Pulse intelligent grouting control method and system

Abstract

The invention provides a pulse intelligent grouting control method and system, and relates to the technical field of civil engineering, according to the pulse intelligent grouting control method and system, measuring point displacement data in a construction site is obtained in real time and used for establishing an optimal grouting parameter prediction analysis model, grouting parameters are incorporated into a finite element model, the fitness of each group of parameters is calculated, and the optimal grouting parameter prediction analysis model is obtained. A combination with the highest fitness is selected as an optimal grouting parameter, a pulse intelligent control technology is utilized, a grouting pulse index is comprehensively generated, a pulse threshold value is set, and when the grouting pulse index exceeds the threshold value, a system automatically stops grouting, so that accurate control over the grouting process is achieved. According to the method, through the grouting parameter analysis model, the optimal value of the grouting fitness is calculated, and the grouting parameters are optimized, so that accurate control and optimization of the grouting process are realized.

Description

Technical Field

[0001] The invention relates to the technical field of civil engineering, and in particular to a pulse intelligent grouting control method and system. Background Art

[0002] At present, with the continuous advancement of construction engineering technology, traditional grouting methods are gradually unable to meet the safety and efficiency requirements in complex construction environments. In recent years, pulse grouting technology has attracted attention because it can achieve precise control of soil reinforcement and stability by adjusting the frequency, intensity and time of grouting. Combined with real-time monitoring technology, the pulse intelligent grouting control method came into being, which dynamically adjusts the grouting parameters by acquiring the displacement data of the measurement point in real time. This method not only improves the accuracy and response speed of the grouting process, but also effectively reduces the impact on the environment, becoming an important means to achieve intelligent and refined management in modern construction.

[0003] In the prior art, publication number CN111058450A discloses a grouting control method, device and system, which obtains current formation cement slurry pressure data in real time; compares the current formation cement slurry pressure data with a preset cement slurry pressure value and obtains a comparison result; generates a control signal based on the comparison result, and the control signal is used to control an actuator to execute cement slurry injection, suck out excess cement slurry or stop cement slurry injection.

[0004] Insufficient existing technology:

[0005] Although the existing technology has achieved real-time monitoring and dynamic adjustment in the grouting control method and device, there are still some shortcomings. First, the current method mainly relies on the formation cement slurry pressure data for control. This single parameter judgment may not be sufficient to fully reflect the complex situation in the grouting process. For example, under different formation conditions, the fluidity, viscosity and environmental factors of the cement slurry will affect the grouting effect, and the existing technology fails to effectively consider the comprehensive influence of these multi-dimensional factors, which may lead to poor grouting effect or adverse effects on the surrounding environment.

[0006] Secondly, the control logic of the existing technology is relatively simple, and the control signal is generated only based on the comparison of pressure data, lacking a more intelligent decision support system. The response time and sensitivity of this method to the grouting process are limited, and it cannot adapt to emergencies in a timely manner, such as changes in the formation structure or external environmental interference. In addition, the lack of in-depth analysis and pattern recognition of data makes it impossible to achieve dynamic optimization and self-learning capabilities, which limits the intelligence level and adaptability of the system. Therefore, improving the intelligence and comprehensiveness of grouting control will be a key direction for future technological development.

[0007] Therefore, it is necessary to provide a pulse intelligent grouting control method and system to solve the above problems.

[0008] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0009] The purpose of the present invention is to provide a pulse intelligent grouting control method and system to solve the problems raised in the above background technology.

[0010] To achieve the above object, the present invention provides the following technical solutions:

[0011] A pulse intelligent grouting control method, the specific steps include:

[0012] Step 1: Acquire multiple groups of historical state data, the historical state data including historical grouting parameters of individuals in the initial population and displacement of corresponding measurement points after grouting, the historical grouting parameters including grouting hole spacing, grouting hole diameter and grouting hole pressure data;

[0013] Step 2: Establish an optimal grouting parameter prediction model, take the historical grouting parameters as input, take the displacement of the corresponding measurement point as the label, train the optimal grouting parameter prediction model, calculate the fitness value of the individuals in the initial population based on the state data, and take minimizing the fitness value as the optimization goal. Based on the genetic algorithm and the optimal grouting parameter prediction model, optimize the initial population and find the individual with the smallest fitness value as the optimal grouting parameter combination;

[0014] Step 3: Based on the optimal grouting parameters, pulse technology is used for grouting, and the pulse frequency, pulse width and pulse intensity under the optimal combination of construction grouting parameters are collected in real time to comprehensively generate the grouting pulse index;

[0015] Step 4: Set up a pulse threshold. When the grouting pulse index exceeds the threshold, stop grouting to achieve precise control of the grouting process.

[0016] Furthermore, the optimal grouting parameter prediction model is established based on the following method:

[0017] Taking historical grouting parameters as input and the displacement of the corresponding measuring point as label, the mean square error is selected as the loss function. The model structure adopts a deep neural network, which consists of an input layer, multiple hidden layers and an output layer. The input layer is responsible for receiving historical grouting parameter data, and multiple hidden layers are responsible for capturing complex nonlinear relationships. The output layer is responsible for outputting the corresponding measuring point displacement. Then the prediction model is trained, and cross-validation and other methods are used to prevent overfitting. The performance of the model is evaluated by training error and validation error. The back propagation algorithm is combined with the optimization method to iteratively update the model parameters until the preset round is reached to minimize the loss function and realize effective prediction of the measuring point displacement.

[0018] Furthermore, the calculation formula of the fitness value is:

[0019]

[0020] Among them, X j represents the final displacement of measurement point j, m is the total number of measurement points, j is the index of the measurement point, j∈[1,m], Indicates the maximum displacement threshold of the measurement point, X av represents the average displacement of the measuring point, ω1, ω2, and ω3 are weight proportional coefficients, which are used to represent the influence of each part on the fitness function, and ω2>ω1>ω3>0, q is the grouting cost coefficient, d, s, and δ represent the grouting hole diameter, spacing, and grouting hole pressure of the grouting parameters, S is the area of ​​the grouting area, and D is the depth of the grouting hole; the smaller the F value, the better the grouting parameter; This part indicates the safety value, X av This part represents the penalty value. This part represents the economic value, and F is the fitness value of the individual;

[0021] The grouting parameter combination with the smallest sum of safety value, economic value and penalty value is selected as the optimal grouting parameter combination.

[0022] Furthermore, the grouting pulse index is comprehensively generated based on the following method:

[0023] Based on pulse intelligent control technology, the grouting parameters are dynamically adjusted according to the displacement data of the measuring points monitored in real time to obtain the pulse frequency f under the optimal construction grouting parameter combination. best , pulse width T best and pulse intensity I best , the grouting pulse index is comprehensively generated based on the formula:

[0024]

[0025] Among them, a, b, and c correspond to the weight ratio of their respective parameters and c>a>b>0, f best 、T best ,I best is the pulse frequency, pulse width and pulse intensity under the optimal construction grouting parameter combination, f max 、T max ,I max It is the maximum allowable value of grouting frequency, width and strength.

[0026] Furthermore, a pulse threshold is set to determine whether the grouting pulse index exceeds the pulse threshold. The logic formula is as follows:

[0027]

[0028] Where Q represents the logic value for judging whether the pulp pulse index exceeds the pulse threshold, J th It is the preset pulse threshold. When Q=0, it indicates that the pulse index does not exceed the pulse threshold and the grouting construction continues; when Q=1, it indicates that the pulse index has exceeded the pulse threshold and the grouting construction is stopped.

[0029] The present invention further provides a pulse intelligent grouting control system, wherein the control system is used to execute the above-mentioned pulse intelligent grouting control method, comprising:

[0030] A data acquisition module, wherein the data acquisition module is used to obtain multiple groups of historical status data, the historical status data including historical grouting parameters of individuals in the initial population and displacements of corresponding measurement points after grouting, the historical grouting parameters including grouting hole spacing, grouting hole diameter and grouting hole pressure data;

[0031] A fitness value calculation and model building module, wherein the fitness value calculation and model building are used to establish an optimal grouting parameter prediction model, taking historical grouting parameters as input and the displacement of corresponding measurement points as labels, training the optimal grouting parameter prediction model, calculating the fitness values ​​of individuals in the initial population based on state data, and taking minimization of the fitness value as the optimization goal, optimizing the initial population based on a genetic algorithm and the optimal grouting parameter prediction model, and finding the individual with the smallest fitness value as the optimal grouting parameter combination;

[0032] A grouting pulse index generation module, which is used to perform grouting using pulse technology based on optimal grouting parameters, collect pulse frequency, pulse width and pulse intensity under the optimal combination of construction grouting parameters in real time, and comprehensively generate a grouting pulse index;

[0033] The grouting process monitoring and threshold control module is used to set up a pulse threshold. When the grouting pulse index exceeds the threshold, the grouting is stopped to achieve precise control of the grouting process.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] The present invention solves the deficiencies of the prior art in grouting control methods and devices through multiple innovative steps and modular designs. First, the invention uses the construction model to comprehensively consider the displacement data of the measuring points. This multi-parameter input method makes the grouting process no longer rely solely on a single pressure data. By establishing a model based on multi-dimensional parameters, the invention can more comprehensively reflect the complexity of the construction environment and formation conditions, thereby improving the accuracy and effectiveness of the grouting effect. This method can adapt to the fluidity, viscosity and environmental changes of different formations, and significantly reduce the potential adverse effects on the surrounding environment;

[0036] Secondly, the present invention introduces a fitness function calculation module, making the generation and optimization process of grouting parameters more intelligent. This method can not only generate multiple sets of grouting parameters in real time, but also select the optimal combination through fitness evaluation, thereby enhancing the system's responsiveness to changes in construction conditions. In addition, combined with pulse intelligent control technology, the invention realizes dynamic adjustment in the way grouting parameters are applied, and can automatically optimize the grouting process according to real-time monitoring data. This intelligent decision support system improves the sensitivity of the system, ensuring that the system can quickly adapt and adjust operations when the stratum structure changes or external interference occurs, reflecting a higher level of intelligence and comprehensiveness, thereby overcoming the limitations of the prior art;

[0037] The present invention uses a finite element numerical analysis model and a particle swarm optimization algorithm to generate and optimize grouting parameters, thereby achieving precise control and optimization of the grouting process. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a schematic diagram of the overall method flow of the present invention.

[0039] Figure 2 It is a schematic diagram of the system module flow of the present invention. DETAILED DESCRIPTION

[0040] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0041] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0042] Example:

[0043] See also Figure 1 , a pulse intelligent grouting control method, the specific steps include:

[0044] Step 1: Acquire multiple groups of historical state data, the historical state data including historical grouting parameters of individuals in the initial population and displacement of corresponding measurement points after grouting, the historical grouting parameters including grouting hole spacing, grouting hole diameter and grouting hole pressure data;

[0045] Step 2: Establish an optimal grouting parameter prediction model, take the historical grouting parameters as input, take the displacement of the corresponding measurement point as the label, train the optimal grouting parameter prediction model, calculate the fitness value of the individuals in the initial population based on the state data, and take minimizing the fitness value as the optimization goal. Based on the genetic algorithm and the optimal grouting parameter prediction model, optimize the initial population and find the individual with the smallest fitness value as the optimal grouting parameter combination;

[0046] Step 3: Based on the optimal grouting parameters, pulse technology is used for grouting, and the pulse frequency, pulse width and pulse intensity under the optimal combination of construction grouting parameters are collected in real time to comprehensively generate the grouting pulse index;

[0047] Step 4: Set up a pulse threshold. When the grouting pulse index exceeds the threshold, stop grouting to achieve precise control of the grouting process.

[0048] It should be noted that the use of deep neural network for training is a key step in the grouting control method, because this process can effectively capture and represent the complex nonlinear relationship between grouting parameters and construction effects. The historical grouting parameters are used as input and the displacement of the corresponding measurement points are used as labels to train the optimal grouting parameter prediction model. This model can not only quantify the difference between the model prediction and the actual situation through the mean square error loss function, but also iteratively update through the back propagation algorithm and optimization method to improve the prediction accuracy. The purpose is to improve the intelligence of the system so that the grouting parameters can be dynamically optimized according to changes in the actual construction environment, thereby ensuring the reliability and safety of the construction effect, and ultimately achieving more efficient construction management and resource utilization.

[0049] The measuring points should be evenly distributed at different locations around the foundation pit, especially the four corners and central area of ​​the foundation pit, to comprehensively monitor the displacement of the foundation pit and the building. The measuring points should also be arranged around the grouting holes, especially the distance between the grouting holes and the measuring points should be guaranteed to effectively capture the impact of grouting on the surrounding environment.

[0050] Therefore, the optimal grouting parameter prediction model is established based on the following method:

[0051] Taking historical grouting parameters as input and the displacement of the corresponding measurement points as labels, the mean square error is selected as the loss function. The model structure adopts a deep neural network, which consists of an input layer, multiple hidden layers and an output layer. The input layer is responsible for receiving historical grouting parameter data, and multiple hidden layers are responsible for capturing complex nonlinear relationships. The output layer is responsible for outputting the corresponding displacement of the measurement points.

[0052] The fitness value of each individual in the initial population is calculated, and the individuals are sorted from small to large according to the fitness value. The individuals in the top 50% of the sorting are selected as the parents, and crossover and mutation are performed to generate new offspring. The offspring and the parents form a new population, and the individuals in the population are input into the optimal grouting parameter prediction model to obtain the displacement of the measuring point. The fitness value of the individual is calculated according to the grouting parameters and the displacement of the measuring point. The selection, crossover and mutation operations are repeated until the predetermined number of iterations is reached, and the individual with the smallest fitness value is selected as the optimal grouting parameter combination. The number of iterations is within 50-100.

[0053] It should be noted that by comprehensively considering safety, economy and penalty value, the impact of each set of grouting parameters on the construction effect can be comprehensively evaluated. This process ensures that the selected parameters not only meet safety standards, but also achieve the best economic benefits. By setting the fitness function, the advantages and disadvantages of different parameter combinations can be effectively quantified and compared, thus providing a scientific basis for decision-making. In particular, by introducing the weight coefficient, the relative importance of each indicator in the fitness calculation can be flexibly adjusted, making the model more adaptable to changes in actual construction conditions.

[0054] The setting of this method introduces a comprehensive evaluation mechanism of safety value, economic value and penalty value, breaking through the limitations of traditional single-objective optimization and realizing multi-objective optimization. This not only improves construction quality and safety, but also maximizes resource utilization efficiency while reducing costs. In addition, the design of the fitness function enables it to dynamically adapt to different construction environments and needs, further enhancing the flexibility and operability of the method, reflecting the advantages of the intelligent decision support system, and thus promoting the development of grouting construction technology.

[0055] Therefore, the fitness value is calculated as:

[0056]

[0057] Among them, X j represents the final displacement of measurement point j, m is the total number of measurement points, j is the index of the measurement point, j∈[1,m], Indicates the maximum displacement threshold of the measurement point, X av represents the average displacement of the measuring point, ω1, ω2, and ω3 are weight proportional coefficients, which are used to represent the influence of each part on the fitness function, and ω2>ω1>ω3>0, q is the grouting cost coefficient, d, s, and δ represent the grouting hole diameter, spacing, and grouting hole pressure of the grouting parameters, S is the area of ​​the grouting area, and D is the depth of the grouting hole; the smaller the F value, the better the grouting parameter; This part indicates the safety value, X av This part represents the penalty value. This part represents the economic value, and F is the fitness value of the individual; the grouting parameter combination corresponding to the minimum sum of the safety value, economic value and penalty value is selected as the optimal grouting parameter combination; in the above fitness function calculation formula, is the total displacement of all m measuring points during construction. The smaller this value is, the better, which means that the foundation has a strong bearing deformation capacity during construction and is not prone to structural damage, which is conducive to subsequent grouting construction; is the average displacement of all m measuring points during construction. The smaller the value, the better, indicating that the displacement of each measuring point is close to the construction displacement standard. In the formula, S represents the size of the area that needs to be grouting, which is usually related to the total amount and cost of grouting. The larger the area, the higher the cost and the greater the economic value. Therefore, a reasonable grouting area should be selected to ensure that no material waste occurs. The depth of the grouting hole D directly affects the distribution and effect of the grouting material. The greater the depth, the more grouting material and the higher the construction cost are required. Therefore, while ensuring that the economic value does not increase significantly, the grouting depth should be detected and determined in advance to avoid cost waste. In the formula, the natural logarithm and square root are taken to smooth and standardize the effect of the grouting hole diameter on the economic value, ensuring that it is quantified in an appropriate way in the fitness function, emphasizing the nonlinear effect of the hole diameter on the grouting effect. The larger the d value, the greater the economic value and the higher the cost; e qδ It indicates that the effect of grouting hole pressure δ on cost is exponentially increasing, which means that with the increase of grouting hole pressure δ, the cost will rise significantly and the economic value will increase significantly. At the same time, the grouting cost coefficient q is also considered, which partially reflects the economic factor and pays attention to the high cost of construction under high pressure. The grouting cost coefficient q can be obtained by referring to the grouting engineering manual; the grouting hole spacing s affects the uniformity of grouting and the efficiency of material use. Since a smaller spacing can usually provide a better grouting effect, it will lead to higher costs and material waste. The smaller s is, the greater the economic value and the higher the cost. Therefore, the hole spacing should be reasonably planned to ensure the best economic benefits.

[0058] The reason why the weight ratio is set to ω2>ω1>ω3>0 is that economy is an important consideration, and the cost of grouting directly affects the overall budget and economic benefits of the project. Therefore, the weight of the economic value ω2 is set higher than the weight of the safety value ω1 to emphasize the importance of controlling costs in the optimization process. The priority of economy reflects the common practice of pursuing cost-effectiveness in engineering management; in grouting construction, it is crucial to ensure structural safety and avoid displacement exceeding the maximum allowable value. Therefore, the weight of the safety value ω1 needs to be higher than the weight of the penalty value ω3 to ensure that safety is not sacrificed while pursuing economic benefits. Even in the case of strong economy, safety must still be kept in a priority position to prevent potential structural risks; the penalty value part is mainly used to punish situations that exceed the safety threshold to ensure that the displacement during the construction process is not too large. Since the penalty value is a penalty mechanism for unsafe behavior, its relative importance in decision-making is relatively low. Therefore, the weight of the penalty value ω3 is set to the lowest, reflecting the priority of avoiding entering the penalty area as much as possible in actual construction.

[0059] The grouting parameter combination with the smallest sum of safety value, economic value and penalty value is selected as the optimal grouting parameter combination.

[0060] It should be noted that by combining real-time monitoring data with intelligent control technology, the accuracy and effectiveness of the grouting process can be ensured. best , pulse width T best and pulse intensity I best, according to the actual displacement of the measuring point, the grouting parameters can be optimized in time, thereby improving the safety and effectiveness of the construction. The weight setting in this formula reflects that the pulse intensity is more important to the pulse index than the frequency and width, ensuring that the grouting effect is given priority during the construction process. This synthetically generated pulse index not only helps to control construction quality and safety risks, but also maximizes the overall performance of the grouting project. The maximum allowable values ​​of grouting frequency, width, and intensity can be obtained by referring to the grouting project manual.

[0061] Therefore, it is necessary to comprehensively generate the grouting pulse index based on the pulse frequency, pulse width and pulse intensity under the optimal combination of construction grouting parameters. The method is as follows:

[0062] Based on pulse intelligent control technology, the grouting parameters are dynamically adjusted according to the displacement data of the measuring points monitored in real time to obtain the pulse frequency f under the optimal construction grouting parameter combination. best , pulse width T best and pulse intensity I best , the grouting pulse index is comprehensively generated based on the formula:

[0063]

[0064] Among them, a, b, and c correspond to the weight ratio of their respective parameters and c>a>b>0, f best 、T best ,I best is the pulse frequency, pulse width and pulse intensity under the optimal construction grouting parameter combination, f max 、T max ,I max is the maximum allowable value of grouting frequency, width, and strength; the reason why c>a>b>0 is that in the grouting process, the pulse intensity directly affects the injection capacity of the liquid and the effective reinforcement of the soil. Pulses with higher intensity can more effectively overcome the pore pressure of the soil, enhance the permeability and diffusion of cement slurry, and thus better fill the soil or cracks. Therefore, it is reasonable to set the strength weight to the highest c to ensure that the effectiveness of the grouting effect is given priority during construction; the pulse frequency affects the time interval for grouting and the continuity of construction. The appropriate frequency can improve the uniformity of grouting and control the stress distribution of the soil. Although the importance of frequency is slightly lower than that of strength, it is still crucial to the construction effect, so the weight a is set in the middle; the pulse width mainly affects the duration of each pulse. Compared with the strength and frequency, its impact on the overall grouting effect is relatively small, so the weight b is set to the lowest. This does not mean that the width is not important, but because in the actual grouting process, changes in strength and frequency often have a more significant impact on the results;

[0065] When f bestThe higher the value, the more times the grouting is applied per unit time, which helps to improve the uniformity and effectiveness of the grouting. In the form of, the greater the frequency, the closer the score is to 1, and the corresponding value is larger, thus increasing J p The value of T best The larger the value, the longer each grouting lasts, which may be beneficial to the full penetration and distribution of cement slurry, similar to the frequency. The increase of J p The increase of best When it increases, it indicates that the strength directly affects the injection capacity of the grouting material. Higher strength can better enhance the bearing capacity and stability of the soil. Similarly, the increase in strength is achieved through Improve J p The value of pulse index J p The larger the value, the better the grouting parameter combination and the better the construction effect. Therefore, in practical applications, the goal is to maximize J p value to ensure the best reinforcement effect and safety performance during the grouting process; the formula uses a proportional form The purpose is to standardize different parameters so that they can be compared within the same framework. This method allows parameters of different units and magnitudes to be reasonably integrated for comprehensive evaluation. The use of square roots can reduce the impact of the ratio between different parameters on the index, so that the contribution of each parameter change to the total index will not be linearly amplified. This design can better reflect the complex relationship between parameters in actual construction. For example, the impact of changes in certain parameters within a certain range on the construction effect will gradually decrease.

[0066] It should be noted that the importance of setting the pulse threshold is that it provides a key safety control mechanism for the grouting construction process. p And with the preset pulse threshold J th By making a comparison, it is possible to determine in time whether the construction process is within the safe range. This logical judgment ensures that when the pulse index exceeds the threshold, the grouting construction can be stopped immediately, thereby effectively avoiding soil damage, excessive structural displacement and even potential safety accidents caused by excessive grouting. This early warning mechanism not only ensures construction safety, but also reduces economic losses and improves construction efficiency. Therefore, setting the pulse threshold is an indispensable and important link in the entire grouting construction process.

[0067] Therefore, it is necessary to set a pulse threshold to determine whether the grouting pulse index exceeds the pulse threshold. The logic formula is as follows:

[0068]

[0069] Where Q represents the logic value for judging whether the pulp pulse index exceeds the pulse threshold, J th It is the preset pulse threshold. When Q=0, it indicates that the pulse index does not exceed the pulse threshold and the grouting construction continues; when Q=1, it indicates that the pulse index has exceeded the pulse threshold and the grouting construction is stopped.

[0070] See also Figure 2 The present invention further provides a pulse intelligent grouting control system, the control system is used to execute the above-mentioned pulse intelligent grouting control method, including:

[0071] A data acquisition module, wherein the data acquisition module is used to obtain multiple groups of historical status data, the historical status data including historical grouting parameters of individuals in the initial population and displacements of corresponding measurement points after grouting, the historical grouting parameters including grouting hole spacing, grouting hole diameter and grouting hole pressure data;

[0072] A fitness value calculation and model building module, wherein the fitness value calculation and model building are used to establish an optimal grouting parameter prediction model, taking historical grouting parameters as input and the displacement of corresponding measurement points as labels, training the optimal grouting parameter prediction model, calculating the fitness values ​​of individuals in the initial population based on state data, and taking minimization of the fitness value as the optimization goal, optimizing the initial population based on a genetic algorithm and the optimal grouting parameter prediction model, and finding the individual with the smallest fitness value as the optimal grouting parameter combination;

[0073] A grouting pulse index generation module, which is used to perform grouting using pulse technology based on optimal grouting parameters, collect pulse frequency, pulse width and pulse intensity under the optimal combination of construction grouting parameters in real time, and comprehensively generate a grouting pulse index;

[0074] The grouting process monitoring and threshold control module is used to set up a pulse threshold. When the grouting pulse index exceeds the threshold, the grouting is stopped to achieve precise control of the grouting process.

[0075] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0076] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0077] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0078] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A pulse intelligent grouting control method, characterized in that: The specific steps include: Step 1: Acquire multiple groups of historical state data, the historical state data including historical grouting parameters of individuals in the initial population and displacements of corresponding measurement points after grouting, the historical grouting parameters including grouting hole spacing, grouting hole diameter, and grouting hole pressure data; Step 2: Establish an optimal grouting parameter prediction model, take the historical grouting parameters as input, take the displacement of the corresponding measurement point as the label, train the optimal grouting parameter prediction model, calculate the fitness value of the individuals in the initial population based on the state data, and take minimizing the fitness value as the optimization goal. Based on the genetic algorithm and the optimal grouting parameter prediction model, optimize the initial population and find the individual with the smallest fitness value as the optimal grouting parameter combination; Step 3: Based on the optimal grouting parameters, pulse technology is used for grouting, and the pulse frequency, pulse width and pulse intensity under the optimal combination of construction grouting parameters are collected in real time to comprehensively generate the grouting pulse index; Step 4: Set up a pulse threshold. When the grouting pulse index exceeds the threshold, stop grouting to achieve precise control of the grouting process.

2. A pulse intelligent grouting control method according to claim 1, characterized in that: The optimal grouting parameter prediction model is established based on the following method: Taking historical grouting parameters as input and the displacement of the corresponding measuring point as label, the mean square error is selected as the loss function. The model structure adopts a deep neural network, which consists of an input layer, multiple hidden layers and an output layer. The input layer is responsible for receiving historical grouting parameter data, and multiple hidden layers are responsible for capturing complex nonlinear relationships. The output layer is responsible for outputting the corresponding measuring point displacement. Then the prediction model is trained, and cross-validation and other methods are used to prevent overfitting. The performance of the model is evaluated by training error and validation error. The back propagation algorithm is combined with the optimization method to iteratively update the model parameters until the preset round is reached to minimize the loss function and realize effective prediction of the measuring point displacement.

3. A pulse intelligent grouting control method according to claim 1, characterized in that: The calculation formula of the fitness value is: Among them, X j represents the final displacement of measurement point j, m is the total number of measurement points, j is the index of the measurement point, j∈[1,m], Indicates the maximum displacement threshold of the measurement point, X av represents the average displacement of the measuring point, ω1, ω2, and ω3 are weight proportional coefficients, which are used to represent the influence of each part on the fitness function, and ω2>ω1>ω3>0, q is the grouting cost coefficient, d, s, and δ represent the grouting hole diameter, spacing, and grouting hole pressure of the grouting parameters, S is the area of ​​the grouting area, and D is the depth of the grouting hole; the smaller the F value, the better the grouting parameter; This part indicates the safety value, X av This part represents the penalty value. This part represents the economic value, and F is the fitness value of the individual; The grouting parameter combination with the smallest sum of safety value, economic value and penalty value is selected as the optimal grouting parameter combination.

4. According to a pulse intelligent grouting control method as claimed in claim 1, it is characterized in that: The grouting pulse index is generated comprehensively based on the following method: Based on pulse intelligent control technology, the grouting parameters are dynamically adjusted according to the displacement data of the measuring points monitored in real time to obtain the pulse frequency f under the optimal construction grouting parameter combination. best , pulse width T best and pulse intensity I best , the grouting pulse index is comprehensively generated based on the formula: Among them, a, b, and c correspond to the weight ratio of their respective parameters and c>a>b>0, f best 、T best ,I best is the pulse frequency, pulse width and pulse intensity under the optimal construction grouting parameter combination, f max 、T max ,I max It is the maximum allowable value of grouting frequency, width and strength.

5. A pulse intelligent grouting control method according to claim 4, characterized in that: The pulse threshold is set to determine whether the grouting pulse index exceeds the pulse threshold. The logic formula is as follows: Where Q represents the logic value for judging whether the pulp pulse index exceeds the pulse threshold, J th It is the preset pulse threshold. When Q=0, it indicates that the pulse index does not exceed the pulse threshold and the grouting construction continues; when Q=1, it indicates that the pulse index has exceeded the pulse threshold and the grouting construction is stopped.

6. A pulse intelligent grouting control system, characterized in that: The control system is used to execute a pulse intelligent grouting control method according to any one of claims 1 to 5, comprising: A data acquisition module, the data acquisition module is used to obtain multiple groups of historical status data, the historical status data includes historical grouting parameters of individuals in the initial population, and the displacement of corresponding measurement points after grouting, the historical grouting parameters include grouting hole spacing, grouting hole diameter and grouting hole pressure data; A fitness value calculation and model building module, wherein the fitness value calculation and model building are used to establish an optimal grouting parameter prediction model, taking historical grouting parameters as input and the displacement of corresponding measurement points as labels, training the optimal grouting parameter prediction model, calculating the fitness values ​​of individuals in the initial population based on state data, and taking minimization of fitness values ​​as the optimization goal, optimizing the initial population based on a genetic algorithm and the optimal grouting parameter prediction model, and finding the individual with the smallest fitness value as the optimal grouting parameter combination; A grouting pulse index generation module, which is used to perform grouting using pulse technology based on optimal grouting parameters, collect pulse frequency, pulse width and pulse intensity under the optimal combination of construction grouting parameters in real time, and comprehensively generate a grouting pulse index; The grouting process monitoring and threshold control module is used to set up a pulse threshold. When the grouting pulse index exceeds the threshold, the grouting is stopped to achieve precise control of the grouting process.

Images