Tunnel surrounding rock prediction method and platform based on artificial intelligence while drilling and measuring

Abstract

The present application provides a method and platform for predicting surrounding rock of a tunnel while drilling based on artificial intelligence, which relates to the technical field of tunnel surrounding rock measurement, including: determining a drilling mechanism for transmitting and receiving signals; generating corresponding signal detection samples; performing attenuation rate analysis, obtaining signal attenuation rate samples, and determining a first signal detection distance; setting a detection fence area based on this distance, in which the drilling mechanism performs real-time detection, and inputs the detection signal into a tunnel surrounding rock risk prediction model, outputs a first predicted risk index, and is used for risk prompts of a host computer. The present application can solve the problem that the prior art is difficult to achieve accurate perception and risk assessment of the geological environment, which further affects the safety, efficiency and accuracy of drilling operations, and achieves more accurate setting of the detection fence area, reduces the impact of signal attenuation on detection accuracy, and improves the safety and efficiency of operations.

Description

Technical Field

[0001] The present application relates to the technical field of tunnel surrounding rock measurement, and in particular to a method and platform for predicting tunnel surrounding rock while drilling and measuring based on artificial intelligence. Background Art

[0002] Tunnel engineering is an important infrastructure construction project in the fields of transportation, water conservancy, mining, etc. During the tunnel construction process, the stability of the surrounding rock is the key to ensuring the safety of the project. However, the tunnel surrounding rock is affected by many factors such as geological conditions and construction disturbances, and its deformation and destruction process is complex and uncertain. Traditional surrounding rock monitoring methods often have lags and cannot reflect the surrounding rock status in real time and accurately, which brings great risks to tunnel construction.

[0003] At present, the signal detection and risk prediction capabilities of the drilling mechanism during the drilling process are relatively limited, making it difficult to achieve comprehensive and real-time perception of the drilling environment. At the same time, the signal attenuation problem is also a challenge that cannot be ignored. It seriously affects the accuracy and reliability of the detection signal, thereby reducing the overall efficiency of the drilling operation.

[0004] In summary, due to the lack of signal detection and risk prediction capabilities, as well as the existence of signal attenuation problems in existing technologies, it is difficult for drilling operations to achieve accurate perception and risk assessment of the geological environment, which further affects the safety, efficiency and accuracy of drilling operations. Summary of the invention

[0005] The purpose of this application is to provide an artificial intelligence-based tunnel surrounding rock prediction method and platform for while-drilling monitoring, in order to solve the problem that the existing technology is difficult to achieve accurate perception and risk assessment of the geological environment, which further affects the safety, efficiency and accuracy of drilling operations.

[0006] In view of the above problems, the present application provides a tunnel surrounding rock prediction method and platform based on artificial intelligence while drilling and measuring.

[0007] In a first aspect, the present application provides a tunnel surrounding rock prediction method based on artificial intelligence while drilling, which is implemented by a tunnel surrounding rock prediction platform based on artificial intelligence, wherein the tunnel surrounding rock prediction method based on artificial intelligence while drilling includes: determining a drilling mechanism, wherein a signal transmitting array and a signal receiving array are provided on the drilling mechanism, wherein the signal receiving array is used to receive a signal transmitted by the signal transmitting array; setting a signal detection distance sample, wherein the signal transmitting array and the signal receiving array perform a signal test according to the signal detection distance sample to generate a signal detection sample, wherein the signal detection distance sample corresponds to the signal detection distance sample; performing an attenuation rate analysis on the signal detection sample to obtain a signal attenuation rate sample corresponding to the signal detection distance sample; obtaining a first signal detection distance according to the signal attenuation rate sample; setting a detection fence area according to the first signal detection distance, wherein the drilling mechanism performs real-time detection based on the detection fence area and outputs a real-time detection signal; inputting the real-time detection signal into a tunnel surrounding rock risk prediction model, outputting a first prediction risk index according to the tunnel surrounding rock risk prediction model, and performing a host computer risk prompt with the first prediction risk index.

[0008] In the second aspect, the present application also provides an artificial intelligence-based tunnel rock prediction platform while drilling and measuring, which is used to execute the artificial intelligence-based tunnel rock prediction method while drilling and measuring as described in the first aspect, wherein the artificial intelligence-based tunnel rock prediction platform while drilling and measuring includes: a signal receiving module, used to determine a drilling mechanism while drilling, the drilling mechanism is provided with a signal transmitting array and a signal receiving array, the signal receiving array is used to receive the signal transmitted by the signal transmitting array; a detection sample generating module, used to set a signal detection distance sample, the signal transmitting array and the signal receiving array perform signal testing according to the signal detection distance sample to generate a signal detection sample, wherein the signal detection distance sample is the same as the signal A signal detection sample corresponds to a signal detection sample; an attenuation rate analysis module is used to perform attenuation rate analysis on the signal detection sample, and obtain a signal attenuation rate sample corresponding to the signal detection distance sample; a first signal detection distance acquisition module is used to obtain a first signal detection distance according to the signal attenuation rate sample; a real-time detection module is used to set a detection fence area according to the first signal detection distance, and the drilling mechanism performs real-time detection based on the detection fence area, and outputs a real-time detection signal; a first predicted risk indicator output module is used to input the real-time detection signal into a tunnel surrounding rock risk prediction model, output a first predicted risk indicator according to the tunnel surrounding rock risk prediction model, and use the first predicted risk indicator to issue a risk prompt to the host computer.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] By determining a drilling mechanism, the drilling mechanism is provided with a signal transmitting array and a signal receiving array, and the signal receiving array is used to receive the signal transmitted by the signal transmitting array; setting a signal detection distance sample, the signal transmitting array and the signal receiving array perform signal testing according to the signal detection distance sample to generate a signal detection sample, wherein the signal detection distance sample corresponds to the signal detection sample; performing attenuation rate analysis with the signal detection sample to obtain a signal attenuation rate sample corresponding to the signal detection distance sample; obtaining a first signal detection distance according to the signal attenuation rate sample; setting a detection fence area according to the first signal detection distance, the drilling mechanism performs real-time detection based on the detection fence area, and outputs a real-time detection signal; inputting the real-time detection signal into a tunnel surrounding rock risk prediction model, outputting a first predicted risk index according to the tunnel surrounding rock risk prediction model, and performing a host computer risk prompt with the first predicted risk index, which effectively solves the problem that the prior art is difficult to achieve accurate perception and risk assessment of the geological environment, further affecting the safety, efficiency and accuracy of the drilling operation, and achieving more accurate setting of the detection fence area, reducing the impact of signal attenuation on detection accuracy, and improving the safety and efficiency of the operation.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 This is a flow chart of the tunnel surrounding rock prediction method based on artificial intelligence while drilling and measuring in this application;

[0014] Figure 2 This is a schematic diagram of the structure of the tunnel surrounding rock prediction platform based on artificial intelligence while drilling.

[0015] Description of reference numerals:

[0016] A signal receiving module 11 , a detection sample generating module 12 , an attenuation rate analyzing module 13 , a first signal detection distance acquiring module 14 , a real-time detecting module 15 , and a first predicted risk index outputting module 16 . DETAILED DESCRIPTION

[0017] This application solves the problem that the existing technology is difficult to achieve accurate perception and risk assessment of the geological environment by providing an artificial intelligence-based tunnel surrounding rock prediction method and platform for drilling and monitoring, which further affects the safety, efficiency and accuracy of drilling operations, achieves more accurate setting of detection fence areas, reduces the impact of signal attenuation on detection accuracy, and improves the safety and efficiency of operations.

[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0019] For example, please refer to the attached Figure 1 The present application provides a tunnel surrounding rock prediction method based on artificial intelligence while drilling and measuring, wherein the tunnel surrounding rock prediction method based on artificial intelligence while drilling and measuring uses a tunnel surrounding rock prediction platform based on artificial intelligence, and the tunnel surrounding rock prediction method based on artificial intelligence while drilling and measuring specifically includes the following steps:

[0020] S1: Determine a drilling-while-drilling mechanism, wherein the drilling-while-drilling mechanism is provided with a signal transmitting array and a signal receiving array, wherein the signal receiving array is used to receive a signal transmitted by the signal transmitting array.

[0021] Specifically, the drilling mechanism is a device used for drilling and detection in tunnel construction. It can obtain real-time geological information around the borehole through built-in signal transmitting and receiving devices while drilling. The signal transmitting array is a group of transmitters on the drilling mechanism that are used to transmit signals around the borehole. These signals can be electromagnetic waves, sound waves, or other forms of physical signals, which are used to detect the geological conditions around the borehole. The signal receiving array is another group of devices on the drilling mechanism that is used to receive signals emitted by the signal transmitting array and reflected or transmitted back by the geological body around the borehole. By receiving these signals, the geological structure and properties around the borehole can be analyzed.

[0022] S2: Setting a signal detection distance sample, the signal transmitting array and the signal receiving array perform a signal test according to the signal detection distance sample to generate a signal detection sample, wherein the signal detection distance sample corresponds to the signal detection sample.

[0023] Specifically, the signal detection distance sample is a preset detection distance, including the shortest and longest possible working distances, as well as several key distance points in the middle. It is used to simulate different working scenarios of the drilling mechanism in actual tunnel construction. These sample distances can cover all working ranges that the drilling mechanism may encounter to ensure the comprehensiveness and accuracy of the test. Under each signal detection distance sample, the signal transmitting array will transmit signals to the set distance. The signal receiving array is responsible for receiving these signals and recording key parameters such as signal strength and frequency. Through signal testing, a series of signal detection samples corresponding to the signal detection distance samples can be obtained. These signal detection samples contain the signal transmission characteristics between the signal transmitting array and the signal receiving array at different detection distances. Each signal detection distance sample corresponds to a specific signal detection sample.

[0024] S3: Perform attenuation rate analysis on the signal detection samples to obtain signal attenuation rate samples corresponding to the signal detection distance samples.

[0025] Specifically, attenuation rate analysis is the process of quantifying the degree to which the signal weakens during transmission. It includes the difference between the initial strength of the signal when it is transmitted and the strength of the signal when it is received. Signal detection samples are records of signals transmitted by the signal transmitting array and received by the signal receiving array at different detection distances. These samples contain key parameters such as signal strength and frequency. By comparing the initial strength of the signal when it is transmitted and the strength when it is received, the attenuation rate of the signal can be calculated. For each signal detection distance sample, there will be a corresponding signal attenuation rate sample. These attenuation rate samples reflect the attenuation characteristics of the signal at different detection distances.

[0026] S4: Acquire a first signal detection distance according to the signal attenuation rate sample.

[0027] Specifically, the signal attenuation rate sample is a record of the signal attenuation rate obtained by receiving and calculating the signal received by the signal receiving array after the signal emitted by the signal transmitting array is transmitted at different detection distances. These samples reflect the attenuation characteristics of the signal at different detection distances. The first signal detection distance refers to the maximum distance at which the signal can maintain sufficient strength for accurate detection when it is attenuated to a certain extent, which is a threshold preset by a person skilled in the art. This distance is an important reference for real-time detection by the drilling mechanism during tunnel construction. Traverse the signal attenuation rate samples, find the sample point where the attenuation rate reaches or exceeds the preset threshold for the first time, and record the detection distance corresponding to the sample point. The recorded detection distance is determined as the first signal detection distance. This distance is the benchmark distance for the drilling mechanism to perform real-time detection in tunnel construction, and finds the detection distance when the signal attenuation rate reaches the preset threshold.

[0028] S5: setting a detection fence area according to the first signal detection distance, the drilling mechanism performing real-time detection based on the detection fence area, and outputting a real-time detection signal.

[0029] Specifically, the first signal detection distance refers to the maximum distance at which the signal can still maintain sufficient strength for accurate detection when it attenuates to a preset threshold. This distance is a key parameter for determining the detection fence area. The detection fence area is a circular or elliptical area with the drilling mechanism as the center and the first signal detection distance as the radius. In this area, the drilling mechanism can detect the geological conditions of the surrounding rock in real time and output corresponding detection signals. During the excavation process, the drilling mechanism will continuously transmit signals into the detection fence area. By analyzing the returned signals, the drilling mechanism can obtain the geological information of the surrounding rock in real time. The drilling mechanism converts the geological information detected in real time into electrical signals or other forms of signals.

[0030] S6: Input the real-time detection signal into a tunnel surrounding rock risk prediction model, output a first predicted risk index according to the tunnel surrounding rock risk prediction model, and use the first predicted risk index to issue a risk prompt to a host computer.

[0031] Specifically, the real-time detection signal is an electrical signal or other form of signal converted by the drilling mechanism during the excavation process based on the surrounding rock geological information detected in real time in the detection fence area. These signals contain the geological information of the surrounding rock. The tunnel surrounding rock risk prediction model is a model built based on machine learning or deep learning algorithms. The model can receive real-time detection signals as input and output risk indicators related to the stability of the tunnel surrounding rock. The first predicted risk indicator is an indicator calculated by the tunnel surrounding rock risk prediction model based on the real-time detection signal to quantify the current stability risk of the tunnel surrounding rock. This indicator can be a probability value, risk level or other form of quantitative representation. The host computer refers to the ground control system or monitoring center during the tunnel construction process. The risk warning is to display the first predicted risk indicator to the technicians of the host computer in a visual or other form, so as to facilitate timely understanding of the stability risk of the tunnel surrounding rock and take corresponding measures.

[0032] Furthermore, step S3 of the present application also includes:

[0033] Collect geological structure samples of the tunnel surrounding rock, including a set of characteristic factors corresponding to different geological structures; identify a historical detection sample data set corresponding to the geological structure samples; perform signal attenuation impact analysis based on the historical detection sample data set, and identify N signal attenuation impact factors greater than a preset impact threshold, where N is a positive integer greater than or equal to 1; perform attenuation rate analysis based on the N signal attenuation impact factors to obtain a signal attenuation rate sample.

[0034] Specifically, surrounding rock samples are collected at different locations in the tunnel, and each sample is subjected to a detailed geological analysis, including rock type, structural characteristics, etc. The characteristic factor set corresponding to each geological structure is recorded, such as density, porosity, pore water content, stress state, etc. The historical detection records of the tunnel are reviewed, and the historical detection data are matched with the geological structure samples to ensure that each geological structure has corresponding detection data. It is sorted into a complete historical detection sample data set. The historical detection sample data set is processed using statistical analysis or machine learning algorithms to identify N factors whose signal attenuation effect is greater than the preset threshold, N ≥ 1. These factors include at least density, porosity, pore water content, and stress state. The attenuation rate is calculated for different geological structures and the N identified signal attenuation influencing factors. The signal attenuation rate samples corresponding to each geological structure are obtained. The signal attenuation rate samples are input into the tunnel surrounding rock risk prediction model. The model is used for real-time risk prediction, and the construction plan is adjusted according to the prediction results. New detection data is collected, and feedback is continuously provided to optimize the model.

[0035] Furthermore, step S3 of the present application also includes:

[0036] The attenuation rate analysis is performed using the signal detection samples, wherein the expression for calculating the attenuation rate of each signal includes: ;in, is the signal attenuation rate corresponding to each group of signal detection samples, is the basic signal attenuation rate, is the decay rate adjustment function, is the i-th signal attenuation factor, N is the total number of signal attenuation factors, Each group of signal detection samples is for the signal strength of the detection distance d, is the initial signal strength.

[0037] Specifically, the attenuation rate analysis expression is used to calculate the signal attenuation rate of the signal detection sample in the tunnel surrounding rock. It includes the basic signal attenuation rate, the attenuation rate adjustment function, and multiple signal attenuation influencing factors. Signal attenuation rate This refers to the rate at which the signal is weakened during propagation due to the influence of the surrounding rock geological structure. Basic signal attenuation rate This is a fixed attenuation rate that represents the signal attenuation without any geological structure influencing factors. Attenuation rate adjustment function This is a function used to adjust the basic signal attenuation rate according to the geological structure influencing factors. Signal attenuation influencing factors These are geological structure characteristics that affect signal attenuation, such as density, porosity, pore water content, stress state, etc. Signal strength refers to the strength of the signal during the detection process. Initial signal strength This refers to the initial strength when the signal is transmitted. The detection distance refers to the distance from the signal transmission point to the receiving point.

[0038] Furthermore, step S4 of the present application also includes:

[0039] According to the signal attenuation rate samples, detection distance samples with a signal attenuation rate less than a preset attenuation rate are obtained, and the detection distance samples with a signal attenuation rate less than the preset attenuation rate are analyzed to determine the signal detection distance interval; the signal transmitting array and the signal receiving array are connected to receive network environment information of the signal transmission; the signal detection distance interval is optimized according to the network environment information, and a first signal detection distance is output.

[0040] Specifically, from the collected signal attenuation rate samples, those samples with attenuation rates less than the preset attenuation rate are screened out. These samples represent the distance range in which the signal can maintain sufficient strength. The screened detection distance samples are statistically analyzed to determine the minimum value, maximum value and common distribution range of these detection distance samples. Based on the analysis results, a signal detection distance interval is determined, which should contain most of the detection distance samples with a less than preset attenuation rate. This interval will serve as a reference range for subsequent signal detection. In the actual tunnel excavation process, the signal transmitting array and the signal receiving array are connected to prepare for signal reception and transmission. In this process, information about the network environment is collected, such as obstacles and electromagnetic interference on the signal propagation path. The previously determined signal detection distance interval is optimized using the collected network environment information. If there are unfavorable factors in the network environment, such as strong electromagnetic interference, the detection distance interval may need to be reduced to ensure the stability of the signal. On the contrary, if the network environment is good, the detection distance interval may be appropriately increased to improve the detection efficiency. According to the optimized signal detection distance interval, a specific first signal detection distance is determined. This distance will serve as the benchmark distance for signal detection during tunnel excavation. Use programming or data analysis tools to filter the signal attenuation rate samples and extract samples with attenuation rates less than the preset value. Perform statistical analysis on the filtered samples, such as calculating the mean, standard deviation, distribution range, etc. Before or during actual excavation, collect network environment information in the tunnel. Adjust the detection distance interval according to the network environment information to ensure the stability of the signal during the actual excavation process. Select a specific distance in the optimized detection distance interval as the first signal detection distance, and use it in the subsequent excavation and detection process.

[0041] Furthermore, the present application also includes:

[0042] A sample test is performed in the signal detection range interval according to the network environment information, and signal transmission data and signal reception data based on the network environment information are output; detection loss probability is identified according to the signal transmission data and the signal reception data, and a detection loss probability sample corresponding to the signal detection range interval is output; and the first signal detection range with the minimum detection loss probability is located in the signal detection range interval using the detection loss probability sample.

[0043] Specifically, multiple detection ranges within the signal detection range interval are selected for sample testing. For each selected detection range, a signal is transmitted and the transmission data is recorded, and then a signal is received and the reception data is recorded. The signal transmission data and signal reception data corresponding to each detection range are sorted and recorded. These data should include key parameters such as signal strength, frequency, and phase, and consider the influence of network environment information. The signal transmission data and signal reception data are analyzed to identify whether detection loss occurs during signal propagation. The detection loss probability corresponding to each detection range is calculated, that is, the ratio of the number of signal losses to the total number of transmissions. The detection loss probability samples corresponding to each detection range are sorted and recorded. These samples will be used for subsequent positioning of the first signal detection range with the smallest detection loss probability. Within the signal detection range interval, the detection loss probability samples corresponding to different detection ranges are compared. The detection range with the smallest detection loss probability is selected as the first signal detection range. Within the selected signal detection range interval, a signal transmission array is used to transmit a signal, and a signal reception array is used to receive a signal. The signal transmission data and signal reception data corresponding to each detection range are recorded. The signal transmission data and signal reception data are sorted into a table or database format for subsequent analysis. Analyze the signal transmission data and signal reception data to identify signal loss. Calculate the detection loss probability for each detection distance and record it as a detection loss probability sample. Arrange the detection loss probability samples in a table or chart format for easy visual analysis and comparison. In the detection loss probability samples, find the detection distance with the lowest detection loss probability. Determine this detection distance as the first signal detection distance and use it in the subsequent tunneling and signal detection process.

[0044] Furthermore, the present application also includes:

[0045] According to the network environment information, the network coverage area is determined; according to the network coverage area, the area edge coordinate set is determined; the real-time positioning coordinates of the drilling mechanism are obtained, and the drilling mechanism is provided with a positioning module, and the real-time positioning coordinates are matched in the area edge coordinate set, and if the return value is 1, a signal processing instruction is obtained; according to the signal processing instruction, the real-time detection signal of the detection fence area is input into a signal amplifier for signal amplification, and the amplified real-time detection signal is output.

[0046] Specifically, according to the collected network environment information, the characteristics of signal propagation and the distribution of obstacles are analyzed. The area range that the signal can effectively cover, that is, the network coverage area, is determined. On the boundary of the network coverage area, a series of key points are selected as edge coordinates. These coordinates will be used to define the boundary of the network coverage area and for subsequent positioning and matching of the drilling mechanism. The drilling mechanism is equipped with a positioning module, such as GPS, Beidou, etc., which can obtain its position coordinates in real time. The real-time positioning coordinates output by the positioning module are read for subsequent processing. The real-time positioning coordinates of the drilling mechanism are compared with the regional edge coordinate set. If the real-time positioning coordinates match a certain edge coordinate, that is, 1 is returned, it means that the drilling mechanism has approached or entered the boundary of the network coverage area. When the match is successful, a signal processing instruction is generated. This instruction is used to trigger the subsequent signal amplification processing flow. According to the signal processing instruction, the real-time detection signal of the detection fence area is input into the signal amplifier. The signal amplifier amplifies the input signal to improve the strength and stability of the signal. The amplified real-time detection signal is output and used for subsequent surrounding rock risk prediction and analysis.

[0047] Furthermore, step S6 of the present application also includes:

[0048] Establish a surrounding rock abnormal signal sample library, which is called by the tunnel surrounding rock risk prediction model; input the real-time detection signal into the tunnel surrounding rock risk prediction model, wherein the tunnel surrounding rock risk prediction model includes a signal similarity twin network; perform a similarity comparison between the real-time detection signal and the surrounding rock abnormal signal sample library according to the signal similarity twin network, and output a first similarity index; convert the first similarity index into a first prediction risk index.

[0049] Specifically, various surrounding rock abnormal signal data encountered during tunnel excavation are collected and sorted. These data are preprocessed, including denoising, standardization, etc., to ensure the quality and consistency of the data. The processed surrounding rock abnormal signal data are stored in the sample library. When the tunnel surrounding rock risk prediction model requires it, the surrounding rock abnormal signal data are extracted from the sample library. These data will be used for similarity comparison with the real-time detection signal. The real-time detection signal is obtained in real time by the signal detector during the tunnel excavation process. These signals are input into the tunnel surrounding rock risk prediction model for further analysis and prediction. The tunnel surrounding rock risk prediction model contains a signal similarity twin network. Use an appropriate machine learning algorithm or deep learning framework to train the network so that it can accurately compare the similarity between the real-time detection signal and the surrounding rock abnormal signal. This network is responsible for the similarity comparison between the real-time detection signal and the signal in the surrounding rock abnormal signal sample library. Through the comparison, a first similarity index is output, which indicates the similarity between the real-time detection signal and the surrounding rock abnormal signal. The first similarity index is converted into a first prediction risk index. The first prediction risk index will be used to guide decision-making and actions during tunnel excavation.

[0050] In summary, the tunnel surrounding rock prediction method based on artificial intelligence while drilling and measuring provided by this application has the following technical effects:

[0051] By determining a drilling mechanism, the drilling mechanism is provided with a signal transmitting array and a signal receiving array, and the signal receiving array is used to receive the signal transmitted by the signal transmitting array; setting a signal detection distance sample, the signal transmitting array and the signal receiving array perform signal testing according to the signal detection distance sample to generate a signal detection sample, wherein the signal detection distance sample corresponds to the signal detection sample; performing attenuation rate analysis with the signal detection sample to obtain a signal attenuation rate sample corresponding to the signal detection distance sample; obtaining a first signal detection distance according to the signal attenuation rate sample; setting a detection fence area according to the first signal detection distance, the drilling mechanism performs real-time detection based on the detection fence area, and outputs a real-time detection signal; inputting the real-time detection signal into a tunnel surrounding rock risk prediction model, outputting a first predicted risk index according to the tunnel surrounding rock risk prediction model, and performing a host computer risk prompt with the first predicted risk index, which effectively solves the problem that the prior art is difficult to achieve accurate perception and risk assessment of the geological environment, further affecting the safety, efficiency and accuracy of the drilling operation, and achieving more accurate setting of the detection fence area, reducing the impact of signal attenuation on detection accuracy, and improving the safety and efficiency of the operation.

[0052] Embodiment 2: Based on the method for predicting surrounding rock of a tunnel while drilling based on artificial intelligence in the previous embodiment, the present application also provides a platform for predicting surrounding rock of a tunnel while drilling based on artificial intelligence. Figure 2 The artificial intelligence-based tunnel surrounding rock prediction platform for drilling and monitoring includes:

[0053] The signal receiving module 11 is used to determine a drilling-while-drilling mechanism, on which a signal transmitting array and a signal receiving array are provided, and the signal receiving array is used to receive the signal transmitted by the signal transmitting array.

[0054] The detection sample generating module 12 is used to set the signal detection distance sample. The signal transmitting array and the signal receiving array perform signal testing according to the signal detection distance sample to generate a signal detection sample, wherein the signal detection distance sample corresponds to the signal detection sample.

[0055] The attenuation rate analysis module 13 is used to perform attenuation rate analysis on the signal detection samples to obtain signal attenuation rate samples corresponding to the signal detection distance samples.

[0056] The first signal detection distance acquisition module 14 is used to acquire the first signal detection distance according to the signal attenuation rate sample.

[0057] The real-time detection module 15 is used to set a detection fence area according to the first signal detection distance, and the drilling mechanism performs real-time detection based on the detection fence area to output a real-time detection signal.

[0058] The first predicted risk indicator output module 16 is used to input the real-time detection signal into the tunnel surrounding rock risk prediction model, output a first predicted risk indicator according to the tunnel surrounding rock risk prediction model, and use the first predicted risk indicator to issue a risk prompt to the host computer.

[0059] Furthermore, the attenuation rate analysis module 13 in the tunnel surrounding rock prediction platform based on artificial intelligence is also used for:

[0060] Collect geological structure samples of the tunnel surrounding rock, including a set of characteristic factors corresponding to different geological structures; identify a historical detection sample data set corresponding to the geological structure samples; perform signal attenuation impact analysis based on the historical detection sample data set, and identify N signal attenuation impact factors greater than a preset impact threshold, where N is a positive integer greater than or equal to 1; perform attenuation rate analysis based on the N signal attenuation impact factors to obtain a signal attenuation rate sample.

[0061] Furthermore, the attenuation rate analysis module 13 in the tunnel surrounding rock prediction platform based on artificial intelligence is also used for:

[0062] The attenuation rate analysis is performed using the signal detection samples, wherein the expression for calculating the attenuation rate of each signal includes: ;in, is the signal attenuation rate corresponding to each group of signal detection samples, is the basic signal attenuation rate, is the decay rate adjustment function, is the i-th signal attenuation factor, N is the total number of signal attenuation factors, Each group of signal detection samples is for the signal strength of the detection distance d, is the initial signal strength.

[0063] Furthermore, the first signal detection distance acquisition module 14 in the artificial intelligence-based tunnel surrounding rock prediction platform while drilling and measuring is also used for:

[0064] According to the signal attenuation rate samples, detection distance samples with a signal attenuation rate less than a preset attenuation rate are obtained, and the detection distance samples with a signal attenuation rate less than the preset attenuation rate are analyzed to determine the signal detection distance interval; the signal transmitting array and the signal receiving array are connected to receive network environment information of the signal transmission; the signal detection distance interval is optimized according to the network environment information, and a first signal detection distance is output.

[0065] Furthermore, the artificial intelligence-based tunnel surrounding rock prediction platform also includes a lost probability sample detection module, which is used to:

[0066] A sample test is performed in the signal detection range interval according to the network environment information, and signal transmission data and signal reception data based on the network environment information are output; detection loss probability is identified according to the signal transmission data and the signal reception data, and a detection loss probability sample corresponding to the signal detection range interval is output; and the first signal detection range with the minimum detection loss probability is located in the signal detection range interval using the detection loss probability sample.

[0067] Furthermore, the artificial intelligence-based tunnel surrounding rock prediction platform also includes a signal amplification module for:

[0068] According to the network environment information, the network coverage area is determined; according to the network coverage area, the area edge coordinate set is determined; the real-time positioning coordinates of the drilling mechanism are obtained, and the drilling mechanism is provided with a positioning module, and the real-time positioning coordinates are matched in the area edge coordinate set, and if the return value is 1, a signal processing instruction is obtained; according to the signal processing instruction, the real-time detection signal of the detection fence area is input into a signal amplifier for signal amplification, and the amplified real-time detection signal is output.

[0069] Furthermore, the first prediction risk indicator output module 16 in the artificial intelligence-based tunnel surrounding rock prediction platform while drilling and measuring is also used for:

[0070] Establish a surrounding rock abnormal signal sample library, which is called by the tunnel surrounding rock risk prediction model; input the real-time detection signal into the tunnel surrounding rock risk prediction model, wherein the tunnel surrounding rock risk prediction model includes a signal similarity twin network; perform a similarity comparison between the real-time detection signal and the surrounding rock abnormal signal sample library according to the signal similarity twin network, and output a first similarity index; convert the first similarity index into a first prediction risk index.

[0071] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The method and specific examples of tunnel surrounding rock prediction based on artificial intelligence while drilling and measuring in Example 1 are also applicable to the tunnel surrounding rock prediction platform based on artificial intelligence while drilling and measuring in this embodiment. Through the detailed description of the method of tunnel surrounding rock prediction based on artificial intelligence while drilling and measuring, those skilled in the art can clearly know the tunnel surrounding rock prediction platform based on artificial intelligence while drilling and measuring in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the platform disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0072] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0073] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for predicting surrounding rock of a tunnel while drilling and measuring based on artificial intelligence, characterized in that: include: Determine a drilling-while-drilling mechanism, wherein the drilling-while-drilling mechanism is provided with a signal transmitting array and a signal receiving array, wherein the signal receiving array is used to receive a signal transmitted by the signal transmitting array; Setting a signal detection distance sample, the signal transmitting array and the signal receiving array perform a signal test according to the signal detection distance sample to generate a signal detection sample, wherein the signal detection distance sample corresponds to the signal detection sample; Performing attenuation rate analysis on the signal detection samples to obtain signal attenuation rate samples corresponding to the signal detection distance samples; Acquiring a first signal detection distance according to the signal attenuation rate sample; A detection fence area is set according to the first signal detection distance, and the drilling mechanism performs real-time detection based on the detection fence area and outputs a real-time detection signal; Inputting the real-time detection signal into a tunnel surrounding rock risk prediction model, outputting a first predicted risk index according to the tunnel surrounding rock risk prediction model, and providing a risk prompt to a host computer with the first predicted risk index; The signal transmitting array and the signal receiving array perform signal testing according to the signal detection range sample, further comprising: Collect geological structure samples of tunnel surrounding rock, including characteristic factor sets corresponding to different geological structures; Identify a historical detection sample data set corresponding to the geological structure sample; Performing signal attenuation impact analysis based on the historical detection sample data set, identifying N signal attenuation impact factors greater than a preset impact threshold, where N is a positive integer greater than or equal to 1; Performing attenuation rate analysis according to the N signal attenuation influencing factors to obtain a signal attenuation rate sample, wherein the N signal attenuation influencing factors at least include density, porosity, pore water content, and stress state; The attenuation rate analysis is performed using the signal detection samples, wherein the expression for calculating the attenuation rate of each signal includes: ； in, is the signal attenuation rate corresponding to each group of signal detection samples, is the basic signal attenuation rate, is the decay rate adjustment function, is the i-th signal attenuation factor, N is the total number of signal attenuation factors, Each group of signal detection samples is for the signal strength of the detection distance d, is the initial signal strength; Acquiring a first signal detection distance according to the signal attenuation rate sample includes: According to the signal attenuation rate samples, a detection distance sample whose signal attenuation rate is less than a preset attenuation rate is obtained, and the detection distance samples whose signal attenuation rate is less than the preset attenuation rate are analyzed to determine the signal detection distance interval; Network environment information for connecting the signal transmitting array and the signal receiving array to receive and transmit signals; The signal detection range interval is optimized according to the network environment information, and a first signal detection range is output.

2. The method for predicting surrounding rock of a tunnel while drilling and measuring based on artificial intelligence according to claim 1, characterized in that: Optimizing the signal detection range interval according to the network environment information includes: Performing a sample test in the signal detection range according to the network environment information, and outputting signal transmission data and signal reception data based on the network environment information; Identify the detection loss probability according to the signal transmission data and the signal reception data, and output a detection loss probability sample corresponding to the signal detection range interval; Using the detection loss probability samples, a first signal detection range with a minimum detection loss probability is located in the signal detection range interval.

3. The method for predicting surrounding rock of a tunnel while drilling and measuring based on artificial intelligence according to claim 1, characterized in that: The drilling-while-drilling mechanism performs real-time detection based on the detection fence area, wherein the detection fence area is centered on the position of the drilling-while-drilling mechanism and has the first signal detection distance as a radius, and further includes: Determine the network coverage area according to the network environment information; Determining a set of area edge coordinates according to the network coverage area; Acquire the real-time positioning coordinates of the drilling mechanism, the drilling mechanism is provided with a positioning module, match the real-time positioning coordinates in the area edge coordinate set, and if the return value is 1, acquire a signal processing instruction; According to the signal processing instruction, the real-time detection signal of the detection fence area is input into the signal amplifier for signal amplification, and the amplified real-time detection signal is output.

4. The method for predicting surrounding rock of a tunnel while drilling and measuring based on artificial intelligence according to claim 1, characterized in that: Inputting the real-time detection signal into a tunnel surrounding rock risk prediction model, and outputting a first prediction risk index according to the tunnel surrounding rock risk prediction model, further comprising: Establishing a surrounding rock abnormal signal sample library, wherein the surrounding rock abnormal signal sample library is called by the tunnel surrounding rock risk prediction model; Inputting the real-time detection signal into the tunnel surrounding rock risk prediction model, wherein the tunnel surrounding rock risk prediction model includes a signal similarity twin network; Performing a similarity comparison between the real-time detection signal and the surrounding rock abnormal signal sample library according to the signal similarity twin network, and outputting a first similarity index; The first similarity index is converted and outputted into a first prediction risk index.

5. The artificial intelligence-based tunnel surrounding rock prediction platform is characterized by: The steps for implementing the method for predicting surrounding rock of a tunnel while drilling and measuring based on artificial intelligence according to any one of claims 1 to 4, the platform for predicting surrounding rock of a tunnel while drilling and measuring based on artificial intelligence comprises: A signal receiving module, used to determine a drilling-while-drilling mechanism, wherein the drilling-while-drilling mechanism is provided with a signal transmitting array and a signal receiving array, wherein the signal receiving array is used to receive a signal transmitted by the signal transmitting array; A detection sample generating module, used for setting a signal detection distance sample, the signal transmitting array and the signal receiving array perform a signal test according to the signal detection distance sample, and generate a signal detection sample, wherein the signal detection distance sample corresponds to the signal detection sample; An attenuation rate analysis module, used to perform attenuation rate analysis on the signal detection samples to obtain signal attenuation rate samples corresponding to the signal detection distance samples; A first signal detection distance acquisition module, used to acquire a first signal detection distance according to the signal attenuation rate sample; A real-time detection module, configured to set a detection fence area according to the first signal detection distance, and the drilling mechanism performs real-time detection based on the detection fence area and outputs a real-time detection signal; The first predicted risk indicator output module is used to input the real-time detection signal into the tunnel surrounding rock risk prediction model, output the first predicted risk indicator according to the tunnel surrounding rock risk prediction model, and use the first predicted risk indicator to issue a risk prompt to the host computer.

Images