An intelligent adjustment method and system for jacks during jacking of a curved and inclined steel box girder bridge

Abstract

The present invention relates to the field of bridge jacking, and specifically to a method and system for intelligently adjusting jacks during jacking of a curved inclined steel box girder bridge. The method comprises: obtaining historical sample data of jacking of a curved inclined steel box girder bridge; constructing a jack control model, and using the historical sample data to train and evaluate the jack control model; obtaining real-time data of the curved inclined steel box girder bridge during jacking construction, and using the real-time data to dynamically adjust the weights and biases of the jack control model; introducing a noise alarm system, and using the noise alarm system and the dynamically adjusted jack control model to intelligently adjust the jacks. The method solves the problem in the prior art that the jack control is complex and not intelligent enough during jacking of a curved inclined steel box girder bridge. The method realizes the adaptive adjustment of the weights and biases of the jack control model during the jacking construction of the curved inclined steel box girder bridge, thereby improving the intelligent control and practicality of the present invention.

Description

Technical Field

[0001] The present invention relates to the field of bridge jacking, and in particular to an intelligent adjustment method and system for a jack during jacking of a curved slope inclined steel box girder bridge. Background Art

[0002] In bridge construction, curved and sloped steel box girder bridges are increasingly used in complex terrain and traffic environments due to their unique advantages. However, the jacking construction of these bridges faces many challenges, especially in jack control.

[0003] When jacking a curved, sloped, and inclined steel box girder bridge, the complexity of its spatial form places extremely high demands on the coordinated operation of the jacks. Existing technologies make it difficult to achieve precise coordination of the force size, direction, and stroke extension of multiple jacks, making it easy for the box girder to deflect and twist during the jacking process. Currently, the control of the jacks mostly relies on traditional methods, using finite element analysis software combined with manual intervention to control the jacks. However, the curved, sloped, and inclined steel box girder bridge has a special structure. Its curved, sloped, and inclined characteristics result in extremely complex and variable force conditions at different locations. Finite element analysis also makes it difficult to accurately determine the optimal force for each jack, increasing the difficulty and risk of construction. In addition, environmental factors at the construction site and subtle differences in material properties may cause the actual working conditions to deviate from the preset conditions, and the existing automation system is difficult to adjust flexibly, further affecting construction safety and progress.

[0004] With the development of the bridge construction industry, the requirements for construction safety, precision, and efficiency are becoming increasingly stringent. Traditional jack control technology is no longer able to meet the complex requirements of jacking construction for curved, sloped, and inclined steel box girder bridges. Therefore, a more intelligent jack control technology is urgently needed. Summary of the Invention

[0005] In response to the defects in the existing technology, the present invention provides an intelligent adjustment method and system for the jack when pushing a curved and inclined steel box girder bridge, which solves the problem in the existing technology that the jack control is complex and not intelligent enough when pushing a curved and inclined steel box girder bridge.

[0006] In order to achieve the above-mentioned purpose, one aspect of the present invention provides an intelligent adjustment method for the jacks during the jacking of a curved and inclined steel box girder bridge, the method comprising: obtaining historical sample data of the jacking of the curved and inclined steel box girder bridge; constructing a jack control model, and using the historical sample data to train and evaluate the jack control model; obtaining real-time data of the curved and inclined steel box girder bridge during the jacking construction, and using the real-time data to dynamically adjust the weights and biases of the jack control model; introducing a noise alarm system, and using the noise alarm system and the dynamically adjusted jack control model to intelligently adjust the jacks.

[0007] The present invention provides a solid data foundation for the training of the jack control model through historical sample data of the jacking of curved and sloped inclined steel box girder bridges, thereby enabling the jack control model to have reliable jack control capabilities. The introduction of real-time data can dynamically adjust the model weights and biases, allowing the model to adapt to various changes during the construction process and improve the accuracy and adaptability of the control. Utilizing the noise alarm system and the dynamically adjusted model to intelligently adjust the jacks can effectively cope with the complex working conditions during the jacking construction of curved and sloped inclined steel box girder bridges, as well as provide guarantees for safe construction, thereby improving the intelligence and practicality of the jack control model.

[0008] Optionally, obtaining historical sample data of the jacking of the curved slope inclined steel box girder bridge includes: obtaining first historical data related to the jacking of the curved slope inclined steel box girder bridge; eliminating outliers and interpolating missing values in the first historical data to obtain second historical data; dividing the second historical data into multiple historical construction stage data according to the characteristics of different construction stages of the jacking of the curved slope inclined steel box girder bridge; adding noise to the historical construction stage data according to the characteristics of the different construction stages to obtain noise fusion data; and preprocessing the noise fusion data to obtain the historical sample data.

[0009] The present invention ensures the quality and integrity of the historical data of the jacking of curved and sloped inclined steel box girders by eliminating outliers and interpolating missing values. It also divides the data according to the construction stage and adds corresponding noise to simulate the uncertainty and variables in the real construction environment, thereby improving the diversity of the data. This not only makes the data closer to the actual operating environment, but also enhances the model's sensitivity and responsiveness to changes in key parameters.

[0010] Optionally, the preprocessing of the noise fusion data to obtain the historical sample data includes: extracting features from the noise fusion data according to the characteristics of the different construction stages to obtain characteristic data of different construction stages; and normalizing the characteristic data of different construction stages to obtain the historical sample data.

[0011] The present invention performs feature extraction and normalization processing on the noise fusion data. Feature extraction targets the data characteristics of different construction stages and extracts key information. Normalization processing ensures that the data of different construction stages have a unified scale, thereby greatly improving the overall data quality and providing a solid foundation for the training of the jack control model.

[0012] Optionally, constructing the jack control model includes: constructing a first loss function based on the force size, force direction and stroke extension of the jack; setting a constraint penalty item, and constructing a second loss function based on the first loss function and the constraint penalty item; based on a long short-term memory network, using the second loss function to construct the jack control model.

[0013] This invention leverages the jack's actual functionality, using the force magnitude, direction, and stroke extension to form a multi-dimensional first-order loss function. This allows the jack control system to accurately capture key performance indicators during the jacking process during training. The introduction of a constraint penalty term not only optimizes the model's prediction accuracy but also ensures structural safety and construction quality. By processing time series data using a long short-term memory network (LSTM), the model learns the temporal dependencies in historical data, enabling more accurate predictions and adjustments to the jack's behavior.

[0014] Optionally, the first loss function satisfies the following formula:

[0015] ,

[0016] in, is the loss function, is the number of predicted values of the jack, For the The force of a jack, For the The predicted force of the jack, No. The direction of force of the jack, for The predicted force direction of each jack, For the The stroke of the jack is extended. For the The predicted stroke extension of each jack.

[0017] The formula of the present invention fully considers the three key parameters of the jack: force size, force direction and stroke extension, providing a comprehensive performance evaluation standard for the jack control model. In addition, the penalty for large deviations is strengthened in the form of square sum, thereby guiding the precise control of these key parameters during the model learning process and structurally encouraging the model to achieve smoother and more controllable operations during the jacking process, which helps to optimize construction efficiency, reduce safety risks, and ultimately improve the quality of the entire bridge jacking project.

[0018] Optionally, setting the constraint penalty item and constructing the second loss function based on the first loss function and the constraint penalty item includes: obtaining the maximum allowable stress in the box girder design, the maximum allowable offset in the box girder design, and the minimum allowable height of the guide beam based on relevant characteristics of the box girder; setting a stress equalization penalty item, a maximum offset penalty item, and a guide beam height penalty item according to the maximum allowable stress in the box girder design, the maximum offset in the box girder design, and the minimum allowable height of the guide beam; setting penalty weights for the stress equalization penalty item, the maximum offset penalty item, and the guide beam height penalty item respectively; setting the constraint penalty item based on the stress equalization penalty item, the maximum offset penalty item, the guide beam height penalty item, and the penalty weight; and constructing the second loss function in combination with the first loss function and the constraint penalty item.

[0019] By setting constraint penalty terms, the present invention can significantly improve the adaptability and accuracy of the jack control model in actual construction environments. At the same time, the weight setting can improve the accuracy of the jack control model's decision-making strategy and provide a clear direction for model training.

[0020] Optionally, the dynamic adjustment of the weights and bias of the jack control model using the real-time data includes: using the real-time data to calculate the complexity index of the real-time data; dynamically adjusting the penalty weight of the second loss function based on the complexity index; using the real-time data to calculate the loss value of the adjusted second loss function; based on the loss value, using the back propagation algorithm to calculate the gradient of the loss function; and dynamically adjusting the weights and bias of the jack control model based on the gradient.

[0021] The present invention can intelligently adjust the penalty weight in the second loss function by accurately calculating the complexity index of real-time data, so as to better meet the needs of the actual construction environment. By calculating the loss value of the loss function after adjusting the penalty weight and using the back propagation algorithm to obtain gradient information, the weight and bias of the jack control model are dynamically adjusted, which not only improves the response speed of the jack control model to changes in real-time data, but also enhances the accuracy of model prediction, improves the precision of jack control, and at the same time improves the adaptability of the jack control model to complex environments.

[0022] Optionally, the complexity index includes a stress complexity index, an offset complexity index, and a guide beam height complexity index, and the stress complexity index satisfies the following formula:

[0023] ,

[0024] in, is the stress complexity index, is the number of stress monitoring points, For the The value of each stress monitoring point, is the average value of the stress monitoring points, is the maximum value of the stress monitoring point, is the minimum value of the stress monitoring point;

[0025] The offset complexity index satisfies the following formula:

[0026] ,

[0027] in, is the offset complexity index, is the number of offset monitoring points, For the The value of the offset monitoring point, is the average value of the offset monitoring points, is the maximum value of the offset monitoring point, is the minimum value of the offset monitoring point, The value with the largest change in the offset monitoring point between adjacent real-time data collection moments;

[0028] The guide beam height complexity index satisfies the following formula:

[0029] ,in, is the guide beam height complexity index, is the number of guide beam height monitoring points, For the The value of each guide beam height monitoring point, is the average value of the guide beam height monitoring points, is the maximum value of the guide beam height monitoring point, is the minimum value of the guide beam height monitoring point, It is the value with the largest change in the guide beam height monitoring point at adjacent real-time data collection moments.

[0030] The complexity index formula of the present invention comprehensively considers the degree of dispersion of the monitoring point value and the average value, the fluctuation range of the monitoring point value, and the maximum change value of the monitoring point at adjacent moments. Through multi-dimensional calculation, it can comprehensively and accurately measure the complexity of the offset.

[0031] Optionally, dynamically adjusting the weights and biases of the jack control model according to the gradient includes: introducing adaptive moment estimation, calculating the first-order moment estimation and the second-order moment estimation of the adaptive moment estimation according to the gradient; correcting the first-order moment estimation and the second-order moment estimation, and using the corrected first-order moment estimation and the second-order moment estimation to dynamically adjust the weights and biases of the jack control model.

[0032] The present invention introduces an adaptive moment estimation mechanism to adjust the weights and biases of the jack control model, thereby improving the robustness of the weights and biases of the jack control model in complex environments, reducing the need for manual intervention, achieving more precise and intelligent bridge jacking construction control, and further improving the flexibility and adaptability of the jack control model.

[0033] Another aspect of the present invention provides an intelligent adjustment system for jacks during jacking of a curved and inclined steel box girder bridge, comprising: a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the intelligent adjustment method for jacks during jacking of a curved and inclined steel box girder bridge as described in any one of the previous aspects of the present invention.

[0034] The intelligent adjustment system for jacks during the jacking of a curved and inclined steel box girder bridge of the present invention has a compact structure, stable performance, high integration and simple composition. It can stably execute the intelligent adjustment method for jacks during the jacking of a curved and inclined steel box girder bridge provided in the previous aspect of the present invention, further improving the overall applicability and practical application capabilities of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a flow chart of an intelligent adjustment method for jacks during jacking of a curved and inclined steel box girder bridge according to an embodiment of the present invention;

[0036] Figure 2 The present invention is a schematic structural diagram of an intelligent adjustment system for jacks during jacking of a curved and inclined steel box girder bridge according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] Specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are for illustrative purposes only and are not intended to limit the present invention. In the following description, numerous specific details are set forth to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that these specific details are not necessarily required to practice the present invention. In other instances, well-known circuits, software, or methods are not specifically described to avoid obscuring the present invention.

[0038] Throughout this specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment of the present invention. Therefore, appearances of the phrases "in one embodiment," "in an embodiment," "an example," or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combinations and / or subcombinations in one or more embodiments or examples. Furthermore, those of ordinary skill in the art will appreciate that the figures provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0039] Figure 1 This is a flow chart of an intelligent adjustment method for jacks during the jacking of a curved, skewed steel box girder bridge according to an embodiment of the present invention. This method addresses the existing problem of complex and insufficiently intelligent jack control during the jacking of curved, skewed steel box girder bridges. This method achieves adaptive adjustment of the weights and biases of the jack control model using real-time data in the jacking construction environment for curved bridge designs and overall sloped box girder bridges, improving the intelligent control and practicality of the present invention. Figure 1 The method shown comprises the following steps:

[0040] Step S1, obtaining historical sample data of jacking of a curved slope inclined steel box girder bridge.

[0041] The acquisition of historical sample data for the jacking of a curved sloped steel box girder bridge specifically includes the following sub-steps:

[0042] Step S101: obtaining first historical data related to the jacking of the curved slope inclined steel box girder bridge.

[0043] In an embodiment, the first historical data is historical data related to the jacking of the curved sloped inclined steel box girder bridge. The first historical data includes but is not limited to structural design parameters, construction parameters, environmental conditions, monitoring data, and operation records. The structural design parameters include but are not limited to the length, width, height, curvature, slope, box girder strength, elastic modulus and the overall structure of the bridge. The construction parameters include but are not limited to the force direction, force size, and stroke elongation of the jack. The environmental conditions include but are not limited to the weather temperature, humidity, wind speed, and terrain conditions during the historical jacking construction of the curved sloped inclined steel box girder bridge. The monitoring data includes but is not limited to the jacking path, speed control, and pause point.

[0044] Step S102: remove outliers and interpolate missing values from the first historical data to obtain second historical data.

[0045] In this embodiment, the second historical data is data obtained by removing abnormal values and interpolating missing values from the first historical data.

[0046] By removing outliers, outliers caused by equipment failure, measurement errors or extreme events can be eliminated as much as possible, thereby improving the reliability of data and the accuracy of analysis. The K-nearest neighbor distance method can be selected as a method for removing outliers.

[0047] The K-nearest neighbor distance method works by calculating the Euclidean distance of each data point in the pumping data to the other data points. The distribution of the K nearest neighbor data points surrounding the data point is used to determine whether it is an outlier. If the distance between a data point and its K nearest neighbor data points is significantly greater than the distance between all other data points, it is likely an outlier.

[0048] First, calculate the Euclidean distance between two arbitrary monitoring points, which satisfies the following formula:

[0049] ,

[0050] in, For two different monitoring points and The Euclidean distance between is the number of features of the monitoring points, For monitoring points In the The value of the feature, For monitoring points In the The value of a feature.

[0051] Then, calculate the average distance between the monitoring point and all other monitoring points, satisfying the following formula:

[0052] ,

[0053] in, For the The average distance between a monitoring point and all other monitoring points, The number of monitoring points, For two different monitoring points and The Euclidean distance between .

[0054] Finally, identify abnormal monitoring points if the average distance between the monitoring point and other monitoring points is significantly greater than the average distance of all monitoring points. , then the monitoring point is determined to be an abnormal monitoring point, and the average distance of all monitoring points is Satisfies the following formula:

[0055] ,

[0056] in, is the average distance of all monitoring points, for The number of monitoring points, For the The average distance between a monitoring point and all other monitoring points.

[0057] Interpolating missing values ensures the integrity of the primary historical data, avoids analytical bias or inadequate model training caused by missing primary historical data, and enhances the usability of the primary historical data. Mean interpolation is a common method for interpolating missing values. The principle is that the value of a data point is generally close to the values of its adjacent points. Therefore, if the values of the two points before and after a data point are known, the value of that point can be estimated by calculating the average of these two values. This method is particularly suitable for time series data or relatively uniformly distributed spatially distributed datasets, where the differences between data points are generally small.

[0058] The mean interpolation method to fill missing values satisfies the following formula:

[0059] ,

[0060] In the formula, Indicates the Dimension Missing values for monitoring points, Indicates the Dimension The value of the monitoring point, Indicates the The value of the monitoring point of the dimension.

[0061] Step S103 , dividing the second historical data into a plurality of historical construction stage data according to the characteristics of different construction stages of the jacking of the curved slope inclined steel box girder bridge.

[0062] In this embodiment, the characteristics of different construction stages of the curved slope inclined steel box girder jacking construction project are that different project progresses have different concerns about construction safety, structural stress, linear control, and equipment operating conditions. The project progress is divided into early, mid-term and late stages, and the second historical data is correspondingly divided into early historical construction stage data, mid-term historical construction stage data and late historical construction stage data.

[0063] Step S104 : adding noise to the historical construction stage data according to the characteristics of the different construction stages to obtain noise fusion data.

[0064] In this embodiment, the addition of noise primarily considers the impact of uncertainties on the data. The greater the impact, the greater the added noise. Taking into account the different characteristics of the initial, intermediate, and final stages of the advancement process, different noise levels should be added. Noise is added by first determining the error range caused by uncertainties at the current stage of the data. A random number generator is then used to generate a random value within this range. This value is then added to the data to produce data that is more realistic.

[0065] Taking the jack force parameters as an example, the early stage, which involves construction preparation and initial jacking, is likely to produce relatively low noise levels, primarily due to equipment calibration and testing. A relatively small range of Gaussian noise can be added to simulate random errors during initial equipment calibration and testing. The mid-stage, the main stage of the jacking process, involves significant variations in the jack force parameters. Wear of mechanical components and fluctuations in the hydraulic system can lead to relatively high noise levels. Therefore, a medium range of uniformly distributed noise can be added to simulate random fluctuations and impacts during the jacking process. The late stage, after the box girder is jacked into place, primarily involves structural adjustments and inspections. While noise levels may be relatively low, the accuracy of the final position must be ensured. A relatively small range of normally distributed noise can be added to simulate minor errors during the final adjustments.

[0066] In summary, adding noise to historical construction data according to the characteristics of forces at different construction stages can significantly improve the adaptability of the jack control model to various uncertainties in actual construction, thereby achieving more intelligent and precise adjustment of the jacks and ensuring the quality and safety of the jacking construction of curved and sloped inclined steel box girder bridges.

[0067] Step S105 , preprocessing the noise fusion data to obtain the historical sample data.

[0068] Preprocessing the noise fusion data to obtain the historical sample data specifically includes the following sub-steps:

[0069] Step S10501: extract features from the noise fusion data according to the characteristics of the different construction stages to obtain feature data of different construction stages.

[0070] In this embodiment, due to the differences in data characteristics of different construction stages, different feature extraction methods need to be adopted to more accurately obtain feature data reflecting the construction status of each stage.

[0071] During the early construction phase, during the construction preparation and initial jacking phase, the force parameters of the jack are relatively stable, and the data changes are relatively small, but there may be some small fluctuations due to factors such as the instability of the initial state of the equipment. At this time, the discrete Fourier transform can be used to extract features from the noise fusion data. The discrete Fourier transform can convert time domain signals into frequency domain signals. By analyzing the frequency domain characteristics, the periodic components and potential frequency characteristics in the data can be clearly identified. During the early construction phase, some small vibrations or unstable factors of the equipment may appear as components of specific frequencies in the frequency domain. These features can be accurately captured using the discrete Fourier transform. Its beneficial effect is that it can discover in advance possible problems with the equipment in its initial state, such as the resonant frequency of equipment components, etc., to provide a reference for subsequent construction operations and ensure that the equipment is in good operating condition before the formal jacking.

[0072] The mid-term construction phase is the main stage of the jacking process. The jack's force parameters vary significantly, and wear of mechanical components and fluctuations in the hydraulic system can cause complex nonlinear and non-stationary characteristics in the data. In this case, the wavelet transform is more suitable for feature extraction. The wavelet transform has the characteristics of multi-resolution analysis and can analyze signals at different time and frequency scales, which has unique advantages for processing non-stationary signals. During the mid-term construction phase, noise and useful signals in the data are often intertwined. The wavelet transform can effectively decompose and reconstruct the signal, highlighting the signal's characteristic components and suppressing noise interference. By analyzing the wavelet coefficients at different scales, detailed information on the jack's force changes, the degree of wear of mechanical components, and other aspects can be obtained. This helps to monitor the construction process in real time, adjust construction parameters in a timely manner, and ensure smooth construction.

[0073] The later construction stage is when the box girder is pushed into place, and the main focus is on structural adjustments and inspections. At this time, the data is relatively stable, but the accuracy of the final position is required to be high. At this stage, the principal component analysis method can be used to extract features from the noise fusion data. The principal component analysis method is a dimensionality reduction technique that can convert multiple related variables into a few unrelated principal components. These principal components contain the main information of the original data. In the later construction stage, the principal component analysis method can be used to remove redundant information in the data and extract key features related to structural adjustments and position accuracy. For example, by analyzing the data from multiple monitoring points using the principal component analysis method, the principal components that have the greatest impact on the final position of the structure can be found, thereby more accurately assessing the status of the structure, providing an accurate basis for structural adjustments, and ensuring the accuracy and stability of the final position of the bridge.

[0074] Therefore, according to the characteristics of different stages of the jacking construction of the curved slope steel box girder bridge, the appropriate feature extraction method can more effectively obtain the feature data of different construction stages, provide more accurate input for the jack control model, thereby realizing the intelligent adjustment of the jack and improving the quality and safety of the bridge jacking construction.

[0075] Step S10502: normalize the characteristic data of different construction stages to obtain the historical sample data.

[0076] In this embodiment, normalization is a data preprocessing technique designed to convert data of varying ranges and magnitudes into a unified numerical range, making the data comparable and consistent. When processing characteristic data from different stages of the jacking construction of a curved, sloped, and inclined steel box girder bridge, normalization primarily adjusts the numerical ranges of characteristic data extracted using different methods during the early, mid, and late stages.

[0077] First, the frequency domain features obtained in the early stages through discrete Fourier transforms, the features extracted in the middle stages through wavelet transforms, and the principal component data obtained in the later stages through principal component analysis can result in significant differences in numerical range and magnitude. Without normalization, using this data to train the jack control model would require more time and computing resources to adjust weights and biases to accommodate the varying magnitudes of input data. After normalization, the data falls within a relatively uniform range, enabling faster model convergence and improving training results, reducing training time and increasing training efficiency.

[0078] Secondly, normalization makes the data distribution more stable and consistent, preventing certain feature dimensions from having an overly large or undersized impact on model training due to excessively large or small values. This allows the model to more evenly consider all features when learning data characteristics, thereby better capturing the inherent patterns in the data. When faced with new, real-world construction data, the model can more accurately and intelligently adjust the jacks, improving the model's generalization and enabling it to perform well in diverse construction scenarios and conditions.

[0079] Furthermore, during model training and calculation, raw data of varying magnitudes can lead to numerical instabilities. Normalizing data to a relatively small and stable range effectively avoids these numerical instabilities and ensures the stability and reliability of the model training process.

[0080] Finally, the physical meaning and measurement units of characteristic data at different construction stages may differ. Normalization eliminates these differences, allowing data from different stages to be compared and analyzed on the same scale. For example, normalization allows characteristic data reflecting changes in jack force to be considered together with characteristic data reflecting structural position accuracy, facilitating a more comprehensive assessment of construction status and precise control of the jacks.

[0081] Step S2: constructing a jack control model, and using the historical sample data to train and evaluate the jack control model.

[0082] Among them, building the jack control model specifically includes the following sub-steps:

[0083] Step S201: construct a first loss function according to the force magnitude, force direction and stroke extension of the jack.

[0084] The first loss function satisfies the following formula:

[0085] ,

[0086] in, is the loss function, is the number of predicted values of the jack, For the The force of a jack, For the The predicted force of the jack, No. The direction of force of the jack, for The predicted force direction of each jack, For the The stroke of the jack is extended. For the The predicted stroke extension of each jack.

[0087] Step S202: Set a constraint penalty term, and construct a second loss function based on the first loss function and the constraint penalty term.

[0088] The step of setting a constraint penalty term and constructing a second loss function based on the first loss function and the constraint penalty term specifically includes the following sub-steps:

[0089] Step S20201: Based on the relevant characteristics of the box girder, obtain the maximum allowable stress in the box girder design, the maximum allowable offset in the box girder design, and the minimum allowable height of the guide beam.

[0090] The maximum allowable stress in a box girder design refers to the maximum stress the structure can withstand, determined through precise calculation and analysis during the box girder design phase. If the actual stress exceeds this value, it will seriously affect the structural quality of the box girder and may even cause a safety accident.

[0091] The maximum allowable offset in the box girder design is the maximum allowable offset during the jacking process for construction safety. Excessive offset may cause the box girder to deviate from its position, affecting the overall structure of the bridge and subsequent construction.

[0092] The minimum allowable height of the guide beam is the minimum height between the guide beam at the front end of the box beam and the next support from the ground.

[0093] Step S20202: setting a stress equalization penalty item, a maximum deviation penalty item, and a guide beam height penalty item according to the maximum allowable stress in the box beam design, the maximum allowable deviation in the box beam design, and the minimum allowable height of the guide beam.

[0094] The stress equilibrium penalty term ensures balanced stress distribution in critical sections during the jacking process, preventing local stress from exceeding the maximum design stress and thus preventing structural damage and failure. This penalty term calculates the deviation between the stress value at each monitoring point and the maximum design stress, averages the squared sum, and uses this as a penalty signal to feed back to the model.

[0095] A maximum deviation penalty term is set to limit the horizontal deviation of the structure during the jacking process, ensuring that the deviation does not exceed the maximum allowable design deviation. This penalty term calculates the deviation between the deviation value of each monitoring point and the maximum allowable design deviation, averages the squared sum, and uses this as a penalty signal to feed back to the model.

[0096] A guide beam height penalty is set to ensure that the guide beam's height does not fall below the designed minimum allowable height to maintain structural stability and functionality. This penalty is calculated by averaging the squared sum of the deviations between the height of each monitoring point and the designed minimum allowable height, and this is fed back to the model as a penalty signal. The minimum allowable height is dynamically determined based on the relative height of the guide beam and the next support point. The guide beam height should ideally be 10 to 20 cm higher than the highest point of the next support point.

[0097] The stress equilibrium penalty term satisfies the following formula:

[0098] ,

[0099] in, is the stress equilibrium penalty term, is the total number of stress monitoring points, For the The value of each stress monitoring point, Design the maximum allowable stress for the box girder.

[0100] The maximum offset penalty term satisfies the following formula:

[0101] ,

[0102] in, is the maximum offset penalty term, is the number of offset monitoring points, For the The value of the offset monitoring point, Design the maximum allowable deflection for the box girder.

[0103] The guide beam height penalty term satisfies the following formula:

[0104] ,

[0105] in, is the guide beam height penalty term, is the number of guide beam height monitoring points, For the The value of each guide beam height monitoring point, The minimum allowable height of the guide beam.

[0106] Step S20203: setting penalty weights for the stress equalization penalty item, the maximum offset penalty item, and the guide beam height penalty item, respectively.

[0107] In this embodiment, respectively set 、 、 The weights of the stress equilibrium penalty, maximum deflection penalty, and guide beam height penalty, respectively. The weights should reflect the importance of each penalty in ensuring structural safety and meeting design requirements.

[0108] In an optional embodiment, from the perspective of safe construction, through empirical analysis, the weight of the initial stress equilibrium penalty term is Set to 0.3, the weight of the initial maximum offset penalty term Set to 0.4, the weight of the initial guide beam height penalty term Set to 0.3. You can combine the jack control model for preliminary verification and manually adjust the weights based on the verification results to meet the model training requirements as much as possible.

[0109] Step S20204: setting the constraint penalty item according to the stress equilibrium penalty item, the maximum offset penalty item, the guide beam height penalty item, and the penalty weight.

[0110] In this embodiment, all penalty terms are combined and weighted to form a constrained penalty term. The jack control model can optimize the jacking process while satisfying specific constraints. This approach improves the adaptability and intelligence of construction, helping to optimize construction plans, reduce risks, and enhance the overall efficiency and quality of bridge jacking construction. Dynamically adjusting these weights further ensures the model's adaptability across different construction phases, ensuring the stability and safety of the construction process.

[0111] Step S20205: Construct the second loss function by combining the first loss function and the constraint penalty term.

[0112] The second loss function satisfies the following formula:

[0113] ,

[0114] in, is the second loss function, is the first loss function, is the weight of the stress equilibrium penalty term, is the stress equilibrium penalty term, is the weight of the maximum offset penalty term, is the maximum offset penalty term, is the weight of the guide beam height penalty term, is the penalty term for the guide beam height.

[0115] Step S203: Based on the long short-term memory network, the second loss function is used to construct the jack control model.

[0116] In this embodiment, the long short-term memory network LSTM is an advanced recurrent neural network structure specifically designed to solve the gradient vanishing and gradient exploding problems encountered by traditional recurrent neural networks when processing time series data. It effectively controls the inflow and outflow of information by introducing a unique gating mechanism, including input gates, forget gates, and output gates, thereby being able to capture and remember long-term dependencies. This capability enables LSTM to perform well in processing tasks such as natural language processing, speech recognition, and time series prediction, with better flexibility and robustness, while alleviating the gradient problem in traditional RNNs and improving the model's ability to process long sequence data. These advantages of LSTM make it the preferred model in the field of time series analysis and are widely used in various practical applications.

[0117] Based on the long short-term memory network, a jack control model is constructed, and the second loss function is set as the loss function of the constructed jack control model. The selection of hyperparameters also plays a vital role in the training of the jack control model.

[0118] In an optional embodiment, the hyperparameters are optimized using the sparrow algorithm, which can greatly improve the training effect of the jack control model.

[0119] First, determine the hyperparameters of the jack control model. Based on experience and data, determine the range of values for these hyperparameters. Each combination of hyperparameters within this range forms a solution space. Use the sparrow algorithm to find any parameter combination in the solution space. Use the jack control model to configure this parameter combination, and then further verify it using historical sample data. Finally, find the set of production parameters with the best prediction results, which will serve as the production parameters for the jack control model.

[0120] Step S3, obtaining real-time data of the curved slope inclined steel box girder bridge during the jacking construction, and dynamically adjusting the weight and bias of the jack control model using the real-time data.

[0121] In this embodiment, the installation position of the strain gauge or fiber grating sensor is accurately determined based on the structural characteristics and force analysis of the steel box girder, and stress concentration or key stress-bearing parts should be selected, such as near welds, support points, etc. The installation surface needs to be cleaned and polished before installation to ensure that the sensor fits tightly against the surface of the structure to ensure the accuracy of the measurement data. At the same time, the range and accuracy of the sensor should be considered to avoid data distortion due to overload or insufficient accuracy. The control points of the total station should be set in a stable position that is not disturbed by construction, and good visibility conditions should be ensured between the control points. When installing the laser ranging sensor or displacement sensor, ensure that its measurement direction is consistent with the displacement direction to be monitored, and it should be firmly installed to prevent displacement or loosening during construction that affects the measurement results.

[0122] The installation and debugging of other equipment will not be described in detail here. After the equipment corresponding to the data to be obtained is installed, the equipment and the jack control model are integrated, and long-distance real-time communication is carried out using long-distance radio line of sight. Then the box girder enters the jacking stage, and the equipment sends real-time data to the jack control model. After feature extraction and normalization based on historical sample data, real-time data is generated.

[0123] The method of dynamically adjusting the weight and bias of the jack control model using the real-time data specifically includes the following sub-steps:

[0124] Step S301: Calculate the complexity index of the real-time data using the real-time data.

[0125] The complexity index includes a stress complexity index, an offset complexity index, and a guide beam height complexity index. The stress complexity index satisfies the following formula:

[0126] ,

[0127] in, is the stress complexity index, is the number of stress monitoring points, For the The value of each stress monitoring point, is the average value of the stress monitoring points, is the maximum value of the stress monitoring point, is the minimum value of the stress monitoring point;

[0128] In this embodiment, the first component of the offset complexity index generally reflects the dispersion of the stress monitoring point data relative to the average value. The higher the dispersion, the greater its contribution to the stress complexity index. The second component reflects the maximum fluctuation in the stress monitoring point data. The larger the fluctuation range, the greater its contribution to the stress complexity index.

[0129] By adding the first and second parts, the discrete degree and fluctuation range of the stress monitoring point data are comprehensively reflected to evaluate the complexity of the stress distribution.

[0130] The offset complexity index satisfies the following formula:

[0131] ,

[0132] in, is the offset complexity index, is the number of offset monitoring points, For the The value of the offset monitoring point, is the average value of the offset monitoring points, is the maximum value of the offset monitoring point, is the minimum value of the offset monitoring point, The value with the largest change in the offset monitoring point between adjacent real-time data collection moments;

[0133] In this embodiment, the first component of the migration complexity index generally reflects the dispersion of the migration monitoring point data relative to the average value. The higher the dispersion, the greater the contribution to the migration complexity index. The second component reflects the maximum fluctuation in the migration monitoring point data. The larger the fluctuation range, the greater the contribution to the migration complexity index. The third component highlights the impact of the maximum change in the migration between adjacent moments on the migration complexity.

[0134] By adding the three parts of the migration complexity index, the discreteness of the migration monitoring point data, the fluctuation range, and the changes in adjacent moments are comprehensively considered, which can more comprehensively evaluate the complexity of the migration.

[0135] The guide beam height complexity index satisfies the following formula:

[0136] ,

[0137] in, is the guide beam height complexity index, is the number of guide beam height monitoring points, For the The value of each guide beam height monitoring point, is the average value of the guide beam height monitoring points, is the maximum value of the guide beam height monitoring point, is the minimum value of the guide beam height monitoring point, It is the value with the largest change in the guide beam height monitoring point at adjacent real-time data collection moments.

[0138] In this embodiment, the first component of the guide beam height complexity index generally reflects the dispersion of the guide beam height monitoring point data relative to the average value. The higher the dispersion, the greater the contribution to the guide beam height complexity index. The second component reflects the maximum fluctuation in the guide beam height monitoring point data. The larger the fluctuation range, the greater the contribution to the guide beam height complexity index. The third component highlights the impact of the maximum change in guide beam height between adjacent moments on the guide beam height complexity.

[0139] By adding the three components of the guide beam height complexity index, the discreteness, fluctuation range, and changes in the data at adjacent moments of the guide beam height monitoring points are comprehensively considered. This allows for a more comprehensive assessment of the complexity of the guide beam height and provides a reference for related construction and analysis.

[0140] Step S302: dynamically adjust the penalty weight of the second loss function according to the complexity index.

[0141] In this embodiment, the value ranges of the weights of the penalty weight stress equilibrium penalty item, the maximum offset penalty item, and the guide beam height penalty item are pre-set according to actual engineering requirements and experience, and then the mapping relationship between the complexity index and the corresponding weight is further confirmed. The calculated complexity index is substituted into the mapping relationship to obtain the corresponding penalty weight, and it is applied to the second loss function.

[0142] In an optional embodiment, taking into account the complex construction environment, the curvature of the bridge, and the slope of the bridge, which have a significant impact on the force of the jack and the stress of the box girder, etc., to ensure that the model can quickly adapt to environmental changes and make timely responses, an exponential function is used to map the mapping relationship between the complexity index and the corresponding weight.

[0143] The penalty weight of the second loss function is dynamically adjusted to satisfy the following formula:

[0144] ,

[0145] in, For the The penalty weights corresponding to the class complexity indicators include stress complexity index, offset complexity index and guide beam height complexity index, which are used to adjust the penalty degree of the corresponding construction conditions in the loss function of the jack control model. For the The minimum value of the class penalty weight, For the The maximum value of the class penalty weight, For the Class complexity index, For the The median value of the class complexity index, To control the The parameter of the curve shape of the function of the relationship between the class complexity index and the penalty weight can be positive or negative. A positive number indicates that Increase, The growth rate is accelerating, and negative numbers indicate that Increase, The growth rate has slowed down.

[0146] in, For the The median value of a class complexity index is determined by collecting a large amount of complexity index data from past construction processes and sorting them from smallest to largest. If the data set is an odd number, the middle value is taken as the median value; if the data set is an even number, the average of the two middle values is taken. For example, 100 sets of stress complexity index data were collected during multiple bridge jacking construction projects. After sorting, the average of the 50th and 51st data points was taken as the median value of the stress complexity index.

[0147] To control the The parameters of the curve that shapes the relationship between complexity indices and penalty weights are calculated. Using historical construction data and the corresponding appropriate penalty weights, and using data fitting techniques such as least squares, we find parameter values that minimize the error between the weights calculated by the function and the actual required weights. For example, given a set of stress complexity index data and its corresponding, proven, effective stress equalization penalty weights, we can use least squares to adjust the parameters so that the weights calculated by the formula are as close as possible to the actual effective weights.

[0148] Step S303: Calculate the adjusted loss value of the second loss function using the real-time data.

[0149] In this embodiment, real-time data is substituted into the second loss function, and the loss value is obtained by calculation. The loss value measures the performance of the jack control model under the current data, that is, the degree of deviation between the actual situation and the model prediction, which can provide a quantitative basis for further optimizing the model or adjusting the construction strategy.

[0150] Step S304: Calculate the gradient of the loss function using a back propagation algorithm based on the loss value.

[0151] In this embodiment, the core idea of the back-propagation algorithm is to propagate the output error of the network back to each layer in the network, thereby calculating the contribution of each weight to the final error.

[0152] The loss value is used to initiate the backpropagation process. For the model's output layer, the partial derivative of the loss function with respect to the output layer's output is calculated. This step forms the basis for subsequent calculations. This partial derivative is then backpropagated to the previous layer using the chain rule. Specifically, if the previous layer uses an activation function, the derivative of the activation function is first taken. Then, the partial derivative of the loss function with respect to the output layer's weights is calculated using the weights from that layer to the output layer. This cycle continues, backpropagating layer by layer. For each layer, the partial derivative of the loss function with respect to the weight parameters of that layer is calculated using the chain rule. For example, in a three-layer neural network, backpropagation is performed from the output layer to the hidden layer, and then from the hidden layer to the input layer, continuously calculating the partial derivatives for each layer's weight parameters. During the calculation process, the computational logic and parameter relationships of each layer must be carefully considered to ensure the accuracy of the partial derivative calculations. Ultimately, the partial derivatives of the loss function with respect to each weight parameter are obtained. The vector formed by these partial derivatives is the gradient.

[0153] Step S305: Dynamically adjust the weight and bias of the jack control model according to the gradient.

[0154] Dynamically adjusting the weight and bias of the jack control model according to the gradient specifically includes the following sub-steps:

[0155] Step S30501: introducing adaptive moment estimation, and calculating the first-order moment estimation and the second-order moment estimation of the adaptive moment estimation according to the gradient.

[0156] In this embodiment, the core of adaptive moment estimation is to substitute the calculated gradient into the first-order moment estimation formula and the second-order moment estimation formula to calculate the corresponding results. First, the key parameters are initialized, the time step is 0, and the first-order moment estimation and the second-order moment estimation of each weight parameter are set to 0. Assume that The gradient of the second loss function with respect to the weight parameter after adjusting the penalty weight is obtained through the back propagation algorithm in the time step, and the first-order moment estimate satisfies the following formula:

[0157] ,

[0158] in, is the first-order moment estimate, is the exponential decay rate of the first-order moment estimate, which is usually close to 0.9. is the first-order moment estimate of the previous time step, is the gradient.

[0159] The second-order moment estimate satisfies the following formula:

[0160] ,

[0161] in, is the second-order moment estimate, is the exponential decay rate of the second-order moment estimate, which is generally close to 0.999. is the second-order moment estimate of the previous time step, is the gradient.

[0162] Step S30502: calibrate the first-order moment estimate and the second-order moment estimate, and dynamically adjust the weight and bias of the jack control model using the calibrated first-order moment estimate and the second-order moment estimate.

[0163] Since the first-order moment estimate and the second-order moment estimate are both 0 at initialization, the first-order moment estimate and the second-order moment estimate obtained early will also be biased towards 0, so the first-order moment estimate and the second-order moment estimate need to be corrected to satisfy the following formula:

[0164] ,

[0165] in, is the bias-corrected first-order moment estimate, is the unbias-corrected first-order moment estimate, is the exponential decay rate of the first-order moment estimate of Power, is the time step.

[0166] ,

[0167] is the bias-corrected second-order moment estimate, is the unbias-corrected second-order moment estimate, is the exponential decay rate of the second-order moment estimate of Power, is the time step.

[0168] In this embodiment, after the first-order moment estimate and the second-order moment estimate are corrected, the update amount of the weight and bias can be calculated. Assuming that the learning rate is , a very small constant , the value is , the purpose is to prevent the denominator from being 0 during calculation, and update the amount , is the weight or bias.

[0169] The update amount satisfies the formula:

[0170] After obtaining the update amount, the weights and biases of the jack control model can be dynamically adjusted to meet the following formula:

[0171] ,

[0172] in, For in time The updated weight matrix, is the weight matrix of the current time step, is the weight update amount.

[0173] ,

[0174] in, For in time The updated bias matrix, is the bias matrix of the current time step, is the bias update amount.

[0175] The above steps are repeated iteratively, and as the time step increases, the weights and biases of the jack control model are dynamically adjusted based on the gradients calculated in real time. In each iteration, new gradients are calculated using the backpropagation algorithm, and the first-order and second-order moment estimates are updated. After correction, the update amount is recalculated and the weights and biases are adjusted. This allows the jack control model to better adapt to different working conditions and real-time data, improving control accuracy and stability.

[0176] Step S4: introducing a noise alarm system, and using the noise alarm system and the dynamically adjusted jack control model to perform intelligent adjustment on the jack.

[0177] Intelligently adjusting the jack using the noise alarm system and the dynamically adjusted jack control model includes:

[0178] Using the noise alarm system to monitor the offset of the box beam and the height of the guide beam in real time;

[0179] Controlling the jack to suspend the jacking construction according to the monitoring result, and manually correcting the jacking construction;

[0180] Based on the result of the manual deviation correction, the jack is intelligently adjusted using the dynamically adjusted jack control model.

[0181] Intelligent adjustment here means that, compared with the existing technology, the present invention requires manual correction when the noise alarm system detects a major deviation. At other times, the jack is controlled by the adjusted jack control model. The jack control model can dynamically adapt to the complex pushing environment and intelligently provide a jack force plan. Therefore, it is intelligent adjustment.

[0182] In this embodiment, a noise alarm system is introduced, and the jack is intelligently adjusted using the noise alarm system and the dynamically adjusted jack control model, which can improve the adaptability and safety control of the jack control model to complex environments. For example, for a curved inclined steel box girder bridge, the bridge is characterized in that the bridge is bent into a certain arc, and the bridge itself has a certain slope. Calculating the force of the jack by traditional methods will undoubtedly add a lot of difficulty to the jacking construction. However, the jack control model of the present invention can be adaptively adjusted according to real-time data, and is easy to implement. Because during the jacking construction process, the arc and slope of the bridge will extend according to a rule, due to the existence of this rule, the jack control model can more easily learn changes in the environment, thereby realizing intelligent control of the jack.

[0183] The noise alarm system is a system that monitors the offset of the box girder and the height of the guide beam in real time for the safety of the jacking construction. It also issues a noise alarm when the offset of the box girder and the height of the guide beam exceed the safety threshold. After receiving the alarm signal, the jack control model controls the jack to stop working, and the jacking construction is manually corrected. After the manual correction is completed, the jack control model continues to control the jacking.

[0184] The addition of a noise alarm system can ensure safety in complex construction environments by preventing uncontrollable factors from causing excessive deviations in jacking construction, which can greatly improve the safety of jacking construction.

[0185] like Figure 2 As shown, the present invention also provides an intelligent adjustment system for jacks during jacking of a curved and inclined steel box girder bridge, comprising: a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute relevant steps of a relevant embodiment of a method for intelligent adjustment of jacks during jacking of a curved and inclined steel box girder bridge in the previous aspect of the present invention.

[0186] The present invention provides an intelligent adjustment system for jacks during jacking of a curved, sloped, and inclined steel box girder bridge. Each functional component can be integrated into a single processing unit, each component can exist physically separately, or two or more components can be integrated into a single unit. These integrated components can be implemented as either hardware or software functions, further enhancing the overall applicability and practical application capabilities of the present invention.

Claims

1. An intelligent adjustment method for jacks during jacking of a curved and inclined steel box girder bridge, characterized in that: The method comprises: Obtain historical sample data of jacking of curved sloped steel box girder bridge; Constructing a jack control model, and using the historical sample data to train and evaluate the jack control model; Acquiring real-time data of a curved sloped steel box girder bridge during jacking construction, and dynamically adjusting the weights and biases of the jack control model using the real-time data; Introducing a noise alarm system, and utilizing the noise alarm system and the dynamically adjusted jack control model to intelligently adjust the jack; The construction of the jack control model includes: Constructing a first loss function according to the force magnitude, force direction and stroke extension of the jack; Setting a constraint penalty term, and constructing a second loss function based on the first loss function and the constraint penalty term; Based on a long short-term memory network, constructing the jack control model using the second loss function; The setting of the constraint penalty term and constructing the second loss function according to the first loss function and the constraint penalty term includes: According to the relevant characteristics of the box girder, the maximum allowable stress of the box girder design, the maximum allowable offset of the box girder design, and the minimum allowable height of the guide beam are obtained; According to the maximum allowable stress in the box girder design, the maximum allowable offset in the box girder design and the minimum allowable height of the guide beam, a stress equalization penalty item, a maximum offset penalty item and a guide beam height penalty item are respectively set; Setting penalty weights for the stress equalization penalty item, the maximum deviation penalty item, and the guide beam height penalty item respectively; Setting the constraint penalty item according to the stress equilibrium penalty item, the maximum deviation penalty item, the guide beam height penalty item, and the penalty weight; The second loss function is constructed by combining the first loss function and the constraint penalty term.

2. The intelligent adjustment method for jacks during jacking of a curved and inclined steel box girder bridge according to claim 1 is characterized in that: The historical sample data of the jacking of the curved slope inclined steel box girder bridge is obtained as follows: Acquire first historical data related to the jacking of the curved slope inclined steel box girder bridge; Eliminating outliers and interpolating missing values from the first historical data to obtain second historical data; Dividing the second historical data into a plurality of historical construction stage data according to the characteristics of different construction stages of the jacking of the curved slope inclined steel box girder bridge; adding noise to the historical construction stage data according to the characteristics of the different construction stages to obtain noise fusion data; The noise fusion data is preprocessed to obtain the historical sample data.

3. The intelligent adjustment method for jacks during jacking of a curved and inclined steel box girder bridge according to claim 2 is characterized in that: The preprocessing of the noise fusion data to obtain the historical sample data includes: Performing feature extraction on the noise fusion data according to the characteristics of the different construction stages to obtain feature data of different construction stages; The characteristic data of different construction stages are normalized to obtain the historical sample data.

4. The intelligent adjustment method for jacks during jacking of a curved and inclined steel box girder bridge according to claim 1 is characterized in that: The first loss function satisfies the following formula: , in, is the loss function, is the number of predicted values of the jack, For the The force of a jack, For the The predicted force of the jack, No. The direction of force of the jack, for The predicted force direction of each jack, For the The stroke of the jack is extended. For the The predicted stroke extension of each jack.

5. The intelligent adjustment method for jacks during jacking of a curved and inclined steel box girder bridge according to claim 1 is characterized in that: The dynamically adjusting the weight and bias of the jack control model using the real-time data includes: Calculating a complexity index of the real-time data using the real-time data; Dynamically adjusting the penalty weight of the second loss function according to the complexity index; Calculating the adjusted loss value of the second loss function using the real-time data; Calculating the gradient of the loss function using a back-propagation algorithm according to the loss value; The weights and biases of the jack control model are dynamically adjusted according to the gradient.

6. The intelligent adjustment method for jacks during jacking of a curved and inclined steel box girder bridge according to claim 5 is characterized in that: The complexity index includes a stress complexity index, an offset complexity index, and a guide beam height complexity index. The stress complexity index satisfies the following formula: , in, is the stress complexity index, is the number of stress monitoring points, For the The value of each stress monitoring point, is the average value of the stress monitoring points, is the maximum value of the stress monitoring point, is the minimum value of the stress monitoring point; The offset complexity index satisfies the following formula: , in, is the offset complexity index, is the number of offset monitoring points, For the The value of the offset monitoring point, is the average value of the offset monitoring points, is the maximum value of the offset monitoring point, is the minimum value of the offset monitoring point, The value with the largest change in the offset monitoring point between adjacent real-time data collection moments; The guide beam height complexity index satisfies the following formula: , in, is the guide beam height complexity index, is the number of guide beam height monitoring points, For the The value of each guide beam height monitoring point, is the average value of the guide beam height monitoring points, is the maximum value of the guide beam height monitoring point, is the minimum value of the guide beam height monitoring point, It is the value with the largest change in the guide beam height monitoring point at adjacent real-time data collection moments.

7. The intelligent adjustment method for jacks during jacking of a curved and inclined steel box girder bridge according to claim 5 is characterized in that: The dynamically adjusting the weight and bias of the jack control model according to the gradient includes: Introducing an adaptive moment estimation, and calculating a first-order moment estimation and a second-order moment estimation of the adaptive moment estimation according to the gradient; The first-order moment estimate and the second-order moment estimate are corrected, and the weight and bias of the jack control model are dynamically adjusted using the corrected first-order moment estimate and the second-order moment estimate.

8. An intelligent adjustment system for jacks during jacking of a curved and inclined steel box girder bridge, characterized in that: include: A processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the intelligent adjustment method for the jack during the jacking of a curved slope inclined steel box girder bridge as described in any one of claims 1 to 7.

Images