Intelligent decision-making method and device for prevention and control measures of tunnel water inrush and mud inrush disasters

Abstract

The invention relates to the technical field of tunnel geological disaster prevention and control, in particular to an intelligent decision-making method and device for tunnel water inrush and mud inrush disaster prevention and control measures, and the method comprises the steps: obtaining the exploration design and multi-source detection data, disaster-causing structure data, disaster prevention and control measures and disaster prevention and control effects of water inrush and mud inrush of a tunnel; establishing a nonlinear mapping relation model; obtaining a disaster prediction equation, a prevention and control measure decision equation and a prevention and control effect prediction equation of the tunnel water inrush and mud inrush disasters according to the nonlinear mapping relation model; and training the equation, constructing a prevention and control measure prediction model of the tunnel water inrush and mud inrush disasters, and obtaining prevention and control measures of the current tunnel water inrush and mud inrush disasters by using the prevention and control measure prediction model. Therefore, the problems that in related technologies, the most appropriate and most efficient prevention and control measures are difficult to select in time according to disaster types, and targeted prevention and control guidance suggestions are difficult to provide for tunnel water inrush and mud inrush disasters are solved.

Description

Technical Field

[0001] The present application relates to the technical field of tunnel geological disaster prevention and control, and in particular to an intelligent decision-making method and device for prevention and control measures for tunnel water and mud inrush disasters. Background Art

[0002] With the vigorous development of tunnel and underground engineering construction, the construction of tunnel and underground engineering will inevitably pass through extremely unfavorable geological areas. Tunnel excavation often encounters serious hazards such as water and mud inrush. Tunnel water and mud inrush disasters have a very high mortality rate. Failure to take scientific and effective prevention and control measures in time or the use of unreasonable prevention and control measures can easily cause huge economic losses and casualties. Therefore, in the construction of tunnel and underground engineering, timely obtaining scientific and effective tunnel water and mud inrush disaster prevention and control measures is of great practical significance for ensuring the safe construction of tunnel and underground engineering and avoiding casualties.

[0003] In the relevant technology, advanced geological forecasts can be used to detect the disaster-causing structures of water and mud bursts, and then prevention and control measures can be selected based on expert experience. Alternatively, during the tunnel survey stage, the risk classification value of each tunnel section can be calculated based on the risk status of the geological conditions of each tunnel section, so as to divide the segment distribution characteristics of the tunnel water burst risk and realize the dynamic assessment of the water and mud burst risk.

[0004] However, in the relevant technologies, due to the complex structure of water and mud bursts causing disasters, different types of water and mud bursts correspond to different prevention and control measures, and it is difficult to timely select the most appropriate and efficient prevention and control measures according to the type of disaster. This leads to huge deficiencies in the selection and effectiveness of prevention and control measures for tunnel water and mud bursts, and it is difficult to provide targeted prevention and control guidance and suggestions for tunnel water and mud bursts, which needs to be solved urgently. Summary of the invention

[0005] The present application provides an intelligent decision-making method and device for prevention and control measures for water and mud bursts in tunnels, so as to solve the problems in related technologies, such as the complexity of the structure of water and mud bursts causing disasters, different types of water and mud bursts corresponding to different prevention and control measures, and difficulty in timely selecting the most appropriate and efficient prevention and control measures according to the type of disaster, resulting in huge deficiencies in the selection and effectiveness of prevention and control measures for water and mud bursts in tunnels, and difficulty in providing targeted prevention and control guidance and suggestions for water and mud bursts in tunnels.

[0006] The first aspect of the present application provides an intelligent decision-making method for prevention and control measures of water and mud inrush disasters in tunnels, which is applied to the model construction stage, wherein the method includes the following steps: obtaining the survey and design and multi-source detection data of water and mud inrush in tunnels, disaster-causing structural data, disaster prevention and control measures and disaster prevention and control effects, so as to establish a nonlinear mapping relationship model; obtaining the disaster prediction equation, prevention and control measure decision equation and prevention and control effect prediction equation of the tunnel water and mud inrush disaster according to the nonlinear mapping relationship model; training the disaster prediction equation, prevention and control measure decision equation and prevention and control effect prediction equation of the tunnel water and mud inrush disaster, and constructing the prevention and control measures prediction model of the tunnel water and mud inrush disaster, so as to use the prevention and control measures prediction model to obtain the prevention and control measures of the current tunnel water and mud inrush disaster.

[0007] Optionally, in one embodiment of the present application, the establishment of a nonlinear mapping relationship model includes: obtaining the influence weights of the survey and design and multi-source detection data of tunnel water and mud inrush disasters, and inputting the survey and design and multi-source detection data and their influence weights and the disaster-causing structural data into a first Gaussian process regression model to obtain a disaster prediction model in the nonlinear mapping relationship model; obtaining the influence weights of the disaster-causing structural data of the tunnel water and mud inrush disasters, and inputting the disaster-causing structural data and their influence weights and the disaster prevention and control measures into a second Gaussian process regression model to obtain a disaster prevention and control measures prediction model in the nonlinear mapping relationship model; obtaining the influence weights of the prevention and control measures of the tunnel water and mud inrush disasters, and inputting the disaster prevention and control measures and their influence weights and the disaster prevention and control effects into a third Gaussian process regression model to obtain a disaster prevention and control effect prediction model in the nonlinear mapping relationship model.

[0008] Optionally, in one embodiment of the present application, the disaster prediction equation, prevention and control measures decision equation and prevention and control effect prediction equation for tunnel water and mud inrush disasters are obtained according to the nonlinear mapping relationship model, including: based on the disaster prediction model, constructing a disaster prediction equation with the disaster-causing structural data as the target, and the survey and design and the multi-source detection data as control variables; based on the disaster prediction equation, constructing a prevention and control measures decision equation for tunnel water and mud inrush disasters with the disaster prevention and control measures as the target, and the disaster-causing structural data as the control variable; based on the disaster prevention and control measures decision equation, constructing a prevention and control measures effect prediction equation for tunnel water and mud inrush disasters with the disaster prevention and control effect as the target, and the disaster prevention and control measures as the control variable.

[0009] Optionally, in one embodiment of the present application, the disaster prediction equation, prevention and control measures decision equation and prevention and control effect prediction equation of the tunnel water and mud burst disaster are trained to construct the prevention and control measures prediction model of the tunnel water and mud burst disaster, including: taking the prevention and control measures of the tunnel water and mud burst disaster as the optimization target, and taking the prevention and control measures effect prediction equation as the constraint function to construct the objective function; setting at least one algorithm-related parameter; initializing the population position, and calculating the fitness value of the individuals in the initialized population to update the parameter vector and the position of the updated population individuals, recalculating the fitness of the individuals, and comparing with the preset threshold for updating; judging whether the operation result meets the termination condition; if the operation result meets the termination condition, ending the algorithm, otherwise continuing the iterative calculation until the optimal gray wolf position is output, the final solution set is obtained, and the prevention and control measures prediction model is output.

[0010] The second aspect of the present application provides an intelligent decision-making method for prevention and control measures for water and mud inrush disasters in tunnels, which is applied to the model application stage, wherein the method includes the following steps: acquiring survey and design and multi-source detection data during the tunnel construction process; inputting the survey and design and multi-source detection data into a pre-constructed tunnel water and mud inrush disaster prevention and control measures prediction model to obtain the prevention and control measures for the current tunnel water and mud inrush disaster, wherein the prevention and control measures prediction model is constructed by survey and design and multi-source detection data of water and mud inrush in tunnels, disaster-causing structural data, disaster prevention and control measures and disaster prevention and control effects.

[0011] The third aspect of the present application provides an intelligent decision-making device for prevention and control measures of water and mud inrush disasters in tunnels, which is applied to the model construction stage, wherein the device includes: an establishment module, which is used to obtain the survey and design and multi-source detection data of water and mud inrush in tunnels, disaster-causing structural data, disaster prevention and control measures and disaster prevention and control effects, so as to establish a nonlinear mapping relationship model; a first acquisition module, which is used to obtain the disaster prediction equation, prevention and control measure decision equation and prevention and control effect prediction equation of tunnel water and mud inrush disasters according to the nonlinear mapping relationship model; a construction module, which is used to train the disaster prediction equation, prevention and control measure decision equation and prevention and control effect prediction equation of the tunnel water and mud inrush disaster, and construct the prevention and control measures prediction model of the tunnel water and mud inrush disaster, so as to use the prevention and control measures prediction model to obtain the prevention and control measures of the current tunnel water and mud inrush disaster.

[0012] Optionally, in one embodiment of the present application, the establishment module includes: a first acquisition unit, used to obtain the influence weights of the survey and design and multi-source detection data of the tunnel water and mud inrush disaster, and input the survey and design and multi-source detection data and their influence weights and the disaster-causing structural data into the first Gaussian process regression model to obtain the disaster prediction model in the nonlinear mapping relationship model; a second acquisition unit, used to obtain the influence weights of the disaster-causing structural data of the tunnel water and mud inrush disaster, and input the disaster-causing structural data and their influence weights and the disaster prevention and control measures into the second Gaussian process regression model to obtain the disaster prevention and control measures prediction model in the nonlinear mapping relationship model; a third acquisition unit, used to obtain the influence weights of the prevention and control measures of the tunnel water and mud inrush disaster, and input the disaster prevention and control measures and their influence weights and the disaster prevention and control effects into the third Gaussian process regression model to obtain the disaster prevention and control effect prediction model in the nonlinear mapping relationship model.

[0013] Optionally, in one embodiment of the present application, the acquisition module includes: a first construction unit, for constructing, based on the disaster prediction model, a disaster prediction equation with the disaster-causing structural data as the target and the survey and design and the multi-source detection data as the control variables; a second construction unit, for constructing, based on the disaster prediction equation, a prevention and control measures decision equation for tunnel water and mud inrush disasters with the disaster prevention and control measures as the target and the disaster-causing structural data as the control variable; a third construction unit, for constructing, based on the disaster prevention and control measures decision equation, a prevention and control measures effect prediction equation for tunnel water and mud inrush disasters with the disaster prevention and control effect as the target and the disaster prevention and control measures as the control variable.

[0014] Optionally, in one embodiment of the present application, the construction module includes: a fourth construction unit, used to construct an objective function with the prevention and control measures for the tunnel water and mud inrush disasters as the optimization target and the prevention and control measures effect prediction equation as the constraint function; a setting unit, used to set at least one algorithm-related parameter; an updating unit, used to initialize the population position, and calculate the fitness value of the individuals in the initialized population, so as to update the parameter vector and the update population individual position, recalculate the individual fitness, and compare it with a preset threshold for updating; a judgment unit, used to judge whether the operation result meets the termination condition; a generation unit, used to end the algorithm when the operation result meets the termination condition, otherwise continue the iterative calculation until the optimal gray wolf position is output, the final solution set is obtained, and the prevention and control measures prediction model is output.

[0015] The fourth aspect of the present application provides an intelligent decision-making device for prevention and control measures of water and mud inrush disasters in tunnels, which is applied to the model application stage, wherein the device includes: a second acquisition module, used to acquire the survey and design and multi-source detection data during the tunnel construction process; a generation module, used to input the survey and design and multi-source detection data into a pre-constructed tunnel water and mud inrush disaster prevention and control measures prediction model to obtain the prevention and control measures of the current tunnel water and mud inrush disaster, wherein the prevention and control measures prediction model is constructed by the survey and design and multi-source detection data of water and mud inrush in the tunnel, disaster-causing structure data, disaster prevention and control measures and disaster prevention and control effects.

[0016] The fifth aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent decision-making method for prevention and control measures for water and mud inrush disasters in tunnels as described in the above embodiments.

[0017] A sixth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above-mentioned intelligent decision-making method for prevention and control measures of tunnel water and mud inrush disasters.

[0018] The seventh aspect of the present application provides a computer program product, including a computer program, which, when executed, implements the above-mentioned intelligent decision-making method for prevention and control measures of tunnel water and mud inrush disasters.

[0019] The embodiment of the present application can establish a nonlinear mapping relationship model based on the survey and design and multi-source detection data, disaster-causing structural data, disaster prevention and control measures and disaster prevention and control effects of tunnel water and mud bursts, and then obtain the disaster prediction equation, prevention and control measures decision equation and prevention and control effect prediction equation of tunnel water and mud bursts disasters, and conduct training to construct a prevention and control measures prediction model for tunnel water and mud bursts disasters, and use the prevention and control measures prediction model to obtain the prevention and control measures for the current tunnel water and mud bursts disaster. By comprehensively considering multiple factors such as survey and design and multi-source detection data, disaster-causing structural data, disaster prevention and control measures and disaster prevention and control effects, it can more accurately reflect the complexity and uncertainty of tunnel water and mud bursts disasters, and then timely discover potential risks, avoid or reduce the occurrence of disasters, and continuously improve the accuracy and timeliness of early warnings through model training and learning, and take prevention and control measures in advance. Therefore, the problem in the relevant technologies is solved that due to the complex structure of water and mud bursts causing disasters, different types of water and mud bursts correspond to different prevention and control measures, and it is difficult to timely select the most appropriate and efficient prevention and control measures according to the type of disaster. This leads to huge deficiencies in the selection and effectiveness of prevention and control measures for tunnel water and mud bursts, and it is difficult to provide targeted prevention and control guidance and suggestions for tunnel water and mud bursts.

[0020] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0022] Figure 1 A flowchart of an intelligent decision-making method for prevention and control measures for water and mud inrush disasters in tunnels provided according to an embodiment of the present application;

[0023] Figure 2 A flowchart of constructing a prevention and control measures prediction model using a multi-objective grey wolf optimization algorithm according to an embodiment of the present application;

[0024] Figure 3 A block diagram of an intelligent decision-making device for preventing and controlling water and mud inrush disasters in tunnels provided according to an embodiment of the present application;

[0025] Figure 4 A flowchart of an intelligent decision-making method for prevention and control measures for water and mud inrush disasters in tunnels provided according to another embodiment of the present application;

[0026] Figure 5 A block diagram of an intelligent decision-making device for preventing and controlling water and mud inrush disasters in tunnels provided according to another embodiment of the present application;

[0027] Figure 6 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0029] The following describes the intelligent decision-making method and device for prevention and control measures for water and mud inrush disasters in tunnels according to the embodiments of the present application with reference to the accompanying drawings. In view of the problem mentioned in the above background technology that due to the complex structure of water and mud inrush disasters, different types of water and mud inrush disasters correspond to different prevention and control measures, and it is difficult to timely select the most appropriate and efficient prevention and control measures according to the type of disaster, resulting in huge deficiencies in the selection and effectiveness of prevention and control measures for water and mud inrush disasters in tunnels, and it is difficult to provide targeted prevention and control guidance and suggestions for water and mud inrush disasters in tunnels, the present application provides an intelligent decision-making method for prevention and control measures for water and mud inrush disasters in tunnels, in which a nonlinear mapping relationship model can be established based on the survey and design of water and mud inrush disasters in tunnels and multi-source detection data, disaster-causing structure data, disaster prevention and control measures, and disaster prevention and control effects. , and then the disaster prediction equation, prevention and control measures decision equation and prevention and control effect prediction equation of tunnel water and mud gushing disaster are obtained, and training is carried out to construct a prevention and control measures prediction model for tunnel water and mud gushing disaster, and the prevention and control measures prediction model is used to obtain the current prevention and control measures for tunnel water and mud gushing disaster. By comprehensively considering the survey and design and multi-source detection data, disaster-causing structural data, disaster prevention and control measures and disaster prevention and control effects, it can more accurately reflect the complexity and uncertainty of tunnel water and mud gushing disasters, and then timely discover potential risks, avoid or reduce the occurrence of disasters, and continuously improve the accuracy and timeliness of early warning through model training and learning, and take prevention and control measures in advance. Therefore, the relevant technology solves the problem that due to the complex structure of water and mud gushing disasters, different types of water and mud gushing disasters correspond to different prevention and control measures, and it is difficult to timely select the most appropriate and efficient prevention and control measures according to the disaster type, resulting in a huge lack of prevention and control measures for tunnel water and mud gushing disasters and effectiveness, and it is difficult to provide targeted prevention and control guidance and suggestions for tunnel water and mud gushing disasters.

[0030] Specifically, Figure 1 The present invention is a flowchart of an intelligent decision-making method for prevention and control measures for water and mud inrush disasters in tunnels provided according to an embodiment of the present application.

[0031] like Figure 1 As shown, the intelligent decision-making method for prevention and control measures of water and mud inrush disasters in tunnels is applied in the model building stage, wherein the method includes the following steps:

[0032] In step S101, the survey and design of water and mud inrush in the tunnel, multi-source detection data, disaster-causing structural data, disaster prevention and control measures and disaster prevention and control effects are obtained to establish a nonlinear mapping relationship model.

[0033] It can be understood that in the embodiments of the present application, the survey, design and multi-source detection data may include but are not limited to tunnel design data, engineering geological data, hydrogeological data, advanced forecast data, advanced drilling data, field monitoring data, etc., and the present application does not impose specific restrictions.

[0034] Among them, in the embodiments of the present application, the tunnel design data may include but is not limited to tunnel length, entrance and exit locations, tunnel direction, tunnel cross-sectional dimensions, tunnel slope, support scheme, etc., and the present application does not make specific restrictions.

[0035] Engineering geological data may include, but are not limited to, geographical location, topography, stratum lithology, geological structure, etc., and this application does not impose any specific restrictions.

[0036] Hydrogeological data may include, but are not limited to, groundwater dynamic conditions, groundwater distribution, precipitation, precipitation intensity, etc., and this application does not impose any specific restrictions.

[0037] The advanced forecast data may include, but are not limited to, geological radar data, transient electromagnetic data, TSP data (Total Suspended Particulate), induced polarization number data, borehole radar data, etc., and this application does not impose any specific restrictions.

[0038] On-site monitoring data may include, but is not limited to, water flow rate data, water level data, water inrush data after disaster prevention and control measures are taken, etc. This application does not impose any specific restrictions.

[0039] Furthermore, in the embodiments of the present application, the disaster-causing structure data may include but is not limited to the type, scale, location, nature, morphology, filling medium, evolution stage, etc. of the disaster-causing structure, and the present application does not impose any specific limitations.

[0040] Furthermore, in the embodiments of the present application, disaster prevention and control measures may include but are not limited to drainage, water drainage tunnels, accumulation reinforcement, avoidance, grouting to block water, energy release and pressure reduction, etc., and the present application does not impose specific limitations.

[0041] Furthermore, in an embodiment of the present application, the disaster prevention and control effect can be the effect of controlling water and mud bursts after the disaster prevention and control measures are adopted to control the water and mud bursts disasters based on survey and design and multi-source detection data, disaster-causing structural data. The specific settings can be made by technical personnel in this field according to actual conditions, and the present application does not impose any specific restrictions.

[0042] In addition, it should be noted that the nonlinear mapping relationship model established in the embodiment of the present application may include but is not limited to a disaster prediction model, a disaster prevention and control measures prediction model, a disaster prevention and control effect prediction model, etc., and the present application does not impose any specific restrictions.

[0043] As a possible implementation method, the embodiment of the present application can establish a nonlinear mapping relationship model by obtaining the survey and design of water and mud inrush in the tunnel and multi-source detection data, disaster-causing structure data, disaster prevention and control measures and disaster prevention and control effects.

[0044] It can be understood that the embodiments of the present application establish a nonlinear relationship between the survey and design and multi-source detection data and the disaster-causing structural data by analyzing the survey and design and multi-source detection data, and then establish a nonlinear mapping model for disaster prevention and control measures, thereby effectively improving the accuracy of disaster prevention and control measures decision-making.

[0045] Optionally, in one embodiment of the present application, a nonlinear mapping relationship model is established, including: obtaining the influence weights of the survey and design and multi-source detection data of tunnel water and mud inrush disasters, and inputting the survey and design and multi-source detection data and their influence weights and disaster-causing structural data into a first Gaussian process regression model to obtain a disaster prediction model in the nonlinear mapping relationship model; obtaining the influence weights of the disaster-causing structural data of tunnel water and mud inrush disasters, and inputting the disaster-causing structural data and their influence weights and disaster prevention and control measures into a second Gaussian process regression model to obtain a disaster prevention and control measures prediction model in the nonlinear mapping relationship model; obtaining the influence weights of the prevention and control measures of tunnel water and mud inrush disasters, and inputting the disaster prevention and control measures and their influence weights and disaster prevention and control effects into a third Gaussian process regression model to obtain a disaster prevention and control effect prediction model in the nonlinear mapping relationship model.

[0046] It is understandable that the Gaussian process regression model has a solid and rigorous theoretical statistical foundation, which can well solve complex regression problems such as high dimensionality and high nonlinearity in the data, and it has strong generalization ability. Therefore, it can well establish the nonlinear correlation between survey and design and multi-source detection data, disaster-causing structural data and disaster prevention and control measures, and effectively improve the decision-making accuracy of tunnel water and mud inrush disaster prevention and control measures.

[0047] In some embodiments, the embodiments of the present application can first obtain the influence weights of the survey and design and multi-source detection data of tunnel water and mud inrush disasters, and input the survey and design and multi-source detection data and their influence weights and disaster-causing structural data into the first Gaussian process regression model to obtain a disaster prediction model in the nonlinear mapping relationship model.

[0048] Exemplarily, the embodiment of the present application can use the hierarchical analysis method to obtain the influence weights of the survey and design of tunnel water and mud inrush disasters and multi-source detection data, and input the survey and design and multi-source detection data and their influence weights and disaster-causing structural data into the first Gaussian process regression model to obtain a disaster prediction model.

[0049] It can be understood that the embodiment of the present application inputs the survey and design and multi-source detection data and their influence weights and disaster-causing structural data into the first Gaussian process regression model, and obtains the disaster prediction model based on the first Gaussian process regression model, performs training and learning according to the training set, obtains the non-mapping relationship between the survey and design and multi-source detection data and the disaster-causing structural data, and then establishes the disaster prediction model.

[0050] It should be noted that the training set of the first Gaussian process regression model in the embodiment of the present application can be expressed as but not limited to: D = (Xi, Yi), the first Gaussian noise model can be expressed as but not limited to Yi = F(Xi) + ε, and the first Gaussian process regression model can be expressed as but not limited to P(X) = GP[f, K(X, X')], where f is the mean of the first Gaussian process regression model; K(X, X') is a covariance function, which is used to express the correlation between the survey and design and the multi-source detection data and the disaster-causing structure data.

[0051] Among them, in the embodiment of the present application, the input value can be but not limited to: Xi = [X1, X2, ..., Xi], which is the survey design and multi-source detection data; the output value can be but not limited to: Yi = [Y1, Y2, ..., Yi], which is the disaster-causing structural data; ε is an independent random variable between the survey design and multi-source detection data and the disaster-causing structural data, which conforms to the Gaussian distribution Among them, σ n is the variance of the noise.

[0052] In some embodiments, the embodiments of the present application can input the acquired disaster-causing structural data of tunnel water and mud inrush disasters, their impact weights and disaster prevention and control measures into a second Gaussian process regression model to obtain a disaster prevention and control measures prediction model in a nonlinear mapping relationship model.

[0053] Exemplarily, the embodiment of the present application can use the hierarchical analysis method to obtain the influence weight of the disaster-causing structural data of tunnel water and mud inrush disasters, and input the disaster-causing structural data and its influence weight and disaster prevention and control measures into the second Gaussian process regression model to obtain a disaster prevention and control measures prediction model.

[0054] It can be understood that the embodiment of the present application inputs the disaster-causing structural data, its impact weights and disaster prevention and control measures into the second Gaussian process regression model, and obtains the disaster prevention and control measures prediction model based on the second Gaussian process regression model. Training and learning are performed according to the training set to obtain the non-mapping relationship between the disaster-causing structural data and the disaster prevention and control measures, and then establish the disaster prevention and control measures prediction model.

[0055] It should be noted that the training set of the second Gaussian process regression model in the embodiment of the present application can be expressed as but not limited to: D = (Xi, Yi), the second Gaussian noise model can be expressed as but not limited to Yi = F(Xi) + ε, and the second Gaussian process regression model can be expressed as but not limited to P(X) = GP[f, K(X, X')], where f is the mean of the second Gaussian process regression model; K(X, X') is a covariance function used to express the correlation between disaster-causing structural data and disaster prevention and control measures.

[0056] Among them, in the embodiment of the present application, the input value can be but not limited to: Xi = [X1, X2, ..., Xi], which is the disaster-causing structural data; the output value can be but not limited to: Yi = [Y1, Y2, ..., Yi], which is the disaster prevention and control measures; ε is an independent random variable between the disaster-causing structural data and the disaster prevention and control measures, which conforms to the Gaussian distribution Among them, σ n is the variance of the noise.

[0057] In some embodiments, the embodiments of the present application can input the acquired disaster prevention and control measures and their impact weights and disaster prevention and control effects into a third Gaussian process regression model to obtain a disaster prevention and control effect prediction model in a nonlinear mapping relationship model.

[0058] Exemplarily, the embodiment of the present application can use the hierarchical analysis method to obtain the impact weights of the prevention and control measures for tunnel water and mud inrush disasters, input the disaster prevention and control measures and their impact weights and disaster prevention and control effects into the third Gaussian process regression model, and obtain a disaster prevention and control effect prediction model.

[0059] It can be understood that the embodiment of the present application inputs disaster prevention and control measures, their impact weights and disaster prevention and control effects into the third Gaussian process regression model. The disaster prevention and control effect prediction model is obtained based on the third Gaussian process regression model. Training and learning are performed according to the training set to obtain the non-mapping relationship between disaster prevention and control measures and disaster prevention and control effects, and then establish a disaster prevention and control effect prediction model.

[0060] It should be noted that the training set of the third Gaussian process regression model in the embodiment of the present application can be expressed but not limited to: D = (Xi, Yi), the third Gaussian noise model can be expressed as Yi = F(Xi) + ε, and the third Gaussian process regression model is P(X) = GP[f, K(X, X')], where f is the mean of the third Gaussian process regression model; K(X, X') is the covariance function, which is used to express the correlation between disaster prevention and control measures and disaster prevention and control effects.

[0061] Among them, in the embodiment of the present application, the input value can be but not limited to: Xi = [X1, X2, ..., Xi], which is the disaster prevention and control measures; the output value can be but not limited to: Yi = [Y1, Y2, ..., Yi], which is the disaster prevention and control effect; ε is an independent random variable between the disaster prevention and control measures and the disaster prevention and control effect, which conforms to the Gaussian distribution Among them, σ n is the variance of the noise.

[0062] In step S102, a disaster prediction equation, a prevention and control measure decision equation, and a prevention and control effect prediction equation for tunnel water and mud inrush disasters are obtained according to the nonlinear mapping relationship model.

[0063] As a possible implementation method, the embodiment of the present application can obtain a disaster prediction equation, a prevention and control measure decision equation, and a prevention and control effect prediction equation based on a nonlinear mapping relationship model.

[0064] Optionally, in one embodiment of the present application, a disaster prediction equation, a prevention and control measure decision equation and a prevention and control effect prediction equation for tunnel water and mud inrush disasters are obtained according to a nonlinear mapping relationship model, including: based on the disaster prediction model, constructing a disaster prediction equation with disaster-causing structural data as the target and survey, design and multi-source detection data as the control variables; based on the disaster prediction equation, constructing a prevention and control measure decision equation for tunnel water and mud inrush disasters with disaster prevention and control measures as the target and disaster-causing structural data as the control variables; based on the disaster prevention and control measure decision equation, constructing a prevention and control measure effect prediction equation for tunnel water and mud inrush disasters with disaster prevention and control effect as the target and disaster prevention and control measures as the control variable.

[0065] In some embodiments, the embodiments of the present application can construct a disaster prediction equation based on a disaster prediction model, with disaster-causing structures as the target and survey and design and multi-source detection data as control variables.

[0066] In some embodiments, the embodiments of the present application can construct a disaster prevention and control measure decision equation based on the disaster prediction equation, which takes disaster prevention and control measures as the target and disaster-causing structural data as the control variable.

[0067] In some embodiments, the embodiments of the present application can construct a disaster prevention and control measures effect prediction equation based on the disaster prevention and control measures decision equation, with the disaster prevention and control effect as the target and the disaster prevention and control measures as the control variables.

[0068] In step S103, the disaster prediction equation, prevention and control measure decision equation and prevention and control effect prediction equation of tunnel water and mud inrush disasters are trained to construct a prevention and control measure prediction model for tunnel water and mud inrush disasters, so as to obtain the prevention and control measures for the current tunnel water and mud inrush disasters using the prevention and control measure prediction model.

[0069] As a possible implementation method, the embodiment of the present application can train the disaster prediction equation, prevention and control measure decision equation and prevention and control effect prediction equation for tunnel water and mud inrush disasters to obtain a prevention and control measure prediction model for tunnel water and mud inrush disasters.

[0070] Exemplarily, the embodiments of the present application may use a multi-objective grey wolf optimization algorithm to train the decision equations for prevention and control measures for water and mud inrush disasters in tunnels, and then obtain a prediction model for prevention and control measures for water and mud inrush disasters in tunnels.

[0071] It is understandable that the multi-objective grey wolf optimization algorithm has the characteristics of simple structure and few parameters that need to be adjusted. It contains a convergence factor that can be adaptively adjusted and an information feedback mechanism, which can achieve a balance between local optimization and global search. Therefore, it has good performance in solving the problem of nonlinear multi-constraints in the prevention and control measures of tunnel water and mud inrush disasters.

[0072] Optionally, in one embodiment of the present application, the disaster prediction equation, prevention and control measures decision equation and prevention and control effect prediction equation of tunnel water and mud inrush disasters are trained to construct a prevention and control measures prediction model for tunnel water and mud inrush disasters, including: taking the prevention and control measures for tunnel water and mud inrush disasters as the optimization target, and taking the prevention and control measures effect prediction equation as the constraint function to construct an objective function; setting at least one algorithm-related parameter; initializing the population position, and calculating the fitness value of the individuals in the initialized population to update the parameter vector and the position of the updated population individuals, recalculating the fitness of the individuals, and comparing them with a preset threshold for updating; judging whether the operation result meets the termination condition; if the operation result meets the termination condition, the algorithm is terminated, otherwise the iterative calculation is continued until the optimal gray wolf position is output, the final solution set is obtained, and the prevention and control measures prediction model is output.

[0073] In some embodiments, the process of constructing a prevention and control measures prediction model using a multi-objective gray wolf optimization algorithm in the present application embodiment is as follows Figure 2 As shown, the content mainly includes:

[0074] Step S201: construct an objective function.

[0075] Among them, the embodiment of the present application takes the prevention and control measures for tunnel water and mud inrush disasters as the optimization goal, takes the prevention and control measures effect prediction equation as the constraint function, and constructs the objective function.

[0076] Step S202: Setting at least one algorithm-related parameter.

[0077] Among them, at least one algorithm-related parameter set in the embodiment of the present application may include but is not limited to the initial population size N, dimension d, maximum number of iterations Tmax, initialization a, A, C, etc., and the present application does not make specific restrictions.

[0078] Step S203: Initialize the population position and calculate the fitness value of the individuals in the initialized population.

[0079] Among them, in the embodiment of the present application, the initialization population position can use the Tent chaotic map to randomly initialize the population position, Xi (i = 1, 2, 3, ....., n). The embodiment of the present application calculates the fitness value of the individuals in the initialized population, including calculating the fitness Fi (i = 1, 2, 3, ....., n) of the individuals in the initialized population, and sorting them according to their fitness size, and designating the top three individuals in fitness as α, β, δ, which are used to guide the ω gray wolf to update its position.

[0080] Step S204: Update parameter vectors a, A, C.

[0081] Among them, the update parameter vectors a, A, and C in the embodiment of the present application can be calculated according to the following formula, which can be expressed as but not limited to:

[0082] C=2r1,

[0083] A=2ar2-a,

[0084]

[0085] Where r1 is a random number between [0, 1]; T max is the maximum number of iterations; r2 is a random number between [0, 1]; a is a control parameter, whose value decreases linearly with the increase of the number of iterations. max =2, a min =0.

[0086] Step S205: Update α, β, δ.

[0087] Among them, the embodiment of the present application updates the position of individuals in the population, recalculates the fitness of the individuals, compares them with a certain threshold (such as an optimal value, which is not specifically limited in this application), and updates α, β, and δ.

[0088] Step S206: Determine whether the operation result meets the termination condition, if so, execute step S207, otherwise, execute step S203.

[0089] Step S207: Output the optimal gray wolf position, obtain the final solution set, and output the prevention and control measures prediction model.

[0090] According to the intelligent decision-making method for prevention and control measures for water and mud inrush disasters in tunnels proposed in the embodiment of the present application, a nonlinear mapping relationship model can be established based on the survey and design and multi-source detection data, disaster-causing structural data, disaster prevention and control measures and disaster prevention and control effects of the acquired tunnel water and mud inrush disasters, thereby obtaining a disaster prediction equation, a prevention and control measures decision equation and a prevention and control effect prediction equation for tunnel water and mud inrush disasters, and training is performed to construct a prevention and control measures prediction model for tunnel water and mud inrush disasters, and use the prevention and control measures prediction model to obtain the prevention and control measures for the current tunnel water and mud inrush disaster. By comprehensively considering multiple factors such as survey and design and multi-source detection data, disaster-causing structural data, disaster prevention and control measures and disaster prevention and control effects, it can more accurately reflect the complexity and uncertainty of tunnel water and mud inrush disasters, thereby timely discovering potential risks, avoiding or reducing the occurrence of disasters, and continuously improving the accuracy and timeliness of early warnings through model training and learning, and taking prevention and control measures in advance. Therefore, the problem in the relevant technologies is solved that due to the complex structure of water and mud bursts causing disasters, different types of water and mud bursts correspond to different prevention and control measures, and it is difficult to timely select the most appropriate and efficient prevention and control measures according to the type of disaster. This leads to huge deficiencies in the selection and effectiveness of prevention and control measures for tunnel water and mud bursts, and it is difficult to provide targeted prevention and control guidance and suggestions for tunnel water and mud bursts.

[0091] Secondly, with reference to the accompanying drawings, an intelligent decision-making device for prevention and control measures of water and mud inrush disasters in tunnels proposed according to an embodiment of the present application will be described.

[0092] Figure 3 A block diagram of an intelligent decision-making device for preventing and controlling measures for water and mud inrush disasters in tunnels provided according to an embodiment of the present application.

[0093] like Figure 3 As shown, the intelligent decision-making device 30 for prevention and control measures of water and mud inrush disasters in tunnels is applied in the model building stage, wherein the device includes: an establishment module 301, a first acquisition module 302 and a construction module 303.

[0094] Among them, a module 301 is established to obtain the survey and design of water and mud inrush in the tunnel and multi-source detection data, disaster-causing structural data, disaster prevention and control measures and disaster prevention and control effects, so as to establish a nonlinear mapping relationship model.

[0095] The first acquisition module 302 is used to obtain the disaster prediction equation, the prevention and control measure decision equation and the prevention and control effect prediction equation of the tunnel water and mud inrush disaster according to the nonlinear mapping relationship model.

[0096] Construction module 303 is used to train the disaster prediction equation, prevention and control measure decision equation and prevention and control effect prediction equation for tunnel water and mud inrush disasters, and to construct a prevention and control measure prediction model for tunnel water and mud inrush disasters, so as to use the prevention and control measure prediction model to obtain the prevention and control measures for the current tunnel water and mud inrush disasters.

[0097] Optionally, in one embodiment of the present application, the establishment module 301 includes: a first acquisition unit, a second acquisition unit and a third acquisition unit.

[0098] Among them, the first acquisition unit is used to obtain the influence weights of the survey and design and multi-source detection data of tunnel water and mud inrush disasters, and input the survey and design and multi-source detection data and their influence weights and disaster-causing structural data into the first Gaussian process regression model to obtain the disaster prediction model in the nonlinear mapping relationship model.

[0099] The second acquisition unit is used to obtain the influence weight of the disaster-causing structural data of tunnel water and mud inrush disasters, and input the disaster-causing structural data and its influence weight and disaster prevention and control measures into the second Gaussian process regression model to obtain the disaster prevention and control measures prediction model in the nonlinear mapping relationship model.

[0100] The third acquisition unit is used to obtain the influence weights of the prevention and control measures for tunnel water and mud inrush disasters, and input the disaster prevention and control measures and their influence weights and disaster prevention and control effects into the third Gaussian process regression model to obtain the disaster prevention and control effect prediction model in the nonlinear mapping relationship model.

[0101] Optionally, in one embodiment of the present application, the acquisition module 302 includes: a first construction unit, a second construction unit and a third construction unit.

[0102] Among them, the first construction unit is used to construct a disaster prediction equation based on the disaster prediction model, which takes the disaster-causing structural data as the target and the survey and design and multi-source detection data as the control variables.

[0103] The second construction unit is used to construct a decision equation for prevention and control measures of tunnel water and mud inrush disasters based on the disaster prediction equation, with disaster prevention and control measures as the target and disaster-causing structural data as the control variable.

[0104] The third construction unit is used to construct a prediction equation for the effect of prevention and control measures for tunnel water and mud inrush disasters based on the disaster prevention and control measures decision equation, with the disaster prevention and control effect as the target and the disaster prevention and control measures as the control variables.

[0105] Optionally, in one embodiment of the present application, the construction module 303 includes: a fourth construction unit, a setting unit, an updating unit, a judging unit and a generating unit.

[0106] Among them, the fourth construction unit is used to construct the objective function with the prevention and control measures of tunnel water and mud inrush disasters as the optimization target and the prediction equation of the prevention and control measures effect as the constraint function.

[0107] The setting unit is used to set at least one algorithm-related parameter.

[0108] The updating unit is used to initialize the population position and calculate the fitness value of the individuals in the initialized population to update the parameter vector and the position of the individuals in the updated population, recalculate the fitness of the individuals, and compare it with a preset threshold for updating.

[0109] The judgment unit is used to judge whether the operation result meets the termination condition.

[0110] The generation unit is used to end the algorithm when the calculation result meets the termination condition, otherwise continue to iterate the calculation until the optimal gray wolf position is output, the final solution set is obtained, and the prevention and control measures prediction model is output.

[0111] It should be noted that the aforementioned explanation of the embodiment of the intelligent decision-making method for prevention and control measures of water and mud inrush disasters in tunnels is also applicable to the intelligent decision-making device for prevention and control measures of water and mud inrush disasters in tunnels of this embodiment, and will not be repeated here.

[0112] According to the intelligent decision-making device for prevention and control measures of water and mud inrush disasters in tunnels proposed in the embodiment of the present application, a nonlinear mapping relationship model can be established based on the survey and design and multi-source detection data, disaster-causing structural data, disaster prevention and control measures and disaster prevention and control effects of the acquired tunnel water and mud inrush disasters, thereby obtaining a disaster prediction equation, a prevention and control measures decision equation and a prevention and control effect prediction equation for the tunnel water and mud inrush disasters, and training is performed to construct a prevention and control measures prediction model for tunnel water and mud inrush disasters, and use the prevention and control measures prediction model to obtain the prevention and control measures for the current tunnel water and mud inrush disasters. By comprehensively considering multiple factors such as survey and design and multi-source detection data, disaster-causing structural data, disaster prevention and control measures and disaster prevention and control effects, it can more accurately reflect the complexity and uncertainty of tunnel water and mud inrush disasters, thereby timely discovering potential risks, avoiding or reducing the occurrence of disasters, and continuously improving the accuracy and timeliness of early warnings through model training and learning, and taking prevention and control measures in advance. Therefore, the problem in the relevant technologies is solved that due to the complex structure of water and mud bursts causing disasters, different types of water and mud bursts correspond to different prevention and control measures, and it is difficult to timely select the most appropriate and efficient prevention and control measures according to the type of disaster. This leads to huge deficiencies in the selection and effectiveness of prevention and control measures for tunnel water and mud bursts, and it is difficult to provide targeted prevention and control guidance and suggestions for tunnel water and mud bursts.

[0113] The above embodiment describes the model building stage, and the following describes an embodiment of the application stage.

[0114] Figure 4 This is a flow chart of an intelligent decision-making method for prevention and control measures for water and mud inrush disasters in tunnels provided according to another embodiment of the present application.

[0115] like Figure 4 As shown, the intelligent decision-making method for prevention and control measures of water and mud inrush disasters in tunnels is applied in the model application stage, wherein the method includes the following steps:

[0116] In step S401, survey, design and multi-source detection data during tunnel construction are obtained.

[0117] In step S402, the survey and design and multi-source detection data are input into a pre-constructed prediction model of prevention and control measures for water and mud inrush disasters in tunnels to obtain prevention and control measures for water and mud inrush disasters in the current tunnel, wherein the prevention and control measures prediction model is constructed by the survey and design and multi-source detection data of water and mud inrush disasters in tunnels, disaster-causing structural data, disaster prevention and control measures and disaster prevention and control effects.

[0118] It can be understood that the survey, design and multi-source detection data acquired in real time by the embodiments of the present application may include but are not limited to tunnel design data, engineering geological data, hydrogeological data, advanced forecast data, advanced drilling data, field monitoring data, etc., and the present application does not impose specific restrictions.

[0119] It can be understood by those skilled in the art that the embodiments of the present application can input the survey, design and multi-source detection data acquired in real time during the tunnel construction process into a pre-built prediction model of prevention and control measures for tunnel water and mud inrush disasters through wireless devices, thereby obtaining the prevention and control measures for the current tunnel water and mud inrush disasters, wherein the prevention and control measures can be understood as disaster prevention and control measures applicable to the current disaster type, scale, location, nature, form, filling medium, and evolution stage.

[0120] In addition, it should be noted that the prevention and control measures prediction model of the embodiment of the present application can be constructed by the survey and design of water and mud bursts in the tunnel and multi-source detection data, disaster-causing structure data, disaster prevention and control measures and disaster prevention and control effects, and this application does not make specific restrictions.

[0121] According to the intelligent decision-making method for prevention and control measures of water and mud gushing disasters in tunnels proposed in the embodiment of the present application, the survey and design data and multi-source detection data obtained in real time during the tunnel construction process can be input into the pre-constructed prevention and control measures prediction model of water and mud gushing disasters in tunnels, so as to obtain the prevention and control measures of the current water and mud gushing disasters in tunnels. Through the pre-constructed prevention and control measures prediction model, the intelligent prediction of water and mud gushing disasters in tunnels can be realized, potential risks can be discovered in time, and prevention and control measures can be taken in advance to avoid or reduce the occurrence of disasters, thereby improving the safety and reliability of tunnel construction, and providing more advanced disaster prevention and control technologies and management methods. Thus, the problem that the water and mud gushing disaster-causing structure is complex, and the prevention and control measures corresponding to different types of water and mud gushing disasters are also different in the related technology is solved, and it is difficult to select the most appropriate and efficient prevention and control measures in time according to the disaster type, resulting in huge deficiencies in the selection and effectiveness of prevention and control measures for water and mud gushing disasters in tunnels, and it is difficult to provide targeted prevention and control guidance and suggestions for water and mud gushing disasters in tunnels.

[0122] Secondly, with reference to the accompanying drawings, an intelligent decision-making device for prevention and control measures of water and mud inrush disasters in tunnels proposed according to an embodiment of the present application will be described.

[0123] Figure 5 It is a block diagram of an intelligent decision-making device for prevention and control measures of water and mud inrush disasters in tunnels according to another embodiment of the present application.

[0124] like Figure 5 As shown, the intelligent decision-making device 50 for preventing and controlling measures for water and mud inrush disasters in tunnels is applied in the model application stage, wherein the device 50 includes: a second acquisition module 501 and a generation module 502.

[0125] The second acquisition module 501 is used to acquire the survey, design and multi-source detection data during the tunnel construction process.

[0126] Generation module 502 is used to input the survey and design and multi-source detection data into a pre-constructed tunnel water and mud inrush disaster prevention and control measures prediction model to obtain the current tunnel water and mud inrush disaster prevention and control measures, wherein the prevention and control measures prediction model is constructed by the survey and design and multi-source detection data of tunnel water and mud inrush, disaster-causing structure data, disaster prevention and control measures and disaster prevention and control effects.

[0127] It should be noted that the aforementioned explanation of the embodiment of the intelligent decision-making method for prevention and control measures of water and mud inrush disasters in tunnels is also applicable to the intelligent decision-making device for prevention and control measures of water and mud inrush disasters in tunnels of this embodiment, and will not be repeated here.

[0128] According to the intelligent decision-making device for prevention and control measures of water and mud gushing disasters in tunnels proposed in the embodiment of the present application, the survey and design data and multi-source detection data acquired in real time during the tunnel construction process can be input into the pre-constructed prevention and control measures prediction model of water and mud gushing disasters in tunnels, so as to obtain the prevention and control measures of water and mud gushing disasters in tunnels. Through the pre-constructed prevention and control measures prediction model, the intelligent prediction of water and mud gushing disasters in tunnels can be realized, potential risks can be discovered in time, and prevention and control measures can be taken in advance to avoid or reduce the occurrence of disasters, thereby improving the safety and reliability of tunnel construction, and providing more advanced disaster prevention and control technologies and management methods. Thus, the problem that the prevention and control measures corresponding to different types of water and mud gushing disasters are different due to the complex structure of water and mud gushing disasters in related technologies, and it is difficult to select the most appropriate and efficient prevention and control measures in time according to the disaster type, resulting in huge deficiencies in the selection and effectiveness of prevention and control measures for water and mud gushing disasters in tunnels, and it is difficult to provide targeted prevention and control guidance and suggestions for water and mud gushing disasters in tunnels.

[0129] Figure 6 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. The electronic device may include:

[0130] A memory 601 , a processor 602 , and a computer program stored in the memory 601 and executable on the processor 602 .

[0131] When the processor 602 executes the program, the intelligent decision-making method for prevention and control measures of tunnel water and mud inrush disasters provided in the above-mentioned embodiment is implemented.

[0132] Furthermore, the electronic device further comprises:

[0133] The communication interface 603 is used for communication between the memory 601 and the processor 602 .

[0134] The memory 601 is used to store computer programs that can be executed on the processor 602 .

[0135] The memory 601 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0136] If the memory 601, the processor 602 and the communication interface 603 are implemented independently, the communication interface 603, the memory 601 and the processor 602 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0137] Optionally, in a specific implementation, if the memory 601, the processor 602 and the communication interface 603 are integrated on a chip, the memory 601, the processor 602 and the communication interface 603 can communicate with each other through an internal interface.

[0138] The processor 602 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0139] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned intelligent decision-making method for prevention and control measures for water and mud inrush disasters in tunnels.

[0140] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed, implements the above-mentioned intelligent decision-making method for prevention and control measures for tunnel water and mud inrush disasters.

[0141] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0142] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0143] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0144] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0145] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of multiple of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0146] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0147] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0148] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. An intelligent decision-making method for prevention and control measures of water and mud inrush disasters in tunnels, characterized in that: Applied to the model building stage, wherein the method comprises the following steps: Obtain the survey and design of water and mud inrush in tunnels, multi-source detection data, disaster-causing structural data, disaster prevention and control measures, and disaster prevention and control effects to establish a nonlinear mapping relationship model; Obtaining a disaster prediction equation, a prevention and control measure decision equation, and a prevention and control effect prediction equation for tunnel water and mud inrush disasters according to the nonlinear mapping relationship model; The disaster prediction equation, prevention and control measure decision equation and prevention and control effect prediction equation of the tunnel water and mud inrush disaster are trained to construct a prevention and control measure prediction model for the tunnel water and mud inrush disaster, so as to use the prevention and control measure prediction model to obtain the prevention and control measures for the current tunnel water and mud inrush disaster.

2. The method according to claim 1, characterized in that: The establishing of the nonlinear mapping relationship model comprises: Obtaining the influence weights of the survey design and multi-source detection data of the tunnel water and mud inrush disaster, and inputting the survey design and multi-source detection data and their influence weights and the disaster-causing structural data into a first Gaussian process regression model to obtain a disaster prediction model in the nonlinear mapping relationship model; Obtaining the influence weight of the disaster-causing structural data of the tunnel water and mud inrush disaster, and inputting the disaster-causing structural data and its influence weight and the disaster prevention and control measures into a second Gaussian process regression model to obtain a disaster prevention and control measures prediction model in the nonlinear mapping relationship model; The influence weights of the prevention and control measures for the tunnel water and mud inrush disasters are obtained, and the disaster prevention and control measures and their influence weights and the disaster prevention and control effects are input into a third Gaussian process regression model to obtain a disaster prevention and control effect prediction model in the nonlinear mapping relationship model.

3. The method according to claim 1 or 2, characterized in that: The disaster prediction equation, prevention and control measure decision equation and prevention and control effect prediction equation of tunnel water and mud inrush disasters are obtained according to the nonlinear mapping relationship model, including: Based on the disaster prediction model, constructing a disaster prediction equation with the disaster-causing structural data as a target and the survey design and the multi-source detection data as control variables; Based on the disaster prediction equation, a decision equation for prevention and control measures for tunnel water and mud inrush disasters is constructed with the disaster prevention and control measures as the target and the disaster-causing structural data as the control variable; Based on the disaster prevention and control measures decision equation, a prediction equation for the effect of prevention and control measures for tunnel water and mud inrush disasters is constructed with the disaster prevention and control effect as the target and the disaster prevention and control measures as the control variables.

4. The method according to claim 1, characterized in that: The training of the disaster prediction equation, the prevention and control measures decision equation and the prevention and control effect prediction equation of the tunnel water and mud inrush disaster to construct the prevention and control measures prediction model of the tunnel water and mud inrush disaster includes: Taking the prevention and control measures for the tunnel water and mud inrush disaster as the optimization target and the prediction equation for the effect of the prevention and control measures as the constraint function, an objective function is constructed; Set at least one algorithm-related parameter; Initialize the population position and calculate the fitness value of the individuals in the initialized population to update the parameter vector and the position of the individuals in the updated population, recalculate the fitness of the individuals and compare it with the preset threshold for updating; Determine whether the operation result meets the termination condition; If the calculation result meets the termination condition, the algorithm is terminated, otherwise the iterative calculation continues until the optimal gray wolf position is output, the final solution set is obtained, and the prevention and control measures prediction model is output.

5. An intelligent decision-making method for prevention and control measures of water and mud inrush disasters in tunnels, characterized in that: Applied to the model application stage, wherein the method comprises the following steps: Acquire survey, design and multi-source detection data during tunnel construction; The survey and design and multi-source detection data are input into a pre-constructed tunnel water and mud inrush disaster prevention and control measures prediction model to obtain the current tunnel water and mud inrush disaster prevention and control measures, wherein the prevention and control measures prediction model is constructed by the survey and design and multi-source detection data of tunnel water and mud inrush, disaster-causing structure data, disaster prevention and control measures and disaster prevention and control effects.

6. An intelligent decision-making device for prevention and control measures of water and mud inrush disasters in tunnels, characterized in that: Applied to the model building stage, wherein the device comprises: Establish a module to obtain the survey and design of tunnel water and mud inrush and multi-source detection data, disaster-causing structural data, disaster prevention and control measures and disaster prevention and control effects, so as to establish a nonlinear mapping relationship model; A first acquisition module is used to obtain a disaster prediction equation, a prevention and control measure decision equation and a prevention and control effect prediction equation for tunnel water and mud inrush disasters according to the nonlinear mapping relationship model; A construction module is used to train the disaster prediction equation, prevention and control measure decision equation and prevention and control effect prediction equation of the tunnel water and mud inrush disaster, and to construct a prevention and control measure prediction model for the tunnel water and mud inrush disaster, so as to use the prevention and control measure prediction model to obtain the prevention and control measures for the current tunnel water and mud inrush disaster.

7. An intelligent decision-making device for prevention and control measures of water and mud inrush disasters in tunnels, characterized in that: Applied to the model application stage, wherein the device comprises: The second acquisition module is used to obtain the survey and design and multi-source detection data during the tunnel construction process; A generation module is used to input the survey and design and multi-source detection data into a pre-constructed tunnel water and mud inrush disaster prevention and control measures prediction model to obtain the current tunnel water and mud inrush disaster prevention and control measures, wherein the prevention and control measures prediction model is constructed by the survey and design and multi-source detection data of tunnel water and mud inrush, disaster-causing structural data, disaster prevention and control measures and disaster prevention and control effects.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement an intelligent decision-making method for prevention and control measures for water and mud inrush disasters in tunnels as described in any one of claims 1 to 4 or claim 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement an intelligent decision-making method for prevention and control measures for water and mud inrush disasters in tunnels as claimed in any one of claims 1 to 4 or claim 5.

10. A computer program product, characterized in that It includes a computer program which, when executed, is used to implement an intelligent decision-making method for prevention and control measures for water and mud inrush disasters in tunnels as claimed in any one of claims 1 to 4 or claim 5.

Images