A plum blossom-shaped reinforcement structure for large semi-filled karst caves and a filling method

Abstract

The present invention provides a plum blossom-shaped reinforcement structure for large semi-filled karst caves and a filling method, which is applicable to the field of karst cave treatment in underground engineering, including karst cave geological exploration and modeling, borehole layout design, grouting construction, and karst cave filling effect detection. By integrating a recurrent neural network prediction model with parametric activation functions and a multi-stage dynamic pressure regulation system, the present invention realizes the integration of accurate borehole positioning, intelligent pressure prediction, and adaptive regulation in the reinforcement construction of large semi-filled karst caves, and has significant engineering applicability and large-scale popularization value in the field of karst cave treatment in infrastructure construction such as tunnels and bridges.

Description

Technical Field

[0001] The present invention relates to a plum blossom-shaped reinforcement structure and filling method for large semi-filled karst caves, which is applicable to the field of karst cave treatment in underground engineering. Background Art

[0002] With the rapid development of infrastructure construction in China, when carrying out projects such as tunnels and bridges in karst landform areas, the reinforcement treatment of large semi-filled karst caves has become a key technical problem. Traditional karst cave reinforcement methods mostly adopt disordered grouting or uniform hole arrangement methods, which have problems such as rough control of grouting pressure, uneven distribution of filling materials, and difficult quantitative evaluation of reinforcement effects. In the prior art, the control of grouting pressure mainly relies on manual experience adjustment and lacks the ability of real-time dynamic prediction, resulting in slurry channeling caused by sudden pressure rise or incomplete filling caused by insufficient pressure during the grouting process. Especially in the scenario of plum blossom-shaped hole arrangement, due to the mutual influence of grouting pressures between the central hole and the edge holes, the traditional PID control method is difficult to adapt to the complex working conditions of multi-device collaborative operation.

[0003] In recent years, although some studies have tried to apply machine learning to grouting pressure prediction, there are still problems such as insufficient data adaptability and lag in dynamic response. Therefore, there is an urgent need to develop a karst cave reinforcement technology system that integrates intelligent prediction and dynamic regulation. Summary of the Invention

[0004] The purpose of the present invention is to solve the problem of dynamic regulation of grouting pressure in the plum blossom-shaped reinforcement filling of semi-filled karst caves at present, and a plum blossom-shaped reinforcement structure and filling method for large semi-filled karst caves are proposed.

[0005] The purpose of the present invention can be achieved by adopting the following technical solutions:

[0006] A plum blossom-shaped reinforcement structure and filling method for large semi-filled karst caves, comprising the following steps:

[0007] S101. Karst cave geological investigation and modeling;

[0008] The karst cave geological investigation and modeling include determining the spatial form of the karst cave through three-dimensional geological radar scanning and establishing a three-dimensional model of the karst cave;

[0009] S102. Drilling layout design;

[0010] The drilling layout design includes arranging grouting drill holes on the surface of the karst cave roof in a plum blossom shape according to the three-dimensional model of the karst cave. The plum blossom-shaped arrangement of grouting drill holes includes a central hole and adjacent drill holes. The distance L between the central hole and the adjacent drill holes is obtained by formula (1),

[0011] (1)

[0012] Wherein, k is an adjustment parameter with a value range of 0.4 to 0.6, and H is the height of the karst cave;

[0013] S103. Grouting construction;

[0014] The grouting construction includes using the layered grouting technique for karst cave grouting. The layered grouting technique includes dividing the karst cave grouting work into n grouting sections for layered grouting, where n ranges from 3 to 5. The karst cave grouting includes a grouting pressure control method to control the karst cave grouting pressure within a reasonable range;

[0015] S104. Form a plum blossom-shaped reinforcement structure for a large semi-filled karst cave;

[0016] The formation of the plum blossom-shaped reinforcement structure for a large semi-filled karst cave includes using the layered grouting technique for karst cave grouting to finally form a plum blossom-shaped reinforcement structure for a large semi-filled karst cave;

[0017] S105. Detection of karst cave filling effect;

[0018] The detection of the karst cave filling effect includes detecting the karst cave filling effect of the plum blossom-shaped reinforcement structure for the large semi-filled karst cave.

[0019] Furthermore, in the above step S103, the implementation steps of the grouting pressure control method are as follows:

[0020] a) There are a total of n grouting devices, marked as S 1 ~S n . Install a grouting pressure sensor P i on the grouting device S i . Obtain the pressure sensing data P i of the pressure sensor P ij at a fixed time interval t, and organize the pressure sensing data P i of the pressure sensor P ij for a period of time to form a data set C i ;

[0021] b) Preprocess the data in the data set C i . The preprocessing includes querying and interpolating missing values in the data in the data set C i . The interpolation of missing values uses the cubic spline interpolation method. The preprocessing also includes normalizing the data in the data set C i . The preprocessing includes dividing the data in the data set C i into a training set and a test set;

[0022] c) Construct a recurrent neural network model prediction model. The recurrent neural network prediction model includes an input layer, a hidden layer, and an output layer. The activation function used in the hidden layer is a parametric hyperbolic tangent function, and the expression of the parametric hyperbolic tangent function is shown in Equation (2).

[0023] (2)

[0024] In the formula, β is a trainable parameter, and its value range is [0.2, 0.4];

[0025] d) Use the data in the training set to train the recurrent neural network model prediction model, and use the data in the test set to test and optimize the recurrent neural network model prediction model, and finally obtain a deployable prediction model;

[0026] e) Use the prediction model to perform model prediction to obtain the future predicted value W ij of the pressure sensing data P ij+1 ;

[0027] f) Evaluate the grouting pressure situation according to the obtained future predicted value W ij+1 and perform corresponding processing actions to achieve the purpose of controlling the grouting pressure.

[0028] Furthermore, the evaluation of the grouting pressure situation according to the obtained future predicted value W ij+1 and performing corresponding processing actions include the following steps:

[0029] a) Determine which stage it is in according to the obtained future predicted value W ij+1 and the time T ij+1 when obtaining the future predicted value W ij+1 through Equation (3).

[0030] (3)

[0031] In the formula, T is the planned grouting time;

[0032] b) When the judgment result is the initial stage, judge whether the future predicted value W ij+1 meets the initial stage pressure requirement through formula (4). If it meets, do nothing. If it does not meet, issue a warning;

[0033] (4)

[0034] c) When the judgment result is the final pressure stage, judge whether the future predicted value W ij+1 meets the final pressure stage pressure requirement through formula (5). If it meets, do nothing. If it does not meet, issue a warning;

[0035] (5)

[0036] d) Regardless of the judgment result at any stage, it is necessary to judge whether the future predicted value W ij+1 meets the requirements of sudden pressure drop,

[0037] (6)

[0038] If it meets the requirements, no action is taken; if it does not meet the requirements, a warning is issued.

[0039] Further, in the above step S104, the large semi-filled karst cave plum blossom-shaped reinforcement structure is composed of an unproven karst cave boundary part outside the karst cave, a proven karst cave boundary part inside the karst cave, a part of sand, gravel, and soft mud filling, a double-slurry agitation mixture grout curtain part, a part of multiple normal-pressure grouting of cement mortar, a part of multiple high-pressure filling grouting of cement, and a part of high-pressure grouting to fill gaps and cracks to form a sand and gravel vein grout mixture.

[0040] Further, in the above step S105, the method for detecting the filling effect of the karst cave includes a filling effect calculation method based on weight calculation, and the filling effect calculation method based on weight calculation includes the following steps:

[0041] a) Divide the filling area into n grids, the shape of the grids is a square with a side length of a, and the value of a is 5 - 15m,

[0042] b) Use ground penetrating radar to scan in the nth grid to obtain the volume filling rate , and the calculation formula of the volume filling rate is shown in formula (7),

[0043] (7)

[0044] In the formula, V 1 is the void volume 28 days after grouting, and V 2 is the volume of the karst cave before grouting;

[0045] c) Use the drilling method to calculate the volume filling rate in the nth grid area, and the calculation formula of the volume filling rate is shown in formula (8),

[0046] (8)

[0047] In the formula, L 1 is the sum of the lengths of the cement mixture and the void in the core drilling section, and L 2 is the total length of the drilling;

[0048] d) Calculate the weighted filling rate, and use the weighted calculation method to calculate the comprehensive filling rate of the nth grid. , and the calculation formula is shown in Equation (9).

[0049] (9)

[0050] d) Grading judgment of filling effect. When ≥95%, it is judged as a first-level filling effect, and at this time, no additional grouting is required. When 95% > ≥90%, it is judged as a second-level filling effect, and grouting needs to be combined with the geological radar scanning results. When <90%, it is judged as a third-level grouting effect, and at this time, the grouting plan needs to be redesigned.

[0051] The beneficial effects of the present invention are as follows: (1) Space-adaptive plum blossom-shaped hole layout design; based on the three-dimensional model of the karst cave, the hole spacing is dynamically calculated through the formula L = k⋅H (k = 0.4∼0.6), and the space-adaptive hole layout is realized in combination with the height H of the karst cave. (2) Intelligent hierarchical grouting pressure control system; innovatively use the parametric hyperbolic tangent function as the activation function of the hidden layer of the recurrent neural network. This function adaptively adjusts the non-linear response intensity through trainable parameters, and in the grouting pressure prediction task, the mean absolute error is reduced compared with the standard tanh function. (3) Multi-stage pressure threshold dynamic judgment; design a three-stage pressure evaluation mechanism to judge the grouting state through the two dimensions of time and pressure. Brief Description of the Drawings

[0052] Figure 1 is the flow chart of a plum blossom-shaped reinforcement structure and filling method for a large semi-filled karst cave of the present invention;

[0053] Figure 2 is the plum blossom-shaped reinforcement structure diagram of the embodiment of the present invention;

[0054] 1 - Double-fluid grouting area, 2 - Double-fluid stirring mixture grout curtain wall, 3 - Outer unexplored karst cave boundary, 4 - Fillings such as sand, gravel, and soft mud, 5 - Cement slurry grouting, 6 - High-pressure grouting to fill cracks and fissures, 7 - Cement mortar grouting, 8 - Inner explored karst cave boundary;

[0055] Figure 3 is the detailed drawing of the plum blossom-shaped reinforcement structure of the embodiment of the present invention; 9 - Cement mortar normal-pressure grouting, 10 - Cement high-pressure filling grouting. Detailed Embodiments

[0056] The following is a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings; it should be understood that the specific embodiments given here are only used to illustrate and explain the present invention and cannot be used to limit the present invention.

[0057] The following is a specific embodiment of a large semi-filled karst cave plum blossom-shaped reinforcement structure and filling method.

[0058] S101. Karst cave geological exploration and modeling;

[0059] The karst cave geological exploration and modeling includes determining the spatial form of the karst cave through three-dimensional geological radar scanning and establishing a three-dimensional model of the karst cave;

[0060] S102. Borehole layout design;

[0061] The borehole layout design includes arranging grouting boreholes on the surface of the karst cave roof in a plum blossom shape according to the three-dimensional model of the karst cave. The plum blossom-shaped arrangement of grouting boreholes includes a central hole and adjacent boreholes. The distance L between the central hole and the adjacent boreholes is obtained through formula (1),

[0062] (1)

[0063] where k is an adjustment parameter with a value of 0.4 - 0.6, and H is the height of the karst cave;

[0064] S103. Grouting construction;

[0065] The grouting construction includes using the layered grouting technique for karst cave grouting. The layered grouting technique includes dividing the karst cave grouting work into n grouting sections for layered grouting. The value of n is 3 - 5. The karst cave grouting includes a grouting pressure control method to control the karst cave grouting pressure within a reasonable range;

[0066] Further, in the above step S103, the implementation steps of the grouting pressure control method are as follows:

[0067] a) There are a total of n grouting devices, marked as S 1 ~S n , and a grouting pressure sensor P i is installed on the grouting device S i . The pressure sensing data P i of the pressure sensor P ij is obtained at a fixed time interval t. The pressure sensing data P i of the pressure sensor P ij for a period of time is sorted to form a data set C i ;

[0068] b) The data in the data set C i is preprocessed. The preprocessing includes querying and interpolating missing values in the data set C i . The interpolation of missing values uses the cubic spline interpolation method. The preprocessing also includes the data set C iNormalize the data in it, and the preprocessing includes dividing the data set C i in it into a training set and a test set;

[0069] c) Construct a recurrent neural network model prediction model. The recurrent neural network prediction model includes an input layer, a hidden layer, and an output layer. The activation function used in the hidden layer is a parametric hyperbolic tangent function, and the expression of the parametric hyperbolic tangent function is shown in Equation (2).

[0070] (2)

[0071] In the formula, is a trainable parameter, and its value range is [0.2, 0.4];

[0072] d) Use the data in the training set to train the recurrent neural network model prediction model, and use the data in the test set to test and optimize the recurrent neural network model prediction model, and finally obtain a deployable prediction model;

[0073] e) Use the prediction model to perform model prediction to obtain the future predicted value W ij of the pressure sensing data P ij+1 ;

[0074] f) Evaluate the grouting pressure situation according to the obtained future predicted value W ij+1 and make corresponding processing actions to achieve the purpose of controlling the grouting pressure.

[0075] Furthermore, the evaluating the grouting pressure situation according to the obtained future predicted value W ij+1 and making corresponding processing actions include the following steps:

[0076] a) Determine which stage it is in according to the obtained future predicted value W ij+1 and the time T ij+1 when obtaining the future predicted value W ij+1 by judging through Equation (3).

[0077] (3)

[0078] In the formula, T is the planned grouting time;

[0079] b) When the judgment result is the initial stage, judge whether the future predicted value W ij+1 meets the initial stage pressure requirement through formula (4). If it meets, do nothing. If it does not meet, issue a warning;

[0080] (4)

[0081] c) When the judgment result is the final pressure stage, judge the future predicted value W through formula (5). ij+1 Whether it meets the pressure requirement of the final pressure stage. If it meets, do nothing. If it does not meet, issue a warning.

[0082] (5)

[0083] d) Regardless of the judgment result of any stage, it is necessary to judge whether the future predicted value W meets the requirement of sudden pressure drop through formula (6). ij+1 Whether it meets the requirement of sudden pressure drop.

[0084] (6)

[0085] If it meets, do nothing. If it does not meet, issue a warning.

[0086] S104. Form a plum-blossom-shaped reinforcement structure for large semi-filled karsts.

[0087] The formation of the plum-blossom-shaped reinforcement structure for large semi-filled karsts includes using the layered grouting technology to grout the karst, and finally forming a plum-blossom-shaped reinforcement structure for large semi-filled karsts.

[0088] Furthermore, in the above step S104, the plum-blossom-shaped reinforcement structure for large semi-filled karsts is composed of the part of the unproven karst boundary outside the karst, the part of the proven karst boundary inside the karst, the part of sand, gravel, and soft mud fillings, the part of the double-slurry agitation mixture slurry stop curtain wall, the part of multiple normal-pressure grouting of cement mortar, the part of multiple high-pressure filling grouting of cement, and the part of high-pressure grouting to fill the gaps and cracks to form a sand and gravel vein slurry mixture.

[0089] In this embodiment, the formed plum-blossom-shaped reinforcement structure for large semi-filled karsts is as shown in Figure 2 shown, and the detailed drawing of the formed plum-blossom-shaped reinforcement structure is as shown in Figure 3 shown. The composition of this kind of reinforcement structure is: the unproven karst boundary outside the karst, the proven karst boundary inside the karst, fillings such as sand, gravel, and soft mud, the double-slurry agitation mixture slurry stop curtain wall, multiple normal-pressure grouting of cement mortar, multiple high-pressure filling grouting of cement, high-pressure grouting to fill the gaps and cracks to form a sand and gravel vein slurry mixture, etc.

[0090] At the same time, the composition advantages of this part of the structure are: the plum-blossom-shaped grouting can achieve full and saturated grouting. The combination of common grouting of cement mortar and high-pressure grouting of cement slurry enables the sand, soft mud, water, and poisonous gas in the karst to be agitated through grouting, removing water and other poisons. The soft mud reacts chemically with the cement slurry to form a vein-like mixture, and the sand and cement slurry form a concrete-like mixture, achieving the purpose of filling and reinforcing large karsts.

[0091] S105. Detection of the filling effect of the karst.

[0092] The detection of the filling effect of the karst cave includes the detection of the filling effect of the plum blossom-shaped reinforcement structure of the large semi-filled karst cave.

[0093] Further, in the above step S105, the method for detecting the filling effect of the karst cave includes a filling effect calculation method based on weight calculation, and the filling effect calculation method based on weight calculation includes the following steps:

[0094] a) Divide the filling area into n grids, the shape of the grid is a square with a side length of a, and a ranges from 5 to 15 m.

[0095] b) Use ground penetrating radar to scan in the nth grid to obtain the volume filling rate , and the calculation formula of the volume filling rate is shown in formula (7).

[0096] (7)

[0097] In the formula, V 1 is the void volume 28 days after grouting, and V 2 is the volume of the karst cave before grouting.

[0098] c) Use the drilling method to calculate the volume filling rate in the nth grid area , and the calculation formula of the volume filling rate is shown in formula (8).

[0099] (8)

[0100] In the formula, L 1 is the sum of the lengths of the cement mixture and the void in the core drilling section, and L 2 is the total length of the drilling.

[0101] d) Calculate the weighted filling rate, and use the weighted calculation method to calculate the comprehensive filling rate of the nth grid , and the calculation formula is shown in formula (9).

[0102] (9)

[0103] e) Grade determination of the filling effect. When ≥95%, it is determined as a first-level filling effect, and at this time, no additional grouting is required. When 95% > ≥90%, it is determined as a second-level filling effect, and grouting needs to be carried out in combination with the ground penetrating radar scanning results. When <90%, it is determined as a third-level grouting effect, and at this time, a new grouting plan needs to be designed.

[0104] In the above embodiments, the present invention discloses a large semi-filled karst cave plum blossom-shaped reinforcement structure and filling method; including karst cave geological investigation and modeling, borehole layout design, grouting construction, and karst cave filling effect detection. Through the recurrent neural network prediction model integrating parametric activation functions and the multi-stage dynamic pressure regulation system, the present invention realizes the integration of precise borehole positioning, intelligent pressure prediction, and adaptive regulation in the reinforcement construction of large semi-filled karst caves, and has significant engineering applicability and large-scale popularization value in the field of karst cave treatment in infrastructure construction such as tunnels and bridges.

[0105] The above are the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A large semi-filled karst cave plum blossom-shaped reinforcement structure and filling method, characterized in that: The following steps are involved: S101, karst geological survey and modeling; The karst cave geological survey and modeling includes determining the spatial morphology of the karst cave through three-dimensional geological radar scanning and establishing a three-dimensional model of the karst cave; S102, drilling arrangement design; The drilling arrangement design includes arranging grouting drilling holes in a plum blossom shape on the surface of the cave roof according to the three-dimensional model of the cave. The plum blossom-shaped grouting drilling holes include a center hole and adjacent drilling holes. The spacing L between the center hole and the adjacent drilling holes is obtained by formula (1). （1） In the formula, k is the adjustment parameter, with a value of 0.4~0.6, and H is the cave height; S103, grouting construction; The grouting construction includes adopting the layered grouting technology to carry out cave grouting, the layered grouting technology includes dividing the cave grouting work into n grouting sections for layered grouting, the value of n is 3-5, the cave grouting includes a grouting pressure control method to control the cave grouting pressure within a reasonable range; the implementation steps of the grouting pressure control method are: a) There are n grouting equipments, marked as S1~S n , in the grouting equipment S i Install the grouting pressure sensor P i , obtain the pressure sensor P at a fixed time interval t i The pressure sensing data P ij , sort out the pressure sensor P for a period of time i The pressure sensing data P ij , forming the data set C i ; b) For the dataset C i The data in the data set C is preprocessed, and the preprocessing includes i The missing values ​​of the data in the C are queried and interpolated, and the interpolation of the missing values ​​adopts the cubic spline interpolation method. The preprocessing also includes the data set C i The data in the data set C are normalized. The preprocessing includes normalizing the data set C i The data in is divided into training set and test set; c) constructing a recurrent neural network model prediction model, wherein the recurrent neural network model prediction model includes an input layer, a hidden layer and an output layer, wherein the activation function used by the hidden layer is a parameterized hyperbolic tangent function, and the expression of the parameterized hyperbolic tangent function is shown in formula (2). （2） Where β is a trainable parameter, and its value range is [0.2, 0.4]; d) Using the data of the training set to carry out model training on the recurrent neural network model prediction model, and using the data of the test set to carry out model testing and optimization on the recurrent neural network model prediction model, and finally obtaining a deployable prediction model; e) Using the prediction model to perform model prediction to obtain pressure sensing data P ij The future prediction value W ij+1 ; f) Based on the obtained future prediction value W ij+1 Evaluate the grouting pressure and take corresponding actions to achieve the purpose of controlling the grouting pressure; S104, forming a large semi-filled cave plum blossom-shaped reinforcement structure; The forming of a large semi-filled karst cave plum blossom-shaped reinforcement structure comprises using the layered grouting technology to perform karst cave grouting to finally form a large semi-filled karst cave plum blossom-shaped reinforcement structure; S105, cave filling effect detection; The cave filling effect detection includes performing cave filling effect detection on the large semi-filled cave plum blossom-shaped reinforcement structure.

2. A large-scale semi-filled karst cave plum blossom-shaped reinforcement structure and filling method according to claim 1, characterized in that: The future prediction value W obtained according to ij+1 Evaluating the grouting pressure and taking corresponding action includes the following steps: a) Based on the obtained future prediction value W ij+1 And get the future prediction value W ij+1 Time T ij+1 To determine which stage it is in, we use formula (3) to make a judgment: (3) Where T is the planned grouting time; b) When the judgment result is the initial stage, the future prediction value W is determined by formula (4) ij+1 Whether the initial stage pressure requirements are met, if they are met, no action is taken, if they are not met, an early warning is issued; （4） c) When the judgment result is the final pressure stage, the future prediction value W is determined by formula (5) ij+1 Whether the pressure requirement of the final pressure stage is met, if it is met, no action is taken, if it is not met, an early warning is issued; （5） d) Regardless of the stage of the judgment result, it is necessary to use formula (6) to determine the future prediction value W ij+1 Whether the pressure drop requirements are met, （6） If it meets the requirements, no action will be taken; if it does not meet the requirements, an early warning will be issued.

3. A large-scale semi-filled karst cave plum blossom-shaped reinforcement structure and filling method according to claim 1, characterized in that: In step S104, the large semi-filled cave plum blossom-shaped reinforcement structure consists of an unexplored cave boundary portion outside the cave, an explored cave boundary portion inside the cave, a sand, gravel, and soft mud filling portion, a double-slurry stirring mixture grouting curtain wall portion, a cement mortar multiple normal pressure grouting portion, a cement multiple high-pressure filling grouting portion, and a high-pressure grouting to fill gaps and cracks to form a sand and gravel vein slurry mixture portion.

4. A large-scale semi-filled karst cave plum blossom-shaped reinforcement structure and filling method according to claim 1, characterized in that: In step S105, the method for detecting the filling effect of the cave includes a filling effect calculation method based on weight calculation, and the filling effect calculation method based on weight calculation includes the following steps: a) Divide the filling area into n grids, each grid is a square with a side length of a, where a is 5-15 m. b) Obtain volume filling rate using geological radar scanning on the nth grid , volume filling rate The calculation formula is shown in formula (7): (7) where V1 is the void volume after 28 days of grouting, and V2 is the cave volume before grouting; c) The volume filling rate β is calculated by the drilling method in the nth grid area. The calculation formula of the volume filling rate β is shown in formula (8): (8) where L1 is the sum of the lengths of the cement mixture and the voids in the coring section of the borehole, and L2 is the total length of the borehole; d) Calculate the weighted filling rate and use the weighted calculation method to calculate the comprehensive filling rate of the nth grid , the calculation formula is shown in formula (9), （9） e) Filling effect grading judgment, when ≥95%, it is judged as the first-level filling effect, and no further grouting is required. ≥90%, it is judged as the secondary filling effect, and grouting needs to be carried out in combination with the geological radar scanning results. When it is less than 90%, it is judged as the third-level grouting effect, and the grouting plan needs to be redesigned.

Images