Automatic operation method for accurate positioning during installation of bridge hanging basket

Abstract

The invention relates to the technical field of constructional engineering, and discloses a bridge hanging basket installation accurate positioning automatic operation method, which comprises the following steps of: acquiring image data of the position, the speed, the posture and the construction environment of a bridge hanging basket in real time by installing a high-precision sensor and a visual system; analyzing the acquired image data by using a deep learning model, and identifying and estimating the spatial position and angle of the hanging basket; the system comprises a high-precision sensor and an image acquisition system which are used for acquiring the position, attitude and environmental data of the hanging basket in real time; the deep learning module comprises a convolutional neural network and a recurrent neural network and is used for recognizing the position of the hanging basket in real time and predicting future deviation; and the nonlinear optimization module is used for calculating optimal control input in real time according to the optimization objective function and correcting the optimal control input. By adopting the technical scheme of the high-precision sensor and the image acquisition system, real-time accurate monitoring of the position, the posture and the construction environment of the hanging basket is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of construction engineering, and particularly to an automated operation method for precise positioning of bridge hanging baskets during installation. Background Art

[0002] In the prior art, during the installation of bridge hanging baskets, the accuracy of positioning and dynamic adjustment are very crucial. However, many traditional techniques still rely on a single positioning sensor or low-precision equipment, which results in the inability to guarantee the accurate measurement of the position and angle of the hanging basket in a complex construction environment. For example, although the total station and laser rangefinder conventionally used can provide spatial position data of the hanging basket, these devices often perform unstably in a dynamic environment, especially under conditions such as light changes, weather changes, or construction interference, where the accuracy is greatly reduced and the correction process is often lagged, making it difficult to adjust the position of the hanging basket in a timely manner.

[0003] Another obvious problem occurs during the process of correcting the position of the hanging basket. Existing correction schemes usually adopt fixed control strategies, ignoring the variability and dynamics in actual construction. Such strategies often lead to overcorrection or energy waste. In some cases, due to the lack of consideration of the energy consumption of the control input during the correction process, the system may inefficiently use excessive resources, resulting in low operation efficiency and increased unnecessary energy consumption. Moreover, when the correction deviation of the hanging basket is large, traditional control methods often require multiple adjustments, increasing the construction time and cost.

[0004] Meanwhile, traditional feedback systems mostly rely on static error calculation and linear correction methods, which are prone to large error accumulation in a dynamic and complex construction environment. For example, external conditions at the construction site (such as wind speed, climate, etc.) have a great impact on the stability of the hanging basket, but existing technologies rarely can respond quickly to these changes and make adjustments. This limitation leads to a high error rate in the correction process and has an adverse impact on the safety and stability of construction.

[0005] In addition, existing technologies are still insufficient in predicting future deviation trends and making dynamic adjustments. Many systems rely on manual intervention to adjust the position of the hanging basket, which not only reduces the operation efficiency but also increases the risk of human error. Systems with low automation levels cannot react in a timely manner to the immediate changes at the construction site, making it difficult for the system to maintain high-precision operation under variable construction conditions.

[0006] Therefore, the present invention proposes an automated operation method for precise positioning of bridge hanging baskets during installation to solve the deficiencies of the prior art. Summary of the Invention

[0007] In view of the deficiencies of the prior art, the present invention provides an automated operation method for precise positioning of bridge hanging baskets, which solves the problems of insufficient position accuracy, lag in dynamic adjustment, and energy waste during the installation of bridge hanging baskets in complex construction environments.

[0008] To achieve the above objectives, the present invention is realized through the following technical solutions: An automated operation method for precise positioning of bridge hanging baskets, comprising the following steps:

[0009] By installing high-precision sensors and a vision system, real-time acquisition of the position, speed, attitude of the bridge hanging basket and image data of the construction environment is carried out;

[0010] Using a deep learning model to analyze the collected image data, identifying and estimating the spatial position and angle of the hanging basket;

[0011] According to the output of the deep learning model, a non-linear optimization objective function is constructed, and by minimizing the position deviation and the energy consumption of the control input, an optimal correction strategy is calculated;

[0012] Using a non-linear optimization algorithm to adjust the control input in real time to correct the deviation of the hanging basket;

[0013] Through an automated execution system, the correction instructions are executed in real time to adjust the position and angle of the hanging basket;

[0014] Compare the correction result with the target position, and feedback and adjust the control strategy in real time.

[0015] Preferably, the high-precision sensors include the following devices:

[0016] LiDAR, used to measure the position of the hanging basket in three-dimensional space in real time, and by emitting laser and receiving reflected signals, accurately obtain the relative position of the hanging basket and the surrounding environment.

[0017] Total station, used to accurately measure the angle and attitude of the hanging basket, and combine laser ranging and angle measurement to provide high-precision position and attitude data.

[0018] Accelerometer and gyroscope, the accelerometer monitors the acceleration of the hanging basket, and the gyroscope is used to measure the angular velocity;

[0019] The vision system collects environmental data around the hanging basket through a camera or other imaging devices, including at least illumination and surrounding obstacles, provides visual information related to the environment, and supports the analysis of the deep learning module.

[0020] Preferably, the optimization objective function obtains an optimal control strategy by minimizing the position deviation and the power consumption of the correction control input;

[0021] The optimization objective function is:

[0022]

[0023] Among them, J represents the optimization objective function; T represents the total number of time steps in the optimization process; t is the time step, from t = 0 to t = T; X(t) is the position vector of the hanging basket at time t; X target is the predetermined target position; u(t) is the control input; ∥X(t) - X target ∥ 2 represents the squared error between the position of the hanging basket and the target position; λ is the regularization parameter, which is used to control the balance between the energy consumption of the control input and the position error; ∥u(t)∥ 2 represents the squared energy consumption of the control input.

[0024] Preferably, the deep learning model includes a convolutional neural network and a recurrent neural network, which are used to identify the position of the hanging basket and predict the deviation trend respectively.

[0025] Preferably, the steps of the non-linear optimization algorithm include:

[0026] Construct a non-linear optimization objective function according to the hanging basket position deviation data output by the deep learning model;

[0027] Select the gradient descent method and the Newton method as the optimization algorithms to calculate the optimal correction control input;

[0028] By calculating the gradient of the objective function, adjust the control input in real time to minimize the position deviation and control energy consumption;

[0029] During the iterative optimization process, continuously update the control input according to the real-time feedback;

[0030] Apply the optimized control input to the automatic execution system to adjust the actual position and angle of the hanging basket.

[0031] Preferably, the steps of the automatic execution system include:

[0032] Generate corresponding correction instructions according to the optimized control input;

[0033] Use automated equipment to execute the correction instructions to adjust the position and angle of the hanging basket;

[0034] Verify the correction effect of the hanging basket through a real-time monitoring system;

[0035] Further adjust the execution strategy according to the real-time feedback data;

[0036] After completing the correction of the hanging basket, the automatic execution system enters the standby state, ready for the next round of correction operation.

[0037] Preferably, the steps of real-time feedback and adjustment of the control strategy include:

[0038] Monitor the current position and attitude of the hanging basket in real time through sensors and vision systems;

[0039] Compare the actual position with the target position, calculate the deviation and generate a feedback signal;

[0040] Input the feedback signal into the control system, adjust the control input, and optimize the correction path of the hanging basket;

[0041] Adjust the control strategy in real time according to the feedback result, and continuously correct the position and angle of the hanging basket;

[0042] It is used to stop adjusting after the hanging basket reaches the predetermined target position and complete the correction process.

[0043] Preferably, the deep learning network enhances the adaptability of the system in an uncertain environment through a generative adversarial network, and simulates data under different lighting and wind speed environmental conditions.

[0044] Preferably, the correction strategy performs closed-loop control through real-time feedback and adjustment, and is used to keep the hanging basket always at the predetermined target position during the installation process. The real-time feedback and adjustment include:

[0045] Monitor the current position and attitude of the hanging basket in real time through sensors and vision systems;

[0046] Compare the actual position with the target position, calculate the deviation and generate a feedback signal;

[0047] Input the feedback signal into the control system, adjust the control input, and optimize the correction path of the hanging basket;

[0048] Adjust the control strategy in real time according to the feedback result, and continuously correct the position and angle of the hanging basket;

[0049] It is used to stop adjusting after the hanging basket reaches the predetermined target position and complete the correction process.

[0050] The present invention also provides an automated operating system for precise positioning of bridge hanging baskets, including:

[0051] A high-precision sensor and image acquisition system for real-time acquisition of the position, attitude and environmental data of the hanging basket;

[0052] A deep learning module, including a convolutional neural network and a recurrent neural network, for real-time identification of the hanging basket position and prediction of future deviations;

[0053] A non-linear optimization module for real-time calculation of the optimal control input according to the optimization objective function and correction;

[0054] An execution system for automatically adjusting the position and angle of the hanging basket according to the optimization instruction;

[0055] A real-time feedback system is used to compare with the target position and the correction result, and adjust the control strategy in real time.

[0056] The present invention provides an automatic operation method for precise positioning of bridge hanging baskets. It has the following beneficial effects:

[0057] 1. By adopting the technical solution of high-precision sensors and image acquisition systems, the present invention achieves real-time and accurate monitoring of the position, attitude and construction environment of the hanging basket. Compared with the single sensor or low-precision equipment commonly used in the prior art, the present invention solves the problem that it is difficult to accurately measure the position and angle of the hanging basket in a complex construction environment, and significantly improves the accuracy and real-time performance of the correction operation.

[0058] 2. The present invention introduces a deep learning module, combines convolutional neural network and recurrent neural network, and achieves real-time recognition and prediction of the position and future deviation of the hanging basket. Compared with the traditional rule-based control system, the present invention effectively solves the problem of correction lag caused by environmental changes and the dynamic nature of the hanging basket, and provides a more intelligent and accurate dynamic adjustment scheme.

[0059] 3. The present invention adopts a non-linear optimization module to calculate the optimal correction control input in real time according to the output data of the deep learning module, and achieves a balance between optimizing position correction and energy consumption. Compared with the traditional fixed control strategy, the present invention solves the problems of energy waste and over-adjustment existing in the process of hanging basket correction, and realizes a more efficient correction process.

[0060] 4. Through continuous monitoring and dynamic adjustment of the real-time feedback system, the present invention achieves the ability to calibrate the position of the hanging basket in real time during the construction process. Compared with the feedback mechanism with lower correction accuracy in the prior art, the present invention effectively solves the problems of correction error accumulation and instability caused by external environmental interference, and significantly improves the construction safety and stability. Description of the Drawings

[0061] Figure 1 It is the flowchart of the method of the present invention;

[0062] Figure 2 It is the system architecture diagram of the present invention. Detailed Embodiments

[0063] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0064] Please refer toFigure 1 , an embodiment of the present invention provides an automated operation method for precise positioning of bridge hanging baskets, including the following steps:

[0065] S1. By installing high-precision sensors and a vision system, real-time acquisition of image data on the position, speed, attitude of the bridge hanging basket and the construction environment is carried out;

[0066] S2. Using a deep learning model to analyze the collected image data, identify and estimate the spatial position and angle of the hanging basket;

[0067] S3. According to the output of the deep learning model, construct a non-linear optimization objective function, and calculate the optimal correction strategy by minimizing the position deviation and the energy consumption of the control input;

[0068] S4. Use a non-linear optimization algorithm to adjust the control input in real time and correct the deviation of the hanging basket;

[0069] S5. Through an automated execution system, execute the correction instruction in real time and adjust the position and angle of the hanging basket;

[0070] S6. Compare the correction result with the target position, and give real-time feedback and adjust the control strategy.

[0071] For step S1, first of all, during the installation process of the bridge hanging basket, it is crucial to obtain the positioning data of the hanging basket in real time, especially as the complexity of hoisting and moving operations in bridge engineering increases. To ensure the accuracy of the hanging basket installation, the present invention uses a series of high-precision sensors and a vision system to collect the position, speed, attitude of the hanging basket and the construction environment data in real time. These data provide basic support for subsequent deep learning analysis and correction control.

[0072] In this embodiment, first, by installing a plurality of high-precision sensors and a vision system at the bridge construction site, all-round data collection of the hanging basket is carried out. Including but not limited to lidar, total station, accelerometer, gyroscope, and image acquisition equipment, etc. These sensors and devices obtain the position, speed, attitude of the hanging basket in space and the environmental data of the construction site in real time through precise measurement and capture.

[0073] In a possible implementation, the lidar is used to measure the position of the hanging basket in three-dimensional space in real time. The lidar can accurately provide the relative position data of the hanging basket and the surrounding environment by emitting laser beams and receiving their reflected signals, especially at the bridge construction site with complex structures. These position data are transmitted to the data processing module in real time for subsequent analysis by the deep learning module.

[0074] As an option, a total station is installed at an appropriate angle and position to measure the angles and postures of the hanging basket. The total station can not only provide high-precision angle measurement, but also monitor the posture changes of the hanging basket in real time through an automatic tracking system. This is particularly important for precisely controlling the installation process of the hanging basket, especially when the hanging basket needs to be precisely adjusted in a multi-dimensional space.

[0075] In some embodiments, accelerometers and gyroscopes are used to monitor the dynamic changes of the hanging basket. These sensors can obtain the acceleration and angular velocity data of the hanging basket in real time. Through the accelerometer, the system can obtain the acceleration information of the hanging basket in each direction, while the gyroscope can provide the angular velocity data of the hanging basket's rotation. These dynamic data are crucial for tracking the real-time movement changes of the hanging basket during the installation process and can help the system predict and adjust the future position of the hanging basket during the processing.

[0076] Specifically, a vision system is used to collect the environmental data of the construction site, mainly including environmental change information such as the light, temperature, and humidity around the hanging basket. The vision system not only provides direct visual data of the hanging basket, but also can assist in evaluating the changes in the construction environment through image recognition technology. This is of great significance for dealing with unforeseen environmental changes during construction, such as sudden weather changes or light changes.

[0077] In this embodiment, the real-time data of all sensors and the vision system are transmitted to a deep learning module for subsequent processing. The deep learning model can extract valuable information from these multi-modal data and provide data support for the subsequent optimization algorithm.

[0078] In another implementation, to ensure the accuracy and real-time nature of the data, the sensor system of the present invention can be connected to a data processing system through a wireless communication network. In this way, the data collected by all sensors and vision devices can be immediately transmitted to the central processing system and processed through a data fusion algorithm to improve the reliability and accuracy of the data. Real-time data collection and processing provide a solid foundation for the subsequent analysis, especially for the precise positioning and correction of the hanging basket in a complex environment.

[0079] Generally speaking, through multi-sensor data collection in step S1, the accuracy of the hanging basket installation is ensured. The collaborative work of the sensors and the vision system can not only provide accurate position information, but also monitor the dynamic behavior of the hanging basket and the surrounding environment in real time, thus providing rich data support for the subsequent deep learning model analysis, optimization algorithm calculation, and execution system adjustment.

[0080] For step S2 immediately following the aforementioned data acquisition step, the collected image data is mainly analyzed through a deep learning model to realize the recognition of the spatial position and angle of the hanging basket. The connection between step S2 and step S1 is crucial. Step S1 provides high-precision sensor and visual data support, while step S2 uses these data to achieve accurate estimation of the position of the hanging basket.

[0081] In this embodiment, in step S1, the spatial position information, attitude data, and environmental data of the hanging basket are collected through devices such as lidar, total station, accelerometer, and gyroscope. On this basis, the deep learning module is responsible for processing these multi-modal data. In particular, convolutional neural network (CNN) and recurrent neural network (RNN) are used for the analysis of position and dynamic state.

[0082] Specifically, in the implementation process of the deep learning model, the convolutional neural network (CNN) is first used to extract features from the image data. CNN has powerful capabilities in image recognition and can extract the spatial position features of the hanging basket from complex image data, including key information such as the shape, position, and size of the hanging basket. Specifically, the multi-layer structure of the convolutional neural network can gradually extract features from simple to complex, and finally identify the accurate spatial position and angle of the hanging basket.

[0083] In some embodiments, CNN not only processes static image data but also can handle image changes in dynamic scenarios. Therefore, even in a complex and dynamic construction environment, the system can still accurately identify the position and attitude of the hanging basket through CNN. This ability is particularly important in cases where the construction environment changes frequently. For example, there may be factors such as rapidly changing lighting and weather at the construction site, and CNN can adapt to these changes to ensure the robustness and accuracy of data analysis.

[0084] As an option, a recurrent neural network (RNN) is introduced to model the dynamic state of the hanging basket. Different from traditional neural networks, RNN has the advantage of processing sequential data and can capture the temporal information in the time series. During the position adjustment of the hanging basket, RNN predicts the deviation trend at future moments based on the current state and historical state of the hanging basket, and makes position corrections in advance. This method greatly improves the response speed to position changes in a dynamic environment. Through the prediction of the RNN model, the system can identify and respond to possible deviations of the hanging basket in advance, reducing the time for real-time correction.

[0085] In a possible implementation, by combining CNN and RNN, the system can simultaneously perform spatial position recognition and dynamic trend prediction. Specifically, CNN is responsible for processing static data to identify the real-time position and attitude of the hanging basket; while RNN is responsible for processing time series data to predict the possible deviation of the hanging basket in the next period of time. The combination of the two not only improves the accuracy of position recognition, but also provides more comprehensive support for subsequent non-linear optimization and control strategies.

[0086] To ensure accuracy, the training process of the deep learning module is crucial. Generally, deep learning models are trained using a large amount of labeled data. In the application of hanging basket positioning, the model needs to be trained with a large amount of construction site data (such as the position, attitude, environmental conditions, etc. of the hanging basket). Through deep learning algorithms, the model can learn the positioning patterns in different environments and construction scenarios from these data, further improving the accuracy of recognition and prediction.

[0087] In some embodiments, to optimize the performance of the model, a generative adversarial network (GAN) can also be added for training. Through GAN, the system can self-learn in a simulated complex environmental condition, enhancing its adaptability to changes in the actual construction environment. By simulating environmental changes (such as lighting, weather, etc.), the generative adversarial network can make the model more robust when facing real construction scenarios.

[0088] Through the deep learning analysis in step S2, not only can the spatial position and angle of the hanging basket be accurately identified, but also its future deviation can be predicted. The core advantage of this process is that through the inference and prediction of deep learning, the system can dynamically adjust the position of the hanging basket, anticipate possible deviations in advance, thus significantly improving the installation accuracy of the hanging basket.

[0089] In step S2, the results output by the deep learning model will become the key input for the subsequent non-linear optimization process. The optimization objective function will be adjusted according to these outputs to ensure the precise positioning of the hanging basket throughout the installation process. Therefore, step S2 provides crucial data support for subsequent non-linear optimization and correction control.

[0090] In summary, step S2 processes multi-modal sensor data through deep learning technology to accurately identify the position of the hanging basket and predict the deviation trend. By combining CNN and RNN, not only the positioning accuracy of the hanging basket is improved, but also the adaptability of the system to the dynamic environment is enhanced. The combination of these technologies provides a strong technical guarantee for the precise positioning of the hanging basket, effectively improving the construction efficiency and accuracy, and reducing errors and risks.

[0091] For step S3, in the previous step S2, the data from various sensors and the vision system have been processed by the deep learning model to accurately identify the spatial position, attitude, and dynamic state of the hanging basket, and predict the future deviation trend. Based on this information, the task of step S3 is to construct a non-linear optimization objective function that calculates the optimal correction strategy by minimizing the position deviation and the energy consumption of the control input, thereby achieving the precise positioning and dynamic correction of the hanging basket.

[0092] In this embodiment, step S3 constructs an optimization objective function based on the current position information of the hanging basket provided by the deep learning model and the future deviation prediction. The core of this objective function lies in balancing the relationship between the position deviation and the energy consumption of the control input to ensure the precise positioning of the hanging basket. During this process, the design of the optimization objective function should take into account the deviation between the hanging basket and the target position, as well as the energy required for the correction operation, to avoid unnecessary energy consumption.

[0093] Specifically, the optimization objective function can generally be expressed in the following form:

[0094]

[0095] where J represents the optimization objective function; T represents the total number of time steps in the optimization process; t is the time step, ranging from t = 0 to t = T; X(t) is the position vector of the hanging basket at time t; X target is the predetermined target position; u(t) is the control input; ∥X(t) - X target ∥ 2 represents the squared error between the position of the hanging basket and the target position; λ is the regularization parameter used to control the balance between the energy consumption of the control input and the position error; ∥u(t)∥ 2 represents the squared energy consumption of the control input.

[0096] The core of this objective function is to simultaneously minimize the position error and the energy consumption of the control input. In this way, the optimization algorithm can not only accurately adjust the position of the hanging basket but also effectively control the energy use during the correction process, thereby improving the efficiency of the correction process.

[0097] In a possible implementation, the construction of the optimization objective function considers not only the position error but also the energy consumption of the control input. By introducing the regularization parameter λ, the system can adjust the balance between the position accuracy and the energy consumption of the control input during the correction process. In different construction environments, the appropriate balance point of accuracy and efficiency can be selected by adjusting λ. For example, if more accurate positioning is required, the system can increase the value of λ, allowing the energy consumption of the control input to increase moderately while ensuring the accuracy; conversely, if the energy consumption needs to be minimized, λ can be reduced to lower the consumption of the control input.

[0098] As an option, the optimization objective function can be further extended to consider the dynamic response of the hanging basket. For example, the control of the speed or acceleration of the hanging basket can be increased to avoid instability caused by overcorrection or violent movement. At this time, the optimization objective function can be extended to:

[0099]

[0100] where J ′ is the optimization objective function, representing the comprehensive optimization objective in the entire correction process; T represents the total number of time steps in the optimization process; t represents the time step, from t = 0 to t = T, representing each time point in the optimization process; X(t) represents the position vector of the hanging basket at time t, that is, the three-dimensional coordinate information of the hanging basket; X target is the predetermined target position, which is the position that the hanging basket should finally reach; u(t) represents the correction control input, and the control input is an instruction to adjust the position and attitude of the hanging basket, which can be the actions of controlling equipment such as robotic arms and automated guided vehicles (AGVs); ∥X(t) - X target ∥ 2 is the squared error of the position deviation, representing the deviation between the current position of the hanging basket and the target position, and the goal is to minimize this deviation; λ is the regularization parameter, used to balance the weight between the position deviation and the energy consumption of the control input; ∥u(t)∥ 2 is the energy consumption of the control input, measuring the energy consumed in the correction process; μ is the regularization parameter, used to balance the influence of the control speed and other terms; is the speed of the hanging basket at time t, representing the speed of the hanging basket during the correction process; is the square of the speed of the hanging basket, representing the movement rate of the hanging basket during the correction process

[0101] This extended optimization objective function can more comprehensively control the dynamic response during the correction process, ensure that the correction process is smoother, and reduce unnecessary oscillations or vibrations.

[0102] In some embodiments, the design of the optimization objective function may be further adjusted according to real-time feedback information. For example, in the construction environment, the position and attitude of the hanging basket are not only affected by the control input, but may also be affected by external factors (such as wind speed, temperature, etc.). At this time, the system can dynamically update the parameters in the objective function according to the real-time feedback signal to further optimize the correction process.

[0103] Specifically, once the objective function is constructed, the next step is to calculate the optimal correction strategy through a non-linear optimization algorithm. The optimization algorithm utilizes the state information of the hanging basket at the current moment, the target position, and the predicted deviation trend to calculate the best correction control input. Generally, common methods such as the gradient descent method, Newton's method, or quasi-Newton method are adopted by the non-linear optimization algorithm for iterative optimization.

[0104] In a possible implementation, through the gradient descent method, the system gradually calculates the gradient of the objective function with respect to the correction control input and adjusts the control input according to the gradient information. After each iteration, the system calculates the error between the current position and the target position, updates the control input until a predetermined accuracy is achieved. For complex construction environments, optimization techniques such as heuristic search or genetic algorithms may also be adopted to further accelerate the optimization process and ensure the real-time performance and accuracy of the correction operation.

[0105] In summary, step S3 constructs a non-linear optimization objective function and adjusts the control input in real time through an optimization algorithm to ensure that the hanging basket can be accurately adjusted to the predetermined position during the installation process. The optimization objective function balances the position deviation and energy consumption and is flexibly adjusted by introducing a regularization parameter to adapt to different construction requirements. Through this optimization control method, the present invention can maximize the efficiency of the correction process while ensuring high-precision positioning, and ensure the safety and accuracy of the installation of the bridge hanging basket.

[0106] Regarding S4, in the foregoing step S3, based on the predicted data of the position, attitude, and dynamic deviation of the hanging basket output by the deep learning model, a non-linear optimization objective function is constructed. This objective function comprehensively considers the position deviation, correction energy consumption, and possible dynamic responses, and calculates the optimal correction strategy through an optimization algorithm. Step S4 then applies this non-linear optimization algorithm to adjust the control input in real time, thereby correcting the deviation of the hanging basket and ensuring that the hanging basket is always in the target position. The connection between step S4 and the foregoing steps is very crucial. The optimization calculation result provides decision support for the subsequent correction operation and ensures the accuracy and efficiency of the entire correction process.

[0107] In this embodiment, step S4 applies a non-linear optimization algorithm (such as the gradient descent method, Newton's method, or quasi-Newton method) to adjust the control input and correct the deviation of the hanging basket. The role of the non-linear optimization algorithm here is to calculate the optimal correction control input according to the optimization objective function, so that the hanging basket can be gradually adjusted and finally accurately positioned. The design of the objective function has been clearly defined in step S3, including the error term of the hanging basket position and the control input energy consumption term. On this basis, the optimization algorithm calculates the correction instruction in real time.

[0108] Specifically, the optimization algorithm first needs to calculate the gradient of the objective function with respect to the control input and make adjustments based on the gradient information. The gradient descent method is a commonly used optimization algorithm that updates the control input step by step by calculating the gradient of the objective function with respect to the control input. After each optimization iteration, the system adjusts the control strategy according to the deviation between the current position and the target position to minimize the error. At the same time, attention should be paid to the energy consumption of the control input to avoid unnecessary corrections.

[0109] As an option, if higher computational efficiency or faster convergence speed is required, the system can use second-order optimization methods such as the Newton method or quasi-Newton method. Compared with the gradient descent method, these methods can more accurately estimate the optimal update direction for correcting the control input in each iteration by using the second derivative of the objective function (i.e., the Hessian matrix). This is particularly effective when the correction error is large and can significantly improve the efficiency of the correction process.

[0110] In some embodiments, to improve the optimization efficiency, the system can also adjust the learning rate or step size of the algorithm according to real-time feedback. By dynamically adjusting the learning rate, the system can quickly adapt in a more complex or uncertain environment and improve the convergence speed. For example, at the initial stage of correction, the learning rate can be set larger to speed up the correction process; while approaching the target position, the learning rate can be reduced to avoid oscillations caused by over-adjustment.

[0111] In a possible implementation, the optimization algorithm in step S4 makes gradual corrections based on real-time data. For example, whenever the system performs a correction and updates the position of the hanging basket, the real-time feedback system provides new error values and correction results, which are input into the optimization algorithm to recalculate the optimal control input. The optimization algorithm adjusts the control input in real time based on this feedback information, causing the hanging basket to gradually converge to the target position. This process forms a dynamic closed loop to ensure that the correction operation can be precisely adjusted at each time step.

[0112] Specifically, in some complex environments, the system can also use an adaptive control algorithm to optimize the parameter settings in the optimization process. Adaptive control can automatically adjust the control parameters in the optimization algorithm, such as the regularization parameter, learning rate, etc., according to the actual effect of the hanging basket position correction. This adaptive mechanism can ensure that the system maintains high-precision positioning in different construction environments and improve the robustness of the correction process.

[0113] For example, in the case of large external disturbances (such as strong winds, sudden environmental changes), the control system can reduce the impact of external factors on the correction process by automatically adjusting the parameters. This enables the system to maintain accuracy and efficiency in a complex construction site.

[0114] For step S5, the system has calculated and adjusted the corrective control input through a non - linear optimization algorithm to ensure the establishment of the optimal strategy for the hanging basket correction. Step S5 follows step S4, and its goal is to execute the correction instructions in real - time through an automated execution system, adjust the position and angle of the hanging basket, and ensure the precise positioning of the hanging basket during construction. Step S5 is crucial in the system process. It transforms the results of the optimization calculation into actual control actions and ensures that the correction operations can be precisely executed.

[0115] In this embodiment, the automated execution system receives the corrective control input calculated in step S4 and transmits these control instructions to the execution devices, such as robotic arms, automated guided vehicles (AGVs), hydraulic control systems, etc. The execution devices adjust the position and angle of the hanging basket according to the optimized instructions. This process involves transforming the control input obtained from the optimization algorithm into specific operation signals to guide the execution system to precisely control the hanging basket.

[0116] Specifically, in the automated execution system, the execution of the correction instructions first dynamically adjusts the position and attitude of the hanging basket through the control system. For example, if the optimization result indicates that the hanging basket needs to move along the X - axis, the automated guided vehicle (AGV) will receive the corresponding instructions and adjust the position of the hanging basket through the vehicle - mounted control system. Similarly, if the instruction requires adjusting the angle of the hanging basket, the robotic arm will execute precise angle adjustment according to the control input instructions to ensure that the hanging basket reaches the target attitude.

[0117] As an option, in some embodiments, the execution system further includes multiple feedback loops to ensure the accuracy of the correction operations. Specifically, the execution system can be equipped with position sensors, angle sensors, etc. to monitor the movement and adjustment effect of the hanging basket in real - time. These sensors feed the data back to the control system in real - time, allowing the system to determine whether the current correction effect meets the expected accuracy. If the correction accuracy does not reach the expectation, the system will recalculate the correction strategy and adjust the control input to ensure the accuracy of the correction process.

[0118] In some embodiments, to further improve the accuracy and safety of the correction operations, the automated execution system can integrate an environment perception system, such as lidar, vision systems, etc., for real - time monitoring of the construction environment. The environment perception system can identify surrounding obstacles, changes in construction conditions, etc., and timely adjust the execution path and correction strategy to avoid correction errors caused by environmental changes.

[0119] Specifically, there is a close collaborative relationship between the execution system and the real-time monitoring system. The real-time monitoring system is not only used to supervise the completion of the correction operation, but also provides instant feedback to the execution system. For example, when the execution system completes the correction of the hanging basket position, the monitoring system will verify the gap between the final position and the target position of the hanging basket through devices such as sensors or cameras. If the gap is large, the real-time feedback system will immediately send a warning signal to the control system, indicating that there may be insufficient correction or error accumulation. The control system will further adjust the correction strategy and re-adjust the control input based on the real-time feedback information for the next refined correction.

[0120] As an option, in some embodiments, the execution system may also make the correction process of the hanging basket smoother and more efficient through a preset path planning and correction trajectory, combined with the precise control of automated equipment. For example, an automated guided vehicle (AGV) not only moves according to the target position, but also presets various possible correction trajectories in the path planning to ensure the continuity and smoothness of the execution process and avoid sudden errors caused by environmental changes.

[0121] In a possible implementation, to ensure that the correction operation is both efficient and highly accurate, the execution system can improve the control accuracy through multi-sensor fusion technology. Multi-sensor fusion technology can integrate data from different sensors (such as lidar, accelerometers, gyroscopes, etc.) in real time, thereby more accurately estimating the position and motion state of the hanging basket. After the sensor data is fused, the automated execution system can obtain more accurate correction instructions to finely adjust each movement step of the hanging basket.

[0122] Specifically, when the sensor data and optimization instructions are combined, the execution system can dynamically adjust the position of the hanging basket with higher accuracy. For example, visual sensors can be used to monitor the relative position of the hanging basket and the construction target and provide high-resolution position information; lidar provides three-dimensional space data of the hanging basket to help the execution system accurately adjust the angle and attitude of the hanging basket. All this data is processed through multi-sensor fusion and finally provided to the execution system to ensure the precise alignment of the hanging basket at the target position.

[0123] In some embodiments, the system may also be equipped with a safety warning function. During the correction process, if the execution system detects that the correction speed is too fast or exceeds the preset safety range, the system will automatically abort the current operation to prevent overcorrection or equipment damage. This function ensures the safety of the system while maintaining high efficiency by analyzing the real-time data during the correction process.

[0124] In step S5, the optimal control input calculated in step S4 is converted into actual operations for correcting the hanging basket through an automated execution system. The close cooperation between the automated equipment and the real-time monitoring system ensures the accuracy and efficiency of the correction operations. Through the precise control system and multi-sensor fusion, the correction process can maintain high efficiency and precision under changing construction environments. Meanwhile, the safety guarantee mechanism and real-time feedback loop within the execution system further enhance the stability and reliability of the system. In this way, through precise automated execution and real-time monitoring, the system can effectively complete the precise installation and dynamic adjustment of the bridge hanging basket, ensuring the efficient and safe progress of the project.

[0125] Regarding step S6, in the previous step S5, the automated execution system has successfully corrected the hanging basket according to the optimal control input calculated by the optimization algorithm in step S4, adjusting the position and angle of the hanging basket. Step S6 follows this process, monitoring and evaluating the correction results through a real-time feedback system, and adjusting the control strategy based on real-time data to ensure that the hanging basket can always accurately align with the predetermined target position. The main objective of step S6 is to dynamically adjust the control input through real-time feedback to ensure the high precision and efficiency of the correction process.

[0126] In this embodiment, the real-time feedback system calculates and generates a feedback signal in real time by monitoring the error between the current position and the target position of the hanging basket. This feedback signal is transmitted to the control system to assist in adjusting the current control strategy. If the correction result does not meet the predetermined accuracy requirements, the system will immediately initiate a new correction calculation and adjust the control input. Through this real-time feedback mechanism, the system can quickly respond to the position deviation of the hanging basket to ensure its precise positioning.

[0127] Specifically, the real-time feedback system includes multiple high-precision sensors and monitoring devices, such as lidar, vision sensors, accelerometers, gyroscopes, etc. Lidar can provide precise distance data between the hanging basket and the target position, while vision sensors can capture the angular differences between the hanging basket and the target. Accelerometers and gyroscopes are used to monitor the dynamic motion state of the hanging basket, including speed, acceleration, and rotation angle. All this data is processed in real time through sensor fusion technology to form precise correction results and provide feedback suggestions for the dynamic adjustment of the hanging basket.

[0128] As an option, the real-time feedback system not only monitors the position but can also adjust the speed and acceleration parts in the control input through integrated dynamic response analysis. For example, during the correction process, if a rapid change in the dynamic response of the hanging basket (such as oscillation) is detected, the system will automatically reduce the correction speed or change the correction strategy to avoid deviations caused by overcorrection of the hanging basket. By introducing control terms for speed and acceleration, the system can avoid rapid dynamic changes during the correction of the hanging basket, ensuring a smooth and oscillation-free correction process.

[0129] In some embodiments, to further improve the accuracy and intelligence of feedback, the real-time feedback system can be used in combination with a deep learning model to predict possible future errors through the deep learning model. The deep learning model can predict the future deviation trend of the hanging basket position based on historical data and real-time input, and dynamically adjust the control input to further optimize the correction path. This intelligent feedback mechanism can greatly improve the adaptability of the system in complex environments and reduce errors in the correction process.

[0130] In a possible implementation, the real-time feedback mechanism in step S6 is combined with the non-linear optimization objective function in steps S3 and S4. By dynamically updating the parameters in the optimization objective function, the accuracy and robustness of the control strategy are further improved. For example, when the real-time feedback system detects the deviation between the hanging basket and the target position, the feedback signal will affect the position error term in the objective function, thereby adjusting the control input in the optimization process. This dynamic adjustment mechanism enables the system to better cope with the dynamic changes at the construction site and optimize the correction path in real time at each correction step.

[0131] By integrating a dynamic control function into the real-time feedback system, the system can adjust the control strategy according to the real-time feedback after each correction. The feedback signal plays a crucial role in this process. By providing data such as position, attitude, speed, and acceleration, the system can adjust the parameters in the objective function in real time to ensure that the correction process finds a balance between accuracy and efficiency.

[0132] Specifically, the real-time feedback signal affects the correction strategy through the following steps:

[0133] Calculate the error between the current position and the target position to generate a feedback signal.

[0134] Input the feedback signal into the control system and determine whether to adjust the correction strategy according to the magnitude of the error.

[0135] Update the corresponding terms in the optimization objective function (such as the position error term, control energy consumption term, etc.) to dynamically optimize the correction path.

[0136] If the current correction does not reach the target accuracy, recalculate the optimal correction input and perform a new correction operation.

[0137] This closed-loop control mechanism ensures that the system can adjust the control input according to real-time data after each correction, avoiding error accumulation and overcorrection, and maintaining the efficiency and accuracy of the correction process.

[0138] In a further implementation, step S6 may involve the extension of the objective function to incorporate dynamic control with real-time feedback. This extended objective function will not only be limited to minimizing the position error but may also incorporate controls for speed, acceleration, and environmental factors.

[0139] Through the dynamic adjustment of the real-time feedback system and the control strategy, step S6 ensures the accuracy and efficiency of the hanging basket correction operation. The real-time feedback system continuously collects the dynamic data of the hanging basket and adjusts the control input in real time based on this data to optimize the correction path. By introducing the feedback signal into the dynamic update of the objective function, the system can accurately adjust the position, speed, and acceleration of the hanging basket in each correction step to ensure that the hanging basket is always in the predetermined target position. In addition, the system also ensures stable and efficient correction operations in complex construction environments through environmental adaptability control. This process guarantees the high precision, automation, and safety of the installation of the bridge hanging basket.

[0140] Please refer to Figure 2 , the present invention also provides an automated precise positioning operating system for the installation of a bridge hanging basket, including:

[0141] A high-precision sensor and image acquisition system for real-time acquisition of the position, attitude, and environmental data of the hanging basket;

[0142] The task of the high-precision sensor and image acquisition system is to collect the position information, attitude information, and data of the construction environment of the hanging basket in real time to ensure precise monitoring and dynamic adjustment of the position of the hanging basket throughout the construction process.

[0143] This module plays a crucial role in the entire automated system. It provides the basic input data for the subsequent deep learning module and optimization module. Through the collaborative work of sensors and imaging devices, the high-precision sensor and image acquisition system can provide information in multiple dimensions for the system, including position, attitude, speed, acceleration, etc. The precise acquisition of this information is the prerequisite for ensuring that the system can judge the state and dynamic deviation of the hanging basket in real time and accurately.

[0144] LiDAR: LiDAR accurately measures the distance to the target object by emitting laser beams and receiving the reflected signals, and can effectively calculate the position and movement trajectory of the hanging basket in three-dimensional space. By real-time monitoring the distance changes between the hanging basket and the surrounding environment, LiDAR provides precise real-time positioning data for the system.

[0145] Total station: The total station combines laser ranging and angle measurement to accurately measure the attitude and angle of the hanging basket, thereby helping the system to finely adjust the posture of the hanging basket. This device is crucial for measuring the position of the hanging basket with high precision.

[0146] Accelerometers and gyroscopes: These sensors can monitor the dynamic state of the hanging basket in real time, providing measurement data of acceleration and angular velocity. This information is crucial for real-time judgment of the stability, movement trend, and adjustment plan of the hanging basket, especially during the construction process when the position and attitude of the hanging basket are constantly changing.

[0147] Vision sensors (such as cameras): Vision sensors are used to collect image information of the hanging basket and its surrounding environment. Through image processing technology, spatial position information and attitude information of the hanging basket can be obtained, providing data support for the deep learning model. Especially in a complex construction environment, the vision system can assist the system in identifying the surrounding environment and making decisions.

[0148] Deep learning module, including convolutional neural network and recurrent neural network, for real-time identifying the position of the hanging basket and predicting future deviations;

[0149] The deep learning module is responsible for analyzing the data provided by the sensors and the image acquisition system, and making real-time estimations of the position and angle of the hanging basket, and predicting future possible deviation trends, providing data support for the subsequent optimization module.

[0150] The deep learning module is the core part of the entire system. It can make real-time predictions and estimations of the position and dynamic deviations of the hanging basket by processing complex image and time-series data. By using convolutional neural network (CNN) and recurrent neural network (RNN), this module realizes the accurate identification of the position and dynamic behavior of the hanging basket. Its superiority lies in its ability to adapt to different environments and scenarios and its high fault tolerance.

[0151] Convolutional neural network (CNN): Through multiple convolutional layers, pooling layers, and fully connected layers, CNN can effectively extract spatial features from the input images. For the identification of the hanging basket, CNN can accurately capture the shape, position, and attitude information of the hanging basket under various conditions such as complex backgrounds, changing lighting, and occlusion. It is especially suitable for processing image data and providing accurate visual feedback for the system.

[0152] Recurrent neural network (RNN): RNN is the key to processing time-series data. It can predict the deviation trend within a certain period in the future based on the past state of the hanging basket. In actual operation, RNN predicts the future state according to historical time-series data such as acceleration, speed, and angle changes, and provides accurate pre-judgment information for the optimization objective function, reducing delay correction.

[0153] Nonlinear optimization module, for calculating the optimal control input in real time according to the optimization objective function and making corrections;

[0154] The non - linear optimization module, based on the data output provided by the deep - learning module, constructs an optimization objective function to calculate and output the optimal corrective control input in real - time, ensuring that the hanging basket is accurately aligned with the target position.

[0155] The optimization module is an important bridge connecting the deep - learning module and the execution system. It converts the state of the hanging basket identified and predicted in the deep - learning module into actual control instructions. This module ensures that the balance between precision and the consumption of corrective energy is maintained during the adjustment of the hanging basket, preventing over - correction.

[0156] The optimization objective function is based on position error terms, energy consumption terms of the corrective input, and possible dynamic change terms (such as the acceleration and velocity of the hanging basket, etc.). The aim is to minimize the error between the hanging basket and the target position and ensure the rationality of energy consumption. The system usually uses optimization algorithms such as gradient descent method, Newton's method, quasi - Newton method, etc. to calculate the optimal corrective input.

[0157] By adjusting the regularization coefficient in the optimization function, the system can flexibly control the balance between precision and energy consumption during the correction process. The optimization module adjusts the control input according to the real - time data output to correct the deviation of the hanging basket as precisely as possible without wasting too much energy.

[0158] The execution system is used to automatically adjust the position and angle of the hanging basket according to the optimization instructions;

[0159] The execution system is responsible for receiving the control instructions calculated by the optimization module and precisely adjusting the position and angle of the hanging basket through automated equipment to ensure that the hanging basket is accurately aligned with the target.

[0160] The execution system is the final execution unit for achieving the precise positioning of the hanging basket. It converts the optimization instructions into physical actions through automated equipment. A precise execution system can maximize the efficiency of the correction process and ensure that each correction meets the target requirements.

[0161] Automated Guided Vehicle (AGV): When the optimization instructions require adjusting the spatial position of the hanging basket, the AGV will accurately move the hanging basket to the target position according to the control input instructions. The AGV system uses precise positioning and path - planning technologies to ensure the fast and accurate movement of the hanging basket near the target position.

[0162] Robotic arm: If the correction instructions require adjusting the attitude (such as angle) of the hanging basket, the robotic arm will perform precise attitude adjustment under the guidance of the optimization input. The flexibility and high precision of the robotic arm make it an essential component during the installation process.

[0163] Hydraulic control system: For some specific correction operations (such as adjustments requiring large torques), the hydraulic system can provide sufficient power support. The hydraulic control system, in cooperation with sensor feedback, ensures the precise operation of the hanging basket during the correction process.

[0164] A real-time feedback system is used to compare with the target position based on the correction result and adjust the control strategy in real time.

[0165] The real-time feedback system is used to compare the position, attitude of the hanging basket and the effect of the correction operation with the target position, and adjust the control strategy in real time according to the correction result.

[0166] The real-time feedback system ensures that each correction operation can be verified by providing real-time data support. Through the rapid feedback of the correction result, the system can immediately adjust the correction strategy when an error is found, thereby avoiding the accumulation of errors and ensuring high-precision correction.

[0167] Real-time data acquisition and monitoring: The real-time feedback system monitors every detail of the hanging basket during the correction process through multiple sensors such as lidar, cameras, accelerometers, etc. The system continuously calculates the error between the position of the hanging basket and the target position, and generates a real-time feedback signal when a deviation is detected.

[0168] Environmental adaptation and dynamic adjustment: The real-time feedback system not only pays attention to the position of the hanging basket, but also can adjust the correction strategy according to changes in the environment (such as wind speed, temperature, etc.). The system will monitor the changes in the construction environment in real time and optimize the correction strategy in a timely manner according to the influence of the external environment to cope with different construction challenges.

[0169] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. The automatic operation method for precise positioning of bridge hanging basket installation is characterized in that, It includes the following steps: By installing high-precision sensors and a vision system, real-time acquisition of image data on the position, speed, attitude of the bridge hanging basket and the construction environment is carried out; Using a deep learning model to analyze the acquired image data to identify and estimate the spatial position and angle of the hanging basket; According to the output of the deep learning model, a non-linear optimization objective function is constructed, and by minimizing the position deviation and the energy consumption of the control input, an optimal correction strategy is calculated; Using a non-linear optimization algorithm to adjust the control input in real time to correct the deviation of the hanging basket; Through an automatic execution system, the correction instructions are executed in real time to adjust the position and angle of the hanging basket; Compare the correction result with the target position, and give real-time feedback and adjust the control strategy.

2. The automated operation method for precise positioning of bridge hanging basket installation according to claim 1, characterized in that, The high-precision sensors include the following devices: LiDAR, which is used to measure the position of the hanging basket in three-dimensional space in real time. By emitting laser and receiving the reflected signal, the relative position of the hanging basket and the surrounding environment can be accurately obtained. Total station, which is used to accurately measure the angle and attitude of the hanging basket, and combines laser ranging and angle measurement to provide high-precision position and attitude data. Accelerometer and gyroscope. The accelerometer monitors the acceleration of the hanging basket, and the gyroscope is used to measure the angular velocity; The vision system acquires the environmental data around the hanging basket through a camera or other imaging devices, including at least illumination and surrounding obstacles, provides visual information related to the environment, and supports the analysis of the deep learning module.

3. The automated operation method for precise positioning of bridge hanging baskets according to claim 1, characterized in that, The optimization objective function obtains an optimal control strategy by minimizing the position deviation and the power consumption of the correction control input; The optimization objective function is: Among them, J represents the optimization objective function; T represents the total number of time steps in the optimization process; t is the time step, from t = 0 to t = T; X(t) is the position vector of the hanging basket at time t; X target is the predetermined target position; u(t) is the control input; ∥X(t)-X target ∥ 2 represents the squared error between the position of the hanging basket and the target position; λ is the regularization parameter, used to control the balance between the energy consumption of the control input and the position error; ∥u(t)∥ 2 represents the squared energy consumption of the control input.

4. The automated operation method for precise positioning of bridge hanging basket installation according to claim 1, characterized in that, The deep learning model includes a convolutional neural network and a recurrent neural network, which are used to identify the position of the hanging basket and predict the deviation trend respectively.

5. The automated operation method for precise positioning of the bridge hanging basket installation according to claim 1, characterized in that The steps of the non-linear optimization algorithm include: According to the position deviation data of the hanging basket output by the deep learning model, a non-linear optimization objective function is constructed; Select the gradient descent method and the Newton method as the optimization algorithms to calculate the optimal correction control input; By calculating the gradient of the objective function, the control input is adjusted in real time to minimize the position deviation and the control energy consumption; During the iterative optimization process, the control input is continuously updated according to the real-time feedback; The optimized control input is used for the automatic execution system to adjust the actual position and angle of the hanging basket.

6. The automated operation method for precise positioning of the bridge hanging basket installation according to claim 1, characterized in that, The steps of the automatic execution system include: According to the optimized control input, corresponding correction instructions are generated; Using automatic equipment to execute the correction instructions to adjust the position and angle of the hanging basket; Verify the correction effect of the hanging basket through a real-time monitoring system; According to the real-time feedback data, further adjust the execution strategy; After the correction of the hanging basket is completed, the automatic execution system enters the standby state, ready for the next round of correction operation.

7. The automated operation method for precise positioning of the bridge hanging basket installation according to claim 1, characterized in that, The steps of the real-time feedback and adjustment of the control strategy include: Real-time monitoring of the current position and attitude of the hanging basket through sensors and the vision system; Compare the actual position with the target position, calculate the deviation and generate a feedback signal; Input the feedback signal into the control system to adjust the control input and optimize the correction path of the hanging basket; According to the feedback result, adjust the control strategy in real time to continuously correct the position and angle of the hanging basket; After ensuring that the hanging basket reaches the predetermined target position, stop the adjustment and complete the correction process.

8. The automated operation method for precise positioning of bridge hanging basket installation according to claim 1, characterized in that, The deep learning network enhances the adaptability of the system in an uncertain environment through a generative adversarial network, simulating data under different lighting and wind speed environmental conditions.

9. The automated operation method for precise positioning of bridge hanging basket installation according to claim 1, characterized in that, The correction strategy performs closed-loop control through real-time feedback and adjustment, and is used to keep the hanging basket at a predetermined target position during the installation process. The real-time feedback and adjustment include: Real-time monitoring of the current position and attitude of the hanging basket through sensors and a vision system; Comparing the actual position with the target position, calculating the deviation and generating a feedback signal; Inputting the feedback signal into the control system, adjusting the control input, and optimizing the correction path of the hanging basket; Real-time adjusting the control strategy according to the feedback result, continuously correcting the position and angle of the hanging basket; Used to stop the adjustment after the hanging basket reaches the predetermined target position and complete the correction process.

10. An automated operating system for precise positioning of bridge hanging baskets, which is applied to the automated operating method for precise positioning of bridge hanging baskets as described in any one of claims 1-9, and is characterized in that, Including: A high-precision sensor and an image acquisition system for real-time acquisition of the position, attitude and environmental data of the hanging basket; A deep learning module, including a convolutional neural network and a recurrent neural network, for real-time identification of the hanging basket position and prediction of future deviations; A non-linear optimization module for real-time calculation of the optimal control input according to the optimization objective function and correction; An execution system for automatically adjusting the position and angle of the hanging basket according to the optimization instruction; A real-time feedback system for comparing the target position with the correction result and real-time adjusting the control strategy.

Images