Tunneling intelligent grouting control method and device

Abstract

The application discloses a tunnel excavation intelligent grouting control method and device, and relates to the technical field of tunnel safety, which comprises the following steps: firstly, matching a risk level according to a rock mass state and setting initial grouting parameters; then, establishing a coupling optimization model, adopting a discrete temperature scheduling strategy with k as a period to perform simulated annealing iteration, and efficiently converging to obtain optimal parameters; finally, dynamically executing grouting through a PLC controller and forming a closed-loop control to realize safe, accurate and economic grouting operation. The application establishes a grouting dynamic coupling optimization model, iterates by using a simulated annealing algorithm, constructs the model by using a pressure difference value, an ungrouted value and a total grouting amount, preferentially prevents pressure overrun and water gushing, and solves the safety risk of traditional experience parameters; the application introduces a discretized temperature scheduling, sets an iteration period k, and performs step-by-step temperature reduction when the period k is evenly divided, so that exploration and precision seeking are balanced, and efficient convergence in a limited period is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tunnel safety, in particular to a tunnel excavation intelligent grouting control method and device. BACKGROUND

[0002] Tunnel excavation is an engineering activity that excavates an underground channel with a specific cross-sectional shape, length and function in a concealed space such as underground, mountain and underwater, through professional engineering technology and equipment. The core purpose is to build a channel across geographical barriers and save surface space for transportation, water conservancy, energy and urban municipal fields.

[0003] During operation, special grout is injected into the stratum fissure, pore and structure gap according to the stratum condition and risk demand, filling the internal gap of the stratum, improving the overall strength and stability of the stratum, and avoiding the collapse and block of the working face during excavation; and filling the gap to prevent later stratum settlement and ensure long-term stability of the tunnel structure.

[0004] For example, the grouting structure and matching grouting method in the tunnel excavation process disclosed in the patent with publication number CN106761837B include, from the tunnel inner wall, rock layer and tube piece layer in sequence to form a side top arch with a section as a unit; a support frame is arranged between the tube piece layer and the rock layer to form a hollow interlayer; a bottom lining platform is arranged at the bottom of the side top arch, and a grouting reserved hole that communicates with the hollow interlayer is arranged at the top of the tube piece layer of each section of the side top arch; the grouting reserved hole is movably connected with a grouting pipeline, and the other end of the pipeline is connected with a grouting machine. The beneficial effects of the present application are that the grouting cost is not increased, the grouting process is smooth, the utilization rate of grout is high, the equipment structure is simple, maintenance and later maintenance are convenient, the installation and disassembly time is short, the grouting pressure can be monitored at any time, the grouting quality is guaranteed, the mortar water glass quickly forms a skeleton layer at the contact surface, and the amount of mortar flowing to the cutter head is reduced.

[0005] However, the traditional tunnel excavation grouting support mainly relies on engineering experience. In the case where the geology in front cannot be accurately explored, the grouting parameters are set by experience, which easily leads to splitting of surrounding rock caused by excessive pressure and causes water gushing accidents, hindering tunnel excavation. SUMMARY

[0006] Technical problems solved

[0007] In view of the deficiencies of the prior art, the present application provides a tunnel excavation intelligent grouting control method and device, which solves the problem that the traditional tunnel excavation grouting support is dependent on experience and the geology is unknown, and the surrounding rock is often split and water gushing due to unbalanced setting of grouting parameters.

[0008] To achieve the above object, the present application is implemented by the following technical solutions: a tunnel excavation intelligent grouting control method, comprising the following specific steps: step one: according to the degree of rock mass looseness and water content, matching the preset excavation risk level, and setting the initial decision variables of grouting pressure, hole spacing and water-cement ratio according to the same; at the same time, obtaining the maximum splitting pressure of the rock mass, the area to be covered by the grout, the area of the grout filled region and the total grouting amount; step two: analyzing the grouting pressure, grouting hole spacing and water-cement ratio to obtain a grouting dynamic coupling optimization model, iterating the grouting dynamic coupling optimization model through an annealing simulation algorithm, setting the number k according to the actual demand, and counting the number of iterations to obtain the number of iterations, when the number of iterations is divisible by the number k, the annealing simulation algorithm is optimized to obtain the best grouting parameters; step three: writing the best grouting parameters into the register of the PLC controller, dynamically adjusting the grouting pressure, grouting hole spacing and water-cement ratio to execute the grouting task, and returning to step one or directly ending.

[0009] Further, the specific acquisition method of the grouting dynamic coupling optimization model is as follows: analyzing the grouting pressure and the maximum splitting pressure of the rock mass to obtain a pressure difference value, analyzing the area of the grout filled region and the area to be covered by the grout to obtain an ungrouting value, setting the weights of the pressure difference value, the ungrouting value and the total grouting amount respectively, and performing comprehensive analysis and standardization processing of the pressure difference value, the ungrouting value and the total grouting amount to obtain the grouting dynamic coupling optimization model; ; wherein, represents the grouting dynamic coupling optimization model, represents the pressure difference value, represents the ungrouting value, represents the total grouting amount, wherein, , and all represent the weight.

[0010] Further, the specific acquisition method of the pressure difference value is as follows: calculating the difference between the maximum splitting pressure of the rock mass and the grouting pressure to obtain the pressure difference value.

[0011] Further, the specific acquisition method of the ungrouting value is as follows: calculating the ratio of the area of the grout filled region and the area to be covered by the grout to obtain a filling ratio, and then calculating the difference between 1 and the filling ratio to obtain the ungrouting value.

[0012] Further, the specific way of iterating the grouting dynamic coupling optimization model by the annealing simulation algorithm is: firstly, the grouting dynamic coupling optimization model according to the initial decision variable is recorded as the zeroth iteration model, then the grouting pressure, grouting hole spacing and water-cement ratio in the initial decision variable are randomly adjusted, thereby affecting the pressure difference value, ungrouting value and total grouting amount to make the value of the zeroth iteration model change, and the first iteration model is obtained, the first iteration model is compared with the zeroth iteration model, if the value of the first iteration model is less than the value of the zeroth iteration model, the value of the first iteration model is assigned to the grouting dynamic coupling optimization model, if the value of the first iteration model is greater than or equal to the value of the zeroth iteration model, the acceptance probability is set, and at the same time, a random number is obtained by a numerical random function in the code, the random number is compared with the acceptance probability, if the random number is less than the acceptance probability, the value of the first iteration model is also assigned to the grouting dynamic coupling optimization model, if the random number is greater than or equal to the acceptance probability, the value of the grouting dynamic coupling optimization model is kept as the value of the zeroth iteration model, and so on.

[0013] Further, the specific setting way of the acceptance probability is as follows: the optimization value is obtained according to the difference between the value of the (i+1)th iteration model and the value of the ith iteration model, the temperature coefficient is set, and the temperature coefficient is initially assigned to M, the acceptance probability is obtained by comprehensive calculation and standardization processing according to the optimization value and the temperature coefficient; ; wherein, represents the acceptance probability, represents the optimization value, and is greater than or equal to zero, represents the temperature coefficient.

[0014] Further, the specific setting way of the temperature coefficient is as follows: the cooling value is set, and is initially assigned to 0, the temperature coefficient is obtained by comprehensive calculation and standardization processing according to the initial assignment of the temperature coefficient and the cooling value; ; wherein, represents the temperature coefficient, represents the initial assignment of the temperature coefficient, represents the cooling value.

[0015] Further, the specific way of optimizing the annealing simulation algorithm is: the remainder is calculated by taking the iteration number and the number k, the remainder result is compared with zero, if the remainder result is equal to zero, the integer result is calculated by taking the iteration number and the number k, and the integer result is assigned to the cooling value, if the remainder result is not equal to zero, the remainder result is continuously compared with zero.

[0016] Further, the specific acquisition mode of the optimal grouting parameters is as follows: the holding time is set through historical experience, if the value of the grouting dynamic coupling optimization model is always unchanged within the holding time, the grouting pressure, grouting hole spacing and water-cement ratio corresponding to the model value are set as the optimal grouting parameters, otherwise the grouting dynamic coupling optimization model is iterated continuously, and the annealing simulation algorithm is continuously optimized.

[0017] A tunnel excavation intelligent grouting control device, comprising the following specific modules: a data acquisition module, an optimal grouting parameter analysis module and a PLC grouting module; the data acquisition module: according to the rock mass loose degree and water content, matching the preset excavation risk level, and setting the initial decision variables of grouting pressure, hole spacing and water-cement ratio; at the same time, obtaining the maximum splitting pressure of the rock mass, the area to be covered by the grout, the area filled with grout and the total grouting amount; the optimal grouting parameter analysis module: analyzing according to the grouting pressure, grouting hole spacing and water-cement ratio, obtaining the grouting dynamic coupling optimization model, iteratively processing the grouting dynamic coupling optimization model through the annealing simulation algorithm, setting the k number according to the actual demand, and counting the iteration times to obtain the iteration times, when the iteration times can be divided by the k number, the annealing simulation algorithm is optimized to obtain the optimal grouting parameters; the PLC grouting module: writing the optimal grouting parameters into the register of the PLC controller, dynamically adjusting the grouting pressure, grouting hole spacing and water-cement ratio to execute the grouting task, and returning to the data acquisition module or directly ending.

[0018] Beneficial effects

[0019] Compared with the prior art, the embodiments of the present application have at least the following advantages or beneficial effects:

[0020] 1. By establishing a grouting dynamic coupling optimization model and using the simulated annealing algorithm for iterative solution, intelligent optimization and safety control of grouting parameters are realized, which directly determines the pressure difference that determines the rock mass splitting risk, the ungrouting value that reflects the reinforcement effect and the total grouting amount that affects the economic cost to construct the grouting dynamic coupling optimization model, and ensures that the algorithm always takes preventing pressure overrun and avoiding splitting gushing as the primary premise in the optimization process, thereby fundamentally solving the safety risks caused by traditional experience-dependent parameter setting.

[0021] 2. By introducing a discrete temperature scheduling strategy linked with the number of iterations, the active and controllable management of the convergence process of the traditional simulated annealing is realized. Specifically, the algorithm does not continuously slow down the temperature, but sets an iteration period k, and only when the number of iterations can be divided by k, the temperature coefficient T is stepped down according to the integer result of the number of iterations and k. This design creates a controllable convergence rhythm through the "regulating valve" of k value: within every k iterations, the algorithm fully explores the region at a constant temperature, avoiding premature falling into local optimum due to continuous temperature drop; when reaching the periodic node, the device decisively cools down to enhance the local refinement trend, and such periodic repetition continues until the model output is stable, which effectively avoids the slow convergence or endless iteration problem of the traditional algorithm due to infinite fine cooling, so that the algorithm can efficiently and stably converge to the global optimum or satisfactory solution within the preset limited iteration period matching the engineering progress.

[0022] Of course, implementing any product of the present application does not necessarily require all the advantages described above. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 For the present application: a tunneling intelligent grouting control method flow chart.

[0024] Figure 2 For the present application: a tunneling intelligent grouting control device structure diagram. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0026] It should be noted that in this paper, relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment.

[0027] Embodiment 1:

[0028] As Figure 1As shown, the embodiment of the present application provides a tunneling intelligent grouting control method: comprising the following specific steps:

[0029] Step one: at the tunnel face, that is, at the forefront of the tunnel excavation operation, the horizontal acoustic profile method and the transient electromagnetic method are used to analyze the seismic wave and water conductivity of the rock mass along the tunnel axis direction, and the loose degree and water content of the rock mass structure are obtained, wherein the horizontal acoustic profile method: that is, when the tunnel rock mass has a fracture zone or a weak interlayer, the propagation speed of the seismic wave in this area will decrease, and the energy will attenuate, therefore, the sensor arranged at the tunnel face receives the reflected wave, and analyzes the attenuation changes of the wave speed, amplitude and frequency; the transient electromagnetic method: that is, an electromagnetic field is emitted to the rock mass, and then the secondary electromagnetic field generated by the electrical difference of the rock mass is measured, when the water content of the rock mass is higher, the electrical conductivity is stronger, and the secondary electromagnetic field attenuates slower, by analyzing the attenuation change of the secondary electromagnetic field, the water content of the rock mass is deduced;

[0030] The rock mass tunneling risk level is set, the loose degree and water content range of the rock mass structure are preset for each level according to historical experience, the corresponding rock mass tunneling risk level is traversed according to the loose degree and water content of the rock mass structure, and the initial decision variable is set according to this level, including the grouting pressure, the grouting hole spacing and the water-cement ratio, wherein the grouting pressure represents the driving force for pushing the grout to penetrate and diffuse in the rock mass fracture, that is, this pressure is the fundamental driving force to overcome the flow resistance and ensure the grout to fill the fracture; the grouting hole spacing represents the distance between adjacent grouting holes, that is, the distribution density of the grouting points; the water-cement ratio represents the proportion of water and cement in the grout, which ensures the consistency and fluidity of the grout;

[0031] The maximum splitting pressure of the rock mass is obtained through the field pilot hole water pressure test, that is, a small diameter pilot hole is drilled in front of the tunnel face, and a hole sealer is installed in the target rock mass section to ensure that the pressure does not leak, the test preparation is completed, then the pressure is slowly raised by pipeline grading and the pressure and water discharge are monitored, at the initial stage, the two change in proportion without damaging the rock mass structure, when the water discharge suddenly increases, that is, with water flow injection or rock mass abnormal sound, the pressure is the maximum splitting pressure of the rock mass at this time;

[0032] The area to be covered by the grout is obtained through the tunnel support design requirements and the field stratum survey, the area of the grout filled region is scanned out through the acoustic wave detection, the total grouting amount is obtained through the grouting pump flow sensor measurement, which is used to reflect the grouting cost, that is, the more grouting, the greater the cost.

[0033] Step two: according to the grouting pressure, grouting hole spacing and water-cement ratio, the grouting dynamic coupling optimization model is obtained, the grouting dynamic coupling optimization model is iterated by the annealing simulation algorithm, and k number is set according to the actual demand, k number is 100, 200 and 300, etc. Integer, and the iteration number is counted, the iteration number is obtained, when the iteration number can be divided by k number, the annealing simulation algorithm is optimized, the smaller the k number is, the more the optimization times are, and the best grouting parameters are obtained, including the best grouting pressure, the best grouting hole spacing and the best water-cement ratio.

[0034] Step three: the best grouting parameters are written into the register of PLC controller, PLC is programmable logic controller, which can automatically control the grouting pump and valve and other actuators with millisecond level accuracy, dynamically adjust the grouting pressure, grouting hole spacing and water-cement ratio, so as to accurately and safely execute the grouting task, avoid setting the grouting parameters by experience, prevent the pressure from being too high to split the surrounding rock and cause water gushing accident, and further hinder the tunneling, and return to step one or directly end.

[0035] Example 2, the difference from example 1 is:

[0036] The specific acquisition method of the grouting dynamic coupling optimization model is as follows:

[0037] According to the analysis of grouting pressure and maximum splitting pressure of rock mass, the pressure difference is obtained, according to the analysis of the area of grouting filled area and the area to be covered by grouting, the ungrouting value is obtained, the weight of pressure difference, ungrouting value and total grouting amount is set respectively, and the standardization treatment is carried out according to the comprehensive analysis of pressure difference, ungrouting value and total grouting amount, so as to eliminate the dimension difference and convert the different orders of magnitude of values into the same value range, and the grouting dynamic coupling optimization model is obtained;

[0038] ;

[0039] Among them, represents the grouting dynamic coupling optimization model, represents the pressure difference, represents the ungrouting value, represents the total grouting amount, wherein, , and all represent the weight, and is greater than , is greater than , that is, the pressure difference directly determines whether the rock mass is split, so the weight is the largest, the ungrouting value determines the filling effect of the crack, so the weight is medium, and the total grouting amount reflects the grouting cost, so the weight is the lowest;

[0040] Among them, the values of grouting pressure, grouting hole spacing and water-cement ratio determine the size of pressure difference value, un-grouting value and total grouting quantity. If the grouting pressure is greater than the maximum splitting pressure of rock mass, it will not only cause the rock mass splitting, but also produce new non-filled demand cracks due to the over-high grouting pressure. A large amount of slurry will flow into these useless cracks, resulting in the waste of slurry which does not play a role in reinforcing and stabilizing the rock mass. And the insufficient grouting pressure will lead to the slurry unable to reach the area to be covered by the slurry, forming a large blank area.

[0041] The grouting hole spacing directly affects the filling effect of slurry. If the grouting hole spacing is much greater than the slurry diffusion radius, the number of drill holes will be less. Not only will a blank area not filled with slurry be formed between the grouting holes, but also it will be difficult to form effective pressure accumulation and sufficient flow resistance around the drill holes. The grouting pressure will always be low, and it is difficult to establish the power required for the slurry to fully penetrate into the micro cracks. If the grouting hole spacing is much smaller than the slurry diffusion radius, the number of drill holes will be more. Not only will unnecessary cracks be caused by repeated disturbance to the rock mass due to the over-dense drill holes, but also the slurry will be wasted due to the mutual occupation in the limited space, and the flow resistance will increase sharply. In order to maintain the grouting flow rate, the grouting pressure will be increased passively.

[0042] The water-cement ratio is essentially the ratio of cement to water, which determines the viscosity of the slurry. If the slurry is too thin, it will be lost when filling the cracks, and the flow resistance will be extremely small, making it difficult to effectively maintain the grouting pressure. If the slurry is too thick, the slurry diffusion range will be small, and the flow resistance will be extremely large, causing the drill hole to be blocked, and further leading to the increase of grouting pressure. In addition, the low utilization rate of the slurry will increase the total grouting quantity, resulting in the increase of cost.

[0043] The specific way to obtain the pressure difference value is as follows:

[0044] The pressure difference value is obtained by calculating the difference between the maximum splitting pressure of rock mass and the grouting pressure.

[0045] ;

[0046] Among them, represents the pressure difference value, represents the maximum splitting pressure of rock mass, represents the grouting pressure. Since the maximum splitting pressure of rock mass is greater than or equal to the grouting pressure, the absolute value is not taken.

[0047] The specific way to obtain the un-grouting value is as follows:

[0048] The filling ratio is obtained by calculating the ratio of the area filled with slurry to the area to be covered by the slurry. Then, the difference between 1 and the filling ratio is calculated to obtain the un-grouting value.

[0049] ;

[0050] wherein, represents the ungrouting value, represents the grouting filled area, represents the area to be covered by the grouting.

[0051] The specific way of iterating the grouting dynamic coupling optimization model by the annealing simulation algorithm is as follows:

[0052] Firstly, the grouting dynamic coupling optimization model according to the initial decision variable is recorded as the zeroth iteration model, then the grouting pressure, grouting hole spacing and water-cement ratio in the initial decision variable are randomly adjusted, thereby affecting the pressure difference value, ungrouting value and total grouting amount to make the value of the zeroth iteration model change, and the first iteration model is obtained, the first iteration model is compared with the zeroth iteration model, if the value of the first iteration model is less than the value of the zeroth iteration model, it means that the pressure difference value, ungrouting value and total grouting amount in the first iteration model are smaller, thereby indicating that the blank area filled by the grouting is smaller under the condition of avoiding rock mass splitting, that is, the filling effect of the grouting is better, and the cost is better, therefore the value of the first iteration model is assigned to the grouting dynamic coupling optimization model, if the value of the first iteration model is greater than or equal to the value of the zeroth iteration model, in order to avoid falling into a local optimal solution, that is, to avoid being always the zeroth iteration model better, the acceptance probability is set, and at the same time the random number is obtained through the numerical random function in the code, the range of the random number is between 0 and 1, to represent the range of probability, the random number is compared with the acceptance probability, if the random number is less than the acceptance probability, that is, the random number is in the interval of 0 to the acceptance probability, it means acceptance, also the value of the first iteration model is assigned to the grouting dynamic coupling optimization model, if the random number is greater than or equal to the acceptance probability, it means rejection, therefore the value of the grouting dynamic coupling optimization model is kept as the value of the zeroth iteration model, and so on;

[0053] The specific setting way of the acceptance probability is as follows:

[0054] According to the difference between the value of the i+1th iteration model and the value of the ith iteration model, the optimization value is calculated, the temperature coefficient is set, and the temperature coefficient is initially assigned M, the optimization value and the temperature coefficient are comprehensively calculated, and the standardization processing is performed, to obtain the acceptance probability;

[0055] ;

[0056] wherein, represents the acceptance probability, represents the optimization value, and is greater than or equal to zero, that is, the value of the i+1th iteration model is greater than or equal to the value of the ith iteration model, represents the temperature coefficient, represents the about The independent variable of the temperature coefficient is less than or equal to zero, and according to the exponential form, when the independent variable is less than or equal to zero, The range of the temperature coefficient is between 0 and 1.

[0057] The temperature coefficient is set as follows:

[0058] The cooling value is set to 0, the initial value of the temperature coefficient is calculated, and the temperature coefficient is obtained after standardization.

[0059] ;

[0060] Wherein, The temperature coefficient is represented by T, The initial value of the temperature coefficient is represented by T0, The cooling value is represented by Tc, the greater the cooling value, the smaller the temperature coefficient, because only the smaller the temperature coefficient, the The smaller the acceptance probability, the greater the probability that the random number is greater than or equal to the acceptance probability, and the probability of rejection increases, that is, the probability of keeping the value of the grouting dynamic coupling optimization model unchanged increases.

[0061] The specific way to optimize the annealing simulation algorithm is as follows:

[0062] Since the grouting dynamic coupling optimization model cannot be iterated infinitely, it needs to be converged at the nth iteration, so the annealing simulation algorithm is optimized according to the temperature coefficient, the remainder of the iteration number and the k number is calculated to obtain the remainder result, the remainder result is compared with zero, if the remainder result is equal to zero, the iteration number is calculated by integer, and the integer result is assigned to the cooling value, if the remainder result is not equal to zero, the remainder result is compared with zero.

[0063] The specific way to obtain the best grouting parameters is as follows:

[0064] The holding time is set by historical experience, if the value of the grouting dynamic coupling optimization model is always the same within the holding time, it means that the model has been iterated and converged, so the grouting pressure, grouting hole spacing and water-cement ratio corresponding to the model value are set as the best grouting parameters, otherwise the grouting dynamic coupling optimization model is iterated and the annealing simulation algorithm is optimized.

[0065] Example 3:

[0066] As shown in Figure 2 A tunneling intelligent grouting control device, comprising the following specific modules:

[0067] The data acquisition module: according to the rock mass loose degree and water content, the preset tunneling risk level is matched, and the initial decision variables of grouting pressure, hole spacing and water-cement ratio are set accordingly; at the same time, the maximum splitting pressure of rock mass, the area to be covered by slurry, the area filled with slurry and the total grouting amount are obtained;

[0068] The optimal grouting parameter analysis module: according to the grouting pressure, the grouting hole spacing and the water-cement ratio, the grouting dynamic coupling optimization model is obtained, the grouting dynamic coupling optimization model is iterated through the annealing simulation algorithm, the k number is set according to the actual demand, the iteration number is counted, the iteration number is obtained, when the iteration number can be divided by the k number, the annealing simulation algorithm is optimized, and the optimal grouting parameter is obtained;

[0069] The PLC grouting module: the optimal grouting parameter is written into the register of the PLC controller, the grouting pressure, the grouting hole spacing and the water-cement ratio are dynamically adjusted to execute the grouting task, and the data acquisition module is returned or directly ended.

[0070] The preferred embodiments disclosed above are only used to help explain the application. The preferred embodiments do not describe all the details, and the application is not limited to the specific embodiments described. Obviously, according to the content of the specification, many modifications and changes can be made. The specification selects and describes these embodiments in order to better explain the principles and practical applications of the application, so that those skilled in the art can well understand and utilize the application. The application is limited by the claims and their entire scope and equivalents.

Claims

1. A method for intelligent grouting control in tunnel excavation, characterized in that: The specific steps include the following: Step 1: Based on the looseness and water content of the rock mass, match the preset tunneling risk level, and set the initial decision variables for grouting pressure, hole spacing and water-cement ratio accordingly; at the same time, obtain the maximum splitting pressure of the rock mass, the area to be covered by the grout, the area of ​​the area already filled by the grout and the total grouting volume. Step 2: Based on the analysis of grouting pressure, grouting hole spacing and water-cement ratio, a dynamic coupling optimization model for grouting is obtained. The dynamic coupling optimization model for grouting is iterated through the annealing simulation algorithm. The number of k is set according to actual needs, and the number of iterations is counted. When the number of iterations is divisible by the number of k, the annealing simulation algorithm is optimized to obtain the optimal grouting parameters. The specific method for obtaining the grouting dynamic coupling optimization model is as follows: The pressure difference is obtained by analyzing the grouting pressure and the maximum splitting pressure of the rock mass. The ungrouted value is obtained by analyzing the area of ​​the grout-filled area and the area to be covered by the grout. The weights of the pressure difference, the ungrouted value and the total grouting volume are set respectively. The grouting dynamic coupling optimization model is obtained by comprehensively analyzing the pressure difference, the ungrouted value and the total grouting volume and standardizing the process. ； in, This represents the dynamic coupling optimization model for grouting. Indicates the pressure difference. Indicates the value without grouting. This represents the total grouting volume, of which, as well as All represent weights; The specific method for iterating the dynamic coupling optimization model of grouting using the annealing simulation algorithm is as follows: First, the dynamic coupling optimization model for grouting based on the initial decision variables is denoted as the zeroth iteration model. Then, the grouting pressure, grouting hole spacing, and water-cement ratio in the initial decision variables are randomly adjusted, thereby affecting the pressure difference, ungrouted value, and total grouting volume, thus changing the value of the zeroth iteration model to obtain the first iteration model. The first iteration model is compared with the zeroth iteration model. If the value of the first iteration model is less than the value of the zeroth iteration model, the value of the first iteration model is assigned to the dynamic coupling optimization model for grouting. If the value of the first iteration model is greater than or equal to the value of the zeroth iteration model, the acceptance probability is set, and at the same time, a random number is obtained through a numerical random function in the code. The random number is compared with the acceptance probability. If the random number is less than the acceptance probability, the value of the first iteration model is also assigned to the dynamic coupling optimization model for grouting. If the random number is greater than or equal to the acceptance probability, the value of the dynamic coupling optimization model for grouting is kept as the value of the zeroth iteration model, and so on. Step 3: Write the optimal grouting parameters into the register of the PLC controller, dynamically adjust the grouting pressure, grouting hole spacing and water-cement ratio to execute the grouting task, and return to Step 1 or end directly.

2. The intelligent grouting control method for tunnel excavation according to claim 1, characterized in that: The specific method for obtaining the pressure difference value is as follows: The pressure difference is calculated by taking the difference between the maximum splitting pressure of the rock mass and the grouting pressure.

3. The intelligent grouting control method for tunnel excavation according to claim 2, characterized in that: The specific method for obtaining the ungrouted value is as follows: The ratio of the area already filled with grout to the area to be covered by grout is calculated to obtain the filling ratio. Then, the difference between 1 and the filling ratio is calculated to obtain the ungrouted value.

4. The intelligent grouting control method for tunnel excavation according to claim 3, characterized in that: The specific method for setting the acceptance probability is as follows: The optimal value is calculated based on the difference between the value of the (i+1)th iteration model and the value of the i-th iteration model. The temperature coefficient is set and initially assigned a value M. The acceptance probability is obtained by comprehensively calculating the optimal value and the temperature coefficient and performing standardization. ； in, Indicates the probability of acceptance. This represents the optimized value, which is greater than or equal to zero. This represents the temperature coefficient.

5. The intelligent grouting control method for tunnel excavation according to claim 4, characterized in that: The specific method for setting the temperature coefficient is as follows: Set a cooling value, initially set to 0, combine the initial temperature coefficient with the cooling value for comprehensive calculation, and then perform standardization to obtain the temperature coefficient. ； in, Indicates the temperature coefficient. This indicates the initial assignment of the temperature coefficient. This indicates the temperature drop value.

6. The intelligent grouting control method for tunnel excavation according to claim 5, characterized in that: The specific method for optimizing the annealing simulation algorithm is as follows: The iteration count is modulo k, and the remainder is compared with zero. If the remainder is zero, the iteration count is rounded down with k and the result is assigned to the cooling value. If the remainder is not zero, the remainder is compared with zero again.

7. The intelligent grouting control method for tunnel excavation according to claim 6, characterized in that: The specific method for obtaining the optimal grouting parameters is as follows: By setting a holding time based on historical experience, if the value of the grouting dynamic coupling optimization model remains unchanged within the holding time, the grouting pressure, grouting hole spacing, and water-cement ratio corresponding to this model value are set as the optimal grouting parameters; otherwise, the grouting dynamic coupling optimization model is iterated and the annealing simulation algorithm is optimized.

8. A smart grouting control device for tunnel excavation, used to implement the smart grouting control method for tunnel excavation as described in any one of claims 1-7, characterized in that, The intelligent grouting control device for tunnel excavation includes: a data acquisition module, an optimal grouting parameter analysis module, and a PLC grouting module; The data acquisition module: matches the preset tunneling risk level according to the looseness and water content of the rock mass, and sets the initial decision variables of grouting pressure, hole spacing and water-cement ratio accordingly; at the same time, it obtains the maximum splitting pressure of the rock mass, the area to be covered by grout, the area of ​​the area already filled by grout and the total grouting volume. The optimal grouting parameter analysis module analyzes the grouting pressure, grouting hole spacing, and water-cement ratio to obtain a dynamic coupling optimization model for grouting. Iterates the dynamic coupling optimization model for grouting using an annealing simulation algorithm, sets the number of k according to actual needs, and counts the number of iterations. When the number of iterations is divisible by the number of k, the annealing simulation algorithm is optimized to obtain the optimal grouting parameters. The PLC grouting module writes the optimal grouting parameters into the register of the PLC controller, dynamically adjusts the grouting pressure, grouting hole spacing, and water-cement ratio to perform the grouting task, and returns to the data acquisition module or terminates directly.

Images