Tunnel construction geological disaster monitoring and early warning method and system

Abstract

The invention relates to a tunnel construction geological disaster monitoring and early warning method and system, and the method comprises the steps: constructing a three-dimensional geological model: constructing the three-dimensional geological model for revealing spatial information based on geological survey and advanced forecast data; real-time monitoring of multivariate information: monitoring and obtaining the multivariate information in real time through various sensors installed on a tunnel construction site, and converting the multivariate information into time sequence data; wherein the multivariate information comprises stress, displacement, apparent resistivity and microseismic event number; spatio-temporal information fusion: fusing the spatial information disclosed by the three-dimensional geologic model with a time sequence; disaster monitoring and early warning: monitoring occurrence and development of disasters in real time according to a result of time-space information fusion, and sending out an early warning signal in time.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel construction geological disaster monitoring and early warning, and in particular to a tunnel construction geological disaster monitoring and early warning method and system. Background Art

[0002] The occurrence of geological disasters during tunnel construction can cause damage to the tunnel structure, damage to mechanical facilities, and casualties among operators, which can seriously affect the progress of the project and increase construction costs. In order to reduce the impact of geological disasters during construction, effective disaster monitoring and early warning must be carried out.

[0003] In engineering applications, the "Technical Code for Safety Monitoring of Sichuan-Tibet Railway Tunnel Construction" (TB 10315-2021), the "Technical Code for Monitoring and Measurement of Railway Tunnels" (Q / CR 9218-2015) and the "Technical Code for Risk Management of Railway Tunnel Engineering" (Q / CR9247-2016) regulate the safety monitoring and risk management of tunnels with sudden water and mud, high ground temperature and harmful gases. However, traditional monitoring and early warning methods often find it difficult to fully and accurately capture the temporal and spatial characteristics of disasters, resulting in unsatisfactory early warning effects.

[0004] Therefore, there is an urgent need to provide a tunnel construction geological disaster monitoring and early warning method and system to improve the accuracy and timeliness of tunnel construction geological disaster monitoring and early warning. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a tunnel construction geological disaster monitoring and early warning method and system that comprehensively utilizes a three-dimensional geological model constructed based on geological survey and advance prediction and a time series obtained based on real-time monitoring of multi-information to perform spatiotemporal information fusion.

[0006] To solve the above problems, the technical solution adopted by the present invention is:

[0007] In a first aspect, a tunnel construction geological disaster monitoring and early warning method is provided, the method comprising:

[0008] 3D geological model construction: Based on geological survey and advance forecast data, a 3D geological model is constructed to reveal spatial information;

[0009] Real-time monitoring of multivariate information: Various sensors installed at the tunnel construction site are used to monitor and obtain multivariate information in real time and convert it into time series data; the multivariate information includes stress, displacement, apparent resistivity and the number of microseismic events;

[0010] Space-time information fusion: integrating the spatial information revealed by the three-dimensional geological model with the time series;

[0011] Disaster monitoring and early warning: Based on the results of spatiotemporal information fusion, real-time monitoring of the occurrence and development of disasters is carried out, and early warning signals are issued in a timely manner.

[0012] As an implementation method of the present invention, geological survey provides macroscopic engineering geology and hydrogeology conditions along the tunnel; advanced forecasting uses geological survey, geophysical prospecting, drilling, and navigation methods to obtain detailed engineering geology and hydrogeology conditions in key sections of the tunnel;

[0013] The three-dimensional geological model is constructed in the following manner:

[0014] Step S101, establishing an initial three-dimensional geotechnical model according to the real spatial coordinate data of the tunnel;

[0015] Step S102, inputting geological attribute data into an external database and grouping them according to numbers, wherein the geological attribute data includes: numbers, macroscopic engineering geology and hydrogeology conditions along the tunnel;

[0016] Step S103, connecting the initial three-dimensional geotechnical model and the external database through the numbering to generate the three-dimensional geological model; the three-dimensional geological model is used to reveal the type, scale, and spatial location information of geological hazards in tunnel construction.

[0017] As an implementation mode of the present invention, the multivariate information is converted into time series data in the following manner:

[0018] Step S201, obtaining multiple groups of time series information according to all the multivariate information, wherein each group of the time series information is obtained by obtaining any one type of information through real-time monitoring;

[0019] Step S202: for any set of time series information, a denoising method based on multivariate normal distribution is used to remove outliers;

[0020] Step S203: Obtain the time series data according to each group of time series information after removing outliers.

[0021] As an implementation of the present invention, step S202 includes:

[0022] (1) For any set of time series information, the Mahalanobis distance from each data in the time series information to the center of the dual ring segment is calculated using the following formula:

[0023]

[0024] Among them, y i is a data in the double ring segment X, is the center of Y, S is the covariance matrix of Y;

[0025] (2) Use the following formula to determine normal values ​​and abnormal values ​​based on the D value, and eliminate abnormal values:

[0026]

[0027] Among them, P 90 The percentile that is the boundary between normal and abnormal values.

[0028] As an implementation mode of the present invention, the spatiotemporal information fusion step includes:

[0029] Step S301: a plurality of scoring intervals are obtained according to different disaster safety levels. For each scoring interval, an initial cloud model parameter corresponding to the scoring interval is input into a plurality of cloud droplets (x, μ(x)) in a forward generator, and these cloud droplets are combined to obtain a standard cloud model, thereby obtaining a plurality of standard cloud models, each of which corresponds to one scoring interval.

[0030] Step S302: for the jth monitoring point, obtain its disaster safety level during the construction of the tunnel numbered i to obtain a time data sequence, and then use a reverse cloud generator to obtain time cloud model parameters based on the time data sequence and the standard cloud model;

[0031] Step S303: According to the cloud model parameters and the macroscopic engineering geological and hydrogeological conditions along the tunnel corresponding to any number, the space-time cloud parameters corresponding to the number are obtained, so as to obtain the target cloud model.

[0032] As an implementation mode of the present invention, the disaster monitoring and early warning includes:

[0033] Step S401, obtaining the disaster safety level corresponding to each number, and selecting alarm signals of different urgency based on different disaster safety levels;

[0034] For any number, the disaster safety level of the number is determined by comparing the target cloud model corresponding to the number with all standard cloud models.

[0035] As an implementation mode of the present invention, in step S301, for any scoring interval, the following formula is used to obtain the initial cloud model parameters Ex, En and He corresponding to the scoring interval:

[0036]

[0037] He takes a constant;

[0038] Wherein, S1 is the minimum value in the scoring interval, S2 is the maximum value in the scoring interval, and the constant range is [0.01, 0.1];

[0039] The standard cloud model is obtained using the following formula:

[0040]

[0041] Among them, the random parameter En′ obeys the normal distribution, the expected value is Ex, the standard deviation is He, and μ(x) represents the degree of membership.

[0042] As an implementation mode of the present invention, in step S302, the time data sequence X j ={x1,x2,…,x L}, where L represents the total number of numbers;

[0043] The time cloud model parameters are expressed by the following formula:

[0044]

[0045] As an implementation of the present invention, in step S303, the space-time cloud parameter is obtained by the following formula:

[0046]

[0047]

[0048] In a second aspect, a tunnel construction geological disaster monitoring and early warning system is provided, the system comprising:

[0049] A three-dimensional geological model construction model is used to construct a three-dimensional geological model for revealing spatial information based on geological survey and advance forecast data;

[0050] The multivariate information real-time monitoring model is used to obtain multivariate information through real-time monitoring of various sensors installed at the tunnel construction site, and convert the multivariate information into time series data; the multivariate information includes stress, displacement, apparent resistivity and number of microseismic events;

[0051] A spatiotemporal information fusion module, which is used to fuse the spatial information revealed by the three-dimensional geological model with the time series;

[0052] The disaster monitoring and early warning module is used to monitor the occurrence and development of disasters in real time based on the results of spatiotemporal information fusion, and issue early warning signals in a timely manner.

[0053] The beneficial effects of adopting the above technical solution are:

[0054] The tunnel construction geological disaster monitoring and early warning method and system provided by the present invention comprehensively utilizes the three-dimensional geological model constructed based on geological survey and advance prediction and the time series obtained based on real-time monitoring of multi-information to fuse time and space information, and has the following advantages:

[0055] 1. The present invention organically integrates the spatial information of the three-dimensional geological model with the time series of real-time monitoring of multivariate information, which can more comprehensively and accurately reflect the spatiotemporal evolution characteristics of disasters and improve the accuracy of monitoring and early warning.

[0056] 2. The present invention comprehensively utilizes multi-source data such as geological survey, advance forecast, and real-time monitoring of multiple information, giving full play to the advantages of each data and providing richer and more accurate information support for disaster monitoring and early warning.

[0057] 3. The present invention can automatically identify the patterns and characteristics of disasters, realize intelligent early warning, and improve the timeliness and reliability of early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a schematic diagram of a tunnel construction geological disaster monitoring and early warning method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention is clearly and completely described below in conjunction with specific embodiments.

[0060] Example 1

[0061] An embodiment of the present invention provides a tunnel construction geological disaster monitoring and early warning method, the method comprising:

[0062] Step 1: Construction of 3D geological model: Based on geological survey and advance forecast data, a 3D geological model is constructed to reveal spatial information;

[0063] Among them, geological survey provides macroscopic engineering geology and hydrogeology conditions along the tunnel; advanced forecast uses geological survey, geophysical prospecting, drilling, and navigation methods to obtain detailed engineering geology and hydrogeology conditions in key sections of the tunnel;

[0064] The three-dimensional geological model is constructed in the following manner:

[0065] Step S101, establishing an initial three-dimensional geotechnical model according to the real spatial coordinate data of the tunnel;

[0066] Step S102, inputting geological attribute data into an external database and grouping them according to numbers, wherein the geological attribute data includes: numbers, macroscopic engineering geology and hydrogeology conditions along the tunnel;

[0067] Step S103, connecting the initial three-dimensional geotechnical model and the external database through the numbering to generate the three-dimensional geological model; the three-dimensional geological model is used to reveal the type, scale, and spatial location information of geological hazards in tunnel construction.

[0068] Step 2: Real-time monitoring of multivariate information: Various sensors installed at the tunnel construction site are used to obtain multivariate information in real time and convert the multivariate information into time series data.

[0069] The multivariate information includes stress, displacement, apparent resistivity and number of microseismic events.

[0070] In this step, the multivariate information is converted into time series data in the following way:

[0071] Step S201, obtaining multiple groups of time series information according to all the multivariate information, wherein each group of the time series information is obtained by obtaining any one type of information through real-time monitoring;

[0072] Step S202: for any set of time series information, a denoising method based on multivariate normal distribution is used to remove outliers;

[0073] This step specifically includes:

[0074] (1) For any set of time series information, the Mahalanobis distance from each data in the time series information to the center of the dual ring segment is calculated using the following formula:

[0075]

[0076] Among them, y i is a data in the double ring segment X, is the center of Y, S is the covariance matrix of Y;

[0077] In the present invention, the time series Y = {y1, y2, ..., y t-1}, where y k ∈R m It represents the measured value at time k, m represents the variable dimension, and all the data in the time series information are divided into periodicities with double ring segments, and the data in the time series information are aligned.

[0078] All the data in the time series information can be described as Y z = {Y (z-1)×T+1 ,Y (z-1)×T+2 ,…,Y z×T}, where z is the number of cycles and T is the number of sequence data in the double ring segment.

[0079] (2) Use the following formula to determine normal values ​​and abnormal values ​​based on the D value, and eliminate abnormal values:

[0080]

[0081] Among them, P 90 The percentile that is the boundary between normal and abnormal values.

[0082] Step S203: Obtain the time series data according to each group of time series information after removing outliers.

[0083] Step 3: Fusion of spatiotemporal information: Fusion of the spatial information revealed by the three-dimensional geological model with the time series.

[0084] This step includes:

[0085] Step S301: a plurality of scoring intervals are obtained according to different disaster safety levels. For each scoring interval, an initial cloud model parameter corresponding to the scoring interval is input into a plurality of cloud droplets (x, μ(x)) in a forward generator, and these cloud droplets are combined to obtain a standard cloud model, thereby obtaining a plurality of standard cloud models, each of which corresponds to one scoring interval.

[0086] Among them, the disaster safety level can be divided according to needs, and the total number of levels can be set to 3 levels, or 4 levels, 5 levels, etc. The present invention is not limited to this. Exemplarily, 5 levels are set.

[0087] For any scoring interval, the following formula is used to obtain the initial cloud model parameters Ex, En and He corresponding to the scoring interval:

[0088]

[0089] He takes a constant;

[0090] Wherein, S1 is the minimum value in the scoring interval, S2 is the maximum value in the scoring interval, and the constant range is [0.01, 0.1];

[0091] The standard cloud model is obtained using the following formula:

[0092]

[0093] Among them, the random parameter En′ obeys the normal distribution, the expected value is Ex, the standard deviation is He, and μ(x) represents the degree of membership.

[0094] Step S302: for the jth monitoring point, obtain its disaster safety level during the construction of the tunnel numbered i to obtain a time data sequence, and then use a reverse cloud generator to obtain time cloud model parameters based on the time data sequence and the standard cloud model;

[0095] Among them, the time data series Xj ={x1,x2,…,x L}, where L represents the total number of numbers;

[0096] The time cloud model parameters are expressed by the following formula:

[0097]

[0098]

[0099] Step S303: According to the cloud model parameters and the macroscopic engineering geological and hydrogeological conditions along the tunnel corresponding to any number, the space-time cloud parameters corresponding to the number are obtained, so as to obtain the target cloud model.

[0100] Specifically, the space-time cloud parameters are obtained using the following formula:

[0101]

[0102] Step 4: Disaster monitoring and early warning: Based on the results of spatiotemporal information fusion, real-time monitoring of the occurrence and development of disasters is carried out, and early warning signals are issued in a timely manner.

[0103] This step includes:

[0104] Step S401, obtaining the disaster safety level corresponding to each number, and selecting alarm signals of different urgency based on different disaster safety levels;

[0105] For any number, the disaster safety level of the number is determined by comparing the target cloud model corresponding to the number with all standard cloud models.

[0106] For example, it can be set that when the disaster safety level is level 1, the alarm signal is the most urgent; or when the total level is level 5, it can be set that when the disaster safety level is level 5, the alarm signal is the most urgent. The degree of urgency can be determined by the volume of the alarm signal or the signal frequency, which is not specifically limited in the present invention.

[0107] In addition, early warning information will be promptly released to construction workers, management personnel and other relevant personnel through text messages, emails, etc. to ensure that they can take prompt response measures.

[0108] The tunnel construction geological disaster monitoring and early warning method provided by the present invention comprehensively utilizes the three-dimensional geological model constructed based on geological survey and advance prediction and the time series obtained based on real-time monitoring of multivariate information to perform spatiotemporal information fusion, and has the following advantages:

[0109] 1. The present invention organically integrates the spatial information of the three-dimensional geological model with the time series of real-time monitoring of multivariate information, which can more comprehensively and accurately reflect the spatiotemporal evolution characteristics of disasters and improve the accuracy of monitoring and early warning.

[0110] 2. The present invention comprehensively utilizes multi-source data such as geological survey, advance forecast, and real-time monitoring of multiple information, giving full play to the advantages of each data and providing richer and more accurate information support for disaster monitoring and early warning.

[0111] 3. The present invention can automatically identify the patterns and characteristics of disasters, realize intelligent early warning, and improve the timeliness and reliability of early warning.

[0112] 4. The present invention can intuitively present the type, scale, spatial location and other information of geological disasters in tunnel construction through the visualization of three-dimensional geological models, which is convenient for users to understand and analyze.

[0113] Example 2

[0114] The embodiment of the present invention provides a tunnel construction geological disaster monitoring and early warning system, which includes:

[0115] A three-dimensional geological model construction model is used to construct a three-dimensional geological model for revealing spatial information based on geological survey and advance forecast data;

[0116] The multivariate information real-time monitoring model is used to obtain multivariate information through real-time monitoring of various sensors installed at the tunnel construction site, and convert the multivariate information into time series data; the multivariate information includes stress, displacement, apparent resistivity and number of microseismic events;

[0117] A spatiotemporal information fusion module, which is used to fuse the spatial information revealed by the three-dimensional geological model with the time series;

[0118] The disaster monitoring and early warning module is used to monitor the occurrence and development of disasters in real time based on the results of spatiotemporal information fusion, and issue early warning signals in a timely manner.

[0119] The tunnel construction geological disaster monitoring and early warning system provided by the present invention comprehensively utilizes the three-dimensional geological model constructed based on geological survey and advance prediction and the time series obtained based on real-time monitoring of multi-information to fuse time and space information, and has the following advantages:

[0120] 1. The present invention organically integrates the spatial information of the three-dimensional geological model with the time series of real-time monitoring of multivariate information, which can more comprehensively and accurately reflect the spatiotemporal evolution characteristics of disasters and improve the accuracy of monitoring and early warning.

[0121] 2. The present invention comprehensively utilizes multi-source data such as geological survey, advance forecast, and real-time monitoring of multiple information, giving full play to the advantages of each data and providing richer and more accurate information support for disaster monitoring and early warning.

[0122] 3. The present invention can automatically identify the patterns and characteristics of disasters, realize intelligent early warning, and improve the timeliness and reliability of early warning.

[0123] 4. The present invention can intuitively present the type, scale, spatial location and other information of geological disasters in tunnel construction through the visualization of three-dimensional geological models, which is convenient for users to understand and analyze.

[0124] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art may still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A tunnel construction geological disaster monitoring and early warning method, characterized in that: The method comprises: 3D geological model construction: Based on geological survey and advance forecast data, a 3D geological model is constructed to reveal spatial information; Real-time monitoring of multivariate information: Various sensors installed at the tunnel construction site are used to monitor and obtain multivariate information in real time and convert it into time series data; the multivariate information includes stress, displacement, apparent resistivity and the number of microseismic events; Space-time information fusion: integrating the spatial information revealed by the three-dimensional geological model with the time series; Disaster monitoring and early warning: Based on the results of spatiotemporal information fusion, real-time monitoring of the occurrence and development of disasters is carried out, and early warning signals are issued in a timely manner.

2. A tunnel construction geological disaster monitoring and early warning method according to claim 1, characterized in that: Geological survey provides macroscopic engineering geology and hydrogeology conditions along the tunnel; advanced forecast uses geological survey, geophysical prospecting, drilling and navigation methods to obtain detailed engineering geology and hydrogeology conditions in key sections of the tunnel; The three-dimensional geological model is constructed in the following manner: Step S101, establishing an initial three-dimensional geotechnical model according to the real spatial coordinate data of the tunnel; Step S102, inputting geological attribute data into an external database and grouping them according to numbers, wherein the geological attribute data includes: numbers, macroscopic engineering geology and hydrogeology conditions along the tunnel; Step S103, connecting the initial three-dimensional geotechnical model and the external database through the numbering to generate the three-dimensional geological model; the three-dimensional geological model is used to reveal the type, scale, and spatial location information of geological hazards in tunnel construction.

3. A tunnel construction geological disaster monitoring and early warning method according to claim 1, characterized in that: The multivariate information is converted into time series data in the following way: Step S201, obtaining multiple groups of time series information according to all the multivariate information, wherein each group of the time series information is obtained by obtaining any one type of information through real-time monitoring; Step S202: for any set of time series information, a denoising method based on multivariate normal distribution is used to remove outliers; Step S203: Obtain the time series data according to each group of time series information after removing outliers.

4. A tunnel construction geological disaster monitoring and early warning method according to claim 3, characterized in that: Step S202 includes: (1) For any set of time series information, the Mahalanobis distance from each data in the time series information to the center of the dual ring segment is calculated using the following formula: Among them, y i is a data in the double ring segment X, is the center of Y, S is the covariance matrix of Y; (2) Use the following formula to determine normal values ​​and abnormal values ​​based on the D value, and eliminate abnormal values: Among them, P 90 The percentile that is the boundary between normal and abnormal values.

5. A tunnel construction geological disaster monitoring and early warning method according to claim 1, characterized in that: The spatiotemporal information fusion step comprises: Step S301: a plurality of scoring intervals are obtained according to different disaster safety levels. For each scoring interval, an initial cloud model parameter corresponding to the scoring interval is input into a plurality of cloud droplets (x, μ(x)) in a forward generator, and these cloud droplets are combined to obtain a standard cloud model, thereby obtaining a plurality of standard cloud models, each of which corresponds to one scoring interval. Step S302: for the jth monitoring point, obtain its disaster safety level during the construction of the tunnel numbered i to obtain a time data sequence, and then use a reverse cloud generator to obtain time cloud model parameters based on the time data sequence and the standard cloud model; Step S303: According to the cloud model parameters and the macroscopic engineering geological and hydrogeological conditions along the tunnel corresponding to any number, the space-time cloud parameters corresponding to the number are obtained, so as to obtain the target cloud model.

6. A tunnel construction geological disaster monitoring and early warning method according to claim 5, characterized in that: The disaster monitoring and early warning includes: Step S401, obtaining the disaster safety level corresponding to each number, and selecting alarm signals of different urgency based on different disaster safety levels; For any number, the disaster safety level of the number is determined by comparing the target cloud model corresponding to the number with all standard cloud models.

7. A tunnel construction geological disaster monitoring and early warning method according to claim 5, characterized in that: In step S301, for any scoring interval, the following formula is used to obtain the initial cloud model parameters Ex, En and He corresponding to the scoring interval: He takes a constant; Wherein, S1 is the minimum value in the scoring interval, S2 is the maximum value in the scoring interval, and the constant range is [0.01, 0.1]; The standard cloud model is obtained using the following formula: Among them, the random parameter En′ obeys the normal distribution, the expected value is Ex, the standard deviation is He, and μ(x) represents the degree of membership.

8. A tunnel construction geological disaster monitoring and early warning method according to claim 7, characterized in that: In step S302, the time data series X j ={x1,x2,…,x L }, where L represents the total number of numbers; The time cloud model parameters are expressed by the following formula:

9. A tunnel construction geological disaster monitoring and early warning method according to claim 8, characterized in that: In step S303, the space-time cloud parameters are obtained using the following formula:

10. A tunnel construction geological disaster monitoring and early warning system, characterized in that: The system comprises: A three-dimensional geological model construction model is used to construct a three-dimensional geological model for revealing spatial information based on geological survey and advance forecast data; The multivariate information real-time monitoring model is used to obtain multivariate information through real-time monitoring of various sensors installed at the tunnel construction site, and convert the multivariate information into time series data; the multivariate information includes stress, displacement, apparent resistivity and number of microseismic events; A spatiotemporal information fusion module, which is used to fuse the spatial information revealed by the three-dimensional geological model with the time series; The disaster monitoring and early warning module is used to monitor the occurrence and development of disasters in real time based on the results of spatiotemporal information fusion, and issue early warning signals in a timely manner.

Images