrete surface image based on the concrete surface image, calculate the deviation error, and determine the deviation data;

[0173] The prediction unit 26 is used to integrate multi-source data to monitor the tower structure and predict the health status of the tower structure, wherein the multi-source data includes the initial data, the correction data, the dynamic data and the offset data.

[0174] See also Figure 3 The embodiment of the present application further provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, the steps of any of the above-mentioned methods for digital monitoring of cable-stayed bridge towers are implemented.

[0175] Since the electronic device introduced in this embodiment is a device used to implement a digital monitoring device for a cable-stayed bridge tower in the embodiment of the present application, based on the method introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0176] During the specific implementation process, when the computer program 311 is executed by a processor, any implementation method in the embodiments corresponding to the first aspect can be implemented.

[0177] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0178] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-readable program code.

[0179] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0180] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0181] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0182] The present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes Figure 1 The process of the digital monitoring method for cable-stayed bridge towers in the corresponding embodiment.

[0183] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0184] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0185] In the several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0186] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0187] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0188] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0189] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0190] Although preferred embodiments of the present specification have been described, additional changes and modifications may be made to these embodiments by those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present specification. Obviously, those skilled in the art may make various changes and modifications to the present specification without departing from the spirit and scope of the present specification. Thus, if these modifications and variations of the present specification fall within the scope of the claims of the present specification and their equivalents, the present specification is also intended to include these modifications and variations.

Claims

1. A digital monitoring method for a cable-stayed bridge tower, characterized in that: The method comprises: Acquiring initial data, wherein the initial data includes tower environment data and three-dimensional morphology information; Locating the skeleton based on the magnetically encoded data and the three-dimensional morphological information; Adjusting the template posture based on the skeleton position so that the template posture matches the skeleton position, and acquiring correction data during the adjustment process; Monitor the pouring process based on the intelligent hydraulic control system to obtain dynamic data; Based on the concrete surface image, analyzing the characteristic points of the concrete surface image, calculating the deviation error, and determining the deviation data; Integrate multi-source data to monitor the tower structure and predict the health status of the tower structure, wherein the multi-source data includes the initial data, the correction data, the dynamic data and the offset data.

2. The method according to claim 1, characterized in that The tower environmental data includes a sensor data matrix containing a time series, and the sensor data matrix includes temperature data, humidity data, stress data and vibration data; The three-dimensional morphological information is point cloud data converted from a three-dimensional coordinate set, and the three-dimensional coordinate set is a set of three-dimensional coordinates of tower nodes obtained by scanning the tower through a laser radar.

3. The method according to claim 1, characterized in that Also includes: Determining the magnetic encoding data according to the coordinate information collected by the magnetic encoder; The skeleton position is calculated based on the spatial position and weight of the encoding point.

4. The method according to claim 1, characterized in that: The adjusting the template posture based on the skeleton position so that the template posture matches the skeleton position includes: Determining a target pose adjustment amount based on minimizing an error between a template position and the skeleton position; Using a deep learning model optimization algorithm to form a posture adjustment signal based on the target posture adjustment amount; The adjustment process of the template posture is controlled based on the posture adjustment signal to make the template posture match the skeleton position.

5. The method according to claim 1, characterized in that Also includes: The intelligent hydraulic control system includes a hydraulic pump, a hydraulic cylinder, and a control system; The control system dynamically adjusts the working parameters of the hydraulic pump based on a PID control algorithm by monitoring the working states of the hydraulic pump and the hydraulic cylinder.

6. The method according to claim 1, characterized in that The step of analyzing the feature points of the concrete surface image based on the concrete surface image and calculating the deviation error includes: Performing preprocessing operations of denoising and illumination correction on the concrete surface image; Extracting feature points of the concrete surface image using a convolutional neural network; The feature point is compared with the preset position of the template to calculate the deviation error.

7. The method according to claim 1, characterized in that The method of integrating multi-source data to monitor the tower structure and predicting the health status of the tower structure includes: According to the multi-source data, the tilt state and damage degree of the tower column are evaluated based on big data analysis technology; The multi-source data, the tilt state and the damage degree are input into a prediction model of time series analysis to obtain the health state of the tower structure.

8. A digital monitoring device for a cable-stayed bridge tower, characterized in that: include: An acquisition unit, used for acquiring initial data, wherein the initial data includes tower environment data and three-dimensional morphology information; A positioning unit, used for positioning the skeleton based on the magnetically encoded data and the three-dimensional morphological information; A matching unit, configured to adjust the template posture based on the skeleton position so that the template posture matches the skeleton position, and obtain correction data during the adjustment process; A monitoring unit is used to monitor the pouring process based on an intelligent hydraulic control system and obtain dynamic data; A recognition unit, used for analyzing feature points of the concrete surface image based on the concrete surface image, calculating the deviation error, and determining the deviation data; A prediction unit is used to integrate multi-source data to monitor the tower structure and predict the health status of the tower structure, wherein the multi-source data includes the initial data, the correction data, the dynamic data and the offset data.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to implement the steps of the digital monitoring method for cable-stayed bridge towers as described in any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the digital monitoring method for cable-stayed bridge towers according to any one of claims 1 to 7 is implemented.

Images