Method and system for predicting stability of diaphragm wall based on LCP (Liquid Crystal Polymer) fiber composite grid

Abstract

The invention relates to the technical field of civil monitoring, in particular to an underground diaphragm wall stability prediction method and system based on an LCP fiber composite grid, and the method comprises the following steps: collecting basic data of a reinforced concrete underground diaphragm wall; the wall strain, the wall stress, the axial force, the bending moment and the curvature of the reinforced concrete underground diaphragm wall are obtained based on the LCP fiber composite grids, and then whether the wall cracks or not is judged; and establishing a reinforced concrete underground diaphragm wall stability prediction data set, further establishing an underground diaphragm wall stability prediction model, and predicting the stability of the wall body according to the basic data, the axial force, the bending moment and the curvature. According to the method, the stress strain, the axial force, the bending moment and the curvature of the reinforced concrete underground diaphragm wall can be rapidly and conveniently monitored in real time, then the cracking condition of the wall body is monitored in real time, the stability of the wall body is predicted, the durability of the wall body and the survival rate of a monitoring system are improved, and the stability prediction efficiency and the intelligent degree of the wall body can be improved.

Description

Technical Field

[0001] The present invention relates to the field of civil engineering monitoring technology, and in particular to a method and system for predicting the stability of a ground-connected wall based on an LCP fiber composite grid. Background Art

[0002] The prior art generally uses two methods to obtain the bending moment and axial force of the ground-connected wall. The first method is to attach strain gauges to the steel bars during the steel bar binding stage, and then calculate the bending moment and axial force of the ground-connected wall based on the monitoring data of the strain gauges. The second method is to install optical fiber sensors on the ground-connected wall, and then calculate the bending moment and axial force of the ground-connected wall based on the monitoring data of the optical fiber sensors. However, these two methods each have their own disadvantages.

[0003] If the first method is used to obtain the bending moment and axial force of the ground-connected wall, the following problems will arise: the strain gauges need to be precisely positioned and fixed during the steel bar binding stage, which may cause certain difficulties in the construction process, especially when the steel bars are dense or the space is limited; the strain gauges may be damaged during construction and use, affecting the accuracy and long-term stability of the monitoring data; the cost of using strain gauges is high, especially in large-scale applications; the data collected by the strain gauges need to be interpreted and analyzed by professionals, which increases the complexity of data processing; the performance of the strain gauges may be affected by environmental factors such as temperature and humidity, which in turn affects the accuracy of the monitoring results.

[0004] If the first method is used to obtain the bending moment and axial force of the ground-connected wall, the following problems will arise: the optical fiber itself is very thin and has poor shear resistance. It is easy to break under the influence of external forces, and it is difficult to use it directly in actual projects; if the optical fiber or fiber grating is combined with a steel structure or cable so that the optical fiber is protected by external components, it will be difficult to install due to the length of the engineering structure, or it will be difficult to protect in subsequent processes after installation.

[0005] Secondly, after obtaining the bending moment, axial force and other relevant data of the ground-anchored wall, the existing technology still needs to spend a lot of time on manual analysis to obtain the stability of the ground-anchored wall. The efficiency and real-time performance of the stability analysis of the ground-anchored wall needs to be improved. Summary of the invention

[0006] In view of the defects in the prior art, the present invention provides a method and system for predicting the stability of a ground-connected wall based on an LCP fiber composite grid.

[0007] In order to achieve the above-mentioned purpose, in a first aspect, the present invention provides a method for predicting the stability of a ground-connected wall based on an LCP fiber composite grid, the method comprising the following steps: collecting basic data of a reinforced concrete underground continuous wall, the basic data comprising geological condition data, design parameter data, external load data and initial displacement data; obtaining the wall strain, wall stress, axial force, bending moment and curvature of the reinforced concrete underground continuous wall based on the LCP fiber composite grid; comparing the wall strain and the wall stress with the concrete ultimate strain and concrete tensile strength in the design parameter data, respectively, to determine whether the reinforced concrete underground continuous wall is cracked; establishing a reinforced concrete underground continuous wall stability prediction data set, and establishing a ground-connected wall stability prediction model based on the reinforced concrete underground continuous wall stability prediction data set; and using the ground-connected wall stability prediction model to predict the stability of the reinforced concrete underground continuous wall according to the basic data, the axial force, the bending moment and the curvature. The present invention can quickly and conveniently monitor the stress and strain, axial force, bending moment and curvature of the reinforced concrete underground continuous wall in real time, and then monitor the cracking of the wall in real time and predict the stability of the wall, thereby improving the durability of the wall and the survival rate of the monitoring system, and can improve the efficiency and intelligence of wall stability prediction.

[0008] Optionally, the LCP fiber composite grid is formed by pultruding LCP fiber as a base material and resin, and organic composite conductive fibers are embedded in the center of the LCP fiber composite grid transverse limbs and the LCP fiber composite grid longitudinal limbs, and the organic composite conductive fibers are connected to the monitoring host.

[0009] Furthermore, obtaining the axial force and bending moment of reinforced concrete underground continuous walls based on LCP fiber composite grids is simple, convenient, low-cost, and not easy to damage, which can improve the survival rate of detection.

[0010] Optionally, the obtaining of the wall strain, wall stress, axial force, bending moment and curvature of the reinforced concrete underground continuous wall based on the LCP fiber composite grid comprises the following steps: When constructing a reinforced concrete underground continuous wall, the LCP fiber composite grid is arranged at the inner edge and the outer edge of the underground continuous wall respectively; Using the monitoring host to monitor the resistance change of the organic composite conductive fiber, and then determine the fiber strain of the organic composite conductive fiber; According to the fiber strain, the wall strain of each section of the reinforced concrete underground continuous wall is obtained by using the interpolation method, and then the wall stress of each section of the reinforced concrete underground continuous wall is obtained by combining the wall elastic modulus; The axial force and the bending moment of the corresponding cross section are calculated according to the wall stress of each cross section of the reinforced concrete underground continuous wall, and the curvature is calculated according to the bending moment.

[0011] Furthermore, the calculations involved in obtaining the strain, stress, axial force, bending moment and curvature of the reinforced concrete underground continuous wall based on the LCP fiber composite grid are not only simple but also highly accurate, which can improve the real-time and accuracy of the stability prediction of the reinforced concrete underground continuous wall. At the same time, the LCP fiber composite grid can also improve the bending stiffness and crack resistance of the reinforced concrete underground continuous wall.

[0012] Optionally, the wall strain and the wall stress of each cross section of the reinforced concrete underground continuous wall respectively satisfy the following relationship: in, is the wall strain of each section of the reinforced concrete underground continuous wall, Indicates interpolation operation. , , is the wall strain at the inner edge, is the fiber strain at the inner edge, is the wall strain at the outer edge, is the fiber strain at the outer edge, is the wall stress of each section of the reinforced concrete underground continuous wall, It is the wall elastic modulus of the reinforced concrete underground continuous wall.

[0013] Optionally, the axial force satisfies the following relationship: in, is the axial force, is the cross-sectional area of ​​the reinforced concrete underground continuous wall, is the wall stress of each section of the reinforced concrete underground continuous wall.

[0014] Optionally, the bending moment and the curvature respectively satisfy the following relationship: in, is the bending moment, is the cross-sectional area of ​​the reinforced concrete underground continuous wall, is the wall stress of each section of the reinforced concrete underground continuous wall, is the distance from each stress point on the reinforced concrete underground continuous wall section to the neutral layer, is the curvature, is the bending stiffness of the reinforced concrete underground continuous wall.

[0015] Optionally, the step of establishing a reinforced concrete underground continuous wall stability prediction data set, and establishing a ground-connected wall stability prediction model based on the reinforced concrete underground continuous wall stability prediction data set comprises the following steps: Collect historical foundation data, historical axial force, historical bending moment, historical curvature and historical stability of reinforced concrete underground continuous walls; Establishing a reinforced concrete underground continuous wall stability prediction data set using the historical basic data, the historical axial force, the historical bending moment, the historical curvature and the historical stability; Improve the sparrow search algorithm to obtain an improved sparrow search algorithm; Using the improved sparrow search algorithm to optimize the weights and thresholds of the long short-term memory neural network, and then constructing an initial stability prediction model; The reinforced concrete underground continuous wall stability prediction data set is used to complete the training and verification of the initial stability prediction model to obtain the underground continuous wall stability prediction model.

[0016] Furthermore, by constructing a ground-anchored wall stability prediction model to predict the stability of the ground-anchored wall, the efficiency and real-time performance of the ground-anchored wall stability analysis can be improved, which is beneficial to reducing safety hazards and economic losses.

[0017] Optionally, the step of improving the sparrow search algorithm to obtain an improved sparrow search algorithm comprises the following steps: Set the basic parameters of the sparrow search algorithm and use the Tent chaos map to initialize the sparrow population; The discovery position update formula and follower position update formula of the sparrow search algorithm are improved. The improved discovery position update formula and follower position update formula are shown as follows: in, For the The iteration The discoverer in The position in the dimension, is a matrix that randomly assigns 1 or -1. and is a constant, is a random number in [-1,1], is the length of the search space, is the number of discoverers, For the The iteration The discoverer in The position in the dimension, is the warning value, is a safe value, is a random number that follows a normal distribution, is a matrix whose elements are all 1, For the The iteration Followers in The position in the dimension, For the The iteration Followers in The position in the dimension, For the The global best position of the finder at the iteration, For the The global best position of the finder at the iteration, For the The global best position of the finder at the iteration, Indicates a transpose operation. is the number of followers; Update the positions of all sparrows in the sparrow population and calculate the fitness of all sparrows; Using a position adjustment function to adjust the position of each sparrow in the sparrow population according to the fitness; It is determined whether the current iteration step reaches the maximum number of iterations, and when the current iteration step reaches the maximum number of iterations, the optimal sparrow individual information is output.

[0018] Furthermore, the present invention improves the sparrow search algorithm, reduces the complexity of the algorithm, improves the optimization speed and accuracy of the algorithm, and thus improves the real-time and accuracy of the prediction of the stability of reinforced concrete underground continuous walls.

[0019] Optionally, the position adjustment function satisfies the following relationship: in, The sparrow position after adjustment. is the current position of the sparrow, is a random number that conforms to the standard normal distribution. is a random number in the Tent chaotic sequence in the interval (0,1), is the fitness of the sparrow, is the fitness threshold.

[0020] Furthermore, the position adjustment function is simple to calculate, which ensures the optimization speed while improving the optimization accuracy, thereby improving the real-time and accuracy of the prediction of the stability of the reinforced concrete underground continuous wall.

[0021] In the second aspect, the present invention provides a ground-connected wall stability prediction system based on LCP fiber composite grids, the reinforced concrete underground continuous wall stability prediction system comprising: a data acquisition device, a data query device, a processor and a storage device, the storage device comprising a computer-readable storage medium, the computer-readable storage medium storing a computer program, the computer program comprising program instructions, the program instructions when executed by the processor enable the processor to implement a ground-connected wall stability prediction method based on LCP fiber composite grids provided by the present invention. The system can stably run the method and improve the efficiency and automation of ground-connected wall stability prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A schematic flow chart of a method for predicting stability of a ground-connected wall based on an LCP fiber composite grid according to an embodiment of the present invention; Figure 2 This is a schematic diagram of an LCP fiber composite grid according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the position of the organic composite conductive fiber in the longitudinal limb of the LCP fiber composite grid according to an embodiment of the present invention; Figure 4 Schematic diagram of the installation of the LCP fiber composite grid in an embodiment of the present invention; Figure 5 It is a schematic diagram of the framework of a ground-connected wall stability prediction system based on LCP fiber composite grid according to an embodiment of the present invention.

[0024] Among them: 1-LCP fiber composite grid, 2-LCP fiber composite grid longitudinal limbs, 3-LCP fiber composite grid transverse limbs, 4-organic composite conductive fiber, 5-reinforced concrete underground continuous wall. DETAILED DESCRIPTION

[0025] The specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that these specific details do not need to be adopted to implement the present invention. In other examples, in order to avoid confusing the present invention, known circuits, software or methods are not specifically described.

[0026] Throughout the specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment of the present invention. Therefore, the phrases "in one embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily all refer to the same embodiment or example. In addition, particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combination and / or subcombination. In addition, it should be understood by those of ordinary skill in the art that the figures provided herein are for illustrative purposes and that the figures are not necessarily drawn to scale.

[0027] It should be noted in advance that, in an optional embodiment, except for independent explanations, the same symbols or letters appearing in all formulas have the same meanings and values.

[0028] In an alternative embodiment, see Figure 1 The present invention provides a method for predicting the stability of a ground-connected wall based on an LCP fiber composite grid, the method comprising the following steps: S1. Collect basic data of reinforced concrete underground continuous wall, wherein the basic data includes geological condition data, design parameter data, external load data and initial deviation data.

[0029] Specifically, in this embodiment, the geological condition data includes groundwater level and stratum thickness, the design parameter data includes wall thickness, burial depth, reinforcement, concrete ultimate strain and concrete tensile strength, and the external load data refers to ground load and water and soil load. The reinforced concrete underground continuous wall can also be referred to as the ground-connected wall. The basic data of the reinforced concrete underground continuous wall used in this embodiment can be obtained using existing technical means, and will not be described in detail here.

[0030] Furthermore, in other optional embodiments, the geological condition data and design parameter data may also include other types of data.

[0031] S2. Obtain the wall strain, wall stress, axial force, bending moment and curvature of reinforced concrete underground continuous wall based on LCP fiber composite grid.

[0032] Wherein, step S2 specifically includes the following steps: S21. When constructing a reinforced concrete underground continuous wall, the LCP fiber composite grid is arranged at the inner edge and the outer edge of the underground continuous wall respectively.

[0033] Specifically, in this embodiment, if Figure 2As shown, the LCP fiber composite mesh 1 is formed by pultruding LCP fiber as a base material and a resin, and includes a plurality of LCP fiber composite mesh longitudinal limbs 2 and LCP fiber composite mesh transverse limbs 3 and organic composite conductive fibers 4. In the LCP fiber composite mesh 1, the organic composite conductive fibers 4 are embedded in the center of the LCP fiber composite mesh longitudinal limbs 2 and the LCP fiber composite mesh transverse limbs 3. Figure 3 As shown, Figure 3 (a) is a LCP fiber composite grid longitudinal limb. Figure 3 (b) is a cross section of the LCP fiber composite grid longitudinal limb 2. The organic composite conductive fiber 4 is connected to the monitoring host.

[0034] For more details, see Figure 4 When manufacturing the reinforced concrete underground continuous wall 5, the LCP fiber composite intelligent grid 1 is placed at the inner edge and the outer edge of the reinforced concrete underground continuous wall 5. In addition, it should be understood that in other optional embodiments, the reinforced concrete underground continuous wall is not limited to Figure 4 The shape shown in the figure may also be other shapes, such as a rectangular reinforced concrete underground continuous wall.

[0035] Furthermore, the LCP fiber composite grid is low in cost and not easily damaged, which can reduce the detection cost and improve the survival rate of the detection. Moreover, placing LCP fiber composite smart grids at the inner and outer edges of the reinforced concrete underground continuous wall can also improve the bending stiffness and crack resistance of the reinforced concrete underground continuous wall.

[0036] S22. Using the monitoring host to monitor the resistance change of the organic composite conductive fiber, and then determining the fiber strain of the organic composite conductive fiber.

[0037] Specifically, in this embodiment, the resistance value of the LCP fiber composite mesh embedded with the organic composite conductive fiber will change with the change of the force, so the strain change of the organic composite conductive fiber can be obtained by detecting the change of the resistance value of the organic composite conductive fiber.

[0038] Furthermore, the implementation process of this step can refer to the prior art, and will not be described in more detail here.

[0039] S23. According to the fiber strain, the wall strain of each section of the reinforced concrete underground continuous wall is obtained by using the interpolation method, and then the wall stress of each section of the reinforced concrete underground continuous wall is obtained by combining the wall elastic modulus.

[0040] Specifically, in the present embodiment, the organic composite conductive fiber and the LCP fiber composite grid are deformed cooperatively, so the measured fiber strain is consistent with the LCP fiber composite grid. In other words, the fiber strain is the grid strain of the LCP fiber composite grid, that is, the wall strain where the LCP fiber composite grid is placed in the reinforced concrete underground continuous wall. When the wall strain at the inner edge of the reinforced concrete underground continuous wall and the wall strain at the outer edge are measured, the interpolation method can be used to obtain the wall strain of each section of the reinforced concrete underground continuous wall, and then the wall stress of each section of the reinforced concrete underground continuous wall is obtained in combination with the wall elastic modulus of the reinforced concrete underground continuous wall. The wall strain and wall stress of each section of the reinforced concrete underground continuous wall respectively satisfy the following relationship: in, is the wall strain of each section of the reinforced concrete underground continuous wall, Indicates interpolation operation. , , is the wall strain at the inner edge, is the fiber strain at the inner edge, is the wall strain at the outer edge, is the fiber strain at the outer edge, is the wall stress of each section of the reinforced concrete underground continuous wall, is the wall elastic modulus of the reinforced concrete underground continuous wall.

[0041] Furthermore, the calculation involved in obtaining the wall strain and wall stress of the reinforced concrete underground continuous wall based on the LCP fiber composite grid is not only simple but also highly accurate, which can improve the real-time and accuracy of the judgment of the cracking and the stability prediction of the reinforced concrete underground continuous wall.

[0042] S24. Calculate the axial force and the bending moment of the corresponding cross section according to the wall stress of each cross section of the reinforced concrete underground continuous wall, and calculate the curvature according to the bending moment.

[0043] Specifically, in this embodiment, the axial force, bending moment and curvature respectively satisfy the following relationships: in, is the axial force, is the cross-sectional area of ​​the reinforced concrete underground continuous wall, is the bending moment, is the distance from each stress point on the reinforced concrete underground continuous wall section to the neutral layer, is the curvature, is the bending stiffness of the reinforced concrete underground continuous wall.

[0044] Furthermore, the calculation involved in obtaining the axial force, bending moment and curvature of the reinforced concrete underground continuous wall based on the LCP fiber composite grid is not only simple, but also highly accurate, which can improve the real-time and accuracy of the judgment of the cracking of the reinforced concrete underground continuous wall and the prediction of its stability. S3. Compare the wall strain and the wall stress with the concrete ultimate strain and concrete tensile strength in the design parameter data respectively, and then determine whether the reinforced concrete underground continuous wall is cracked.

[0045] Specifically, in this embodiment, the wall strain of each section of the reinforced concrete underground continuous wall is compared with the ultimate strain of concrete, and the wall stress of each section of the reinforced concrete underground continuous wall is compared with the tensile strength of concrete. When the wall strain is not greater than the ultimate strain of concrete, and the wall stress is not greater than the tensile strength of concrete, it indicates that the section is not cracked, otherwise it indicates that the section is cracked.

[0046] Furthermore, by determining in real time whether the reinforced concrete underground continuous wall is cracked, timely measures can be taken to maintain the reinforced concrete underground continuous wall, which is beneficial to reducing safety hazards and economic losses.

[0047] S4. Establish a reinforced concrete underground continuous wall stability prediction data set, and establish a ground-connected wall stability prediction model based on the reinforced concrete underground continuous wall stability prediction data set.

[0048] Wherein, step S4 specifically includes the following steps: S41. Collect historical foundation data, historical axial force, historical bending moment, historical curvature and historical stability of reinforced concrete underground continuous walls.

[0049] Specifically, in this embodiment, the sources of historical basic data, historical axial force, historical bending moment, historical curvature and historical stability can be newspapers, periodicals or the Internet. The reinforced concrete underground continuous walls targeted when collecting data can be different reinforced concrete underground continuous walls. The more data sets obtained, the better. The collected data should be no less than 180 sets.

[0050] Furthermore, historical foundation data, historical axial force, historical bending moment, historical curvature and historical stability of different reinforced concrete underground continuous walls can be collected to obtain sufficient data for model training.

[0051] S42. Establish a reinforced concrete underground continuous wall stability prediction data set using the historical basic data, the historical axial force, the historical bending moment, the historical curvature and the historical stability.

[0052] Specifically, in this embodiment, the historical basic data, historical axial force, historical bending moment, historical curvature and historical stability are preprocessed, including outlier removal, missing value supplementation and data quantification. Among them, data quantification refers to the quantification of historical stability, which aims to replace the qualitative evaluation of historical stability with Arabic numerals to facilitate subsequent stability prediction.

[0053] Furthermore, the time series length is set, and the historical basic data, historical axial force, historical bending moment, historical curvature and historical stability are divided into multiple corresponding time series data according to the set time series length, so as to obtain multiple groups of time series data to form a reinforced concrete underground continuous wall stability prediction data set. Each group of time series data contains twelve types of time series data, namely groundwater level sequence data, stratum thickness sequence data, wall thickness sequence data, soil burial depth sequence data, reinforcement sequence data, ground load sequence data, water and soil load sequence data, initial deviation data sequence data, historical axial force sequence data, historical bending moment sequence data, historical curvature sequence data and historical stability sequence data.

[0054] S43. Improve the sparrow search algorithm to obtain an improved sparrow search algorithm.

[0055] Wherein, step S43 specifically includes the following steps: S431. Set the basic parameters of the sparrow search algorithm and use the Tent chaotic map to initialize the sparrow population.

[0056] Specifically, in this embodiment, the population size of the sparrow search algorithm is set to 50, the maximum number of iterations is set to 100, the dimension is the total number of weights and thresholds in the long short-term memory neural network, the optimization parameter target lower bound is 0.1, the optimization parameter target upper bound is 100, the warning value is 0.6, and the safety value is 0.8. After setting the basic parameters of the sparrow search algorithm, the sparrow population is initialized using the Tent chaotic map.

[0057] S432, the discovery position update formula and the follower position update formula of the sparrow search algorithm are improved, and the improved discovery position update formula and the follower position update formula are shown as follows: in, For the The iteration The discoverer in The position in the dimension, is a matrix that randomly assigns 1 or -1. and is a constant, is a random number in [-1,1], is the length of the search space, is the number of discoverers, For the The iteration The discoverer in The position in the dimension, is the warning value, is a safe value, is a random number that follows a normal distribution, is a matrix whose elements are all 1, For the The iteration Followers in The position in the dimension, For the The iteration Followers in The position in the dimension, For the The global best position of the finder at the iteration, For the The global best position of the finder at the iteration, For the The global best position of the finder at the iteration, Indicates a transpose operation. is the number of followers.

[0058] Specifically, in this embodiment, and The improved discovery position update formula and follower position update formula have lower computational complexity than the original position update formula, which can improve the optimization efficiency of the algorithm and avoid the sparrows converging to the origin. In the early stage of iteration, it can be slowly reduced with a larger value to increase the search range of the finder near itself, while in the later stage of iteration, it can be quickly reduced to a smaller value to increase the convergence speed of the algorithm.

[0059] S433, updating the positions of all sparrows in the sparrow population and calculating the fitness of all sparrows.

[0060] Specifically, in this embodiment, the relationship provided in step S332 is used to update the discovery position and the follower position, and the sentinel position is updated using the sentinel position update formula in the standard sparrow search algorithm, and then the fitness of all sparrows in the sparrow population is calculated.

[0061] Furthermore, the fitness function used in this embodiment to calculate the fitness of all sparrows satisfies the following relationship: in, For fitness, It is the mean square error of the long short-term memory neural network on the training set. The calculation method of MSE refers to the existing technology.

[0062] S434. Using a position adjustment function to adjust the position of each sparrow in the sparrow population according to the fitness.

[0063] Specifically, in this embodiment, considering that in the process of optimizing the weights and thresholds of the long short-term memory neural network using the sparrow search algorithm, the objective function may have a large number of local minima, which will cause the algorithm to fall into the local optimum. In order to further improve the optimization accuracy of the algorithm based on step S332, this embodiment introduces a position adjustment function to actively and adaptively adjust the position of the sparrow based on its fitness. The position adjustment function satisfies the following relationship: in, The sparrow position after adjustment. is the current position of the sparrow, is a random number that conforms to the standard normal distribution. is a random number in the Tent chaotic sequence in the interval (0,1), is the fitness of the sparrow, is the fitness threshold. The fitness threshold is the average fitness of all sparrows in the current iteration step.

[0064] S435, judging whether the current iteration step reaches the maximum number of iterations, and outputting the optimal sparrow individual information when the current iteration step reaches the maximum number of iterations.

[0065] S44, using the improved sparrow search algorithm to optimize the weights and thresholds of the long short-term memory neural network, and then constructing an initial stability prediction model.

[0066] Specifically, in this embodiment, the improved sparrow search algorithm is used to optimize the weights and thresholds of the long short-term memory neural network, and then the improved sparrow search algorithm and the long short-term memory neural network are used to construct an initial stability prediction model.

[0067] Using the sparrow search algorithm to optimize the weights and thresholds of the long short-term memory neural network can improve the accuracy of the prediction of the stability of reinforced concrete underground continuous walls. In addition, by improving the sparrow search algorithm, the complexity of the algorithm is reduced, the optimization speed and accuracy of the algorithm are improved, and the real-time prediction of the stability of reinforced concrete underground continuous walls is improved, and the accuracy of the prediction of the stability of reinforced concrete underground continuous walls is further improved.

[0068] S45. Use the reinforced concrete underground continuous wall stability prediction data set to complete the training and verification of the initial stability prediction model to obtain the underground continuous wall stability prediction model.

[0069] Specifically, in this embodiment, the reinforced concrete underground continuous wall stability prediction data set is divided into a training set and a verification set in a ratio of 7:3, thereby completing the training and verification of the initial stability prediction model, and finally obtaining the underground continuous wall stability prediction model.

[0070] S5. Predict the stability of the reinforced concrete underground continuous wall using the underground continuous wall stability prediction model according to the basic data, the axial force, the bending moment and the curvature.

[0071] Specifically, in this embodiment, the basic data, axial force, bending moment and curvature acquired in real time are input into the ground-connected wall stability prediction model, so that the real-time stability of the reinforced concrete underground continuous wall can be predicted, thereby improving the efficiency and real-time performance of the ground-connected wall stability analysis, allowing relevant personnel to quickly understand the stability of the reinforced concrete underground continuous wall and take protective measures in a timely manner when necessary, which is conducive to reducing safety hazards and economic losses.

[0072] It should be noted that, in some cases, the actions described in the specification can be performed in a different order and still achieve the desired results. In this embodiment, the order of steps given is only to make the embodiment appear clearer and easier to explain, rather than to limit it.

[0073] In an alternative embodiment, see Figure 5The present invention also provides a ground-connected wall stability prediction system based on LCP fiber composite grids, the reinforced concrete underground continuous wall stability prediction system includes: data acquisition equipment A1, data query equipment A2, processor A3 and storage A4, the storage A4 includes a computer-readable storage medium, the computer-readable storage medium stores a computer program, the computer program includes program instructions, and when the program instructions are executed by the processor A3, the processor A3 implements a ground-connected wall stability prediction method based on LCP fiber composite grids provided in this embodiment. The system can stably run the method provided by the present invention, and improve the efficiency and automation of ground-connected wall stability prediction.

[0074] Specifically, in this embodiment, the data acquisition device 1 includes a monitoring host, an LCP fiber composite grid and a data input module, and the relevant personnel collect the basic data of the reinforced concrete underground continuous wall and input the data into the data acquisition device 1 through the data input module. The data query device 2 includes a digital display screen, and the stability of the reinforced concrete underground continuous wall can be displayed through the numerical display screen.

[0075] In summary, the present method is based on LCP fiber composite grid to obtain the strain, stress, axial force, bending moment and curvature of the reinforced concrete underground continuous wall in real time, and then monitors in real time whether the reinforced concrete underground continuous wall is cracked. The calculation involved is simple and the accuracy is high. It can improve the real-time and accuracy of the prediction of the stability of the reinforced concrete underground continuous wall. The LCP fiber composite grid has low water absorption, low cost, and is not easy to damage. It can reduce the detection cost and improve the survival rate of the detection, as well as improve the bending stiffness and crack resistance of the reinforced concrete underground continuous wall. After obtaining the basic data, strain, stress, axial force, bending moment and curvature of the reinforced concrete underground continuous wall, the present invention further determines whether the reinforced concrete underground continuous wall is cracked, and uses the ground-connected wall stability prediction model to realize the rapid and accurate prediction of the ground-connected wall stability, which improves the efficiency and real-time analysis of the ground-connected wall stability, and is conducive to reducing safety hazards and economic losses. In addition, the system can stably run the method provided by the present invention to improve the efficiency and automation of the ground-connected wall stability prediction.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the specification of the present invention.

Claims

1. A method for predicting the stability of ground-connected walls based on LCP fiber composite grids, characterized in that: The steps include: Collecting basic data of reinforced concrete underground continuous wall, the basic data including geological condition data, design parameter data, external load data and initial deviation data; Obtain the wall strain, wall stress, axial force, bending moment and curvature of reinforced concrete underground continuous wall based on LCP fiber composite grid; The wall strain and the wall stress are compared with the concrete ultimate strain and concrete tensile strength in the design parameter data, respectively, to determine whether the reinforced concrete underground continuous wall is cracked; Establish a reinforced concrete underground continuous wall stability prediction data set, and establish a ground-connected wall stability prediction model based on the reinforced concrete underground continuous wall stability prediction data set; The stability of the reinforced concrete underground continuous wall is predicted using the underground continuous wall stability prediction model according to the basic data, the axial force, the bending moment and the curvature.

2. The method for predicting the stability of a ground-connected wall based on an LCP fiber composite grid according to claim 1 is characterized in that: The LCP fiber composite grid is formed by pultruding LCP fiber as a base material and resin, and organic composite conductive fibers are embedded in the center of the LCP fiber composite grid transverse limbs and the LCP fiber composite grid longitudinal limbs, and the organic composite conductive fibers are connected to the monitoring host.

3. A method for predicting the stability of a ground-connected wall based on an LCP fiber composite grid according to claim 2, characterized in that: The method of obtaining the wall strain, wall stress, axial force, bending moment and curvature of the reinforced concrete underground continuous wall based on the LCP fiber composite grid includes the following steps: When constructing a reinforced concrete underground continuous wall, the LCP fiber composite grid is arranged at the inner edge and the outer edge of the underground continuous wall respectively; Using the monitoring host to monitor the resistance change of the organic composite conductive fiber, and then determine the fiber strain of the organic composite conductive fiber; According to the fiber strain, the wall strain of each section of the reinforced concrete underground continuous wall is obtained by using the interpolation method, and then the wall stress of each section of the reinforced concrete underground continuous wall is obtained by combining the wall elastic modulus; The axial force and the bending moment of the corresponding cross section are calculated according to the wall stress of each cross section of the reinforced concrete underground continuous wall, and the curvature is calculated according to the bending moment.

4. A method for predicting the stability of a ground-connected wall based on an LCP fiber composite grid according to claim 3, characterized in that: The wall strain and the wall stress of each cross section of the reinforced concrete underground continuous wall respectively satisfy the following relationship: in, is the wall strain of each section of the reinforced concrete underground continuous wall, Indicates interpolation operation. , , is the wall strain at the inner edge, is the fiber strain at the inner edge, is the wall strain at the outer edge, is the fiber strain at the outer edge, is the wall stress of each section of the reinforced concrete underground continuous wall, It is the wall elastic modulus of the reinforced concrete underground continuous wall.

5. The method for predicting the stability of a ground-connected wall based on an LCP fiber composite grid according to claim 3, characterized in that: The axial force satisfies the following relationship: in, is the axial force, is the cross-sectional area of ​​the reinforced concrete underground continuous wall, is the wall stress of each section of the reinforced concrete underground continuous wall.

6. A method for predicting the stability of a ground-connected wall based on an LCP fiber composite grid according to claim 3, characterized in that: The bending moment and the curvature respectively satisfy the following relationship: in, is the bending moment, is the cross-sectional area of ​​the reinforced concrete underground continuous wall, is the wall stress of each section of the reinforced concrete underground continuous wall, is the distance from each stress point on the reinforced concrete underground continuous wall section to the neutral layer, is the curvature, is the bending stiffness of the reinforced concrete underground continuous wall.

7. The method for predicting the stability of a ground-connected wall based on LCP fiber composite grid according to claim 1, characterized in that: The step of establishing a reinforced concrete underground continuous wall stability prediction data set and establishing a ground continuous wall stability prediction model based on the reinforced concrete underground continuous wall stability prediction data set comprises the following steps: Collect historical foundation data, historical axial force, historical bending moment, historical curvature and historical stability of reinforced concrete underground continuous walls; Establishing a reinforced concrete underground continuous wall stability prediction data set using the historical basic data, the historical axial force, the historical bending moment, the historical curvature and the historical stability; Improve the sparrow search algorithm to obtain an improved sparrow search algorithm; Using the improved sparrow search algorithm to optimize the weights and thresholds of the long short-term memory neural network, and then constructing an initial stability prediction model; The reinforced concrete underground continuous wall stability prediction data set is used to complete the training and verification of the initial stability prediction model to obtain the underground continuous wall stability prediction model.

8. The method for predicting the stability of a ground-connected wall based on an LCP fiber composite grid according to claim 7, characterized in that: The improved sparrow search algorithm comprises the following steps: Set the basic parameters of the sparrow search algorithm and use the Tent chaos map to initialize the sparrow population; The discovery position update formula and follower position update formula of the sparrow search algorithm are improved. The improved discovery position update formula and follower position update formula are shown as follows: in, For the The iteration The discoverer in The position in the dimension, is a matrix that randomly assigns 1 or -1. and is a constant, is a random number in [-1,1], is the length of the search space, is the number of discoverers, For the The first iteration The discoverer in The position in the dimension, is the warning value, is a safe value, is a random number that follows a normal distribution, is a matrix whose elements are all 1, For the The first iteration Followers in The position in the dimension, For the The first iteration Followers in The position in the dimension, For the The global best position of the finder at the iteration, For the The global best position of the finder at the iteration, For the The global best position of the finder at the iteration, Indicates a transpose operation. is the number of followers; Update the positions of all sparrows in the sparrow population and calculate the fitness of all sparrows; Using a position adjustment function to adjust the position of each sparrow in the sparrow population according to the fitness; It is determined whether the current iteration step reaches the maximum number of iterations, and when the current iteration step reaches the maximum number of iterations, the optimal sparrow individual information is output.

9. A method for predicting the stability of a ground-connected wall based on LCP fiber composite grid according to claim 8, characterized in that: The position adjustment function satisfies the following relationship: in, The sparrow position after adjustment. is the current position of the sparrow, is a random number that conforms to the standard normal distribution. is a random number in the Tent chaotic sequence in the interval (0,1), is the fitness of the sparrow, is the fitness threshold.

10. A ground-connected wall stability prediction system based on LCP fiber composite grid, the reinforced concrete underground continuous wall stability prediction system comprising: A data acquisition device, a data query device, a processor and a storage device, wherein the storage device comprises a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program comprises program instructions, and when the program instructions are executed by the processor, the processor implements a method for predicting the stability of a ground-connected wall based on an LCP fiber composite grid as described in any one of claims 1 to 9.

Images