Multi-source data fusion tunnel gushing water comprehensive forecasting method and device
By integrating multi-source data and using a Logistic regression model, the problems of single data source and complex weight determination in tunnel water inrush prediction were solved, achieving high-precision and timely tunnel construction risk forecasting and ensuring construction safety and efficiency.
Patent Information
- Application Number
- CN202411459654.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-18
- Publication Date
- 2024-11-22
AI Technical Summary
Existing technologies rely on a single data source for predicting tunnel water inrush, and the determination of risk indicator weights is complex or highly subjective, resulting in low prediction accuracy and difficulty in making predictions quickly and efficiently.
A multi-source data fusion method is adopted to obtain the weights of tunnel water inrush risk assessment indicators by combining subjective and objective data. A logistic regression model is used to establish a prediction model for water inrush risk level and probability, and the actual risk level and probability are output for forecasting.
It improves the accuracy and timeliness of tunnel water inrush prediction, ensures construction safety and stability, and increases construction efficiency.
Smart Images

Figure CN119005705A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of tunnel technology, and in particular to a method and device for comprehensive forecasting of sudden water inrush in tunnels by fusion of multi-source data. Background Art
[0002] When tunnels pass through poor geological formations, they are prone to a variety of geological disasters, among which water inrush in tunnels is a common type, which will cause serious obstacles to construction and cause huge economic losses and casualties. Therefore, in order to ensure the safety of tunnel construction, it is necessary to forecast the level and probability of water inrush in tunnels, and improve construction methods in a timely manner to prevent water inrush accidents.
[0003] In related technologies, a single information source risk assessment model can be established by conducting visual inspections, monitoring measurements, and comprehensive advanced geological forecasts on the tunnel construction site, thereby obtaining the risk assessment values, importance weights, and credibility of each single information source risk assessment model, and then integrating them to obtain the final probability of sudden water risk. It is also possible to construct a multi-factor evaluation standard, determine the weights of the evaluation factors, and then establish an evaluation model to predict sudden water disasters.
[0004] However, in related technologies, the evaluation data source is too single, the determination of the weights of various risk indicators is too complicated or subjective, and the significant influencing factors that lead to sudden water inrush accidents cannot be accurately obtained. The prediction accuracy is low, which makes it difficult to meet the needs of fast and efficient prediction and is in urgent need of improvement. Summary of the invention
[0005] The present application provides a method and device for comprehensive prediction of sudden water inrush in tunnels by fusion of multi-source data, in order to solve the problems in related technologies, such as the evaluation data source is too single, the determination of the weights of various risk indicators is too complicated or subjective, the significant influencing factors leading to sudden water inrush accidents cannot be accurately obtained, the prediction accuracy is low, and it is difficult to meet the needs of fast and efficient prediction.
[0006] The first aspect of the present application provides a multi-source data fusion tunnel water burst comprehensive forecasting method, comprising the following steps: obtaining multiple tunnel water burst risk assessment indicators at a tunnel construction site to obtain an objective weight and a subjective weight of each tunnel water burst risk assessment indicator, so as to perform subjective and objective combined weighting on each tunnel water burst risk assessment indicator to obtain the weight of each tunnel water burst risk assessment indicator; based on the weight of each tunnel water burst risk assessment indicator, using a Logistic regression model to fuse advanced geological forecast information and monitoring measurement data for the tunnel construction site to establish a water burst risk level and risk probability prediction model; using the water burst risk level and risk probability prediction model to output the actual water burst risk level and actual risk probability of the tunnel construction site, so as to make a forecast when any of the actual water burst risk level and the actual risk probability meets a preset forecast condition.
[0007] Optionally, in one embodiment of the present application, it also includes: determining at least one significant influencing factor based on the actual sudden water risk level and the actual risk probability; generating target response measures based on the at least one significant influencing factor, wherein the target response measures may include but are not limited to at least one of grouting reinforcement measures, drainage and decompression measures, and advanced support measures.
[0008] Optionally, in one embodiment of the present application, the multiple tunnel water inrush risk assessment indicators may include but are not limited to at least one of fault fracture zone width, stratum lithology, stratum dip, unfavorable geology, groundwater level, karst development characteristics, construction methods, surrounding rock integrity and seepage water pressure.
[0009] Optionally, in one embodiment of the present application, the expression of the water inrush risk level and risk probability prediction model may be, but is not limited to,: , Among them, n j =P(Y=j)(j=1,2,3,4) is the probability that the hazard assessment belongs to the jth level, x i is the data value of the independent variable factor, including each evaluation index in the risk assessment index system, θ 0 is a constant term, θ i (i=1,2,...,n) is the regression coefficient, w i (i=1,2,...,n) represents the weight value corresponding to the independent variable factor.
[0010] Optionally, in one embodiment of the present application, the independent probability formula of the actual sudden water inrush risk level and the actual risk probability may be expressed as, but not limited to: .
[0011] The second aspect of the present application provides a multi-source data fusion tunnel water burst comprehensive forecasting device, including: an acquisition module, used to acquire multiple tunnel water burst risk assessment indicators at a tunnel construction site, so as to obtain the objective weight and subjective weight of each tunnel water burst risk assessment indicator, so as to perform subjective and objective combined weighting on each tunnel water burst risk assessment indicator, and obtain the weight of each tunnel water burst risk assessment indicator; an establishment module, used to fuse the advanced geological forecast information and monitoring measurement data of the tunnel construction site based on the weight of each tunnel water burst risk assessment indicator using a Logistic regression model, so as to establish a water burst risk level and risk probability prediction model; a forecasting module, used to output the actual water burst risk level and actual risk probability of the tunnel construction site using the water burst risk level and risk probability prediction model, so as to make a forecast when any of the actual water burst risk level and the actual risk probability meets a preset forecasting condition.
[0012] Optionally, in one embodiment of the present application, it also includes: a determination module for determining at least one significant influencing factor based on the actual sudden water risk level and the actual risk probability; a generation module for generating target response measures based on the at least one significant influencing factor, wherein the target response measures may include but are not limited to at least one of grouting reinforcement measures, drainage and decompression measures, and advanced support measures.
[0013] Optionally, in one embodiment of the present application, the multiple tunnel water inrush risk assessment indicators may include but are not limited to at least one of fault fracture zone width, stratum lithology, stratum dip, unfavorable geology, groundwater level, karst development characteristics, construction methods, surrounding rock integrity and seepage water pressure.
[0014] Optionally, in one embodiment of the present application, the expression of the water inrush risk level and risk probability prediction model may be, but is not limited to,: , Among them, n j =P(Y=j)(j=1,2,3,4) is the probability that the hazard assessment belongs to the jth level, x i is the data value of the independent variable factor, including each evaluation index in the risk assessment index system, θ 0 is a constant term, θ i (i=1,2,...,n) is the regression coefficient, w i (i=1,2,...,n) represents the weight value corresponding to the independent variable factor.
[0015] Optionally, in one embodiment of the present application, the independent probability formula of the actual sudden water inrush risk level and the actual risk probability may be expressed as, but not limited to: .
[0016] The third 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 multi-source data fusion tunnel water inrush comprehensive forecasting method as described in the above embodiment.
[0017] The fourth 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 multi-source data fusion tunnel sudden water inrush comprehensive forecasting method.
[0018] The fifth aspect of the present application provides a computer program product, including a computer program, which, when executed, implements the above-mentioned multi-source data fusion tunnel sudden water inrush comprehensive forecasting method.
[0019] The embodiment of the present application can obtain the weight of each tunnel water inrush risk assessment index through subjective and objective combined weighting, and establish a water inrush risk level and risk probability prediction model based on the Logistic regression model to obtain the actual water inrush risk level and actual risk probability of the tunnel construction site, and then make a forecast when any of the actual water inrush risk level and actual risk probability meets certain forecasting conditions. The information source is more comprehensive, and the accuracy and timeliness of tunnel water inrush prediction are improved through subjective and objective combined weighting. By predicting the actual water inrush risk level and actual risk probability, timely forecasting is carried out to ensure the safety and stability of construction, improve the efficiency of tunnel construction, and have wide applicability. Thus, the problems in the related art that the evaluation data source is too single, the determination of the weights of each risk indicator is too complicated or subjective, the significant influencing factors that lead to the occurrence of water inrush accidents cannot be accurately obtained, the prediction accuracy is low, and it is difficult to meet the needs of fast and efficient prediction are solved.
[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: Figure 1 A flowchart of a method for comprehensive prediction of tunnel water inrush by fusion of multi-source data provided according to an embodiment of the present application; Figure 2A flowchart of obtaining subjective weights according to an embodiment of the present application; Figure 3 A flowchart of the working principle of a comprehensive forecasting method for tunnel water inrush with multi-source data fusion provided according to an embodiment of the present application; Figure 4 It is a block diagram of a multi-source data fusion tunnel water inrush comprehensive forecasting device provided according to an embodiment of the present application; Figure 5 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION
[0022] 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.
[0023] The following describes the multi-source data fusion tunnel water inrush comprehensive forecasting method and device of the embodiment of the present application with reference to the accompanying drawings. Aiming at the problem that the evaluation data source mentioned in the above background technology is too single, the determination of the weight of each risk index is too complicated or subjective, the significant influencing factors leading to the occurrence of water inrush accidents cannot be accurately obtained, the prediction accuracy is low, and it is difficult to meet the needs of fast and efficient prediction, the present application provides a multi-source data fusion tunnel water inrush comprehensive forecasting method, in which the weight of each tunnel water inrush risk assessment index can be obtained by subjective and objective combination weighting, and a water inrush risk level and risk probability prediction model based on the Logistic regression model is established to obtain the actual water inrush risk level and actual risk probability of the tunnel construction site, and then forecast when any of the actual water inrush risk level and actual risk probability meets certain forecasting conditions, the information source is more comprehensive, the accuracy and timeliness of tunnel water inrush prediction are improved by subjective and objective combination weighting, and the actual water inrush risk level and actual risk probability are predicted in time to ensure the safety and stability of construction, improve the efficiency of tunnel construction, and have wide applicability. As a result, problems in related technologies such as the evaluation data source being too single, the determination of the weights of various risk indicators being too complex or subjective, the inability to accurately obtain the significant influencing factors leading to sudden water inrush accidents, low prediction accuracy, and difficulty in meeting the needs of fast and efficient prediction are solved.
[0024] Specifically, Figure 1 The present invention is a flowchart of a method for comprehensive prediction of sudden water inrush in tunnels by fusion of multi-source data provided in accordance with an embodiment of the present application.
[0025] like Figure 1As shown, the multi-source data fusion tunnel water inrush comprehensive forecasting method includes the following steps: In step S101, multiple tunnel water burst risk assessment indicators at the tunnel construction site are obtained to obtain the objective weight and subjective weight of each tunnel water burst risk assessment indicator, so as to perform subjective and objective combined weighting on each tunnel water burst risk assessment indicator to obtain the weight of each tunnel water burst risk assessment indicator.
[0026] In some embodiments, the embodiments of the present application can obtain multiple tunnel water burst risk assessment indicators at the tunnel construction site by reading literature, and then use frequency statistics weighting and hierarchical analysis method to obtain the objective weight and subjective weight of each tunnel water burst risk assessment indicator respectively, and take the average value to achieve subjective and objective combined weighting, thereby obtaining the weight of each tunnel water burst risk assessment indicator.
[0027] In some embodiments, the embodiments of the present application can obtain multiple tunnel water burst risk assessment indicators at the tunnel construction site by collecting case information, and then use frequency statistics weighting and hierarchical analysis method to obtain the objective weight and subjective weight of each tunnel water burst risk assessment indicator respectively, and take the average value to achieve subjective and objective combined weighting, thereby obtaining the weight of each tunnel water burst risk assessment indicator.
[0028] Among them, the method of obtaining multiple tunnel sudden water inrush risk assessment indicators at the tunnel construction site can be set by technical personnel in this field according to actual conditions, and this application does not impose specific restrictions.
[0029] Further, in the embodiment of the present application, the process of obtaining objective weights by weighting through frequency statistics method may be: , , in, is the weight vector, For the The weight of the risk assessment indicator is The frequency of sudden water inrush cases.
[0030] Further, in the embodiment of the present application, the process of obtaining subjective weights through hierarchical analysis is as follows: Figure 2 As shown, it can be: Step S201: Establish a hierarchical structure of a multi-objective evaluation index system.
[0031] It can be understood that the embodiment of the present application can divide tunnel water surge into three levels: target level, factor level and indicator level.
[0032] The target layer may include but is not limited to tunnel water inrush, etc., and this application does not impose any specific limitation.
[0033] The factor layer may include, but is not limited to, geological structural factors, monitoring and measurement factors, hydrogeological factors, etc., and this application does not impose any specific limitations.
[0034] The indicator layer may include but is not limited to formation lithology, formation occurrence, adverse geology, groundwater level, fault fracture zone width, karst development characteristics, construction method, surrounding rock integrity, seepage water pressure, etc. This application does not impose specific restrictions.
[0035] Step S202: Establish an importance evaluation matrix according to the importance order of factors.
[0036] It can be understood that the embodiment of the present application can establish an importance evaluation matrix according to the importance order of the factors. ,in, This may include but is not limited to: , Matrix of embodiments of this application Obviously satisfied The conditions, consistency matrix satisfy And meet Among them, .
[0037] Step S203: Approximation of the importance evaluation matrix to the consistency matrix and calculation of the approximate matrix.
[0038] It can be understood that the importance evaluation matrix of the embodiment of the present application is The consistency matrix Approximate and calculate the approximate matrix .in, It can be expressed as: , And satisfy: , In other words, the embodiments of the present application satisfy .
[0039] Approximate matrix of the embodiment of the present application The calculation process can be: First, the embodiment of the present application can transform the importance evaluation matrix Each row vector of is normalized, thus obtaining an approximate matrix . Among them, the matrix The normalization of each row vector can be expressed as: , Then, the embodiment of the present application will Medium Element Query by column ,in, It can be expressed as: , Furthermore, the embodiment of the present application further Normalized, we get: , Thus, the embodiment of the present application can obtain an approximate value of the feature vector, which can be expressed as: , Finally, the embodiment of the present application can calculate the maximum characteristic root, where the approximate value of the maximum characteristic root can be expressed as: , That is to say, the weight values of the n aspects of the embodiment of the present application may be in the following order: , , ..., .
[0040] Step S204: consistency check of the approximate matrix.
[0041] It can be understood that the embodiment of the present application can approximate the matrix Perform consistency check.
[0042] When the approximate matrix A* is a consistent matrix A, we have: , When the approximate matrix A* is not a consistent matrix A, we have: , , in, C·I is one Consistency test judgment index, used to measure the consistency of the approximate matrix A*; is the largest eigenvalue of the approximate matrix A*, are other eigenvalues of the approximate matrix A*.
[0043] Further, in the embodiment of the present application, if C.I ≤0.1, the subjective judgment matrix The consistency is acceptable.
[0044] , in, C.R. is the random consistency ratio, R·I The correction value of the calibration consistency check is determined by the dimension of A*.
[0045] Further, in the embodiment of the present application, if C.R. <0.1, then the matrix is considered to be approximate With satisfactory consistency.
[0046] In the embodiment of the present application, each factor under each aspect can be regarded as having equal weight, and the weight of each indicator can be obtained, which can be expressed as: , Furthermore, the embodiment of the present application can take the average of the objective weight and the subjective weight to obtain the weight of each tunnel water inrush risk assessment index, namely: .
[0047] Optionally, in one embodiment of the present application, multiple tunnel water inrush risk assessment indicators may include but are not limited to at least one of fault fracture zone width, stratum lithology, stratum dip, unfavorable geology, groundwater level, karst development characteristics, construction methods, surrounding rock integrity and seepage water pressure.
[0048] It will be understood by those skilled in the art that the embodiments of the present application can determine multiple tunnel water inrush risk assessment indicators based on data obtained through advanced geological forecasting and monitoring measurements at the tunnel construction site, which may include but are not limited to fault fracture zone width, stratum lithology, stratum occurrence, adverse geology, groundwater level, karst development characteristics, construction methods, surrounding rock integrity and seepage water pressure, etc., and the present application does not impose specific limitations.
[0049] Furthermore, in some embodiments, the embodiments of the present application may select multiple tunnel water inrush risk assessment indicators, such as fault fracture zone width, stratum lithology, stratum occurrence, adverse geology, groundwater level, karst development characteristics, construction methods, etc., and the present application does not impose specific limitations.
[0050] In some other embodiments, the embodiments of the present application may select all tunnel water inrush risk assessment index factors, which may be specifically set by technicians in this field according to actual conditions, and the present application does not impose any specific restrictions.
[0051] In step S102, based on the weight of each tunnel water inrush risk assessment index, a Logistic regression model is used to fuse the advanced geological forecast information and monitoring measurement data of the tunnel construction site to establish a water inrush risk level and risk probability prediction model.
[0052] In the actual implementation process, the embodiment of the present application can use a Logistic regression model to integrate the advanced geological forecast and monitoring measurement data of the tunnel construction site based on the weight of each tunnel sudden water risk assessment index, and then establish a sudden water risk level and risk probability prediction model. This is of great significance for avoiding the single information source and low prediction accuracy of the tunnel sudden water prediction model.
[0053] In some embodiments, the embodiments of the present application can use each tunnel sudden water inrush risk assessment index as the dependent variable to perform regression analysis of an effective logistic regression model, conduct advanced geological forecasting and monitoring measurements on the tunnel construction site, obtain relevant data respectively, and then establish a sudden water inrush risk level and risk probability prediction model to obtain the sudden water inrush risk level and risk probability.
[0054] For example, the embodiments of the present application can use the stratum lithology, stratum dip, adverse geology, groundwater level, fault fracture zone width, karst development characteristics, construction method, surrounding rock integrity, and seepage water pressure in the tunnel sudden water inrush risk assessment index factors as independent variables, and obtain relevant data through advanced geological forecasting and monitoring measurement, and use the sudden water inrush risk level as the dependent variable. Among them, the dependent variable of the embodiments of the present application can be divided into 4 levels from low to high in terms of the strength of sudden water inrush (assigned as Y=1, Y=2, Y=3 and Y=4 respectively).
[0055] Furthermore, the embodiment of the present application can construct a training set of a sudden water surge risk level and risk probability prediction model by analyzing case data, and divide the training set into a training set and a test set by a random sampling method. Among them, the embodiment of the present application can use 70% of the data in the data set as a training set and 30% of the data as a test set. The sudden water surge risk level and risk probability prediction model established using the Logistic regression model can derive model parameters from the training set, and bring the test set into it to evaluate the effectiveness of the established model.
[0056] Optionally, in one embodiment of the present application, the expression of the water inrush risk level and risk probability prediction model may be, but is not limited to,: , Among them, n j =P(Y=j)(j=1,2,3,4) is the probability that the hazard assessment belongs to the jth level, x i is the data value of the independent variable factor, including each evaluation index in the risk assessment index system, θ 0 is a constant term, θ i (i=1,2,...,n) is the regression coefficient, w i (i=1,2,...,n) represents the weight value corresponding to the independent variable factor.
[0057] In some embodiments, the present application embodiment can use the Logistic regression model to obtain: , Among them, n j=P(Y=j)(j=1,2,3,4) is the probability that the hazard assessment belongs to the jth level, x i is the data value of the independent variable factor, including each evaluation index in the risk assessment index system, θ 0 is a constant term, θ i (i=1,2,...,n) is the regression coefficient, which is usually obtained through multiple iterations and has high accuracy. i (i=1,2,...,n) represents the weight value corresponding to the independent variable factor.
[0058] Furthermore, in the embodiment of the present application, the Pearson coefficient can be selected for goodness of fit test, wherein if the significance level is greater than 0.05, it indicates no statistical significance, that is, the model fits well, otherwise the fit is poor.
[0059] Furthermore, in the embodiment of the present application, the value of P is [0,1], P=n i (i=1,2,3,4) can correspond to the probability values of four levels of sudden water risk: low, medium, high and extremely high.
[0060] In step S103, the water inrush risk level and risk probability prediction model is used to output the actual water inrush risk level and actual risk probability of the tunnel construction site, so as to make a forecast when either the actual water inrush risk level or the actual risk probability meets the preset forecasting conditions.
[0061] In some embodiments, the embodiments of the present application can utilize a sudden water surge risk level and risk probability prediction model to output the actual sudden water surge risk level and actual risk probability of a tunnel construction site, and make a forecast when the actual sudden water surge risk level and actual risk probability meet certain forecasting conditions.
[0062] In some embodiments, the embodiments of the present application can utilize a water surge risk level and risk probability prediction model to output the actual water surge risk level and actual risk probability of a tunnel construction site, and make a forecast when the actual water surge risk level meets certain forecast conditions.
[0063] In some embodiments, the embodiments of the present application can utilize a water inrush risk level and risk probability prediction model to output the actual water inrush risk level and actual risk probability of a tunnel construction site, and make a forecast when the actual risk probability meets certain forecast conditions.
[0064] Among them, certain forecast conditions can be set by technicians in this field according to actual conditions, and this application does not make specific restrictions.
[0065] Optionally, in one embodiment of the present application, the independent probability formula of the actual sudden water inrush risk level and the actual risk probability may be expressed as, but not limited to: .
[0066] As a possible implementation method, the embodiment of the present application can analyze the sudden water risk level and risk probability prediction model established by the Logistic regression model to obtain the independent probability formula of the actual sudden water risk level and the actual risk probability, and then determine the significant influencing factors under the sudden water risk level of a certain tunnel, wherein the expression of the independent probability formula of the actual sudden water risk level and the actual risk probability can be but is not limited to: , Among them, j=1,2,3,4.
[0067] Further, in the embodiment of the present application, if the indicator corresponds to θ i >0, p>0.05, it means that there is no significant impact on the evaluation of tunnel water inrush hazard; if θ i <0, p<0.05, it indicates a significant negative impact on the evaluation of tunnel water inrush hazard; if θ i >0, p<0.05, which indicates a significant positive impact on the evaluation of tunnel water inrush hazard.
[0068] Optionally, in one embodiment of the present application, it also includes: determining at least one significant influencing factor based on the actual sudden water risk level and the actual risk probability; generating target response measures based on at least one significant influencing factor, wherein the target response measures may include but are not limited to at least one of grouting reinforcement measures, drainage and decompression measures, and advanced support measures.
[0069] In some embodiments, the embodiments of the present application can determine at least one significant influencing factor based on the actual sudden water risk level and the actual risk probability, and feed back the significant influencing factor to the construction personnel, and then the construction personnel can generate target response measures based on at least one significant influencing factor, such as grouting reinforcement measures.
[0070] In some embodiments, the embodiments of the present application can generate target response measures based on at least one significant influencing factor, such as drainage and pressure relief measures and advanced support measures.
[0071] Among them, specific target response measures can be set by technical personnel in this field according to actual conditions, and this application does not impose any specific restrictions.
[0072] The working principle of the multi-source data fusion tunnel water inrush comprehensive forecasting method proposed in the embodiment of the present application is introduced in detail below in conjunction with a specific embodiment.
[0073] in, Figure 3 The present invention is a flowchart of the working principle of a comprehensive forecasting method for tunnel water inrush using multi-source data fusion according to an embodiment of the present application.
[0074] Step S301: Performing advanced geological prediction and monitoring measurement on the tunnel construction site. That is, the embodiment of the present application can obtain data by performing advanced geological prediction and monitoring measurement on the tunnel construction site.
[0075] Step S302: Obtain multiple tunnel water inrush risk assessment indicators at the tunnel construction site. That is, the embodiment of the present application can determine multiple tunnel water inrush risk assessment indicators based on the data obtained in step S301, which may include but are not limited to the width of the fault fracture zone, stratum lithology, stratum occurrence, adverse geology, groundwater level, karst development characteristics, construction methods, surrounding rock integrity and seepage water pressure, etc., and the present application does not make specific restrictions.
[0076] Step S303: subjective and objective combined weighting. That is, the embodiment of the present application can use the frequency statistics method weighting and the hierarchical analysis method according to the multiple tunnel sudden water risk assessment indicators obtained in step S302 to obtain the objective weight and subjective weight of each tunnel sudden water risk assessment indicator, and take the average value to achieve subjective and objective combined weighting, thereby obtaining the weight of each tunnel sudden water risk assessment indicator.
[0077] Step S304: Use the Logistic regression model to establish a water inrush risk level and risk probability prediction model. That is to say, the embodiment of the present application can use the formation lithology, formation occurrence, adverse geology, groundwater level, fault fracture zone width, karst development characteristics, construction method, surrounding rock integrity, and seepage water pressure in the tunnel water inrush risk assessment index factors as independent variables, and obtain relevant data through advanced geological prediction and monitoring measurement, and use the water inrush risk level as the dependent variable, wherein the dependent variable of the embodiment of the present application can be divided into 4 levels from low to high in terms of the strength of causing water inrush (assigned as Y=1, Y=2, Y=3 and Y=4, respectively).
[0078] Furthermore, the embodiment of the present application can construct a training set of a sudden water surge risk level and risk probability prediction model by analyzing case data, and divide the training set into a training set and a test set by a random sampling method. Among them, the embodiment of the present application can use 70% of the data in the data set as a training set and 30% of the data as a test set. The sudden water surge risk level and risk probability prediction model established using the Logistic regression model can derive model parameters from the training set, and bring the test set into it to evaluate the effectiveness of the established model.
[0079] Step S305: Output the actual risk level and actual risk probability of sudden water inrush at the tunnel construction site. That is, the embodiment of the present application can use the sudden water inrush risk level and risk probability prediction model in step S304 to output the actual sudden water inrush risk level and actual risk probability of the tunnel construction site. Step S306: Determine at least one significant influencing factor. That is, the embodiment of the present application can determine significant influencing factors under a certain tunnel water inrush risk level according to an independent probability formula of the actual water inrush risk level and the actual risk probability.
[0080] Step S307: Generate target response measures. That is, the embodiment of the present application can feed back significant influencing factors to construction personnel, and then the construction personnel can generate target response measures based on at least one significant influencing factor, which may include but are not limited to grouting reinforcement measures, drainage and decompression measures, and advanced support measures, etc., and the present application does not make specific restrictions.
[0081] According to the multi-source data fusion tunnel water inrush comprehensive forecasting method proposed in the embodiment of the present application, the weight of each tunnel water inrush risk assessment index can be obtained by subjective and objective combined weighting, and a water inrush risk level and risk probability prediction model based on the Logistic regression model is established to obtain the actual water inrush risk level and actual risk probability of the tunnel construction site, and then forecast when any of the actual water inrush risk level and actual risk probability meets certain forecasting conditions, the information source is more comprehensive, and the accuracy and timeliness of tunnel water inrush prediction are improved by subjective and objective combined weighting. By predicting the actual water inrush risk level and actual risk probability, timely forecasting is carried out to ensure the safety and stability of construction, improve the efficiency of tunnel construction, and have wide applicability. Thus, the problems in the related art that the evaluation data source is too single, the determination of the weights of each risk indicator is too complicated or subjective, the significant influencing factors leading to the occurrence of water inrush accidents cannot be accurately obtained, the prediction accuracy is low, and it is difficult to meet the needs of fast and efficient prediction are solved.
[0082] Next, a multi-source data fusion tunnel water inrush comprehensive forecasting device proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.
[0083] Figure 4 It is a block diagram of a multi-source data fusion tunnel water inrush comprehensive forecasting device provided according to an embodiment of the present application.
[0084] like Figure 4 As shown, the multi-source data fusion tunnel water inrush comprehensive forecasting device 10 includes: an acquisition module 100, an establishment module 200 and a forecasting module 300.
[0085] Among them, the acquisition module 100 is used to obtain multiple tunnel water burst risk assessment indicators at the tunnel construction site to obtain the objective weight and subjective weight of each tunnel water burst risk assessment indicator, so as to perform subjective and objective combined weighting on each tunnel water burst risk assessment indicator to obtain the weight of each tunnel water burst risk assessment indicator.
[0086] Module 200 is established to integrate the advanced geological prediction information and monitoring measurement data of the tunnel construction site based on the weight of each tunnel sudden water inrush risk assessment index using a Logistic regression model to establish a sudden water inrush risk level and risk probability prediction model.
[0087] The forecast module 300 is used to output the actual water inrush risk level and actual risk probability of the tunnel construction site using the water inrush risk level and risk probability prediction model, so as to make a forecast when either the actual water inrush risk level or the actual risk probability meets the preset forecasting conditions.
[0088] Optionally, in one embodiment of the present application, it also includes: a determination module and a generation module.
[0089] Among them, the determination module is used to determine at least one significant influencing factor based on the actual sudden water risk level and the actual risk probability.
[0090] A generation module is used to generate target response measures based on at least one significant influencing factor, wherein the target response measures may include but are not limited to at least one of grouting reinforcement measures, drainage and pressure relief measures, and advanced support measures.
[0091] Optionally, in one embodiment of the present application, multiple tunnel water inrush risk assessment indicators may include but are not limited to at least one of fault fracture zone width, stratum lithology, stratum dip, unfavorable geology, groundwater level, karst development characteristics, construction methods, surrounding rock integrity and seepage water pressure.
[0092] Optionally, in one embodiment of the present application, the expression of the water inrush risk level and risk probability prediction model may be, but is not limited to,: , Among them, n j=P(Y=j)(j=1,2,3,4) is the probability that the hazard assessment belongs to the jth level, x i is the data value of the independent variable factor, including each evaluation index in the risk assessment index system, θ 0 is a constant term, θ i (i=1,2,...,n) is the regression coefficient, w i (i=1,2,...,n) represents the weight value corresponding to the independent variable factor.
[0093] Optionally, in one embodiment of the present application, the independent probability formula of the actual sudden water inrush risk level and the actual risk probability may be expressed as, but not limited to: .
[0094] It should be noted that the above explanation of the embodiment of the method for comprehensive forecasting of sudden water inrush in a tunnel using multi-source data fusion is also applicable to the device for comprehensive forecasting of sudden water inrush in a tunnel using multi-source data fusion in this embodiment, and will not be repeated here.
[0095] According to the multi-source data fusion tunnel water inrush comprehensive forecasting device proposed in the embodiment of the present application, the weight of each tunnel water inrush risk assessment index can be obtained by subjective and objective combined weighting, and a water inrush risk level and risk probability prediction model based on the Logistic regression model is established to obtain the actual water inrush risk level and actual risk probability of the tunnel construction site, and then forecast when any of the actual water inrush risk level and actual risk probability meets certain forecasting conditions, the information source is more comprehensive, and the accuracy and timeliness of tunnel water inrush prediction are improved by subjective and objective combined weighting. By predicting the actual water inrush risk level and actual risk probability, timely forecasting is carried out to ensure the safety and stability of construction, improve the efficiency of tunnel construction, and have wide applicability. Thus, the problems in the related art that the evaluation data source is too single, the determination of the weights of each risk indicator is too complicated or subjective, the significant influencing factors leading to the occurrence of water inrush accidents cannot be accurately obtained, the prediction accuracy is low, and it is difficult to meet the needs of fast and efficient prediction are solved.
[0096] Figure 5 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: A memory 501 , a processor 502 , and a computer program stored in the memory 501 and executable on the processor 502 .
[0097] When the processor 502 executes the program, the multi-source data fusion tunnel water inrush comprehensive forecasting method provided in the above embodiment is implemented.
[0098] Furthermore, the electronic device further comprises: The communication interface 503 is used for communication between the memory 501 and the processor 502 .
[0099] The memory 501 is used to store computer programs that can be executed on the processor 502 .
[0100] The memory 501 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.
[0101] If the memory 501, the processor 502 and the communication interface 503 are implemented independently, the communication interface 503, the memory 501 and the processor 502 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 5 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.
[0102] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.
[0103] The processor 502 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.
[0104] 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 multi-source data fusion tunnel water inrush comprehensive forecasting method.
[0105] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed, implements the above-mentioned multi-source data fusion tunnel sudden water inrush comprehensive forecasting method.
[0106] 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.
[0107] 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.
[0108] 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.
[0109] 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 purposes 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 (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or N wirings (electronic device), 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), an optical fiber 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.
[0110] 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.
[0111] 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.
[0112] 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.
[0113] 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. A comprehensive forecasting method for tunnel water inrush based on multi-source data fusion. It is characterized in that The following steps are involved: Acquire multiple tunnel water inrush risk assessment indicators at the tunnel construction site to obtain the objective weight and subjective weight of each tunnel water inrush risk assessment indicator, and perform subjective and objective combined weighting on each tunnel water inrush risk assessment indicator to obtain the weight value of each tunnel water inrush risk assessment indicator; Based on the weight of each tunnel water inrush risk assessment index, a Logistic regression model is used to fuse the advanced geological forecast information and monitoring measurement data of the tunnel construction site to establish a water inrush risk level and risk probability prediction model; The water inrush risk level and risk probability prediction model is used to output the actual water inrush risk level and actual risk probability of the tunnel construction site, so as to make a forecast when either the actual water inrush risk level or the actual risk probability meets a preset forecast condition.
2. The multi-source data fusion tunnel water inrush comprehensive forecasting method according to claim 1, It is characterized in that Also includes: Determine at least one significant influencing factor according to the actual sudden water inrush risk level and the actual risk probability; A target response measure is generated based on the at least one significant influencing factor, wherein the target response measure includes at least one of a grouting reinforcement measure, a drainage and pressure relief measure, and an advanced support measure.
3. The method for comprehensive prediction of tunnel water inrush by multi-source data fusion according to claim 1, It is characterized in that The multiple tunnel water inrush risk assessment indicators include at least one of fault fracture zone width, stratum lithology, stratum occurrence, adverse geology, groundwater level, karst development characteristics, construction methods, surrounding rock integrity and seepage water pressure.
4. The method for comprehensive prediction of tunnel water inrush by multi-source data fusion according to claim 1, It is characterized in that The expression of the water inrush risk level and risk probability prediction model is: , Among them, n j =P(Y=j)(j=1,2,3,4) is the probability that the hazard assessment belongs to the jth level, x i is the data value of the independent variable factor, including each evaluation index in the risk assessment index system, θ 0 is a constant term, θ i (i=1,2,...,n) is the regression coefficient, w i (i=1,2,...,n) represents the weight value corresponding to the independent variable factor.
5. The method for comprehensive prediction of tunnel water inrush by multi-source data fusion according to claim 1, It is characterized in that The independent probability formula of the actual sudden water risk level and the actual risk probability is expressed as: 。 6. A multi-source data fusion tunnel water inrush comprehensive forecasting device, It is characterized in that include: An acquisition module is used to acquire multiple tunnel water inrush risk assessment indicators at a tunnel construction site to obtain an objective weight and a subjective weight of each tunnel water inrush risk assessment indicator, so as to perform subjective and objective combined weighting on each tunnel water inrush risk assessment indicator to obtain a weight value of each tunnel water inrush risk assessment indicator; Establishing a module for fusing the advanced geological prediction information and monitoring measurement data of the tunnel construction site based on the weight of each tunnel water inrush risk assessment index, using a Logistic regression model, so as to establish a water inrush risk level and risk probability prediction model; A forecasting module is used to output the actual water surge risk level and actual risk probability of the tunnel construction site using the water surge risk level and risk probability prediction model, so as to make a forecast when either the actual water surge risk level or the actual risk probability meets a preset forecasting condition.
7. The multi-source data fusion tunnel water inrush comprehensive forecasting device according to claim 6, It is characterized in that Also includes: A determination module, configured to determine at least one significant influencing factor according to the actual water inrush risk level and the actual risk probability; A generation module is used to generate target response measures based on the at least one significant influencing factor, wherein the target response measures include at least one of grouting reinforcement measures, drainage and pressure relief measures, and advanced support measures.
8. An electronic device, It is 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 the multi-source data fusion tunnel water inrush comprehensive forecasting method as described in any one of claims 1 to 5.
9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that The program is executed by a processor to implement the multi-source data fusion tunnel water inrush comprehensive forecasting method as described in any one of claims 1 to 5.
10. A computer program product, It is characterized in that It comprises a computer program, which, when executed, is used to implement the comprehensive prediction method for sudden water inrush in a tunnel by fusion of multi-source data as described in any one of claims 1 to 5.
Citation Information
Patent Citations
Evaluation method of geological disaster risk attribute interval of tunnel and underground construction
CN104133985A
Karst tunnel water outburst and mud outburst overall process gradual dynamic risk assessment method
CN104636612A
Tunnel construction water burst risk assessment method based on multi-source information fusion
CN115423210A
Method and system for predicting water inrush disaster risk during multi-stage tunnel crossing of difficult stratum
CN117726182A
Risk assessment method of water inrush in tunnels constructed in water-rich grounds
US20240135069A1
Cited By
Water burst and mud burst prediction method based on comprehensive advanced geological forecast fault fracture zone
CN119270384A
Probability model construction method and system for tunnel engineering geological risk discrimination
CN122332710A
A probability model construction method and system for tunnel engineering geological risk discrimination
CN122332710B
