A bridge pier posture automatic deviation correction method and system based on multi-source sensor fusion and hydraulic servo linkage

Abstract

This invention discloses an automatic attitude correction method and system for bridge piers based on multi-source sensor fusion and hydraulic servo linkage, relating to the field of bridge engineering technology. The method includes collecting attitude data of bridge piers through multi-source sensors and fusing the sensor data into unified attitude data; using the unified attitude data as input to adjust the control parameters of a hydraulic servo device; performing fault detection and early warning based on the working status of the hydraulic servo device and environmental data; and adjusting the working modes of the sensors and the hydraulic servo device based on the detection results. The method described in this invention achieves better results in terms of attitude control accuracy, response speed, system reliability, and adaptability.

Description

Technical Field

[0001] This invention relates to the field of bridge engineering technology, specifically to a method and system for automatic posture correction of bridge piers based on multi-source sensor fusion and hydraulic servo linkage. Background Technology

[0002] Currently, bridge pier attitude monitoring technology largely relies on traditional sensors to collect pier attitude data in real time. These sensors monitor the tilt angle, horizontal displacement, and verticality of bridge piers through data collection.

[0003] However, a single sensor cannot fully reflect the condition of bridge piers, and sensor data is often interfered with in high-vibration environments or complex weather conditions, resulting in inaccurate data and affecting the reliability of judgment and the accuracy of adjustment.

[0004] Traditional methods for adjusting the attitude of bridge piers mainly rely on manual intervention of mechanical structures or fixed control schemes. Manual intervention is not only labor-intensive but also slow in response and difficult to adapt to the needs of real-time dynamic changes. Fixed control schemes have poor adjustment accuracy and adaptability and cannot effectively cope with changes in complex environments or sudden events.

[0005] Existing hydraulic servo systems still have some drawbacks. First, their control algorithms usually rely on traditional PID control, which makes it difficult to guarantee accuracy and response speed in dynamic and complex environments.

[0006] Secondly, hydraulic servo systems are highly sensitive to environmental changes, and when sensors malfunction, manual maintenance is still required to switch sensors or adjust control strategies, resulting in low system reliability and stability. Summary of the Invention

[0007] In view of the above-mentioned problems, the present invention is proposed.

[0008] Therefore, the technical problem solved by the present invention is that existing bridge pier posture adjustment methods have problems such as low control accuracy, slow response speed, and inability to effectively cope with environmental changes and sensor failures.

[0009] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an automatic posture correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage, comprising collecting posture data of bridge piers through multi-source sensors and fusing the sensor data into unified posture data.

[0010] Using uniform attitude data as input, the control parameters of the hydraulic servo device are adjusted.

[0011] Fault detection and early warning are performed based on the working status and environmental data of the hydraulic servo device, and the working mode of the sensor and hydraulic servo device is adjusted according to the detection results.

[0012] The fusion into unified attitude data includes fusing sensor data using deep learning algorithms and fusion algorithms.

[0013] Adjusting the control parameters of the hydraulic servo device includes calculating the attitude error and correction amount, adjusting the attitude error according to the correction amount, and using the attitude error as a reward signal input through a reinforcement learning algorithm to dynamically optimize the control parameters of the hydraulic servo device.

[0014] As a preferred embodiment of the automatic attitude correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage described in this invention, the method for collecting the attitude data of the bridge piers includes collecting key position information of the bridge piers from a large database.

[0015] Based on the key location information of the bridge beams and piers, multiple sensors are installed at multiple key locations of the target bridge piers to collect the pier attitude data in real time.

[0016] The sampling period for each sensor is set to 100ms, and the attitude data is transmitted to the computing device via a communication protocol.

[0017] A data cleaning algorithm is used to denoise the collected attitude data.

[0018] The processed attitude data is converted into a standardized format and output.

[0019] As a preferred embodiment of the automatic posture correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage described in this invention, the fusion of sensor data includes sorting according to the characteristics of the time series and performing standardization processing.

[0020] The pose data is processed by a deep learning model, which uses a convolutional neural network to learn and extract features from real-time pose data from multiple sensors.

[0021] A deep learning model is used to perform multi-level analysis of real-time attitude data from multiple sensors, and feature selection is performed based on the analysis results.

[0022] The real-time attitude data from multiple sensors after filtering are fused into unified attitude data.

[0023] As a preferred embodiment of the automatic posture correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage described in this invention, the step of adjusting the posture error according to the correction amount includes taking the ideal posture specified in the bridge design as the target posture.

[0024] The attitude error is calculated by comparing the fused unified attitude data with the target attitude.

[0025] The correction amount is set according to the actual impact of external environmental factors on bridge piers.

[0026] The attitude error is corrected based on the correction amount.

[0027] The actual impacts include temperature, humidity, and wind speed.

[0028] As a preferred embodiment of the automatic attitude correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage described in this invention, the dynamic optimization of the control parameters of the hydraulic servo device includes taking the attitude error as input and using a reinforcement learning algorithm to take the attitude error as a reward signal input.

[0029] The reinforcement learning model adjusts the control strategy of the hydraulic servo device based on the feedback error signal.

[0030] Reinforcement learning models learn by comparing with historical data and gradually optimize control parameters.

[0031] The control parameters include hydraulic oil pressure, flow rate, and valve opening.

[0032] The optimal control parameters calculated each time are transmitted to the hydraulic servo device in real time.

[0033] As a preferred embodiment of the automatic posture correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage described in this invention, the fault detection and early warning includes real-time monitoring of sensor data and the working status of the hydraulic servo device.

[0034] The data from each sensor is analyzed using a fault detection algorithm.

[0035] When fluctuations in sensor data are detected exceeding At that time, by comparing historical data with real-time data, it is possible to identify and determine whether a fault exists.

[0036] The working status of the hydraulic servo device is checked in real time by measuring the hydraulic oil pressure, flow rate, and temperature to ensure it does not exceed the operating range.

[0037] When the sensor or hydraulic servo device detects a malfunction, it issues a corresponding warning signal.

[0038] Choose a response strategy based on the corresponding warning signal.

[0039] As a preferred embodiment of the automatic posture correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage described in this invention, the adjustment of the working modes of the sensors and hydraulic servo devices includes adjusting the working modes of the sensors and hydraulic servo devices according to the output response strategy.

[0040] When a sensor fails, a backup sensor is activated, the data fusion algorithm is recalibrated, the data acquisition frequency is adjusted, and the sensor's operating mode is optimized.

[0041] When the hydraulic servo device fails, switch to the backup device and adjust the control strategy. Also, dynamically adjust the working mode of the hydraulic servo device according to changes in external environmental factors.

[0042] Adjusting the operating mode of the hydraulic servo device includes adjusting the viscosity, flow rate, and pressure of the hydraulic oil to ensure stable operation of the hydraulic servo device when environmental conditions change.

[0043] Another objective of this invention is to provide an automatic attitude correction system for bridge piers based on multi-source sensor fusion and hydraulic servo linkage. This system can fuse sensor data through deep learning algorithms and optimize hydraulic servo control strategies by combining reinforcement learning. This solves the problems of slow response speed, low control accuracy, and inability to cope with environmental changes and sensor failures in current traditional sensor fusion and hydraulic servo system control technologies.

[0044] As a preferred embodiment of the bridge pier attitude automatic correction system based on multi-source sensor fusion and hydraulic servo linkage described in this invention, it includes a data acquisition and fusion module, an attitude control optimization module, and a fault detection and early warning module.

[0045] The data acquisition and fusion module is used to acquire attitude data of bridge piers through multi-source sensors and fuse the sensor data into unified attitude data.

[0046] The attitude control optimization module is used to take uniform attitude data as input and adjust the control parameters of the hydraulic servo device.

[0047] The fault detection and early warning module is used to detect and warn of faults based on the working status of the hydraulic servo device and environmental data, and adjust the working mode of the sensor and the hydraulic servo device according to the detection results.

[0048] Another objective of this invention is to provide an automatic attitude correction device for bridge piers based on multi-source sensor fusion and hydraulic servo linkage, comprising a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the automatic attitude correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage.

[0049] Another objective of this invention is to provide a storage medium for automatic attitude correction of bridge piers based on multi-source sensor fusion and hydraulic servo linkage, wherein a computer program is stored thereon, and when the computer program is executed by a processor, it implements the steps of the method for automatic attitude correction of bridge piers based on multi-source sensor fusion and hydraulic servo linkage.

[0050] The beneficial effects of this invention are as follows: The automatic attitude correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage provided by this invention significantly improves the accuracy and reliability of data fusion by fusing multi-source sensor data through deep learning algorithms; it effectively improves the accuracy and response speed of attitude adjustment by optimizing the control parameters of the hydraulic servo device through reinforcement learning; and it ensures that the system can automatically switch working modes to maintain the stability and safety of the bridge piers through fault detection and early warning mechanisms. This invention achieves better results in terms of attitude control accuracy, response speed, system reliability, and adaptability. Attached Figure Description

[0051] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 The above is an overall flowchart of an automatic posture correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage, provided in Embodiment 1 of the present invention. Detailed Implementation

[0053] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0054] Example 1, referring to Figure 1 As an embodiment of the present invention, a method for automatic attitude correction of bridge piers based on multi-source sensor fusion and hydraulic servo linkage is provided, comprising:

[0055] S1: Collect attitude data of bridge piers through multi-source sensors and fuse the sensor data into unified attitude data.

[0056] Key location information of bridge piers is collected from a large database. Based on the key location information of the bridge beams and piers, multiple sensors are installed at multiple key locations of the target bridge piers to collect the attitude data of the piers in real time.

[0057] A preferred approach for collecting key location information of bridge piers from large databases is as follows:

[0058] By employing Geographic Information System (GIS) and Building Information Modeling (BIM) technologies, key location information of target bridge piers is extracted by querying bridge structure information in a database.

[0059] The key location information of the target bridge pier includes the installation locations of each sensor and the geometric features of the bridge pier.

[0060] The sensors include tilt sensors, accelerometers, GPS positioning sensors, and laser rangefinders.

[0061] One preferred solution for the key position is:

[0062] Support point, center point, stress point.

[0063] The sampling period for each sensor is set to 100ms, and the attitude data is transmitted to the computing device via a communication protocol.

[0064] A data cleaning algorithm is used to denoise the collected attitude data.

[0065] A preferred approach for noise reduction is:

[0066] Remove outliers and noisy data from the collected attitude data.

[0067] The processed attitude data is converted into a standardized format and output.

[0068] A preferred solution for converting to a standardized format is:

[0069] Standardized formats are achieved through Min-Max normalization.

[0070] Furthermore, the data is sorted according to the characteristics of the time series and then standardized.

[0071] The pose data is processed by a deep learning model, which uses a convolutional neural network to learn and extract features from real-time pose data from multiple sensors.

[0072] A deep learning model is used to perform multi-level analysis of real-time attitude data from multiple sensors, and feature selection is performed based on the analysis results.

[0073] The real-time attitude data from multiple sensors after filtering are fused into unified attitude data.

[0074] S2: Use uniform attitude data as input to adjust the control parameters of the hydraulic servo device.

[0075] The fusion into unified attitude data includes fusing sensor data using deep learning algorithms and fusion algorithms.

[0076] A preferred approach for fusing sensor data is as follows:

[0077] Using convolutional neural networks for feature extraction from time-series data, especially for the fusion of spatial and temporal features of multi-sensor data.

[0078] For sensor data that changes significantly with dynamics, a long short-term memory network is used to further process the temporal relationships of the sensor data in order to improve the accuracy of data fusion.

[0079] Through multi-layer convolution and temporal dependency processing, the fused data will serve as unified attitude data for bridge piers, providing accurate input for subsequent attitude error calculation.

[0080] Adjusting the control parameters of the hydraulic servo device includes calculating the attitude error and correction amount, adjusting the attitude error according to the correction amount, and using the attitude error as a reward signal input through a reinforcement learning algorithm to dynamically optimize the control parameters of the hydraulic servo device.

[0081] A preferred scheme for dynamically optimizing the control parameters of a hydraulic servo device is as follows:

[0082] in, This represents the original attitude error. This represents the actual attitude data after sensor data fusion. coordinate, Indicates the target attitude coordinate, This represents the actual attitude data after sensor data fusion. coordinate, Indicates the target attitude coordinate, This represents the actual attitude data after sensor data fusion. coordinate, Indicates the target attitude coordinate.

[0083] Furthermore, the ideal posture specified in the bridge design is taken as the target posture.

[0084] The attitude error is calculated by comparing the fused unified attitude data with the target attitude.

[0085] A preferred method for calculating attitude error is:

[0086] When calculating the attitude error, the ideal attitude of the bridge design is considered as the target attitude. The error value is obtained by calculating the difference between the target attitude and the unified attitude data collected in real time.

[0087] The error was calculated using a weighted average method, taking into account the impact of changes in the external environment on the bridge piers during the error calculation process.

[0088] This error value serves as input for subsequent control, and the hydraulic servo device is adjusted based on real-time data.

[0089] The correction amount is set according to the actual impact of external environmental factors on the bridge piers, and the calculated attitude error is corrected according to the correction amount.

[0090] A preferred method for setting the correction amount is:

[0091]

[0092] in, Indicates the correction amount. A coefficient representing temperature. A coefficient representing humidity. A coefficient representing wind force. Indicates temperature. Indicates humidity. Indicates wind force.

[0093] First, determine the representative parameter, specifically: temperature changes cause materials to expand or contract, and the amount of expansion caused by temperature changes can be calculated using the coefficient of thermal expansion.

[0094] Changes in humidity can affect the volume of materials such as wood and reinforced concrete. The hygroscopic coefficient of a material can be used to quantitatively describe the impact of humidity on bridge structures.

[0095] The effects of wind can cause changes in the stress on the bridge surface, and the influence of wind on the bridge's attitude can be analyzed using mechanical models.

[0096] By establishing finite element models of bridge piers under different environmental conditions, numerical simulations are conducted to obtain the degree of influence of various environmental factors on the attitude of bridge piers.

[0097] The environmental factor coefficients were determined based on the results of multiple simulations.

[0098] One preferred approach for determining environmental factor coefficients is:

[0099] A finite element model of the bridge pier was created using the computer simulation software ANSYS, and environmental factors such as temperature, humidity, and wind force were incorporated into the model.

[0100] Simulations were run under different environmental conditions to record attitude changes. The influence of environmental factors on attitude changes was extracted from the simulation results, and environmental factor coefficients were calculated.

[0101] A preferred approach for correcting the attitude error calculated based on the correction amount is as follows:

[0102]

[0103] in, This represents the final attitude error.

[0104] The actual impacts include temperature, humidity, and wind speed.

[0105] Furthermore, the pose error is used as input, and a reinforcement learning algorithm is used to input the pose error as a reward signal.

[0106] It should be noted that while attitude error is the core of the reward signal, the calculation of the reward signal does not solely depend on the error value itself. It also needs to consider factors such as error convergence speed, control response time, and the stability of the hydraulic servo device, so as to more comprehensively reflect the optimization goal of the system.

[0107] Error convergence rate includes calculating the error convergence rate by observing the rate of change of attitude error over time.

[0108] When the system error converges to zero quickly, it indicates that the adjustment process is efficient and the reward value should be increased.

[0109] The system's response time is incorporated into the reward function; the shorter the response time, the greater the reward value.

[0110] The reinforcement learning model adjusts the control strategy of the hydraulic servo device based on the feedback error signal.

[0111] Reinforcement learning models learn by comparing with historical data and gradually optimize control parameters.

[0112] The control parameters include hydraulic oil pressure, flow rate, and valve opening.

[0113] The optimal control parameters calculated each time are transmitted to the hydraulic servo device in real time.

[0114] One preferred method for calculating the optimal control parameters is:

[0115] The hydraulic oil pressure, flow rate, valve opening, and other control parameters are optimized and calculated using a deep Q-network model.

[0116] The optimization goal is to minimize attitude error and ensure optimal response speed and accuracy of the hydraulic servo device.

[0117] It should be noted that the inputs to deep learning models and reinforcement learning models include uniform pose data, target pose data, external environment data, and time step.

[0118] The state space is composed of unified attitude data, target attitude data, external environment data, and time step.

[0119] The outputs mainly include attitude error, correction amount, control parameters of hydraulic servo device, and reward signal. These output results are used to accurately control the attitude of bridge piers.

[0120] S3: Perform fault detection and early warning based on the working status of the hydraulic servo device and environmental data, and adjust the working mode of the sensor and hydraulic servo device according to the detection results.

[0121] Real-time monitoring of sensor data and the working status of the hydraulic servo device, and analysis of data from each sensor through fault detection algorithms.

[0122] When fluctuations in sensor data are detected exceeding At that time, by comparing historical data with real-time data, it is possible to identify and determine whether a fault exists.

[0123] The working status of the hydraulic servo device is checked in real time by measuring the hydraulic oil pressure, flow rate, and temperature to ensure it does not exceed the operating range.

[0124] When a sensor or hydraulic servo device detects a malfunction, it issues a corresponding warning signal and selects a response strategy based on the warning signal.

[0125] Furthermore, the operating modes of the sensors and hydraulic servo devices are adjusted based on the output response strategy.

[0126] When a sensor fails, a backup sensor is activated, the data fusion algorithm is recalibrated, the data acquisition frequency is adjusted, and the sensor's operating mode is optimized.

[0127] When the hydraulic servo device fails, switch to the backup device and adjust the control strategy. Also, dynamically adjust the working mode of the hydraulic servo device according to changes in external environmental factors.

[0128] Adjusting the operating mode of the hydraulic servo device includes adjusting the viscosity, flow rate, and pressure of the hydraulic oil to ensure stable operation of the hydraulic servo device when environmental conditions change.

[0129] Example 2 is an embodiment of the present invention, which provides an automatic posture correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiment.

[0130] First, using Geographic Information System (GIS) and Building Information Modeling (BIM) technologies, key location information of the target bridge piers is collected from a large database, including the installation locations of sensors and the geometric features of the bridge piers.

[0131] Based on this key information, sensors, including tilt sensors, accelerometers, GPS positioning sensors, and laser rangefinders, were installed at multiple key locations such as the support points, center points, and stress points of the target bridge piers.

[0132] After the sensors are installed, they collect attitude data of the bridge piers in real time by setting the sampling period to 100ms. The sensor data is transmitted to the computing device via a communication protocol, and the collected data is processed using data cleaning algorithms to remove outliers and noise.

[0133] The processed attitude data is standardized and formatted for further use in data fusion.

[0134] The processed data from multiple sensors is input into a deep learning model, and a convolutional neural network is used to extract features from the time-series data, especially in the fusion of spatial and temporal features.

[0135] For sensor data that changes significantly with dynamics, a long short-term memory network is used for time-series processing to further improve the accuracy of data fusion.

[0136] Finally, through multi-level analysis and feature selection using deep learning models, unified pose data was obtained.

[0137] The attitude error is calculated by comparing the fused unified attitude data with the target attitude specified in the design.

[0138] When calculating the error, the actual impact of external environmental factors on the bridge piers is taken into account, a correction amount is set, and the attitude error is adjusted according to the correction amount.

[0139] The control parameters of the hydraulic servo device are optimized by using a reinforcement learning algorithm to input the attitude error as a reward signal.

[0140] The optimized control parameters include hydraulic oil pressure, flow rate, and valve opening, ensuring that the hydraulic servo device can accurately adjust the posture of the bridge piers.

[0141] With real-time monitoring of sensor data and hydraulic servo devices, the fault detection algorithm analyzes the fluctuations in sensor data.

[0142] When the fluctuation of sensor data exceeds a preset threshold, the system will identify and determine whether a fault exists by comparing historical data with real-time data.

[0143] If a sensor malfunction is detected, the system will automatically activate the backup sensor and recalibrate the data fusion algorithm. If the hydraulic servo device malfunctions, the system will switch to the backup device and adjust the control strategy to maintain the stable attitude of the bridge. Specific experimental data are shown in Table 1.

[0144] test subjects Temperature (°C) humidity(%) Wind speed (m / s) Original attitude error (°) Correction amount (°) Final attitude error (°) Bridge pier posture adjustment system 15 50 2 0.5 0.02 0.52 Bridge pier posture adjustment system 20 55 4 0.3 0.03 0.33 Bridge pier posture adjustment system 25 60 6 0.6 0.05 0.65 Bridge pier posture adjustment system 30 65 8 0.4 0.06 0.46 Bridge pier posture adjustment system 35 70 10 0.7 0.08 0.78 Bridge pier posture adjustment system 40 75 12 0.5 0.1 0.6

[0145] The data in the table shows the changes in bridge pier attitude error under different environmental conditions. A detailed analysis follows:

[0146] Original attitude error: The original attitude error fluctuates to some extent as temperature, humidity and wind force increase.

[0147] For example, the original attitude error was 0.6° at a temperature of 25°C, but increased to 0.7° at a temperature of 35°C, indicating that environmental factors affected the attitude.

[0148] Correction amount: The correction amount is set based on environmental factors (temperature, humidity, and wind speed). As the environment changes, the correction amount also increases.

[0149] For example, when the temperature is 40°C, the correction is 0.10°, which is significantly larger than the 0.02° when the temperature is 15°C.

[0150] This reflects the effect of temperature on bridge attitude, and the introduction of correction ensures the accuracy of the final attitude error.

[0151] Final attitude error: The final attitude error is obtained by adding the original attitude error to the correction amount. By adjusting the correction amount, the final attitude error is effectively controlled.

[0152] For example, the final attitude error is 0.65° at a temperature of 25°C, and 0.60° at a temperature of 40°C.

[0153] This indicates that the system can effectively reduce attitude error by calculating the correction amount.

[0154] Environmental adaptability: By taking into account environmental factors such as temperature, humidity and wind, the system can dynamically adjust attitude errors to ensure the stability of bridge piers.

[0155] Data processing and optimization: The introduction of deep learning models and reinforcement learning algorithms enables attitude data fusion and hydraulic servo control to adaptively optimize control parameters, thereby improving the system's accuracy and response speed.

[0156] Adaptive fault handling: When a sensor or hydraulic servo device malfunctions, the system can automatically switch to backup equipment and make adaptive adjustments to ensure the stability and continuous operation of the system.

[0157] Compared with existing technologies, this invention demonstrates significant advantages in attitude adjustment accuracy, response speed, and environmental adaptability. Its innovation lies in integrating deep learning, reinforcement learning, and real-time environmental factors, overcoming the limitations of traditional bridge attitude control methods.

[0158] Example 3, an embodiment of the present invention, provides an automatic attitude correction system for bridge piers based on multi-source sensor fusion and hydraulic servo linkage, including a data acquisition and fusion module, an attitude control optimization module, and a fault detection and early warning module.

[0159] The data acquisition and fusion module is used to collect attitude data of bridge piers through multi-source sensors and fuse the sensor data into unified attitude data.

[0160] The attitude control optimization module is used to take uniform attitude data as input and adjust the control parameters of the hydraulic servo device.

[0161] The fault detection and early warning module is used to detect and warn of faults based on the working status of the hydraulic servo device and environmental data, and adjust the working mode of the sensor and the hydraulic servo device according to the detection results.

[0162] This embodiment also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the automatic posture correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage proposed in the above embodiment.

[0163] This embodiment also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the automatic posture correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage proposed in the above embodiment.

[0164] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0165] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0166] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0167] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0168] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for automatic attitude correction of bridge piers based on multi-source sensor fusion and hydraulic servo linkage, characterized in that, include: Attitude data of bridge piers are collected by multiple source sensors and then fused into unified attitude data. Use uniform attitude data as input to adjust the control parameters of the hydraulic servo device; Fault detection and early warning are performed based on the operating status and environmental data of the hydraulic servo device; the operating modes of the sensors and the hydraulic servo device are adjusted according to the detection results; among these... The fusion into unified attitude data includes fusing sensor data using deep learning algorithms and fusion algorithms; Adjusting the control parameters of the hydraulic servo device includes calculating the attitude error and correction amount, adjusting the attitude error according to the correction amount, and using the attitude error as a reward signal input through a reinforcement learning algorithm to dynamically optimize the control parameters of the hydraulic servo device.

2. The automatic attitude correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage as described in claim 1, characterized in that: The collected attitude data of the bridge piers includes, Collect key location information of bridge piers from a large database; Based on the key position information of the bridge beams and piers, multiple sensors are installed at multiple key positions of the target bridge piers to collect the pier attitude data in real time. The sampling period for each sensor is set to 100ms, and the attitude data is transmitted to the computing device via a communication protocol. A data cleaning algorithm is used to denoise the collected attitude data; The processed attitude data is converted into a standardized format and output.

3. The automatic attitude correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage as described in claim 1 or 2, characterized in that: The fusion of sensor data includes, Sort the data according to the characteristics of the time series and then standardize them. Pose data is processed using deep learning models; Deep learning models use convolutional neural networks to learn and extract features from real-time pose data from multiple sensors. A deep learning model is used to perform multi-level analysis of real-time attitude data from multiple sensors, and feature selection is performed based on the analysis results. The real-time attitude data from multiple sensors after filtering are fused into unified attitude data.

4. The automatic attitude correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage as described in claim 3, characterized in that: The adjustment of attitude error based on the correction amount includes The ideal attitude specified in the bridge design is taken as the target attitude; The attitude error is calculated by comparing the fused unified attitude data with the target attitude. The correction amount is set according to the actual impact of external environmental factors on bridge piers; The calculated attitude error is corrected based on the correction amount; The actual impacts include temperature, humidity, and wind speed.

5. The automatic posture correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage as described in claim 1, 2, or 4, characterized in that: The control parameters of the dynamically optimized hydraulic servo device include: The posture error is used as input, and the reinforcement learning algorithm is used to input the posture error as a reward signal. The reinforcement learning model adjusts the control strategy of the hydraulic servo device based on the feedback error signal; Reinforcement learning models learn by comparing with historical data and gradually optimize control parameters; Control parameters include hydraulic oil pressure, flow rate, and valve opening. The optimal control parameters calculated each time are transmitted to the hydraulic servo device in real time.

6. The automatic attitude correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage as described in claim 5, characterized in that: The fault detection and early warning system includes, Real-time monitoring of sensor data and the operating status of the hydraulic servo device; The data from each sensor is analyzed using a fault detection algorithm; When fluctuations in sensor data are detected exceeding At that time, by comparing historical data with real-time data, it is possible to identify and determine whether a fault exists; The working status of the hydraulic servo device is checked in real time by measuring the hydraulic oil pressure, flow rate, and temperature to see if it exceeds the working range. When the sensor or hydraulic servo device detects a malfunction, it issues a corresponding warning signal. Choose a response strategy based on the corresponding warning signal.

7. The automatic attitude correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage as described in claim 1, 2, 4 or 6, characterized in that: The operating modes of the adjustment sensor and hydraulic servo device include: Based on the output response strategy, adjust the operating modes of the sensors and hydraulic servo devices; When a sensor fails, the backup sensor is activated, the data fusion algorithm is recalibrated, the data acquisition frequency is adjusted, and the sensor's operating mode is optimized. When the hydraulic servo device fails, switch to the backup device and adjust the control strategy. Also, dynamically adjust the working mode of the hydraulic servo device according to changes in external environmental factors. Adjusting the operating mode of the hydraulic servo device includes adjusting the viscosity, flow rate, and pressure of the hydraulic oil to ensure stable operation of the hydraulic servo device when environmental conditions change.

8. An automatic attitude correction system for bridge piers based on multi-source sensor fusion and hydraulic servo linkage, employing the automatic attitude correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage as described in any one of claims 1 to 7, characterized in that: It includes a data acquisition and fusion module, an attitude control optimization module, and a fault detection and early warning module; The data acquisition and fusion module is used to acquire attitude data of bridge piers through multi-source sensors and fuse the sensor data into unified attitude data. The attitude control optimization module is used to take uniform attitude data as input and adjust the control parameters of the hydraulic servo device. The fault detection and early warning module is used to detect and warn of faults based on the working status of the hydraulic servo device and environmental data, and adjust the working mode of the sensor and the hydraulic servo device according to the detection results.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the automatic posture correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the automatic posture correction method for bridge piers based on multi-source sensor fusion and hydraulic servo linkage as described in any one of claims 1 to 7.

Images