An intelligent early warning method and system for tunnel geological disaster risk with self-learning ability

Abstract

The present invention relates to an intelligent early warning method and system for tunnel geological disaster risks with self-learning capabilities, the method comprising: defining the risk index of various geological disasters as the four arithmetic operations of the corresponding advanced detection / monitoring index value and the correction term, so as to achieve the coupling of the empirical method and the detection / monitoring method. The detection / monitoring index value is derived from the advanced detection or monitoring method adopted in the specific project, and the correction term depends on the geological conditions that affect the specific type of geological disaster, and is derived from the geological interpretation of the advanced detection / monitoring. The initial value of the correction term is derived from empirical judgment, and is calculated during the tunnel construction process based on the degree of agreement between the actual situation revealed afterwards and the pre-prediction result, so that the correction coefficient value can be continuously learned and updated according to the actual situation during the tunnel cyclic excavation process, thereby improving the reliability of the early warning result.

Description

Technical Field

[0001] The present invention relates to the field of rock mass engineering, and in particular to an intelligent early warning method and system for tunnel geological disaster risks with self-learning capability. Background Art

[0002] A tunnel is an underground project with a linear layout, including tunnels in the water conservancy and hydropower industry, and vertical shafts, inclined shafts and tunnels in the mining industry. Due to the constraints of technical means and economic factors, it is difficult to reliably predict the potential risk of geological disasters in different parts before the construction of a tunnel project. The uncertainty of the risk of geological disasters in front of the face is the most prominent safety hazard in the excavation process of tunnel projects, especially deep-buried long tunnel projects. In serious cases, it directly affects the success or failure of the project. For this reason, many tunnel construction processes carry out advanced detection work, mainly using geophysical exploration technology to obtain detection index values ​​within a certain range in front of the face, in order to predict the potential geological disaster risks in front of the face based on the distribution and changes of the detection index values. For example, resistivity values ​​are often used to predict water inrush risks. Microseismic monitoring technology is widely used to predict rock burst risks. This technology uses the surrounding rock rupture events that have occurred (accepting the dynamic waves when the rupture occurs) to predict the potential maximum scale rupture risk, which is essentially the application of geophysical exploration methods. All these technologies have the problem of non-uniqueness / uncertainty of solution, that is, when using advanced detection indicators or microseismic monitoring values ​​to predict future risks, there is a practical problem that reliability is difficult to guarantee. Although the existing technology has made some improvements to the above problems, such as the patent with publication number CN 118013744 A, a tunnel advance prediction correction method based on excavation verification constraints is proposed: the lithology of the tunnel excavation face is used as prior information to constrain and correct the results of the advance detection, and the lithology of the tunnel excavation face is used as constraint information, and then a secondary inversion operation is performed according to the initial physical parameter model, constraint conditions and observation data to obtain the corrected advanced detection results; however, this method relies on high-frequency advanced geological prediction and model inversion, which is inefficient for engineering progress. Often, the next cycle of excavation has not yet been released, and this method is a supplementary optimization of the geophysical inversion method for advanced geological prediction. In essence, it is still an application of the geophysical method, and there is still the problem of non-uniqueness / uncertainty of the inversion results.In response to this problem, data-driven artificial intelligence technologies such as deep learning are increasingly being used in tunnel engineering, attempting to improve the reliability of prediction results by learning the risks of geological disasters that have already occurred. The patent with publication number CN109086935A proposes a regional geological disaster trend prediction method: by sorting and analyzing the historical data of geological disasters in the country in recent years, summarizing the laws of geological disasters, including the overall development trend of geological disasters, main disaster types, key occurrence time, spatial distribution and time-space evolution laws, it is estimated that the number of geological disasters in the next prediction period, the main types and key occurrence time periods; the patent with publication number CN116976185A A's patent proposes a geological disaster big data early warning and assessment system based on the Internet of Things cloud platform: using machine learning algorithms to train algorithm models, taking real-time monitoring data from sensors and radar networks as input, outputting the probability and impact of geological disasters, and then comparing and inverting the numerical simulation results obtained by traditional numerical simulation methods with the output results of the machine learning algorithm to ensure the fault tolerance of the system model; the above two methods are essentially data-driven artificial intelligence deep learning technologies, which are seriously affected by the number and quality of sample data of geological disasters that have occurred. The number of geological disasters accumulated in engineering practice may not be enough to train a reliable prediction model; in addition, the differences in the causal mechanisms and control conditions of the same type of geological disasters between different projects, that is, data quality issues, also directly affect the reliability of the prediction model. Because of this, the application of data-driven artificial intelligence technology in the field of rock engineering, including geological disaster early warning, is still in the early stages of exploration, and the acceptance of engineering practice is not high.

[0003] Before the widespread application of detection / monitoring technology, the prediction and early warning of geological disaster risks in engineering construction mainly relied on empirical methods, with the core being geological conditions and geological disaster phenomena that have already occurred and are relatively weak (i.e., precursors). This is because almost all types of geological disasters are closely related to certain specific geological conditions, such as water inrush must occur in permeable rock formations and are often closely related to water-conducting structures, rock burst compressive structures, and surrounding rock quality control; when geological conditions have the ability to conceive disasters and low-level geological disaster phenomena begin to appear during tunnel excavation, it means that the geological disaster risk in the current tunnel excavation process is increasing, which is the main basis for empirical methods. Empirical methods have the advantage of being closely linked to specific conditions and disaster-causing mechanisms, but their reliability is highly dependent on the relevant experience of on-site personnel, and their quantitative degree is insufficient, making them difficult to promote and apply. In fact, many advance detection or monitoring technologies not only obtain the distribution of certain index values ​​in the surrounding rock in front of the face, but also reveal the corresponding geological conditions. For example, most advance detections can reveal the occurrence characteristics of geological structures through the distribution of abnormal values, and microseismic monitoring can also interpret the occurrence of dominant fractures. They are important bases for empirical methods of geological disaster prediction. However, due to the low degree of professional integration and other realistic conditions, modern technical means have not been well used to achieve comprehensive geological disaster warnings that integrate multi-professional information. In the past 10 years, digital technology in rock engineering has made great progress. It can not only use three-dimensional digital models and data to describe on-site geological conditions and related characteristic index values, but also realize the integration of multi-professional data and methods and realize intelligent engineering applications, laying a technical foundation for solving long-standing problems in the past.

[0004] In view of this, the present invention proposes a tunnel geological disaster intelligent early warning method with self-learning ability in accordance with the principle of knowledge-driven artificial intelligence technology. The artificial intelligence is based on the digital twin model of tunnel engineering and is implemented in a "functionalized" way by computer coding to realize the problems existing in the promotion and application of geological disaster early warning experience methods, and to make up for the deficiencies such as multi-solution and uncertainty of advanced detection / monitoring early warning, so as to improve the reliability and intelligence level of tunnel geological disaster risk early warning.

[0005] The methods described in this section are not necessarily methods that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any method described in this section is considered to be prior art simply because it is included in this section. Similarly, unless otherwise indicated, the issues mentioned in this section should not be considered to have been recognized in any prior art. Summary of the invention

[0006] In view of the technical problems existing in the prior art, the present invention provides a tunnel geological disaster risk intelligent early warning method and system with self-learning ability. In view of the uncertainty problem of geological disaster risk prediction results in front of the heading face during tunnel / cavern and mine shaft excavation, a method based on geological experience judgment combined with advanced detection / monitoring is adopted, wherein the geological experience judgment is set as a correction item in the prediction method, and the reliability of the geological disaster prediction results is improved by learning the difference between the prediction results and the actual situation.

[0007] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides a tunnel geological disaster risk intelligent early warning method with self-learning capability, comprising: S1, based on the advanced detection and monitoring data obtained in the current operation cycle and using the detection / monitoring index criterion, obtain the predicted value of the geological disaster risk index; the predicted value of the geological disaster risk index is used to describe the degree of geological disaster risk that may occur in front of the tunnel face; S2, obtaining the geological conditions ahead of the tunnel face according to the current advanced detection / monitoring data interpretation, determining the value of the initial geological condition correction coefficient according to the geological conditions through the built-in empirical method and correcting the geological risk index prediction value of step S1; S3, according to the difference between the actual geological disaster degree index value after excavation and the predicted geological disaster risk index value, adjust the geological condition correction coefficient value and correct the predicted geological disaster risk index value until the difference between the two is minimized, and obtain the adjusted and updated geological condition correction coefficient value; S4, in the next operation cycle, repeat step S1 to obtain the predicted value of the geological disaster risk index, and use the geological condition correction coefficient value updated in step S3 as the risk index correction coefficient value obtained by interpreting the geological conditions in step S2, update the predicted value of the geological disaster risk index, and then automatically warn according to the built-in warning level and threshold standard; S5, repeating steps S1 to S4, obtaining the geological condition correction coefficient value of a new operation cycle, continuously using the actual on-site conditions to realize the self-learning process of the geological condition correction coefficient, and improving the reliability of the prediction of geological disaster risk indicators.

[0008] Furthermore, the predicted value of the geological disaster risk index is the result of four arithmetic operations of the predicted value of the advanced detection / monitoring index and the correction term of the geological conditions; the predicted value of the detection / monitoring index is derived from the advanced detection or monitoring method used in the specific project and the corresponding analysis results; the correction term depends on the geological conditions that affect the specific type of geological disaster, and the dynamic value of the correction term is realized by describing the quantitative characteristic indicators and using self-learning. The relative relationship between the value of the correction term and the size of the predicted value of the advanced detection / monitoring reflects the weight of the two methods, thereby integrating and being compatible with the traditional empirical method and the advanced detection / monitoring method of geological disaster prediction and warning.

[0009] The geological conditions described by the correction items include geological structure, lithology and surrounding rock quality. The occurrence of geological structure reflects the geomechanical causes and the disaster-proneness of some types of geological disasters. It is one of the characteristic indicators for describing geological structure. It is obtained through the interpretation of technologies such as advance detection and microseismic monitoring, and the interpretation method is revised after excavation according to the degree of difference from the actual situation, reflecting the learning ability of the geological condition interpretation link. The lithology is inferred through geological cataloging behind the face and combined with previous geological survey results. The quality of surrounding rock is obtained through geological cataloging and geological interpretation, or a combination of the two.

[0010] The value of the correction item describes the degree of influence of the characteristic index value of geological conditions on the risk of geological disasters, and is closely related to the specific type of geological disasters and control factors; its initial value is set through experience, and it is automatically corrected during the construction process based on the principle of minimizing the difference between the predicted value and the actual value, thereby realizing self-learning of the correction item value during the tunnel excavation process.

[0011] This method is divided into two parts during use: intelligent early warning and self-learning. The intelligent early warning is to predict the risk level of geological disasters in front of the tunnel face at the current position of the tunnel face corresponding to a certain period of time during the tunnel excavation process, using advanced detection or monitoring indicators, and interpreting or speculating geological conditions to obtain the correction item value results and the corrected prediction value of the risk level of geological disasters, which are used as the only input value of the geological disaster early warning and realize intelligent early warning according to the set early warning threshold. Self-learning occurs after the current tunnel face is excavated, and the geological condition interpretation method is corrected according to the difference between the actual geological conditions revealed and the prediction results, and the correction item value method is automatically optimized according to the difference between the actual geological conditions and the prediction results.

[0012] All data and information required for the application of the present invention are collected and managed in accordance with the requirements of digital "mapping" of rock engineering objects. Specifically, they are presented in two forms: a three-dimensional digital geometric model that maps the contours of the tunnel and surrounding rock, and characteristic values ​​attached to the geometric objects. This meets the requirements for quantitative input data when using digital twin technology to "program" the geological empirical method for disaster prediction.

[0013] Furthermore, the types of geological disasters include harmful gases, high ground temperature, water gushing, mud burst, collapse, undesirable deformation and rock burst. In a specific project, each type of geological disaster is associated with one or more detection / monitoring technologies, and the detection / monitoring value is used to predict the risk level of the geological disaster. The advanced detection or monitoring indicators are determined by the detection and monitoring methods used in the specific project and are dynamic. The predicted values ​​of the detection / monitoring indicators are derived from the advanced detection or monitoring methods used in the specific project and the corresponding analysis results, which are the same as the methods currently used; For specific projects, the controlling geological conditions for each type of geological disaster may be different, which is reflected in the value of the specific geological correction items.

[0014] The geological conditions are described by characteristic values ​​related to geological disasters and are obtained through geological interpretation of advance detection / monitoring or geological cataloging and inference.

[0015] Furthermore, the geological structure includes three characteristic indicators: folds, faults and joints, which are important influencing factors of almost all types of geological disasters. They often play a role through geomechanical causes (compression, tension, etc.) and are described by characteristic indicators reflecting geomechanical causes. Among them, folds mainly include anticlines or synclines, corresponding to tensional and compression causes respectively. For a given project, the occurrence of faults and dominant joints reflects the geomechanical causes. Faults also include width and filling type, and dominant joints also include joint surface state. Lithology includes water permeability and rock strength, which describe the disaster-prone capacity and risk level of geological disasters of lithology; The quality of surrounding rock is described by RMR, GSI, Q, T, and BQ indicators, which affect the risk of mechanically related geological disasters, including adverse deformation of surrounding rock and rock burst.

[0016] Furthermore, before the current tunnel face is excavated, the geological conditions and characteristic index values ​​in front of the tunnel face are obtained by using geological interpretation of advanced detection / monitoring data or construction geological cataloging combined with speculation of previous results, providing the necessary basic data for the value of geological condition correction items; when conditions permit, the actual exposed geological conditions are compared after excavation to correct the geological interpretation method.

[0017] When the advanced detection indicators reveal the existence of a geological structure surface / belt in front of the tunnel face, the occurrence and width of the geological structure are interpreted based on the abnormal values; and compared with the actual situation after excavation, the relevant judgment criteria of the interpretation process are corrected for subsequent geological structure interpretation; When conducting microseismic monitoring, interpret the occurrence of the rupture surface corresponding to each event, count the occurrence of each dominant group of rupture surfaces, compare with the previous geological survey results to obtain the geomechanical causes of the dominant rupture surfaces, and obtain the input indicators required for geological condition correction; The lithology in front of the tunnel face and its corresponding characteristic index values ​​are determined through geological cataloging of the tunnel face area and combined with previous geological survey results; The quality index values ​​of the surrounding rock in front of the tunnel face (RMR, BQ, etc.) are determined through the geological cataloging of the tunnel face area and combined with the previous geological survey results. When the detection method used on site can obtain detection indicators (such as longitudinal wave velocity) that reflect the integrity of the surrounding rock in front of the tunnel face, the detection indicators are used for correction.

[0018] Furthermore, the value of the geological condition correction item is determined according to the type of geological disaster and its influencing factors. Before the construction of a specific project, an initial value is set based on geological survey results and experience. During the tunnel excavation process, the correction item value is automatically calculated based on the difference between the actual geological disaster and the predicted result and the principle of minimum difference. It is used for geological disaster warning in the next operation cycle, and the actual situation on site is used in a self-learning manner to correct the prediction deviation and improve the reliability of the warning result.

[0019] Furthermore, the correction item values ​​based on geological structures refer to the geomechanical causes of geological structures and related disaster mechanisms. For example, the risk of water inrush in tensile structures is high, so the correction item value is large, while the risk of rock burst is low, so the correction item value is small. When applied to specific projects, the initial value is set artificially based on the results of previous geological surveys, and the construction process is continuously revised based on the comparison between the actual situation and the predicted results and the latest difference principle. The correction item value based on lithology refers to the internal rules between lithology and disaster-prone conditions, such as high risk of harmful gases in coal seams, low risk of water inrush, low risk of rock burst and high risk of deformation determined by poor impermeability of clay rocks, etc. According to the internal rules, the default correction value is set, so as to intelligently obtain the corresponding correction item value according to the lithology analysis results in front of the tunnel face; Based on the influence of surrounding rock quality on geological disasters affected by mechanical processes, such as large deformation, collapse, rock burst, etc., the surrounding rock quality index values ​​are converted into corresponding input parameter values, such as the uniaxial compressive strength of surrounding rock and HB strength parameters, through the requirements of corresponding criteria for input parameters.

[0020] In the second aspect, the present invention provides a tunnel geological disaster risk intelligent early warning system with self-learning ability, including a tunnel engineering digital twin model, which provides all the data required for intelligent early warning of various geological disasters, specifically in the form of a three-dimensional digital geometric model that "maps" the contour morphology of the rock mass engineering and eigenvalues ​​attached to the geometric object: The three-dimensional digital geometric model includes geological model, design model, construction contour model, and detection / monitoring point layout model; The characteristic values ​​attached to the geological model include the types of geological objects (surface, strata, fractures, joints, groundwater, etc.) and the characteristic values ​​of each type of object; The characteristic values ​​attached to the design model include the buried depth along the axis, rock mass density, lateral pressure coefficient, rock strength, input index of rock mass strength, and the distribution of the predicted results of various geological disasters along the tunnel axis; The detection / monitoring indicators attached to the detection / detection points depend on the detection and monitoring methods adopted in the specific project, and their data values ​​change dynamically.

[0021] In a third aspect, the present invention provides an electronic device, comprising: Memory for storing computer software programs; The processor is used to read and execute the computer software program, thereby realizing an intelligent early warning method for tunnel geological disaster risks with self-learning ability as described in the first aspect of the present invention.

[0022] In a fourth aspect, the present invention provides a non-transitory computer-readable storage medium, in which a computer software program is stored. When the computer software program is executed by a processor, it implements an intelligent early warning method for tunnel geological disaster risks with self-learning ability as described in the first aspect of the present invention.

[0023] The beneficial effects of the present invention are as follows: the present invention utilizes the system's built-in geological disaster prediction method based on advance detection / monitoring values ​​and supports corrections based on geological conditions, automatically calculates correction items in the geological disaster risk prediction method based on the difference between the prior prediction results and the actual situation afterwards, and uses the knowledge-driven artificial intelligence principle to realize the quantitative application of traditional empirical methods, make up for the shortcomings of the advance detection / monitoring and early warning methods, and improve the reliability of geological disaster prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic flow chart of an intelligent early warning method for tunnel geological disaster risk with self-learning capability provided by an embodiment of the present invention; Figure 2 A diagram showing the interpretation of fault occurrence based on advance detection data using spatial data interpolation technology; Figure 3 A flowchart of a geological disaster early warning process combining an empirical method with advanced detection / monitoring provided in an embodiment of the present invention; Figure 4 A schematic diagram of the self-learning value taking principle of the geological correction item provided in an embodiment of the present invention; Figure 5 The browser-side functional components of the software system including the method of the present invention; Figure 6 A functional diagram of the software for obtaining the value of the geological condition correction item in the present invention; Figure 7 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

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

[0026] In the description of this application, 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. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0027] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0028] like Figure 1 As shown, the present invention provides a tunnel geological disaster risk intelligent early warning method with self-learning ability, comprising: S1, based on the advanced detection and monitoring data obtained in the current operation cycle and using the detection / monitoring index criterion, obtain the predicted value of the geological disaster risk index; the predicted value of the geological disaster risk index is used to describe the degree of geological disaster risk that may occur in front of the tunnel face; S2, obtaining the geological conditions ahead of the tunnel face according to the current advanced detection / monitoring data interpretation, determining the value of the initial geological condition correction coefficient according to the geological conditions through the built-in empirical method and correcting the geological risk index prediction value of step S1; S3, according to the difference between the actual geological disaster degree index value after excavation and the predicted geological disaster risk index value, adjust the geological condition correction coefficient value and correct the predicted geological disaster risk index value until the difference between the two is minimized, and obtain the adjusted and updated geological condition correction coefficient value; S4, in the next operation cycle, repeat step S1 to obtain the predicted value of the geological disaster risk index, and use the geological condition correction coefficient value updated in step S3 as the risk index correction coefficient value obtained by interpreting the geological conditions in step S2, update the predicted value of the geological disaster risk index, and then automatically warn according to the built-in warning level and threshold standard; S5, repeating steps S1 to S4, obtaining the geological condition correction coefficient value of a new operation cycle, continuously using the actual on-site conditions to realize the self-learning process of the geological condition correction coefficient, and improving the reliability of the prediction of geological disaster risk indicators.

[0029] Furthermore, the predicted value of the geological disaster risk index is the result of four arithmetic operations of the predicted value of the advanced detection / monitoring index and the correction term of the geological conditions; the predicted value of the detection / monitoring index is derived from the advanced detection or monitoring method used in the specific project and the corresponding analysis results; the correction term depends on the geological conditions that affect the specific type of geological disaster, and the dynamic value of the correction term is realized by describing the quantitative characteristic indicators and using self-learning. The relative relationship between the value of the correction term and the size of the predicted value of the advanced detection / monitoring reflects the weight of the two methods, thereby integrating and being compatible with the traditional empirical method and the advanced detection / monitoring method of geological disaster prediction and warning.

[0030] The value of the correction item describes the degree of influence of the characteristic index value of geological conditions on the risk of geological disasters, and is closely related to the specific type of geological disasters and control factors; its initial value is set through experience, and it is automatically corrected during the construction process based on the principle of minimizing the difference between the predicted value and the actual value, thereby realizing self-learning of the correction item value during the tunnel excavation process.

[0031] The geological conditions described by the correction items include geological structure, lithology and surrounding rock quality. The occurrence of geological structure reflects the geomechanical causes and the disaster-proneness of some types of geological disasters. It is one of the characteristic indicators for describing geological structure. It is obtained through the interpretation of technologies such as advance detection and microseismic monitoring, and the interpretation method is revised after excavation according to the degree of difference from the actual situation, reflecting the learning ability of the geological condition interpretation link. The lithology is inferred through geological cataloging behind the face and combined with previous geological survey results. The quality of surrounding rock is obtained through geological cataloging and geological interpretation, or a combination of the two.

[0032] The geological conditions are described by characteristic values ​​related to geological disasters and are obtained through geological interpretation of advance detection / monitoring or geological cataloging and inference.

[0033] The geological structure includes three characteristic indicators: folds, faults and joints, which are important influencing factors of almost all types of geological disasters. They often play a role through geomechanical causes (compression, tension, etc.) and are described by characteristic indicators reflecting geomechanical causes. Among them, folds mainly include anticlines or synclines, corresponding to tension and compression causes respectively. For a given project, the occurrence of faults and dominant joints reflects the geomechanical causes. Faults also include width and filling type, and dominant joints also include joint surface state. Lithology includes water permeability and rock strength, which describe the disaster-prone capacity and risk level of geological disasters of lithology; The quality of surrounding rock is described by RMR, GSI, Q, T, and BQ indicators, which affect the risk of mechanically related geological disasters, including adverse deformation of surrounding rock and rock burst.

[0034] The types of geological disasters include harmful gases, high ground temperature, water gushing, mud burst, collapse, undesirable deformation and rock burst. In specific projects, each type of geological disaster is associated with one or more detection / monitoring technologies, and the detection / monitoring values ​​are used to predict the risk level of the geological disaster. The advanced detection or monitoring index depends on the detection and monitoring methods used in the specific project and is dynamic. The predicted value of the detection / monitoring index comes from the advanced detection or monitoring method used in the specific project and the corresponding analysis results, which is the same as the actual method currently used. Taking the case of water gushing and resistivity obtained by electrical detection as an example, the resistivity spatial distribution cloud map is obtained based on the point cloud data of resistivity obtained by electrical detection and the computer graphics spatial interpolation method. The low resistivity boundary represents the fracture contour, and the fracture occurrence is interpreted from this. Combined with the geological survey results, the geomechanical cause type of the fracture is determined, and the basis for the geological condition correction item value is obtained. Similarly, when using microseismic monitoring to predict the rock burst risk in the face area, the occurrence of the fracture surface represented by each microseismic event is interpreted, the dominant occurrence is statistically calculated, and the geomechanical cause of the dominant fracture is obtained through geological analysis, and the basis for the geological condition correction item value is obtained when predicting the rock burst risk.

[0035] For specific projects, the controlling geological conditions for each type of geological disaster may be different, which is reflected in the value of the specific geological correction items.

[0036] In this embodiment, the i-th type of geological disaster risk index is , i ranges from 1 to 7, corresponding to seven types of geological disasters: harmful gas, high ground temperature, water gushing, mud burst, collapse, unfavorable deformation and rock burst. This index is the result of four arithmetic operations of the predicted value of the advanced detection / monitoring index (a) and the geological condition correction term (b), including summation, product and other forms, namely: (1) or (2).

[0037] Where j is used to mark the jth type of geological conditions, b j It represents the geological condition correction item of the jth geological condition to the ith geological disaster risk. When different arithmetic operations are used, the principles for selecting the values ​​of each indicator are different. If there is no detection / monitoring value, a is taken when the summation method is used. i Take 0, when using the product method a i Take 1, and so on for the rest; in this way, the integration and compatibility of the two methods can be achieved, playing a role of complementary advantages.

[0038] Take the common spring water as an example. is the predicted water inflow, including the water inflow estimated by advance detection and the correction item according to geological conditions; assuming that electrical detection is adopted to obtain the resistivity change in front of the tunnel face, the a value is the predicted value of the water inflow represented by the resistivity detection result, and the relationship between each other can be established by reference and adoption of relevant research and practical results, which is not within the scope of the rights required by the present invention; the b value is the correction item of the geological conditions of the surrounding rock in front of the tunnel face. Electrical detection can be interpreted according to the abnormal distribution of resistivity, such as according to the occurrence of water-conducting faults and the geomechanical causes of faults revealed by previous geological survey results. In the case of tension, b takes a higher value and in the case of compression, it takes a lower value. The value of b can be further refined according to the interpreted fracture width, etc.

[0039] It should be understood that a certain geological disaster risk is often affected by multiple geological conditions. Therefore, when the correction item includes two or more geological conditions and multiple indicators, it is the superposition or multiplication of multiple correction values.

[0040] The correction item value based on geological structure refers to the geomechanical causes of geological structure and related disaster-pregnancy mechanisms. For example, the risk of water inrush in tensile structure is high, the correction item value is large, and the risk of rock burst is low, the correction item value is small. When applied to specific projects, the initial value is set artificially according to the results of previous geological surveys, and the construction process is continuously revised according to the latest difference principle based on the comparison between the actual situation and the predicted results. The correction item value based on lithology refers to the internal rules between lithology and disaster-prone conditions, such as high risk of harmful gases in coal seams, low risk of water inrush, low risk of rock burst and high risk of deformation determined by poor impermeability of clay rocks, etc. According to the internal rules, the default correction value is set, so as to intelligently obtain the corresponding correction item value according to the lithology analysis results in front of the tunnel face; Based on the influence of surrounding rock quality on geological disasters affected by mechanical processes, such as large deformation, collapse, rock burst, etc., the surrounding rock quality index values ​​are converted into corresponding input parameter values, such as the uniaxial compressive strength of surrounding rock and HB strength parameters, through the requirements of corresponding criteria for input parameters.

[0041] Preferably, when predicting the risk of harmful gases and calculating the correction items for geological conditions, lithology is dominant, and b takes a higher value when it is a coal seam; Preferably, when predicting water inflow risk and calculating geological condition correction items, fractures and lithology are the main conditions, and b takes the highest value when there are permeable rock layers and water-conducting structures; Preferably, when predicting mud burst risk and calculating geological condition correction items, the fracture width and the intersection of the fracture with the tunnel axis are dominant, and the value of b is the highest when the width is large and the angle with the axis is small; Preferably, when predicting rock burst risk and calculating geological condition correction items, the geomechanical origin of the fault occurrence indication is the main condition, and b takes the highest value for compressive faults and the lowest value for tensile faults; Preferably, when microseismic monitoring is carried out on site, the influence of the geomechanical causes of the dominant fracture surface corresponding to the microseismic event can also be considered in an additive or multiplicative manner, with the highest value being taken when the most dominant fracture surface is compressive and the lowest value being taken when the most dominant fracture surface is tensile.

[0042] Before excavation of the current tunnel face, the geological conditions and characteristic index values ​​in front of the tunnel face are obtained by using geological interpretation of advanced detection / monitoring data or construction geological cataloging combined with speculation of previous results, providing the necessary basic data for the selection of geological condition correction items; when conditions permit, the geological conditions actually revealed are compared after excavation to correct the geological interpretation method.

[0043] When the advanced detection indicators reveal the existence of a geological structure surface / belt in front of the tunnel face, the occurrence and width of the geological structure are interpreted based on the abnormal values; and compared with the actual situation after excavation, the relevant judgment criteria of the interpretation process are corrected for subsequent geological structure interpretation; When conducting microseismic monitoring, interpret the occurrence of the rupture surface corresponding to each event, count the occurrence of each dominant group of rupture surfaces, compare with the previous geological survey results to obtain the geomechanical causes of the dominant rupture surfaces, and obtain the input indicators required for geological condition correction; The lithology in front of the tunnel face and its corresponding characteristic index values ​​are determined through geological cataloging of the tunnel face area and combined with previous geological survey results; The quality index values ​​of the surrounding rock in front of the tunnel face (RMR, BQ, etc.) are determined through the geological cataloging of the tunnel face area and combined with the previous geological survey results. When the detection method used on site can obtain detection indicators (such as longitudinal wave velocity) that reflect the integrity of the surrounding rock in front of the tunnel face, the detection indicators are used for correction.

[0044] When the interpretation results differ from the actual revealed fault geomechanical causes, two aspects of checks and corrections are performed: First, the deviation between the fault occurrence interpretation result and the measured value is corrected by adjusting the relevant methods and corresponding parameters of the spatial data interpolation calculation process, including the Kriging interpolation algorithm and the inverse square distance interpolation algorithm, and the parameters include the search radius, etc. When the deviation of the occurrence is small, check and update the relationship between the occurrence and the geomechanical causes of the fracture. The relationship between the occurrence and the geomechanical causes of the fracture is often stable within the same geological structural unit. Therefore, it is necessary to check and update the results of the geological structural unit division along the tunnel, so as to obtain the correct judgment result according to the structural unit to which the prediction area belongs and the corresponding occurrence-geomechanical causes relationship.

[0045] The value of the geological condition correction item is determined according to the type of geological disaster and its influencing factors. The initial value is set before the specific construction of the project based on the geological survey results and experience. During the tunnel excavation process, the correction item value is automatically calculated according to the difference between the actual geological disaster and the predicted result and the principle of minimum difference. It is used for geological disaster warning in the next operation cycle, and the actual situation on site is used in a self-learning manner to correct the prediction deviation and improve the reliability of the warning result.

[0046] Figure 2 It is a diagram that uses advanced detection data to interpret the fault occurrence. Advanced detection often obtains discrete point cloud data. Figure 2 The spatial data interpolation technology shown in the figure obtains a continuously distributed cloud map, thereby automatically or manually interpreting the fracture contour and obtaining the occurrence. Combined with the correlation between the occurrence and the geomechanical genesis of the geological structural unit in the detection area, the cause classification result of the fracture is obtained, and then the value of the geological structure correction item is obtained.

[0047] This method is divided into two parts during use: intelligent warning and self-learning. Figure 3 Figure 4 shown.

[0048] Figure 3 This is the working principle of the intelligent early warning of tunnel geological disasters that combines two prediction methods in the present invention. Figure 3 It is shown that the advanced detection / monitoring and early warning method is the main body, and the geological experience prediction method plays an auxiliary correction role. However, in actual implementation, the weights of these two methods can be adjusted at will by the size of the values ​​to achieve the integration and compatibility of the two methods, and improve the reliability of geological disaster warning by taking advantage of their strengths and making up for their weaknesses.

[0049] Figure 4 It is aimed at the working principle of obtaining reasonable geological condition correction item values ​​in a learning way based on the geological experience method. Simply put, after completing a certain geological disaster prediction, it is compared with the actual situation and the geological condition correction item is calculated based on the principle of minimizing the deviation between the two, so as to improve the adaptability of the general method to specific engineering conditions.

[0050] The intelligent early warning is to predict the risk level of geological disasters ahead of the tunnel face using advanced detection or monitoring indicators at the current position of the tunnel face corresponding to a certain period of time during the tunnel excavation process, and interpret or speculate the geological conditions to obtain the correction item value results and the corrected geological disaster risk level prediction value as the only input value for geological disaster early warning, and to achieve intelligent early warning according to the set warning threshold. Self-learning occurs after the current tunnel face is excavated, and the geological condition interpretation method is corrected according to the difference between the actual geological conditions revealed and the prediction results, and the correction item value method is automatically optimized according to the difference between the actual geological conditions and the prediction results.

[0051] Taking water inflow as an example, when the predicted water consumption is higher or lower than the actual situation, the value is corrected according to the principle of minimum difference and used for the prediction of the next operation cycle. In order to reduce the impact of chance when correcting with a single geological disaster event, the weighted average of multiple geological disaster events can be used as the objective function in actual application, and the correction item value can be calculated according to the principle of minimum enhanced average value; the weighted item can be the distance between the geological disaster event and the tunnel face, and the geological disaster event closest to the tunnel face has the largest weight.

[0052] All data and information required for the application of the present invention are collected and managed in accordance with the requirements of digital "mapping" of rock engineering objects. Specifically, they are presented in two forms: a three-dimensional digital geometric model that maps the contours of the tunnel and surrounding rock, and characteristic values ​​attached to the geometric objects. This meets the requirements for quantitative input data when using digital twin technology to "program" the geological empirical method for disaster prediction.

[0053] The embodiment of the present invention provides a tunnel geological disaster risk intelligent early warning system with self-learning capability, including a tunnel engineering digital twin model, which provides all the data required for intelligent early warning of various geological disasters, specifically in the form of a three-dimensional digital geometric model that "maps" the contour morphology of the rock mass engineering and eigenvalues ​​attached to the geometric object: The three-dimensional digital geometric model includes geological model, design model, construction contour model, and detection / monitoring point layout model; The characteristic values ​​attached to the geological model include the types of geological objects (surface, strata, fractures, joints, groundwater, etc.) and the characteristic values ​​of each type of object; The characteristic values ​​attached to the design model include the buried depth along the axis, rock mass density, lateral pressure coefficient, rock strength, input index of rock mass strength, and the distribution of the predicted results of various geological disasters along the tunnel axis; The detection / monitoring indicators attached to the detection / detection points depend on the detection and monitoring methods adopted in the specific project, and their data values ​​change dynamically.

[0054] The system adopts B / S architecture, web browser realizes application operation, the server stores various data required for system operation, and deploys cloud services required for system operation; The operations implemented by the web browser include uploading of preliminary data, browsing of dynamic data during construction, updating of geological models and cloud service operations such as interpolation of detection data control, assignment and modification of parameter values ​​included in various geological disaster prediction methods, geological risk prediction and early warning, and publication of early warning results. The system server includes static data and dynamic data, which together realize the digital mapping of tunnel projects in different periods, that is, using geometric models to describe various geological interfaces of tunnel surrounding rocks, tunnel contours and construction features, and the layout of detection and monitoring points, and using indicator values ​​attached to different geometric objects to describe the state of surrounding rocks. The two together meet the requirements of input data for intelligent early warning of geological disasters; The cloud services deployed on the system server include geological model update services, spatial data interpolation services, and geological disaster risk indicator calculation services with relatively complex calculation processes.

[0055] Figure 5 It is comprehensive Figure 3 and Figure 4 The geological disaster warning function on the browser side of the B / S architecture software system is composed of the object tree on the right, which contains geometric models such as geological model, design model (tunnel) and monitoring point layout model, which constitute the geometric part of the digital twin model of the tunnel engineering. The geological model is classified and managed according to strata (lithology), fractures and joints, which is actually the assignment of geological type attributes to the geological interface, and the service is respectively for the correction of three types of geological conditions; the tunnel is managed in sections along the axis, which plays multiple roles, one of which is to define the geological unit to which any part along the tunnel belongs (the geological condition changes are considered when the section is divided), and in addition, the relevant parameter index values ​​(burial depth, lateral pressure coefficient, surrounding rock quality, etc.) along the tunnel are recorded, which are the index values ​​attached to the geometric model, and together constitute the digital twin tunnel engineering model.

[0056] Figure 5 On the right are the related operation commands for realizing self-learning intelligent early warning, in which the value of geological condition correction item b is determined by Figure 6 The operation command shown in the figure can be completed by manual setting or automatic update through "learning training", the latter is the self-learning ability. When correcting for fractures or joints, the correction term b can be set for the three situations of compression, torsion and tension as mentioned above, or it can be set as Figure 6 As shown, the values ​​are taken according to 5 situations respectively, and the 5-level classification value taking is relatively more detailed, but it puts forward higher requirements for on-site work. No matter which method is adopted, it does not affect the technical feasibility of the present invention.

[0057] The following uses water inflow as an example to further introduce the implementation mode of the present invention. Assuming that the electrical method is used for advance detection at the construction site, the relationship between the resistivity value and the water inflow volume is shown in the following table (or other forms of results, which do not fall within the scope of the claims of the present invention):

[0058] Assume that the advance detection reveals an obvious low-resistance zone, indicating the presence of water-conducting structures and water inrush risks. The average resistivity of the low-resistance zone is Oi, which is between O3 and O4. According to the above, the a value in formula (2) is between L3 and L4, assuming it is 15L / m.

[0059] Assume that the spatial cloud image after interpolation of the resistivity detection results (point cloud data) is as follows Figure 2 As shown, the occurrence of the fault structure is interpreted as a tensile-torsional origin; Figure 6 As shown, at this time, b in formula (2) is 1.3.

[0060] Therefore, based on the data of this advance detection, the water inflow predicted based on resistivity alone is 15L / m, which is revised to 19.5L / m after considering the causes of the fault structure and the water conductivity determined by it.

[0061] After tunnel excavation and exposure of the water-conducting structure, if the actual water inflow exceeds 19.5L / m, it proves that the previously used b-value (1.3) is too low and needs to be increased for correction of similar (tension-torsion) fractures; otherwise, the b-value needs to be lowered to achieve deviation-based learning; when the system automatically completes the correction of the b-value according to the size of the difference, it has the ability of self-learning.

[0062] According to one aspect of the present disclosure, an electronic device is also disclosed, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above method.

[0063] According to one aspect of the present disclosure, a non-transitory computer-readable storage medium is also disclosed, wherein the storage medium stores computer instructions, and the computer instructions implement the above method when executed by a computer.

[0064] According to one aspect of the present disclosure, a computer program product is also disclosed, including a computer program, wherein: The computer program implements the above method when executed by a processor.

[0065] refer to Figure 7, a block diagram of an electronic device 600 that can be used as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0066] like Figure 7 As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0067] Multiple components in the electronic device 600 are connected to the I / O interface 605, including: an input unit 606, an output unit 607, a storage unit 608, and a communication unit 609. The input unit 606 can be any type of device that can input information to the electronic device 600. The input unit 606 can receive input digital or character information and generate key signal input related to user settings and / or function control of the electronic device, and can include but is not limited to a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and / or a remote controller. The output unit 607 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 608 can include but is not limited to a disk, an optical disk. The communication unit 609 allows the electronic device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0068] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as image processing methods. For example, in some embodiments, the image processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the image processing method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the image processing method in any other appropriate manner (e.g., by means of firmware).

[0069] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0070] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0071] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0072] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0073] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0074] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0075] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0076] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but only by the claims after authorization and their equivalent scope. Various elements in the embodiments or examples can be omitted or replaced by their equivalent elements. In addition, each step can be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples can be combined in various ways. It is important that with the evolution of technology, many elements described herein can be replaced by equivalent elements that appear after the present disclosure.

Claims

1. An intelligent early warning method for tunnel geological disaster risk with self-learning ability, characterized in that: include: S1, based on the advanced detection and monitoring data obtained in the current operation cycle and using the detection / monitoring index criterion, obtain the predicted value of the geological disaster risk index; the predicted value of the geological disaster risk index is used to describe the degree of geological disaster risk that may occur in front of the tunnel face; S2, obtaining the geological conditions ahead of the tunnel face according to the current advanced detection / monitoring data interpretation, determining the value of the initial geological condition correction coefficient according to the geological conditions through the built-in empirical method and correcting the geological risk index prediction value of step S1; S3, according to the difference between the actual geological disaster degree index value after excavation and the predicted geological disaster risk index value, adjust the geological condition correction coefficient value and correct the predicted geological disaster risk index value until the difference between the two is minimized, and obtain the adjusted and updated geological condition correction coefficient value; S4, in the next operation cycle, repeat step S1 to obtain the predicted value of the geological disaster risk index, and use the geological condition correction coefficient value updated in step S3 as the risk index correction coefficient value obtained by interpreting the geological conditions in step S2, update the predicted value of the geological disaster risk index, and then automatically warn according to the built-in warning level and threshold standard; S5, repeating steps S1 to S4, obtaining the geological condition correction coefficient value of a new operation cycle, continuously using the actual on-site conditions to realize the self-learning process of the geological condition correction coefficient, and improving the reliability of the prediction of geological disaster risk indicators.

2. The method according to claim 1, characterized in that The predicted value of the geological disaster risk index is the result of four arithmetic operations of the predicted value of the advanced detection / monitoring index and the correction term of the geological conditions; the predicted value of the detection / monitoring index is derived from the advanced detection or monitoring method adopted in the specific project and the corresponding analysis results; the correction term depends on the geological conditions that affect the specific type of geological disaster, and the dynamic value of the correction term is realized by describing the quantitative characteristic indicators and using the self-learning method; The geological conditions described by the correction items include geological structure, lithology and surrounding rock quality. The occurrence of geological structure reflects the geomechanical causes and the disaster-prone capacity of some types of geological disasters. It is obtained through the interpretation of technologies such as advance detection and microseismic monitoring, and the interpretation method is revised after excavation according to the degree of difference from the actual situation, reflecting the learning ability of the geological condition interpretation link; the lithology is inferred through geological cataloging behind the face and combined with previous geological survey results, and the surrounding rock quality is obtained through geological cataloging and geological interpretation, or a combination of the two.

3. The method according to claim 2, characterized in that The types of geological disasters include harmful gases, high ground temperature, water gushing, mud burst, collapse, undesirable deformation and rock burst. In specific projects, each type of geological disaster is associated with one or more detection / monitoring technologies, and the detection / monitoring values ​​are used to predict the risk level of the geological disaster. The geological conditions are described by characteristic values ​​related to geological disasters and are obtained through geological interpretation of advance detection / monitoring or geological cataloging and inference.

4. The method according to claim 3, characterized in that The geological structure includes three characteristic indicators, namely folds, faults and joints, which are described by characteristic indicators reflecting geomechanical causes; folds mainly include anticlines or synclines, corresponding to tensional and compressional causes respectively; for a given project, the occurrence of faults and dominant joints reflects the geomechanical causes; faults also include width and filling type, and dominant joints also include joint surface state; Lithology includes water permeability and rock strength, which describe the disaster-prone capacity and risk level of geological disasters of lithology; The quality of surrounding rock is described by RMR, GSI, Q, T, and BQ indicators, which affect the risk of mechanically related geological disasters, including adverse deformation of surrounding rock and rock burst.

5. The method according to claim 4, characterized in that Before the tunnel is excavated at the current face, the geological interpretation of the advanced detection / monitoring data or the construction geological catalog is used in combination with the inference of the previous results to obtain the actual geological conditions and characteristic index values ​​in front of the face, providing the basic data required for the selection of geological condition correction items; When the advanced detection indicators reveal the existence of a geological structure surface / belt in front of the tunnel face, the occurrence and width of the geological structure are interpreted based on the abnormal values; and compared with the actual situation after excavation, the relevant judgment criteria of the interpretation process are corrected for subsequent geological structure interpretation; When conducting microseismic monitoring, interpret the occurrence of the rupture surface corresponding to each event, count the occurrence of each dominant group of rupture surfaces, compare with the previous geological survey results to obtain the geomechanical causes of the dominant rupture surfaces, and obtain the input indicators required for geological condition correction; The lithology in front of the tunnel face and its corresponding characteristic index values ​​are determined through geological cataloging of the tunnel face area and combined with previous geological survey results; The quality index value of the surrounding rock in front of the tunnel face is determined through the geological cataloging of the tunnel face area and combined with the previous geological survey results; when the detection method used on site can obtain detection indicators that reflect the integrity of the surrounding rock in front of the tunnel face, the detection indicators are used for correction.

6. The method according to claim 5, characterized in that The value of the geological condition correction item is determined according to the type of geological disaster and its influencing factors. The initial value is set before the construction of a specific project based on geological survey results and experience. During the tunnel excavation process, the correction item value is automatically calculated based on the difference between the actual geological disaster and the predicted result and the principle of minimum difference, and is used for geological disaster warning in the next operation cycle.

7. The method according to claim 6, characterized in that The correction items based on geological structure refer to the geomechanical causes of geological structure and related disaster mechanisms; in specific engineering applications, the initial value is set artificially based on the previous geological survey results, and the construction process is continuously revised according to the latest difference principle based on the comparison between the actual situation and the predicted results; The correction item value based on lithology refers to the internal law between lithology and disaster-pregnant conditions, and sets the default correction value according to the internal law, so as to intelligently obtain the corresponding correction item value according to the lithology analysis result in front of the tunnel face; Based on the geological disasters in which surrounding rock quality is affected by mechanical processes, the surrounding rock quality index values ​​are converted into corresponding input parameter values ​​through the requirements of corresponding criteria for input parameters.

8. A tunnel geological disaster risk intelligent early warning system with self-learning ability, used to implement the tunnel geological disaster risk intelligent early warning method with self-learning ability as claimed in any one of claims 1 to 7, characterized in that: Including the digital twin model of tunnel engineering, the digital twin model of tunnel engineering provides all the data required for intelligent early warning of various geological disasters, specifically in the form of a three-dimensional digital geometric model that "maps" the contour of the rock mass engineering and the characteristic values ​​attached to the geometric object: The three-dimensional digital geometric model includes geological model, design model, construction contour model, and detection / monitoring point layout model; The characteristic values ​​attached to the geological model include the geological object type and the characteristic values ​​of each type of object; The characteristic values ​​attached to the design model include the buried depth along the axis, rock mass density, lateral pressure coefficient, rock strength, input index of rock mass strength, and the distribution of the predicted results of various geological disasters along the tunnel axis; The detection / monitoring indicators attached to the detection / detection points depend on the detection and monitoring methods adopted in the specific project, and their data values ​​change dynamically.

9. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the intelligent early warning method for tunnel geological disaster risks with self-learning ability as described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, which, when executed by a processor, implements an intelligent early warning method for tunnel geological disaster risks with self-learning capability as described in any one of claims 1 to 7.

Images