A method and system for optimizing counterweights in arch bridge construction based on stress monitoring

Abstract

This invention relates to the field of bridge construction technology, specifically a method and system for optimizing the counterweight in arch bridge construction based on stress monitoring. The invention first deploys multiple stress sensors at different locations on the arch bridge and collects stress monitoring data. Data preprocessing and feature extraction are performed on the stress monitoring data. Features, construction state parameters, and structural parameters are input into a machine learning model to obtain the stress trends across multiple sections of the arch bridge. A non-dominated sorting genetic algorithm is used to generate an optimized counterweight scheme for arch bridge construction. The optimized counterweight scheme is dynamically adjusted based on the stress monitoring data and the stress trends across multiple sections of the arch bridge, thereby achieving accurate and scientific optimization of the counterweight scheme during arch bridge construction.

Description

Technical Field

[0001] This invention relates to the field of bridge construction technology, specifically a method and system for optimizing the counterweight in arch bridge construction based on stress monitoring. Background Technology

[0002] During the construction of arch bridges (such as cable hoisting, cast-in-place scaffolding, or rotation construction), counterweights (such as sandbags, water tanks, etc.) are often applied at specific locations to balance the internal forces of the structure, control deformation, or meet the stress requirements of specific construction stages. Existing technologies include schemes for adjusting counterweights during bridge construction. For example, Chinese invention patent (CN120250493A) discloses a method for adjusting the dynamic balance counterweight of a swing bridge, including a real-time weighing monitoring system, a counterweight adjustment system, a hydraulic traction device, and a counterweight moving device. The counterweight moving device includes multiple movable counterweight blocks, multiple flatbed railcars, and a longitudinal moving track for the railcars. The movable counterweight blocks are mounted on the flatbed railcars, and adjacent movable counterweight blocks are connected by connecting ropes. The hydraulic traction device includes two fixed counterweight blocks and two through-type jacks. The two fixed counterweight blocks are respectively set at both ends of the longitudinal track, and the two through-type jacks are respectively installed on the two fixed counterweight blocks. The through-type jacks are connected to the adjacent end movable counterweight blocks. The counterweight adjustment system calculates the distribution points and loading weight of the counterweight blocks in real time based on the monitoring data of the real-time weighing monitoring system, and controls the corresponding through-type jacks to pull the movable counterweight blocks.

[0003] However, the aforementioned schemes suffer from limitations in adjusting counterweights. They rely on experience, resulting in superficial adjustments that fail to consider real-time changes in structural profitability, thus hindering precise and scientific counterweight adjustment during arch bridge construction. Furthermore, they exhibit inaccurate processing of weak stress signals when handling stress monitoring data. Additionally, when using intelligent models to optimize and predict arch bridge construction configurations, they treat all historical information across time steps indiscriminately, failing to automatically distinguish between critical periods (such as peak pouring times) and routine periods (such as nighttime when there is no construction). Moreover, existing schemes cannot accurately match the actual engineering needs of different construction stages when determining the multi-objective function for counterweight optimization. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a method and system for optimizing the counterweight during arch bridge construction based on stress monitoring, which solves the problems existing in the prior art.

[0005] This invention provides a method for optimizing the counterweight in arch bridge construction based on stress monitoring, comprising the following steps:

[0006] S1: Multiple stress sensors are arranged at different locations on the arch bridge to collect stress monitoring data;

[0007] S2: Perform data preprocessing and feature extraction operations on the stress monitoring data;

[0008] S3: Input the extracted features, construction state parameters, and structural parameters into the machine learning model to obtain the stress trend of the arch bridge's multi-section.

[0009] The machine learning model is a long short-term memory network model with an added time attention mechanism layer; the time attention mechanism layer uses key time step weighting to highlight the impact of the construction stage on the stress trend.

[0010] S4: An optimized scheme for the counterweight of arch bridge construction is generated using a non-dominated sorting genetic algorithm.

[0011] S5: The counterweight optimization scheme is dynamically adjusted based on the stress monitoring data and the stress trend of the multi-section of the arch bridge.

[0012] Preferably, the time attention mechanism layer employs key time step weighting to highlight the impact of important construction stages on stress trends, specifically as follows:

[0013] Sa: Calculate the energy fraction at each time step t;

[0014] Sb: Normalize the energy fraction at each time step t to obtain the attention weight at each time step t;

[0015] Sc: Generate a context vector based on the attention weights at each time step t. This context vector serves as the input to the fully connected layer and is used to ultimately predict future stress values.

[0016] Preferably, S4 specifically comprises:

[0017] S4.1: Establish multiple constraints for optimizing the construction counterweight of the arch bridge;

[0018] S4.2: Establish the objective function for optimizing the construction counterweight of the arch bridge;

[0019] The expression for the objective function is:

[0020] ;

[0021] In the formula, f1 is the total counterweight, f2 is the deformation, and f3 is the construction period. l 1 is the weighting coefficient of the total amount of counterweight. l 2 is the weighting coefficient for the deformation amount. l 3 represents the weighting coefficient for the construction period; in the initial stage of construction, l 1 = 0.7, l 2=0.2, l 3=0.1; During the middle of construction, l1 = 0.4, l 2 = 0.3, l 3=0.3; In the later stages of construction, l 1 = 0.5, l 2=0.1, l 3 = 0.4;

[0022] S4.3: Based on the multiple constraints and the objective function, a non-dominated sorting genetic algorithm is used to generate a weight optimization scheme.

[0023] Preferably, the constraints include stress safety constraints, deformation compatibility constraints, construction period constraints, and safety margin constraints.

[0024] Preferably, the stress safety constraint specifically comprises:

[0025] For each critical section i ( i =1,2,..., n Its maximum tensile stress σ t,i and maximum compressive stress s c,i Must meet:

[0026] ;

[0027] In the formula, n is the total number of critical sections, [ s t ]and[ s c These are the design-permissible tensile stress limits and compressive stress limits, respectively.

[0028] The deformation compatibility constraints are specifically as follows:

[0029] The maximum tilt displacement Δ at the top of the temporary support must meet the following requirements:

[0030] ;

[0031] ;

[0032] In the formula, H is the support height, Δ 允许 The maximum allowable tilt displacement for temporary supports;

[0033] The specific time constraints are as follows:

[0034] Total number of counterweight adjustments during construction N 调整 Must meet:

[0035] ;

[0036] In the formula, N允许 This represents the maximum number of adjustments allowed for the construction period.

[0037] The safety margin constraint is specifically as follows:

[0038] The ratio of actual stress to the limit value satisfies:

[0039] ;

[0040] In the formula, k is a coefficient.

[0041] Preferably, k is 0.8 or 0.9.

[0042] Preferably, in step S4.2, the primary objective function is to minimize the total amount of counterweight while satisfying the above constraints; the secondary objective functions are to minimize deformation and minimize the construction period.

[0043] Preferably, in step S1, the stress sensors are arranged at the key cross-sections of the main arch ring of the arch bridge, the temporary supports, and the counterweight application points, respectively.

[0044] Preferably, in step S2, the data preprocessing involves using an adaptive filtering algorithm based on wavelet transform to perform data filtering on the stress monitoring data; specifically:

[0045] The stress monitoring data is subjected to zero-mean normalization to obtain zero-mean normalized data;

[0046] The zero-mean processed data was subjected to a 7-level discrete wavelet transform using Morlet wavelets to obtain the approximation coefficients A7 and detail coefficients D1~D7.

[0047] The approximation coefficients and detail coefficients are subjected to combined threshold denoising; specifically:

[0048] No thresholding is applied to the approximation coefficient layer;

[0049] For the detail coefficients D 1- D 4. Use a universal threshold T for threshold processing;

[0050] For the detail coefficients D5-D7, an adaptive soft threshold T is applied. j It retains some weak high-frequency components that are related to the effective signal.

[0051] According to another aspect of the present invention, a counterweight optimization system for arch bridge construction based on stress monitoring is provided. The system employs the aforementioned method for optimizing counterweights for arch bridge construction based on stress monitoring. The system includes:

[0052] The data acquisition module is used to deploy multiple stress sensors at different locations on the arch bridge and collect stress monitoring data;

[0053] The data processing module is used to perform data preprocessing and feature extraction operations on the stress monitoring data;

[0054] The stress trend prediction module is used to input the features, construction state parameters and structural parameters into the machine learning model to obtain the stress trend of the multi-section of the arch bridge.

[0055] The machine learning model is a long short-term memory network model with an added time attention mechanism layer. The time attention mechanism layer uses key time steps to weight the impact of important construction stages on stress trends.

[0056] The counterweight optimization module is used to generate an optimized counterweight scheme for arch bridge construction using a non-dominated sorting genetic algorithm.

[0057] The dynamic adjustment module is used to dynamically adjust the counterweight optimization scheme based on the stress monitoring data and the stress trend of the multi-section of the arch bridge.

[0058] The embodiments of the present invention have the following technical effects:

[0059] This invention first deploys multiple stress sensors at different locations on an arch bridge to collect stress monitoring data; performs data preprocessing and feature extraction on the stress monitoring data; inputs features, construction state parameters, and structural parameters into a machine learning model to obtain the stress trends of multiple sections of the arch bridge; uses a non-dominated sorting genetic algorithm to generate an optimized counterweight scheme for arch bridge construction; and dynamically adjusts the optimized counterweight scheme based on the stress monitoring data and the stress trends of multiple sections of the arch bridge; thereby achieving accurate and scientific optimization of the counterweight scheme during arch bridge construction.

[0060] This invention employs a combined threshold denoising process on the approximation coefficients and detail coefficients. Through an adaptive threshold strategy, it successfully achieves efficient separation of low-frequency effective components (<1Hz) and high-frequency noise (>10Hz) in construction stress signals. This scheme not only improves the signal-to-noise ratio of strain monitoring data but also provides a reliable input data foundation for subsequent dynamic response prediction and counterweight optimization, making it a key component of the intelligent monitoring system for arch bridge construction.

[0061] This invention automatically focuses on key information by setting up a time attention mechanism and dynamically calculating the importance weight of each time step. It can automatically identify the time steps corresponding to key construction stages such as concrete pouring, counterweight adjustment, and formwork movement, and assign them higher weights. It also reduces interference from regular periods such as nighttime when there is no construction or material transportation, and avoids irrelevant data affecting the prediction results.

[0062] Meanwhile, this invention utilizes a dynamic weight-guided algorithm to prioritize key objectives at different stages. By dynamically adjusting the priority of each objective in multi-objective optimization (such as stress safety, deformation control, and schedule efficiency) according to the construction progress, the counterweight scheme accurately matches the actual needs of the project at different construction stages. This design breaks through the limitations of static weights and global balance in traditional optimization methods, significantly improving the engineering applicability and rationality of the optimization results. The dynamic weight coefficient adjustment, through the technical path of "construction stage perception → dynamic weight allocation → multi-objective collaborative optimization," ensures that the counterweight scheme focuses on the most critical needs at each construction stage: ensuring safety in the initial stage, stabilizing deformation and schedule in the middle stage, and reducing costs and improving efficiency in the later stage. This design not only improves the engineering rationality of the optimization results but also provides a "precise, flexible, and economical" counterweight strategy for arch bridge construction through dynamic adaptability. Attached Figure Description

[0063] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0064] Figure 1 This is a flowchart of a method for optimizing the counterweight in arch bridge construction based on stress monitoring, provided by an embodiment of the present invention.

[0065] Figure 2 This is a flowchart illustrating the key time step weighting method used in the time attention mechanism layer provided in this embodiment of the invention.

[0066] Figure 3 This is a flowchart of an embodiment of the present invention, which uses a non-dominated sorting genetic algorithm to generate an optimized scheme for the counterweight of an arch bridge construction. Detailed Implementation

[0067] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0068] Example 1, Appendix Figure 1 A flowchart of a method for optimizing the counterweight during arch bridge construction based on stress monitoring is shown in the attached diagram. Figure 1 As shown, a method for optimizing the counterweight during arch bridge construction based on stress monitoring includes the following steps:

[0069] S1: Multiple stress sensors are arranged at different locations on the arch bridge to collect stress monitoring data;

[0070] The stress sensors are arranged at key sections (such as arch foot, L / 4 section, and arch crown), temporary supports (such as brackets and hanging baskets), and counterweight application points of the main arch ring of the arch bridge to construct a full-dimensional stress monitoring network.

[0071] In the method for optimizing the counterweight during arch bridge construction, the strain sensor is a key device for monitoring the stress state of the structure, mainly used to measure the linear strain of materials such as concrete and steel. By monitoring the linear strain and combining it with the strain-stress conversion relationship, while also considering temperature compensation, the true stress of the structure can be obtained. This embodiment uses a combination of two types of strain sensors, fiber optic strain gauges and resistance strain gauges, to fully utilize their respective advantages and achieve more accurate and comprehensive monitoring of structural stress.

[0072] S2: Perform data preprocessing and feature extraction operations on the stress monitoring data;

[0073] The data preprocessing involves using an adaptive filtering algorithm based on wavelet transform to perform data filtering on the stress monitoring data.

[0074] Specifically, based on the frequency characteristics of the stress signal, a wavelet basis function and a number of decomposition layers are designed to separate the effective stress signal from the noise component. The wavelet basis function is, for example, the Morlet wavelet, and the number of decomposition layers is 7.

[0075] The specific steps for performing data filtering on the stress monitoring data using an adaptive filtering algorithm based on wavelet transform are as follows:

[0076] The stress monitoring data is subjected to zero-mean normalization to obtain zero-mean normalized data;

[0077] The zero-mean processed data was subjected to a 7-level discrete wavelet transform using Morlet wavelets to obtain approximation coefficients. A 7 and detail factor D 1~ D 7; Table 1 shows the frequency range of the wavelet transform coefficients and the corresponding signal types.

[0078] Table 1. Frequency range of wavelet transform coefficients and corresponding signal types

[0079]

[0080] In this step, the approximation coefficients contain key information about structural stress during construction, such as the slow stress changes caused by the gradual increase in material weight during concrete pouring, and the quasi-static load effect on the structure caused by the movement of the formwork. This information is crucial for analyzing the structural stress state and assessing construction safety. Therefore, by not processing the approximation coefficients, we can ensure that these key and effective signals are not destroyed by threshold processing, thus providing an accurate data foundation for subsequent dynamic response prediction and counterweight optimization. Meanwhile, stress fluctuations caused by construction loads are mainly low-frequency signals, typically less than 1 Hz. These signals reflect the quasi-static load effects of operations such as concrete pouring and formwork movement during construction, as well as the time-varying characteristics of materials such as concrete creep, which are crucial for assessing the structural stress state. Vibration noise and other interference are high-frequency signals, with frequencies greater than 10 Hz. This noise originates from the mechanical vibration of concrete vibrators and the start-up and shutdown impacts of construction machinery, and is characterized by suddenness and wide bandwidth, with energy concentrated in the high-frequency band, which can mask effective low-frequency signals. When there is a mixture of weak signals and strong noise in the stress monitoring data, a combination of soft and hard thresholding can be used. For the high-frequency components dominated by noise, a hard thresholding method is first used to remove obvious strong noise. Then, for the remaining coefficients containing weak effective signals, a soft thresholding method is used for further processing to reduce signal deviation. For example, in some construction stages, vibration noise is very strong. First, a hard thresholding method is used to remove most of the high-frequency spike noise at the high-frequency detail coefficient layer. Then, in subsequent processing, a soft thresholding method is used for coefficient layers that may contain weak effective signals to more accurately preserve the weak effective stress signals.

[0081] Therefore, a combined threshold denoising process is performed on the approximation coefficients and detail coefficients; specifically:

[0082] No thresholding is applied to the approximation coefficient layer;

[0083] For the detail coefficients D 1- D 4. Use a universal threshold T for threshold processing to directly remove values ​​with absolute values ​​less than 1. T The coefficient;

[0084] The formula for calculating the general threshold T is as follows:

[0085] ;

[0086] In the formula, s The standard deviation of the detail coefficients. N The length of the stress monitoring data.

[0087] For the detail coefficients D5-D7, an adaptive soft threshold T is applied. jIt retains some weak high-frequency components related to the effective signal, such as early high-frequency precursor signals of concrete microcrack propagation.

[0088] The detail coefficients D5-D7 are located in a mixed frequency band of 1.56~6.25Hz, therefore, an adaptive soft threshold is used for processing.

[0089] Wherein, the adaptive soft threshold T j The calculation formula is:

[0090] ;

[0091] In the formula, j represents the number of wavelet decomposition layers, and α is the adjustment coefficient, which is taken as 1.2~1.5;

[0092] The approximation coefficients and the detailed coefficients after thresholding are reconstructed by inverse wavelet transform to obtain the preprocessed stress monitoring data.

[0093] By precisely matching the Morlet wavelet basis function with a 7-level decomposition layer and combining it with an adaptive threshold strategy, efficient separation of low-frequency effective components (<1Hz) and high-frequency noise (>10Hz) in construction stress signals was successfully achieved. This scheme not only improves the signal-to-noise ratio of strain monitoring data but also provides a reliable input data foundation for subsequent dynamic response prediction and counterweight optimization, making it a key component in the intelligent monitoring system for arch bridge construction.

[0094] Feature extraction is performed on the preprocessed stress monitoring data;

[0095] The extracted features include:

[0096] Statistical characteristics: mean of preprocessed stress monitoring data, variance of preprocessed stress monitoring data, extreme values ​​of preprocessed stress monitoring data;

[0097] Time-frequency characteristics: wavelet energy entropy of preprocessed stress monitoring data;

[0098] Trend characteristics: The rate of change of stress is calculated using a sliding window.

[0099] S3: Input the features, construction state parameters and structural parameters into the machine learning model to obtain the stress trend of the multi-section of the arch bridge;

[0100] The construction status parameters include concrete pouring progress (current pouring section number / cumulative volume), applied counterweight value (counterweight difference between left and right cantilever ends), and formwork position; the structural parameters include current concrete strength (converted from measured rebound value), temporary support stiffness (inferred from support deformation monitoring value), and ambient temperature gradient.

[0101] The stress trend of the arch bridge at multiple sections is specifically the maximum value and variation trend of the key sections of the main arch ring within the next 2 to 6 hours; the key sections include the compressive stress at the arch foot, the shear stress at the L / 4 section, and the tensile stress at the arch crown.

[0102] The machine learning model is a long short-term memory network model with a time attention mechanism layer added;

[0103] The Long Short-Term Memory (LSTM) network model consists of three stacked LSTM layers. The number of hidden units in each LSTM layer is 128, 64, and 32, respectively, which are reduced layer by layer to reduce computational complexity and extract high-level abstract features.

[0104] The input dimension of the Long Short-Term Memory network model is 12-dimensional;

[0105] The time step of the Long Short-Term Memory Network Model is t=6 (corresponding to the monitoring data of the first 3 hours, with one time step every 30 minutes).

[0106] The activation functions of the Long Short-Term Memory Network model are as follows: the hidden layer uses the tanh function (which restricts the output to the range of [-1,1] to enhance nonlinear expressive power), and the gating mechanism uses the sigmoid function (which outputs a probability value of 0 to 1 to control the information flow).

[0107] In the scenario of counterweight optimization during arch bridge construction, the dynamic response (such as stress and deformation) of the main arch ring is significantly affected by the dynamic changes in loads at multiple stages during construction. For example, key operations such as material accumulation during concrete pouring, load shift at the cantilever end caused by the movement of the formwork, and sudden addition or removal of counterweights will all generate "high-impact loads" at specific time steps. Monitoring data during these periods is crucial for predicting future stress evolution. However, traditional attention-based long short-term memory network models treat historical information from all time steps equally and cannot automatically distinguish between critical periods (such as peak pouring periods) and regular periods (such as nighttime when there is no construction). Therefore, this embodiment sets up a time attention mechanism and automatically focuses on key information by dynamically calculating the importance weight of each time step.

[0108] The input to the time attention mechanism layer is the sequence of hidden states for all time steps output by the LSTM layer of the Long Short-Term Memory network model. H =[ h 1, h 2,..., h t ]( t For example, time step t =6 corresponds to the monitoring data from the previous 3 hours, h t (For the hidden state sequence at time step t), these ht The data will contain semantic information about stages such as "whether it is concrete pouring" and "whether it is counterweight adjustment," because the sensor readings, operation records, and text descriptions for these stages in the training data will have statistical patterns. For example, the sensor load may suddenly increase during concrete pouring, and the displacement / stress may have specific change patterns during counterweight adjustment. h t It is a length of d vectors, for example d =32, determined by the number of hidden units in the last layer of the LSTM.

[0109] Specifically, the time attention mechanism layer employs key time step weighting to highlight the impact of important construction stages on stress trends; as shown in the appendix. Figure 2 As shown, the specific process is as follows:

[0110] Sa: Calculate the energy fraction at each time step t;

[0111] For each time step t, the time-division energy e for that time step is calculated through a learnable linear transformation. t The calculation formula is:

[0112] ;

[0113] In the formula v a T This refers to the weight vector in the attention mechanism, and the dimension of the weight vector is usually equal to tanh( The output dimension is consistent. The weight vector and the subsequent linear transformation result are multiplied by a dot product to weight or map the scores at different positions, so as to finally obtain the attention score at that position.

[0114] W a This is the weight matrix in the attention mechanism, used for each hidden state. h t Perform a linear transformation; its function is to map the input hidden state to a new feature space, with the dimension reduced from... W a The number of columns is determined so that subsequent sums... v a Perform operations such as inner product;

[0115] h t This indicates the time step of the LSTM layer. t The hidden state encodes the preceding sequence. t Information at any given moment is one of the objects that the attention mechanism needs to focus on;

[0116] ba The bias term is used in... W a h t After the linear transformation, a learnable constant offset is added to give the model a stronger fitting ability.

[0117] Sb: Normalize the energy fraction at each time step t to obtain the attention weight at each time step t;

[0118] In this step, the energy fraction e at each time step is calculated using the softmax function. t Convert to attention weight α t Ensure that the sum of all weights is 1;

[0119] Sc: Generate a context vector based on the attention weights for each time step t;

[0120] In this step, the hidden state at each time step t is... h t According to attention weight α t We obtain the context vector c by weighted summation;

[0121] The specific formula is as follows:

[0122] ;

[0123] In this embodiment, c is a weighted summary of all historical time step information, where h is the weighted summary of high-weight time steps (such as the pouring period). t The contribution of h to c is greater for low-weight time steps (such as stationary periods). t It has almost no impact on the results; this vector will be used as the input to the fully connected layer for the final prediction of future stress values. The solution in this embodiment can automatically identify the time steps corresponding to key construction stages such as concrete pouring, counterweight adjustment, and formwork movement, and assign them higher weights; it reduces interference from regular periods such as nighttime when there is no construction or material transportation, and avoids irrelevant data affecting the prediction results.

[0124] S4: An optimized scheme for the counterweight of arch bridge construction is generated using a non-dominated sorting genetic algorithm.

[0125] In the scenario of counterweight optimization during arch bridge construction, the formulation of the counterweight optimization scheme is not simply about "minimizing the total amount of counterweight." Instead, it requires balancing the conflicts between various objectives through intelligent algorithms (non-dominated sorting genetic algorithms) to generate the optimal counterweight adjustment strategy, while satisfying multiple constraints such as structural safety, deformation coordination, construction period control, and material costs. This embodiment uses an improved non-dominated sorting genetic algorithm combined with dynamic weight coefficients to achieve multi-objective collaborative optimization of counterweight in arch bridge construction.

[0126] Specifically, as shown in the attached document Figure 3 As shown, S4 specifically includes:

[0127] S4.1: Establish multiple constraints for optimizing the construction counterweight of the arch bridge;

[0128] In this step, the constraints include stress safety constraints, deformation compatibility constraints, schedule constraints, and safety margin constraints.

[0129] The stress safety constraint is to ensure that the stress in the key sections of the main arch ring (such as the arch foot, L / 4 section, and arch crown) under the action of counterweight does not exceed the allowable limit of the material, so as to avoid concrete cracking or steel yielding.

[0130] Specifically:

[0131] For each critical section i ( i =1,2,..., n Its maximum tensile stress σ t,i and maximum compressive stress s c,i Must meet:

[0132] ;

[0133] In the formula, n is the total number of critical sections, [ s t ]and[ s c These represent the design-permissible tensile stress limit and compressive stress limit, respectively.

[0134] The deformation coordination constraint is used to limit the tilting displacement of temporary supports (such as brackets or hanging baskets) under the action of counterweight, so as to avoid a chain reaction caused by support instability;

[0135] Specifically:

[0136] The maximum tilt displacement Δ at the top of the temporary support must meet the following requirements:

[0137] ;

[0138] ;

[0139] Δ 允许 The maximum allowable tilt displacement for temporary supports.

[0140] The aforementioned schedule constraint controls the number of counterweight adjustment operations and time costs, avoiding frequent hoisting that could affect the overall construction progress.

[0141] Specifically:

[0142] Total number of counterweight adjustments during construction N 调整 Must meet:

[0143] ;

[0144] In the formula, N 允许 This represents the maximum number of adjustments allowed for the construction period.

[0145] The safety margin constraint is to retain a certain stress safety margin to cope with construction errors (such as fluctuations in material strength and sudden changes in ambient temperature).

[0146] Specifically:

[0147] The ratio of actual stress to the limit value must meet the following requirements:

[0148] ;

[0149] In the formula, k is a coefficient. In this embodiment, k is 0.8 or 0.9; that is, the actual stress does not exceed 80% to 90% of the limit value, and a redundancy space of 10% to 20% is reserved.

[0150] S4.2: Establish the objective function for optimizing the construction counterweight of the arch bridge;

[0151] The objective function includes a primary objective function and a secondary objective function. The primary objective function is to minimize the total counterweight while satisfying the above constraints, so as to reduce material costs and hoisting workload. The secondary objective function is to minimize deformation and shorten the construction period.

[0152] The expression for the main objective function is as follows:

[0153] ;

[0154] In the formula, f1 is the total counterweight; oh a For the first a The weight of each counterweight m This represents the total number of counterweights.

[0155] The secondary objective function is specifically as follows:

[0156] Minimize deformation: ;

[0157] In the formula, f2 is the deformation amount, Δ 允许 The maximum allowable tilt displacement for temporary supports;

[0158] Shortest construction period: ;

[0159] In the formula, f3 represents the construction period.

[0160] The expression for the objective function is:

[0161] ;

[0162] In the formula, f1 is the total counterweight, f2 is the deformation, and f3 is the construction period. l 1 is the weighting coefficient of the total amount of counterweight. l 2 is the weighting coefficient for the deformation amount. l 3 is the weighting coefficient for the construction period.

[0163] In this step, this embodiment sets dynamic weight coefficients to adapt to changes in different construction stages based on the engineering characteristics of arch bridge counterweight optimization; that is, in the early stage of construction (such as the concrete pouring stage), stress safety is the primary concern (requiring high weight); in the later stage of construction (such as the formwork moving stage), the construction period and deformation control are more important (requiring weight adjustment).

[0164] That is, in the early stages of construction, l 1 = 0.7, l 2=0.2, l 3=0.1; During the middle of construction, l 1 = 0.4, l 2 = 0.3, l 3=0.3; In the later stages of construction, l 1 = 0.5, l 2=0.1, l 3 = 0.4.

[0165] This embodiment utilizes a dynamic weight-guided algorithm to prioritize key objectives at different stages. By dynamically adjusting the priority of each objective in multi-objective optimization (such as stress safety, deformation control, and schedule efficiency) according to the construction progress, the counterweight scheme accurately matches the actual needs of the project at different construction stages. This design overcomes the limitations of traditional optimization methods' static weights and global balance, significantly improving the engineering applicability and rationality of the optimization results. The dynamic weight coefficient adjustment, through a technical path of "construction stage perception → dynamic weight allocation → multi-objective collaborative optimization," ensures that the counterweight scheme focuses on the most critical needs at each construction stage: ensuring safety in the initial stage, stabilizing deformation and schedule in the middle stage, and reducing costs and improving efficiency in the later stage. This design not only improves the engineering rationality of the optimization results but also provides a "precise, flexible, and economical" counterweight strategy for arch bridge construction through dynamic adaptability.

[0166] S4.3: Based on the multiple constraints and the objective function, a non-dominated sorting genetic algorithm is used to generate a weight optimization scheme;

[0167] In this step, S4.3 specifically refers to:

[0168] Initialize the population;

[0169] Randomly generated N There are several counterweight schemes, each containing... m The weight of each counterweight is determined to ensure that the initial design meets basic engineering constraints, such as the total weight of the counterweights not exceeding the lifting equipment's capacity.

[0170] Multi-objective assessment and ranking;

[0171] For each individual (ballast scheme), calculate four objective function values ​​(f1, f2, f3 and objective F) and check the constraints. If the constraints (stress safety constraints, deformation compatibility constraints, schedule constraints and safety margin constraints) are violated, the solution is marked as infeasible and eliminated.

[0172] Based on the Pareto front ranking, feasible solutions are sorted by non-dominated order and crowding distance is calculated.

[0173] Selection, crossover, and mutation;

[0174] The tournament selection method is adopted to prioritize the retention of individuals with high non-dominant rank and large crowding distance to ensure population diversity and uniform frontier distribution. Simulated binary crossover (SBX) is performed on the selected parent individuals to generate offspring weighting schemes. Gaussian mutation (small perturbation) is applied to the offspring weighting schemes to introduce the possibility of local optimization.

[0175] Dynamic updates and iterations;

[0176] Update the dynamic weight coefficients λ1, λ2, and λ3 according to the current construction progress; repeat the multi-objective evaluation and ranking steps, as well as the selection, crossover, and mutation steps. Continue until the termination condition is met, which is either the number of iterations is ≥100, the Pareto front converges, or the computation time exceeds the limit.

[0177] Optimal strategy extraction;

[0178] From the final Pareto front, the scheme that satisfies all constraints, minimizes the total amount of counterweight, and balances the secondary objectives is selected, and specific counterweight instructions are output through the construction management platform.

[0179] For example, the specific counterweight instruction is: "Add 3 tons of counterweight to the left cantilever end and reduce 1 ton of counterweight to the right end".

[0180] S5: The counterweight optimization scheme is dynamically adjusted based on the stress monitoring data and the stress trend of the multi-section of the arch bridge.

[0181] The counterweight adjustment process will be initiated when any of the following conditions are met:

[0182] The maximum stress monitored in real time is approaching the warning threshold;

[0183] The dynamic response prediction model shows that if the current counterweight is maintained, stress will exceed the limit within the next 2 hours.

[0184] The warning threshold is 80% of the stress design limit.

[0185] The adjustment process is as follows: based on S3, calculate the stress trend under different candidate counterweight schemes;

[0186] Using S4, the optimal weight value that satisfies all constraints is selected from the candidate solutions;

[0187] Adjustment instructions are issued to the site through the construction management platform, and the adjustment process is monitored by drone inspections or cameras to confirm that the counterweight has been adjusted in place.

[0188] Example 2: This invention also provides a stress monitoring-based counterweight optimization system for arch bridge construction. The system employs a stress monitoring-based counterweight optimization method for arch bridge construction as described in Example 1. The system includes:

[0189] The data acquisition module is used to deploy multiple stress sensors at different locations on the arch bridge and collect stress monitoring data;

[0190] The data processing module is used to perform data preprocessing and feature extraction operations on the stress monitoring data;

[0191] The stress trend prediction module is used to input the features, construction state parameters and structural parameters into the machine learning model to obtain the stress trend of the multi-section of the arch bridge.

[0192] The machine learning model is a long short-term memory network model with an added time attention mechanism layer. The time attention mechanism layer uses key time steps to weight the impact of important construction stages on stress trends.

[0193] The counterweight optimization module is used to generate an optimized counterweight scheme for arch bridge construction using a non-dominated sorting genetic algorithm.

[0194] The dynamic adjustment module is used to dynamically adjust the counterweight optimization scheme based on the stress monitoring data and the stress trend of the multi-section of the arch bridge.

[0195] Example 3: The present invention also provides an electronic device, including one or more processors and a memory.

[0196] A processor can be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and can control other components in an electronic device to perform desired functions.

[0197] The memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and a processor may execute the program instructions to implement the stress monitoring-based arch bridge construction counterweight optimization method described above in any embodiment of this application, and / or other desired functions. Various contents such as initial extrinsic parameters and thresholds may also be stored in the computer-readable storage medium.

[0198] In one example, the electronic device may also include input and output devices, which are interconnected via a bus system and / or other forms of connection (not shown). The input device may include, for example, a keyboard, a mouse, etc. The output device may output various information to the outside, including warning messages, braking force, etc. The output device may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0199] Of course, for simplicity, components such as buses and input / output interfaces have been omitted. In addition, depending on the specific application, the electronic device may include any other appropriate components.

[0200] In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to implement the function of the stress monitoring-based arch bridge construction counterweight optimization method provided in any embodiment of this application.

[0201] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to implement the stress monitoring-based arch bridge construction counterweight optimization method provided in any embodiment of this application.

[0202] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A stress monitoring based construction counterweight optimization method for arch bridges, characterized in that, The method comprises the following steps: S1: arranging a plurality of stress sensors at different positions on the arch bridge and collecting stress monitoring data; S2: performing data preprocessing and feature extraction on the stress monitoring data; S3: inputting the extracted features, construction state parameters and structure parameters into a machine learning model to obtain arch bridge multi-section stress trends; The machine learning model is a long short-term memory network model with an added time attention mechanism layer; the time attention mechanism layer adopts key time step weighting to highlight the influence of the construction stage on the stress trend; S4: generating an arch bridge construction counterweight optimization scheme using a non-dominated sorting genetic algorithm; The S4 is specifically: S4.1: establishing a plurality of constraint conditions for the arch bridge construction counterweight optimization; The plurality of constraint conditions include stress safety constraints, deformation coordination constraints, construction period constraints and safety margin constraints; The stress safety constraint is specifically: for each critical section i i =1,2,..., n , the maximum tensile stress t,i and the maximum compressive stress The deformation coordination constraint is specifically: c,i must satisfy:​ ； where n is the total number of key sections, The maximum inclination displacement Δ of the temporary support top needs to meet: t ] and [ The construction period constraint is specifically: c ] are the design allowable tensile and compressive stress limits, respectively. The safety margin constraint is specifically: The ratio of the actual stress to the limit value meets: ； ； where H is the support height, Δ 允许 is the maximum tilt displacement allowed for the temporary support; In the formula, k is a coefficient; Total number of counterweight adjustments during construction N 调整 Must satisfy: ； In the formula, N 允许 is the maximum number of adjustments allowed for the duration. S4.2: establishing an objective function for the arch bridge construction counterweight optimization; The expression of the objective function F is: ； According to the plurality of constraint conditions and the objective function, the non-dominated sorting genetic algorithm is used to generate a counterweight optimization scheme; S5: dynamically adjusting the counterweight optimization scheme according to the stress monitoring data and the arch bridge multi-section stress trend.

2. The arch bridge construction counterweight optimization method based on stress monitoring according to claim 1, wherein: ； In the formula, f1 is the total weight of the counterweight, f2 is the deformation amount, f3 is the construction period, The time attention mechanism layer adopts key time step weighting to highlight the influence of the construction stage on the stress trend is specifically: 1 is the weight coefficient of the total weight of the counterweight, Sa: calculating the energy score of each time step t; 2 is the weight coefficient of the deformation amount, Sb: normalizing the energy score of each time step t to obtain the attention weight of each time step t; 3 is the weight coefficient of the construction period; At the initial stage of construction, Sc: generating a context vector according to the attention weight of each time step t, which is used as the input of the full connection layer for the final prediction of the future stress value. 1 = 0.7, 3. The arch bridge construction counterweight optimization method based on stress monitoring according to claim 2, wherein: 2 = 0.2, k is 0.8 or 0.

9. 3 = 0.1; at the middle stage of construction, 4. The arch bridge construction counterweight optimization method based on stress monitoring according to claim 1, wherein: 1 = 0.4, In the S4.2, the objective function includes a main objective function and a secondary objective function, the main objective function is to minimize the total amount of counterweight under the premise of meeting the above constraints, and the secondary objective function is to minimize deformation and shorten construction period. 2 = 0.3, 5. The arch bridge construction counterweight optimization method based on stress monitoring according to claim 1, wherein: 3 = 0.3; at the late stage of construction, In the S1, the stress sensors are arranged at the key sections of the main arch ring of the arch bridge, the temporary support and the counterweight application point. 1 = 0.5, 6. The arch bridge construction counterweight optimization method based on stress monitoring according to claim 1, wherein: 2 = 0.1, ​ 3 = 0.4; ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ In the S2, the data preprocessing is to perform data filtering operation on the stress monitoring data by using an adaptive filtering algorithm based on wavelet transform; specifically: perform zero-meaning processing on the stress monitoring data to obtain zero-meaning processed data; perform 7-layer discrete wavelet transform on the zero-meaning processed data by using Morlet wavelet to obtain approximation coefficients A7 and detail coefficients D1-D7; perform combined threshold denoising processing on the approximation coefficients and the detail coefficients; specifically: no threshold processing is performed on the approximation coefficient layer; to the detail coefficient D 1- D 4, threshold processing is performed using a general threshold T; For the detail coefficients D5-D7, an adaptive soft threshold T is applied j , preserving the weak high frequency components related to the significant signal.

7. A stress monitoring based arch bridge construction counterweight optimization system, characterized in that, The system adopts the arch bridge construction counterweight optimization method based on stress monitoring in any one of claims 1-6, and the system comprises: a data acquisition module, configured to arrange a plurality of stress sensors at different positions of the arch bridge and collect stress monitoring data; a data processing module, configured to perform data preprocessing operation and feature extraction operation on the stress monitoring data; a stress trend prediction module, configured to input the features, construction state parameters and structure parameters into a machine learning model to obtain the stress trend of the arch bridge at multiple sections; the machine learning model is a long short-term memory network model with a time attention mechanism layer, and the time attention mechanism layer uses key time step weighting to highlight the influence of the construction stage on the stress trend; a counterweight optimization module, configured to generate an arch bridge construction counterweight optimization scheme by using a non-dominated sorting genetic algorithm; a dynamic adjustment module, configured to dynamically adjust the counterweight optimization scheme according to the stress monitoring data and the stress trend of the arch bridge at multiple sections.

Images