An intelligent prediction method for the support strength of underground mine roadways

Abstract

The present application provides an intelligent prediction method for the support strength of underground mine roadways, which relates to the technical field of support strength prediction. The method includes: reading predetermined support characteristics and obtaining target support characteristic information; analyzing the target support characteristic information to obtain a target system strength index; constructing a support impact resistance database based on big data and extracting the first simulation impact resistance record in the support impact resistance database; introducing an impact resistance ability evaluation function to obtain a first simulation impact resistance index, denoted as the target system impact resistance index; using the target system strength index and the target system impact resistance index as input information of the strength prediction model to obtain the target support strength. Through the present application, the problem in the prior art that the support strength of underground mine roadways cannot be scientifically, accurately and quantitatively predicted and evaluated, and thus the failure of roadway support cannot be timely detected and targeted maintenance cannot be carried out in time can be solved. More safe, economic and efficient roadway support can be realized.

Description

Technical Field

[0001] This application relates to the technical field of support strength prediction, and particularly to an intelligent prediction method for the support strength of underground mine roadways. Background Art

[0002] With the increase in coal mining depth and the complexity of geological conditions, the problem of roadway support has become increasingly prominent. Traditional roadway support methods mainly rely on empirical formulas and simple calculations, which are difficult to meet the high requirements of modern coal mines for roadway support. In order to improve the stability and safety of roadway support, researchers have proposed many new support technologies and methods.

[0003] However, there are still some problems in the practical application of these technologies and methods. On the one hand, due to the complexity and uncertainty of geological conditions, traditional support design methods often cannot accurately predict the actual support effect of roadways. On the other hand, traditional roadway support design methods often ignore the mechanical properties and structural characteristics of roadway surrounding rock, resulting in unreasonable support design and frequent roadway accidents.

[0004] In summary, there is a technical problem in the prior art that the support strength of underground mine roadways cannot be scientifically, accurately and quantitatively predicted and evaluated, and thus the failure of roadway support cannot be detected in time and repaired in a targeted manner, ultimately leading to frequent roadway support accidents. Summary of the Invention

[0005] The purpose of this application is to provide an intelligent prediction method for the support strength of underground mine roadways, so as to solve the technical problem in the prior art that the support strength of underground mine roadways cannot be scientifically, accurately and quantitatively predicted and evaluated, and thus the failure of roadway support cannot be detected in time and repaired in a targeted manner, ultimately leading to frequent roadway support accidents.

[0006] In view of the above problems, this application provides an intelligent prediction method for the support strength of underground mine roadways.

[0007] In a first aspect, the present application provides an intelligent prediction method for the support strength of underground mine roadways. The intelligent prediction method for the support strength of underground mine roadways is implemented through an intelligent prediction system for the support strength of underground mine roadways. Among them, the intelligent prediction method for the support strength of underground mine roadways includes: reading predetermined support features, and collecting multi-dimensional features of the target roadway support based on the predetermined support features to obtain target support feature information; analyzing the target support feature information to obtain a target system strength index; building a support impact resistance database based on big data, and extracting the first simulation impact resistance record in the support impact resistance database; introducing an impact resistance ability evaluation function to evaluate and analyze the first simulation impact resistance record to obtain a first simulation impact resistance index; denoting the mean value of the first simulation impact resistance index as the target system impact resistance index; using the target system strength index and the target system impact resistance index as input information of a strength prediction model to obtain output information, where the output information includes the target support strength of the target roadway support.

[0008] In a second aspect, the present application further provides an intelligent prediction system for the support strength of underground mine roadways, which is used to execute the intelligent prediction method for the support strength of underground mine roadways as described in the first aspect. Among them, the intelligent prediction system for the support strength of underground mine roadways includes: a feature collection module, which is used to read predetermined support features and collect multi-dimensional features of the target roadway support based on the predetermined support features to obtain target support feature information; a strength analysis module, which is used to analyze the target support feature information to obtain a target system strength index; a simulation acquisition module, which is used to build a support impact resistance database based on big data and extract the first simulation impact resistance record in the support impact resistance database; a first impact resistance analysis module, which is used to introduce an impact resistance ability evaluation function to evaluate and analyze the first simulation impact resistance record to obtain a first simulation impact resistance index; a second impact resistance analysis module, which is used to denote the mean value of the first simulation impact resistance index as the target system impact resistance index; a strength prediction module, which is used to use the target system strength index and the target system impact resistance index as input information of a strength prediction model to obtain output information, where the output information includes the target support strength of the target roadway support.

[0009] In a third aspect, a computer-readable storage medium stores a computer program, and when the computer program is executed, it implements the steps of the intelligent prediction method for the support strength of underground mine roadways as described in any item of the first aspect above.

[0010] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0011] By reading predetermined support features and collecting multi-dimensional features of the target roadway support based on the predetermined support features, target support feature information is obtained; analyzing the target support feature information to obtain a target system strength index; building a support impact resistance database based on big data and extracting the first simulation impact resistance record in the support impact resistance database; introducing an impact resistance evaluation function to evaluate and analyze the first simulation impact resistance record to obtain a first simulation impact resistance index; denoting the mean value of the first simulation impact resistance index as the target system impact resistance index; using the target system strength index and the target system impact resistance index as input information of a strength prediction model to obtain output information, where the output information includes the target support strength of the target roadway support. That is to say, first, read the predetermined support features and collect multi-dimensional features of the target roadway support based on these features to obtain target support feature information. Then, analyze this information to obtain a target system strength index, which reflects the strength level of the roadway support. Next, based on big data technology, build a support impact resistance database and extract the first simulation impact resistance record therein. Introduce an impact resistance evaluation function to evaluate and analyze these records to obtain a first simulation impact resistance index. Denote the mean value of this index as the target system impact resistance index, representing the ability of the support system to resist impacts. Finally, use the target system strength index and the target system impact resistance index as input information and send them into the strength prediction model. After the model processes the information, the output information includes the target support strength of the target roadway support, which is a prediction of the expected performance of the roadway support in actual work. Through this series of data collection, analysis, and modeling processes, a scientific and systematic method for evaluating the strength of roadway support is provided, which helps to predict and prevent the risk of support failure in advance in actual engineering.

[0012] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present application more obvious and understandable, the following specifically illustrates the specific embodiments of the present application. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easily understood through the following description. Description of the Drawings

[0013] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings described below are only exemplary, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0014] Figure 1Schematic flow chart of an intelligent prediction method for the support strength of underground mine roadways in this application;

[0015] Figure 2 Schematic structural diagram of an intelligent prediction system for the support strength of underground mine roadways in this application.

[0016] Explanation of reference numerals:

[0017] Feature collection module 11, strength analysis module 12, simulation acquisition module 13, first impact resistance analysis module 14, second impact resistance analysis module 15, strength prediction module 16. Detailed implementation manners

[0018] By providing an intelligent prediction method for the support strength of underground mine roadways in this application, the technical problem in the prior art that it is impossible to scientifically, accurately, and quantitatively predict and evaluate the support strength of underground mine roadways, and thus impossible to timely detect the failure of roadway support and carry out targeted maintenance in a timely manner, resulting in frequent roadway support accidents is solved. The technical effect of accurately predicting the support strength of roadways, providing a scientific basis for roadway support design and application guidance, and improving the stability and safety of roadway support is achieved.

[0019] Next, the technical solutions in this application will be described clearly and completely with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited by the example embodiments described here. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application. Additionally, it should be noted that for the sake of description, only the parts related to this application are shown in the accompanying drawings rather than all.

[0020] Embodiment 1. Please refer to the attached Figure 1 This application provides an intelligent prediction method for the support strength of underground mine roadways. Among them, the intelligent prediction method for the support strength of underground mine roadways is applied to an intelligent prediction system for the support strength of underground mine roadways. The intelligent prediction method for the support strength of underground mine roadways specifically includes the following steps:

[0021] Step 1: Read the predetermined support features, and collect multi-dimensional features of the target roadway support based on the predetermined support features to obtain target support feature information.

[0022] Step 2: Analyze the target support feature information to obtain a target system strength index.

[0023] Step 3: Build a support impact resistance database based on big data, and extract the first simulation impact resistance records in the support impact resistance database.

[0024] Step 4: Introduce an impact resistance evaluation function to evaluate and analyze the first simulated impact resistance record, and obtain the first simulated impact resistance index.

[0025] Step 5: Denote the mean value of the first simulated impact resistance index as the target system impact resistance index.

[0026] Step 6: Use the target system strength index and the target system impact resistance index as the input information of the strength prediction model to obtain output information, where the output information includes the target support strength of the target roadway support.

[0027] Specifically, first read the predetermined support characteristics, and collect multi-dimensional characteristics of the target roadway support based on these characteristics to obtain the target support characteristic information. This step aims to establish the basis for analysis and ensure the accuracy and comprehensiveness of the subsequent analysis data. Traditional roadway support design relies on simplified assumptions and empirical formulas, which may lead to under-design or over-support. By reading the predetermined support characteristics and collecting multi-dimensional characteristics, more accurate support characteristic information can be obtained, thereby improving the accuracy of support design. Then, analyze the target support characteristic information to obtain the target system strength index. This provides a preliminary assessment of the strength of the support system. Due to the complexity and uncertainty of geological conditions, roadway support accidents occur frequently. By analyzing the target support characteristic information and obtaining the target system strength index, the safety of the support structure can be better evaluated, and the occurrence of support accidents can be reduced. Next, establish a support impact resistance database based on big data, and extract the first simulated impact resistance record from the database. This step involves the application of big data, and by extracting the simulation record, it prepares for the subsequent evaluation and analysis. In addition, introduce an impact resistance evaluation function to evaluate and analyze the first simulated impact resistance record to obtain the first simulated impact resistance index. This index is a quantitative assessment of the impact resistance of the support system. Denote the mean value of the first simulated impact resistance index as the target system impact resistance index. Finally, use the target system strength index and the target system impact resistance index as the input information of the strength prediction model, and through the processing of the model, obtain output information, including the target support strength of the target roadway support. This series of actions are linked together to achieve an accurate evaluation and prediction of the target roadway support strength. Through this analysis method, not only the accuracy of the evaluation is improved, but also strong data support is provided for the design and optimization of roadway support.

[0028] Furthermore, the intelligent prediction method for the support strength of underground mine roadways further includes: the predetermined support characteristics at least include the length of the top cable bolt, the spacing of the top cable bolts, the row spacing of the top cable bolts, and the anchoring length, and the anchoring length includes the top anchoring length and the rib anchoring length.

[0029] Specifically, first, an overall analysis is conducted on the predetermined support features, which include the length of the top cable bolts, the spacing of the top cable bolts, the row spacing of the top cable bolts, and the anchorage length. These parameters are key elements in the roadway support design and directly affect the stability and safety of the support structure. By accurately measuring and setting these parameters, it can be ensured that the support system can effectively withstand underground pressure and impact, thereby guaranteeing the stability and safety of the roadway. Specifically, first, determine the length of the top cable bolts, which is the distance that the cable bolts extend into the deep surrounding rock and affects the anchoring force and support effect. Then, set the spacing of the top cable bolts, that is, the lateral distance between the cable bolts, which determines the uniformity and overall stability of the support. Next, consider the row spacing of the top cable bolts, that is, the longitudinal distance between the cable bolts, which affects the load-bearing capacity and deformation resistance of the anchoring structure. In addition, the anchorage length is also an important parameter, including the top anchorage length and the rib anchorage length. The top anchorage length refers to the anchoring depth of the cable bolts in the roof, while the rib anchorage length refers to the anchoring depth of the cable bolts in the rib of the roadway. The setting of these two parameters needs to comprehensively consider the properties of the surrounding rock, the stress state, and the support requirements to ensure the anchoring effect and support efficiency. Finally, by accurately measuring and setting these predetermined support features, a scientific design basis can be provided for the roadway support. The reasonable configuration of these parameters helps to improve the stability of the support structure, enhance its ability to resist underground pressure and impact, and thus ensure the safety and long-term stability of the roadway.

[0030] Furthermore, the intelligent prediction method for the support strength of an underground mine roadway further includes: reading a predetermined exposed length value; reading the anchorage length value of the anchorage length, where the anchorage length value includes a top anchorage length value and a rib anchorage length value; the predetermined exposed length value, the top anchorage length value, and the rib anchorage length value together form a predetermined limit value; reading a predetermined reinforcement arch strategy, and analyzing and calculating the predetermined limit value based on the predetermined reinforcement arch strategy to obtain the parameter value of the length of the top cable bolts, denoted as the top cable bolt length value; reading a predetermined spacing and row strategy, and analyzing and calculating based on the predetermined spacing and row strategy to obtain the parameter values of the spacing of the top cable bolts and the row spacing of the top cable bolts, denoted as the top cable bolt spacing value and the top cable bolt row spacing value respectively; the predetermined limit value, the top cable bolt length value, the top cable bolt spacing value, and the top cable bolt row spacing value together form the target support feature information.

[0031] Specifically, first, this process involves reading and calculating multiple key parameters to determine the target support feature information. It mainly includes the predetermined exposed length value, the anchorage length value (divided into the top anchorage length value and the rib anchorage length value), and the top cable bolt length value, the top cable bolt spacing value, and the top cable bolt row spacing value calculated based on the predetermined reinforcement arch strategy and the predetermined spacing and row strategy. These parameters together constitute a detailed description of the roadway support design and are crucial for ensuring the stability and safety of the roadway.

[0032] Specifically, first, read the predetermined exposed length value, which is the length of the cable bolt exposed outside the surrounding rock and has a direct impact on the overall performance of the cable bolt. Then, read the anchoring length values, including the top anchoring length value and the rib anchoring length value, which determine the bonding strength and anchoring effect between the cable bolt and the surrounding rock. Next, combine the predetermined exposed length value with the top anchoring length value and the rib anchoring length value to jointly form a predetermined limit value. This limit value is the basic requirement for the support design and affects the overall performance of the support structure. Based on the predetermined reinforcement arch strategy, analyze and calculate the predetermined limit value to obtain the parameter value of the top cable bolt length, that is, the top cable bolt length value. This step is an important link in determining the cable bolt length and requires comprehensive consideration of the surrounding rock conditions, support requirements, and the effect of the reinforcement arch. In addition, read the predetermined spacing and row spacing strategy and analyze and calculate the top cable bolt spacing value and the top cable bolt row spacing value based on this strategy. These values have a significant impact on the layout method and support effect of the cable bolt and need to be determined according to specific engineering conditions and design requirements. Finally, the predetermined limit value, the top cable bolt length value, the top cable bolt spacing value, and the top cable bolt row spacing value jointly form the target support characteristic information. These information provide detailed parameter basis for the roadway support design, help to ensure the stability and safety of the support structure, and improve the overall support effect of the roadway.

[0033] Furthermore, the intelligent prediction method for the support strength of an underground mine roadway further includes: performing standardization processing on the target support characteristic information to obtain target standardized support characteristic information; performing variation weighted calculation on the target standardized support characteristic information by using the coefficient of variation principle to obtain a target variation weighted result; and denoting the target variation weighted result as the target system strength index.

[0034] Specifically, first, standardize the target support characteristic information. The purpose of this step is to eliminate the influence of dimensions between different parameters, enabling each parameter to be compared and analyzed on the same scale. Through standardization, the target standardized support characteristic information can be obtained, which serves as the basis for subsequent analysis and calculation. Specifically, first, standardize the target support characteristic information. This typically involves subtracting the mean value of each parameter from its value and then dividing by the standard deviation. In this way, each parameter is converted into dimensionless data, with its mean value becoming 0 and the standard deviation becoming 1. This processing method helps eliminate the influence of dimensions, allowing direct comparison between different parameters. Then, use the coefficient of variation principle to perform variation weighting calculation on the target standardized support characteristic information. The coefficient of variation is an index that measures the relative dispersion of data, taking into account the mean value and standard deviation of the data. In the variation weighting calculation, the weight of each parameter is determined by its coefficient of variation, that is, the greater the data fluctuation, the higher its weight. This weighting method can highlight the parameters that have a greater impact on the support effect, making the analysis results more accurate and reliable. Finally, record the target variation weighting result as the target system strength index. This index is a comprehensive evaluation of the strength of the target support system, considering the influence of multiple parameters and weighted by the coefficient of variation principle. The target system strength index can be used as an important indicator to evaluate and compare the strength and stability of different support schemes. Through this analysis and calculation method, a scientific and accurate evaluation basis can be provided for roadway support design.

[0035] Furthermore, the intelligent prediction method for the roadway support strength in an underground mine further includes: the first simulation impact resistance record refers to the record of the impact resistance simulation test of the first vibration event on the target roadway support; wherein, the first simulation impact resistance record includes the first vibration kinetic energy and the first vibration potential energy of the first vibration event and the first simulation energy absorption of the target roadway support, and the first simulation energy absorption includes the first simulation energy absorption of the top cable bolts and the first simulation energy absorption of the side bolts; obtain the first source distance of the first vibration event, and retrieve the impact resistance evaluation function to analyze the first simulation impact resistance record to obtain the first simulation impact resistance index.

[0036] Specifically, first, an overall analysis is conducted on the first simulation anti-impulse records. These records are from the anti-impulse simulation tests of the first vibration event on the support of the target roadway. They contain key information such as the first vibration kinetic energy and the first vibration potential energy of the first vibration event, as well as the first simulation energy absorption of the target roadway support, and the latter includes the first simulation energy absorption of the top cable bolts and the first simulation energy absorption of the rib bolts. These data are crucial for evaluating the anti-impulse ability and stability of the support structure. Specifically, first, obtain the first source distance of the first vibration event. This refers to the distance from the vibration source to the roadway support and plays an important role in evaluating the vibration impact and support response. Then, retrieve the anti-impulse ability evaluation function, which is a key tool for analyzing and evaluating the anti-impulse ability of the support structure. Next, use the anti-impulse ability evaluation function to analyze the first simulation anti-impulse records. This analysis involves a comprehensive consideration of the first vibration kinetic energy, the first vibration potential energy, and the first simulation energy absorption. The first simulation energy absorption, especially the simulation energy absorption of the top cable bolts and the rib bolts, is an important indicator for evaluating the energy absorption ability of the support structure. Finally, obtain the first simulation anti-impulse index through analysis. This index is a quantitative evaluation of the anti-impulse ability shown by the support structure in the first vibration event. It comprehensively considers the vibration energy and the energy absorption characteristics of the support structure, providing an important basis for evaluating the anti-impulse performance of the support structure.

[0037] Furthermore, the intelligent prediction method for the support strength of underground mine roadways further includes: The expression of the anti-impulse ability evaluation function is as follows: where E(x) refers to the first simulation anti-impulse index of the target roadway support under the first vibration event x, A cable and A bolt respectively refer to the first simulation energy absorption of the top cable bolts and the first simulation energy absorption of the rib bolts, R1(x) and R2(x) respectively refer to the first vibration kinetic energy and the first vibration potential energy of the first vibration event x, e refers to the attenuation coefficient, and r refers to the first source distance.

[0038] Specifically, the expression of the anti-impulse ability evaluation function is as follows: where E(x) refers to the first simulation anti-impulse index of the target roadway support under the first vibration event x, A cable and A bolt respectively refer to the first simulation energy absorption of the top cable bolts and the first simulation energy absorption of the rib bolts, R1(x) and R2(x) respectively refer to the first vibration kinetic energy and the first vibration potential energy of the first vibration event x, e refers to the attenuation coefficient, and r refers to the first source distance.

[0039] Furthermore, the intelligent prediction method for the support strength of underground mine roadways further includes: obtaining the first vibration energy of the first vibration event; when the first vibration energy meets the energy limit, performing an impact resistance simulation on the first vibration event.

[0040] Specifically, first analyze the first vibration energy of the first vibration event. This is a quantification of the energy magnitude of the vibration event and is crucial for evaluating the impact of the vibration on roadway support. The magnitude of the vibration energy is directly related to the impact force that the support structure needs to withstand, so it is an important input parameter for the impact resistance simulation test. When the first vibration energy meets the energy limit, that is, the vibration energy is within a predetermined range, perform an impact resistance simulation on the first vibration event. This step ensures the pertinence and practicality of the simulation test. Only when the vibration energy reaches a certain level and may have a significant impact on the support structure does it make sense to perform an impact resistance simulation. Finally, in this way, the vibration events that need to be simulated can be effectively screened out, ensuring the efficiency and accuracy of the simulation test.

[0041] Furthermore, the intelligent prediction method for the support strength of underground mine roadways further includes: constructing a prediction training data set, where the prediction training data set includes a prediction training strength index, a prediction training impact resistance index, and a prediction training support strength; performing supervised learning and verification on the prediction training data set to obtain the strength prediction model.

[0042] Specifically, first construct a prediction training data set. This data set is the basis for constructing the strength prediction model and contains key data such as the prediction training strength index, the prediction training impact resistance index, and the prediction training support strength. These data reflect the strength and impact resistance performance of the roadway under different support conditions and are crucial for training an accurate and reliable prediction model. Specifically, first collect and organize historical support data, including strength indexes, impact resistance indexes, and support strengths under various support conditions. Then, integrate these data into the prediction training data set. This data set needs to be large enough and representative to ensure that the trained model has good generalization ability. Next, perform supervised learning on the prediction training data set. This means using the known support strength as a label and training the model through machine learning algorithms so that it can predict the support strength based on the strength index and the impact resistance index. In this process, the model will learn the relationships between different parameters and how they jointly affect the support strength. Finally, verify the trained model. This is to evaluate the prediction accuracy of the model and ensure that it can provide reliable results in practical applications. In this way, a verified strength prediction model can be obtained, which can predict the support strength of the target roadway based on the input strength index and impact resistance index.

[0043] In summary, the intelligent prediction method for the support strength of underground mine roadways provided by this application has the following technical effects:

[0044] By reading the predetermined support features and collecting multi-dimensional features of the target roadway support based on the predetermined support features, target support feature information is obtained; analyzing the target support feature information to obtain a target system strength index; building a support impact resistance database based on big data and extracting the first simulation impact resistance record in the support impact resistance database; introducing an impact resistance ability evaluation function to evaluate and analyze the first simulation impact resistance record to obtain a first simulation impact resistance index; denoting the mean value of the first simulation impact resistance index as the target system impact resistance index; using the target system strength index and the target system impact resistance index as the input information of the strength prediction model to obtain output information, where the output information includes the target support strength of the target roadway support. That is to say, first, read the predetermined support features and collect multi-dimensional features of the target roadway support based on these features to obtain target support feature information. Then, analyze this information to obtain a target system strength index, which reflects the strength level of the roadway support. Next, based on big data technology, build a support impact resistance database and extract the first simulation impact resistance record therein. Introduce an impact resistance ability evaluation function to evaluate and analyze these records to obtain a first simulation impact resistance index. Denote the mean value of this index as the target system impact resistance index, representing the ability of the support system to resist impacts. Finally, use the target system strength index and the target system impact resistance index as input information and send them into the strength prediction model. After the model processes the information, the output information includes the target support strength of the target roadway support, which is a prediction of the expected performance of the roadway support in actual work. Through this series of data collection, analysis, and modeling processes, a scientific and systematic method is provided for the strength evaluation of roadway supports, which helps to predict and prevent the risk of support failure in advance in actual engineering.

[0045] Embodiment 2. Based on the same inventive concept as the intelligent prediction method for the support strength of underground mine roadways in the foregoing embodiment, this application also provides an intelligent prediction system for the support strength of underground mine roadways. Please refer to the attached Figure 2 , the intelligent prediction system for the support strength of underground mine roadways includes:

[0046] A feature collection module 11, which is used to read predetermined support features and collect multi-dimensional features of the target roadway support based on the predetermined support features to obtain target support feature information; a strength analysis module 12, which is used to analyze the target support feature information to obtain a target system strength index; a simulation acquisition module 13, which is used to build a support impact resistance database based on big data and extract the first simulation impact resistance record in the support impact resistance database; a first impact resistance analysis module 14, which is used to introduce an impact resistance ability evaluation function to evaluate and analyze the first simulation impact resistance record to obtain a first simulation impact resistance index; a second impact resistance analysis module 15, which is used to record the mean value of the first simulation impact resistance index as the target system impact resistance index; a strength prediction module 16, which is used to use the target system strength index and the target system impact resistance index as input information of a strength prediction model to obtain output information, and the output information includes the target support strength of the target roadway support.

[0047] Further, the feature collection module 11 in the intelligent prediction system for the support strength of underground mine roadways is further used for: the predetermined support features at least include the top cable length, the top cable spacing, the top cable row spacing, and the anchorage length, and the anchorage length includes the top anchorage length and the rib anchorage length.

[0048] Further, the feature collection module 11 in the intelligent prediction system for the support strength of underground mine roadways is further used for: reading a predetermined exposed length value; reading the anchorage length values of the anchorage length, where the anchorage length values include the top anchorage length value and the rib anchorage length value; the predetermined exposed length value, the top anchorage length value, and the rib anchorage length value together form a predetermined limit value; reading a predetermined reinforcement arch strategy and analyzing and calculating the predetermined limit value based on the predetermined reinforcement arch strategy to obtain the parameter value of the top cable length, denoted as the top cable length value; reading a predetermined spacing and row strategy and analyzing and calculating based on the predetermined spacing and row strategy to obtain the parameter values of the top cable spacing and the top cable row spacing, denoted as the top cable spacing value and the top cable row spacing value respectively; the predetermined limit value, the top cable length value, the top cable spacing value, and the top cable row spacing value together form the target support feature information.

[0049] Further, the strength analysis module 12 in the intelligent prediction system for the support strength of underground mine roadways is further configured to: perform standardization processing on the target support feature information to obtain target standardized support feature information; perform variation weighting calculation on the target standardized support feature information by using the coefficient of variation principle to obtain a target variation weighting result; and record the target variation weighting result as the target system strength index.

[0050] Further, the first impact resistance analysis module 14 in the intelligent prediction system for the support strength of underground mine roadways is further configured to: the first simulation impact resistance record refers to the record of the impact resistance simulation test of the target roadway support for the first vibration event; wherein, the first simulation impact resistance record includes the first vibration kinetic energy, the first vibration potential energy of the first vibration event, and the first simulation energy absorption of the target roadway support, and the first simulation energy absorption includes the first top cable bolt simulation energy absorption and the first rib bolt simulation energy absorption; obtain the first source distance of the first vibration event, and call the impact resistance evaluation function to analyze the first simulation impact resistance record to obtain the first simulation impact resistance index.

[0051] Further, the first impact resistance analysis module 14 in the intelligent prediction system for the support strength of underground mine roadways is further configured to: the expression of the impact resistance evaluation function is as follows: wherein, E(x) refers to the first simulation impact resistance index of the target roadway support under the first vibration event x, A cable and A bolt respectively refer to the first top cable bolt simulation energy absorption and the first rib bolt simulation energy absorption, R1(x) and R2(x) respectively refer to the first vibration kinetic energy and the first vibration potential energy of the first vibration event x, e refers to the attenuation coefficient, and r refers to the first source distance.

[0052] Further, the simulation acquisition module 13 in the intelligent prediction system for the support strength of underground mine roadways is further configured to: obtain the first vibration energy of the first vibration event; when the first vibration energy meets the energy limit value, perform impact resistance simulation on the first vibration event.

[0053] Further, the strength prediction module 16 in the intelligent prediction system for the support strength of underground mine roadways is further configured to: construct a prediction training data set, where the prediction training data set includes a prediction training strength index, a prediction training impact resistance index, and a prediction training support strength; perform supervised learning and verification on the prediction training data set to obtain the strength prediction model.

[0054] The various embodiments in this specification are described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The aforesaid Figure 1 An intelligent prediction method and specific example of the support strength of underground mine roadways in the first embodiment are equally applicable to the intelligent prediction system of the support strength of underground mine roadways in this embodiment. Through the detailed description of the intelligent prediction method of the support strength of underground mine roadways, those skilled in the art can clearly understand the intelligent prediction system of the support strength of underground mine roadways in this embodiment. Therefore, for the sake of simplicity of the specification, it will not be elaborated here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For related parts, refer to the description in the method section.

[0055] Embodiment 3: Based on the same inventive concept as the intelligent prediction method of the support strength of underground mine roadways in the foregoing embodiments, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, it implements the steps of the intelligent prediction method of the support strength of underground mine roadways described in any one of the foregoing Embodiment 1.

[0056] 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 obvious to those skilled in the art. The general principles defined herein can 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 these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0057] 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 fall within the scope of the present application and its equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. An intelligent prediction method for underground mine tunnel support strength, characterized in that: include: Reading predetermined support features, and collecting multi-dimensional features of target tunnel support based on the predetermined support features to obtain target support feature information; Analyzing the target support characteristic information to obtain a target system strength index; Establishing a support and impact resistance database based on big data, and extracting the first simulation impact resistance record in the support and impact resistance database; Introducing an impact resistance evaluation function to evaluate and analyze the first simulation impact resistance record to obtain a first simulation impact resistance index; Recording the average value of the first simulation impact resistance index as the target system impact resistance index; The target system strength index and the target system impact resistance index are used as input information of a strength prediction model to obtain output information, wherein the output information includes the target support strength of the target tunnel support; The predetermined support characteristics at least include top anchor cable length, top anchor cable spacing, top anchor cable row spacing and anchor length, and the anchor length includes top anchor length and side anchor length; The first simulation anti-impact record refers to a record of an anti-impact simulation test of a first vibration event on the target tunnel support; The first simulated impact resistance record includes the first vibration kinetic energy, the first vibration potential energy of the first vibration event and the first simulated energy absorption of the target tunnel support, and the first simulated energy absorption includes the first top anchor cable simulated energy absorption and the first side anchor rod simulated energy absorption; Acquiring a first earthquake source distance of the first vibration event, and calling the shock resistance evaluation function to analyze the first simulation shock resistance record to obtain the first simulation shock resistance index; The expression of the impact resistance evaluation function is as follows: Wherein, E(x) refers to the first simulation impact resistance index of the target tunnel support under the first vibration event, A cable and A bolt They respectively refer to the simulated energy absorption of the first top anchor cable and the simulated energy absorption of the first side anchor rod, R1(x) and R2(x) respectively refer to the first vibration kinetic energy and the first vibration potential energy of the first vibration event, e refers to the attenuation coefficient, and r refers to the first earthquake source distance.

2. The intelligent prediction method for underground mine tunnel support strength according to claim 1, characterized in that: include: Read the predetermined exposed length value; Read the anchoring length value of the anchoring length, wherein the anchoring length value includes the top anchoring length value and the side anchoring length value; The predetermined exposed length value, the top anchoring length value, and the side anchoring length value together constitute a predetermined limit value; Reading a predetermined reinforcement arch strategy, and analyzing and calculating the predetermined limit value based on the predetermined reinforcement arch strategy to obtain a parameter value of the top anchor cable length, which is recorded as the top anchor cable length value; Reading a predetermined spacing strategy, and analyzing and calculating the parameter values ​​of the top anchor cable spacing and the top anchor cable row spacing based on the predetermined spacing strategy, which are recorded as the top anchor cable spacing value and the top anchor cable row spacing value respectively; The predetermined limit value, the top anchor cable length value, the top anchor cable spacing value and the top anchor cable row spacing value together constitute the target support characteristic information.

3. The intelligent prediction method for underground mine tunnel support strength according to claim 1 is characterized in that: include: Standardizing the target support characteristic information to obtain target standardized support characteristic information; Using the coefficient of variation principle, a weighted variation calculation is performed on the target standardized support characteristic information to obtain a target variation weighted result; The target variation weighted result is recorded as the target system strength index.

4. The intelligent prediction method for underground mine tunnel support strength according to claim 1 is characterized in that: Also includes: Acquiring a first vibration energy of the first vibration event; When the first vibration energy meets the energy limit, an impact simulation is performed on the first vibration event.

5. The intelligent prediction method for underground mine tunnel support strength according to claim 1, characterized in that: include: Establishing a prediction training data set, wherein the prediction training data set includes a prediction training intensity index, a prediction training impact resistance index, and a prediction training support strength; The intensity prediction model is obtained by performing supervised learning and testing on the prediction training data set.

6. An intelligent prediction system for underground mine tunnel support strength, characterized in that: The steps for implementing the intelligent prediction method of underground mine tunnel support strength according to any one of claims 1 to 5 include: A feature collection module, the feature collection module is used to read the predetermined support features, and based on the predetermined support features, perform multi-dimensional feature collection on the target tunnel support to obtain target support feature information; A strength analysis module, the strength analysis module is used to analyze the target support characteristic information to obtain a target system strength index; A simulation acquisition module, the simulation acquisition module is used to establish a support and impact resistance database based on big data, and extract the first simulation impact resistance record in the support and impact resistance database; A first impact resistance analysis module, the first impact resistance analysis module is used to introduce an impact resistance capability evaluation function to evaluate and analyze the first simulation impact resistance record to obtain a first simulation impact resistance index; A second impact analysis module, wherein the second impact analysis module is used to record the average value of the first simulation impact index as the target system impact index; A strength prediction module is used to use the target system strength index and the target system impact resistance index as input information of a strength prediction model to obtain output information, wherein the output information includes the target support strength of the target tunnel support.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed, implements the steps of an intelligent prediction method for the support strength of underground mine tunnels as described in any one of claims 1 to 5.

Images