An analytical method and system for the mechanism of roadway floor heave

Abstract

This invention provides a method and system for analyzing the mechanism of roadway floor heave, belonging to the technical field of roadway floor heave mechanism analysis. The invention first deploys multiple monitoring points within the roadway to collect real-time monitoring data, including pressure, vibration, temperature, and humidity data. Based on the monitoring data, the discrete element method and the finite element method are applied to construct microscopic and macroscopic models of the roadway. A state assessment is performed on historical monitoring data and corresponding contact forces and total stresses using an expert scoring method, constructing a risk prediction model based on the random forest algorithm. The model predicts the current state of each monitoring point to identify those with anomalies. The floor heave risk index at the abnormal monitoring points is analyzed to determine whether an early warning should be issued. This method effectively integrates multi-source data and model analysis, providing a scientific basis for roadway safety. Through this method, early warning of roadway floor heave risk can be achieved, helping to reduce safety hazards.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of analysis of roadway floor heave mechanism, in particular to a method and system for analyzing the mechanism of roadway floor heave. BACKGROUND

[0002] Roadway floor heave is a common geological phenomenon in underground mines, tunnels and other underground engineering, which refers to the surface subsidence or bottom uplift phenomenon caused by factors such as pressure change, soil structure damage or hydrological condition change. This phenomenon not only affects the safety and stability of underground engineering, but also may have adverse effects on the surrounding environment, and even cause safety accidents.

[0003] In modern mining and underground engineering, the phenomenon of roadway floor heave is a common and serious technical problem. The generation of floor heave is usually closely related to the surrounding geological conditions, construction methods and the passage of time. Traditional analysis methods of roadway floor heave often rely on experience and simple physical models, which leads to insufficient prediction of the stress state of the roadway in complex geological environments, and it is difficult to accurately identify the potential risks of floor heave. This deficiency not only leads to construction safety hazards, but also delays the progress of the project and increases the cost.

[0004] The existing technology has the following deficiencies:

[0005] The deficiencies of the prior art mainly lie in the insufficient timeliness of data collection and processing, the limited accuracy of model establishment and the poor adaptability to complex geological conditions. Traditional monitoring methods often rely on a single sensor, resulting in incomplete data and failing to fully reflect the true state of the roadway. In addition, existing numerical models often fail to achieve ideal accuracy when dealing with complex geological environments, dynamic changes and multi-factor coupling, thereby affecting the accuracy and timeliness of risk assessment. These deficiencies make the monitoring and early warning system of roadway floor heave face challenges in practical application, and urgent improvement and innovation are needed.

[0006] The above information disclosed in the background section is only used to strengthen the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0007] The purpose of the present application is to provide a method and system for analyzing the mechanism of roadway floor heave to solve the problems raised in the background.

[0008] To achieve the above purpose, the present application provides the following technical solutions:

[0009] A method for analyzing the mechanism of roadway floor heave, the specific steps include:

[0010] Step 1: multiple monitoring points are arranged in the tunnel to collect monitoring data, pressure, vibration, temperature and humidity data of the monitoring points at the current time, and historical monitoring data of the monitoring points at past historical times, the monitoring data including stress, displacement and material parameters;

[0011] Step 2: based on the monitoring data, a micro model and a macro model of the tunnel are constructed, and the micro model is coupled with the macro model to obtain contact force and total stress data of particles in the tunnel corresponding to the monitoring data;

[0012] Step 3: using expert scoring method, the historical monitoring data of the monitoring points at the past historical times and the corresponding contact force and total stress data are evaluated, and corresponding state labels are given, a risk prediction model is constructed based on random forest algorithm, and the historical monitoring data and the corresponding contact force and total stress data are taken as inputs, and the state labels are taken as labels to train the risk prediction model, the state labels including normal state and abnormal state;

[0013] Step 4: the monitoring data, contact force and total stress data of each monitoring point at the current time are input into the risk prediction model to obtain the state labels of each monitoring point at the current time;

[0014] Step 5: analyzing the monitoring points with abnormal state labels, calculating the floor heave risk index of the monitoring point at the current time, and comparing with the preset risk threshold to determine whether to issue a warning.

[0015] Further, the specific logic for collecting data at the tunnel monitoring points is as follows:

[0016] Starting from the starting point of the tunnel, a monitoring point is set every 3 meters, and stress sensors, displacement sensors, pressure sensors, vibration sensors, temperature sensors and humidity sensors are arranged at the monitoring points to collect stress, displacement, pressure, vibration, temperature and humidity data at the monitoring points, the material parameters including normal stiffness, tangential stiffness, elastic modulus and Poisson's ratio of the material.

[0017] Further, the specific logic for constructing the micro model and the macro model of the tunnel is as follows:

[0018] The discrete element method is used to construct the micro soil model, and the contact force expression between particles in the model is as follows:

[0019] F ij =F n,ij +F t,ij =k n,ij ·δ n,ij +k t,ij ·δ t,ij

[0020] Wherein, Fij represents the contact force between particle i and particle j, F n,ij represents the normal force between particle i and particle j, F t,ij represents the tangential force between particle i and particle j, k n,ij is the normal stiffness of particle i and particle j, k t,ij is the tangential stiffness of particle i and particle j, δ n,ij is the normal displacement of particle i and particle j, δ t,ij is the tangential displacement of particle i and particle j, i and j are the indices of the particles;

[0021] The normal displacement of the particles is determined by the amount of overlap of the two particle contact points, and the calculation formula is:

[0022] δ n,ij = R i + R j - d ij , d ij < R i + R j

[0023] wherein R i is the radius of particle i, R j is the radius of particle j, d ij is the distance between the centers of particle i and particle j, when d ij ≥ R i + R j , there is no contact between the particles, the normal displacement δ n,ij = 0; the tangential displacement is the relative displacement in the contact surface, which can be directly calculated and obtained in the discrete element method model, and in the discrete element method model, the tangential force needs to satisfy the Coulomb friction condition:

[0024] F t ≤ μ· F n

[0025] wherein μ is the friction coefficient, if the tangential force F t exceeds the friction force limit, then slip occurs, and the tangential displacement needs to be adjusted again;

[0026] The formula for obtaining the normal stiffness between particles is:

[0027]

[0028] wherein E * is the equivalent elastic modulus, R * ij is the equivalent contact radius of particle i and particle j, the equivalent contact radius is dynamically calculated in the discrete element method model from the radii of particle i and particle j;

[0029]

[0030] where E i is the elastic modulus of particle i, E j is the elastic modulus of particle j, v i is the Poisson's ratio of particle i, v j is the Poisson's ratio of particle j;

[0031]

[0032] where R i is the radius of the contacting particle i, r j is the radius of the contacting particle j;

[0033] The tangential stiffness is calculated using an empirical ratio:

[0034] k t,ij = η · k n,ij

[0035] where η is a proportionality coefficient;

[0036] The formula used to construct the macroscopic roadway structure model using the finite element method is:

[0037] σ A = D · ∈

[0038] where σ A represents the macroscopic stress matrix, D is the elastic modulus matrix of the material, and ∈ is the strain matrix;

[0039] The formula used to calculate the total stress in the macroscopic model is:

[0040]

[0041] where σ macro represents the total stress in the macroscopic model, V represents the volume of the macroscopic model, F op represents the contact force between particle o and particle p in the microscopic model, n represents the total number of particles in the macroscopic model, o and p are the indices of the particles, and o, p ∈ [1, n], o ≠ p;

[0042] The formula used to couple the microscopic model and the macroscopic model, and to feed back the contact force in the microscopic model to the macroscopic model, is:

[0043]

[0044] where σ macro ' represents the total stress after coupling the microscopic model, k n,ab is the normal stiffness of particle a and particle b, k t,ab is the tangential stiffness of particle a and particle b, δn,ab is the normal displacement of particle a and particle b, δ t,ab is the tangential displacement of particle a and particle b, N represents the total number of particles in the micro model, a and b are the indices of the particles, a, b ∈ [1, N], a ≠ b;

[0045] The macro stress is fed back to the micro model, and the formula for correcting the contact force between particles is expressed as follows:

[0046] F ij ′=k n,ij ·δ n,ij +k t,ij ·δ t,ij +σ macro ·A ij

[0047] Wherein, F ij ′ represents the contact force between particle i and particle j after coupling the macro model, A ij is the contact area between particle i and particle j;

[0048] For the contact area of the spherical, the contact radius is calculated, and the formula is:

[0049] A ij =π|R * ij ·δ n,ij |

[0050] Wherein, R * ij is the equivalent contact radius of particle i and particle j, and the equivalent contact radius can be dynamically calculated from the radius of particle i and particle j in the discrete element method model.

[0051] Further, the specific logic for constructing the risk prediction model is:

[0052] The historical monitoring data of the monitoring points at the past historical moments and the corresponding contact force and total stress data are evaluated by expert scoring method, and are given labels of normal state or abnormal state, wherein the normal state is represented by a risk value B=0, and the abnormal state is represented by a risk value B=1. The historical monitoring data of the monitoring points at the past historical moments and the corresponding contact force and total stress data are normalized and integrated into a sample data set, and the sample data set is divided into a training set and a test set with a division ratio of 7:3. A risk prediction model is constructed based on a random forest algorithm, the historical monitoring data, the contact force and the total stress data in the training set are taken as inputs, and the corresponding state labels are taken as labels. The risk prediction model is trained, and the historical monitoring data, the contact force and the total stress in the test set are input to evaluate the performance of the model. The evaluation indexes include accuracy, precision and recall. If the change amplitudes of all evaluation indexes are less than 0.01 in five iterations, it is determined that the model training is completed. Further, the specific logic for the model to predict the state of the current moment is as follows:

[0053] The monitoring data, the contact force and the total stress data of each monitoring point at the current moment are normalized and input into the trained risk prediction model to obtain the risk value predicted by the model. If the risk value B=1, it is an abnormal state, and if the risk value B=0, it is a normal state. The abnormal state monitoring point is labeled.

[0054] Further, the specific logic for calculating the floor heave risk index of the abnormal state monitoring point at the current moment is as follows:

[0055] The stress, displacement, pressure, vibration, temperature and humidity data of the monitoring point labeled as an abnormal state are obtained, and the formula for obtaining the floor heave risk index is as follows:

[0056]

[0057] Wherein, R is the floor heave risk index, P is the pressure, E is the stress, D is the displacement, V is the vibration amplitude, T is the temperature, is the ideal temperature value, H is the humidity, is the ideal humidity value, ω1, ω2, ω3, ω4, ω5 are weight coefficients of each term respectively, 0<ω1<ω5<ω4<ω2<ω3<1, and ω1+ω2+ω3+ω4+ω5=1;

[0058] The floor heave risk index at the current moment is compared with the preset risk threshold value. If the floor heave risk index at the current moment is lower than the preset risk threshold value, the monitoring continues. If the floor heave risk index at the current moment is higher than the preset risk threshold value, the corresponding monitoring point has an abnormality, and a danger warning is issued.

[0059] The application further provides a roadway floor heave mechanism analysis system for implementing the roadway floor heave mechanism analysis method.

[0060] A data acquisition module is configured to arrange a plurality of monitoring points in the roadway to acquire monitoring data, pressure, vibration, temperature and humidity data of the monitoring points at a current time, and to acquire historical monitoring data of the monitoring points at past historical times, wherein the monitoring data includes stress, displacement and material parameters.

[0061] A multi-scale model construction module is configured to construct a micro model and a macro model of the roadway based on the monitoring data, and to couple the micro model and the macro model to acquire contact force and total stress data of particles in the roadway corresponding to the monitoring data.

[0062] A risk prediction model construction module is configured to use an expert scoring method to perform state evaluation on the historical monitoring data of the monitoring points at the past historical times and the corresponding contact force and total stress data, and to assign corresponding state labels, to construct a risk prediction model based on a random forest algorithm, and to train the risk prediction model by taking the historical monitoring data and the corresponding contact force and total stress data as inputs and taking the state labels as labels, wherein the state labels include a normal state and an abnormal state.

[0063] A real-time state prediction module is configured to input the monitoring data, contact force and total stress data of the monitoring points at the current time into the risk prediction model to acquire state labels of the monitoring points at the current time.

[0064] An abnormal state analysis module is configured to analyze the monitoring points labeled as the abnormal state, to calculate a floor heave risk index of the monitoring point at the current time, and to compare the floor heave risk index with a preset risk threshold to determine whether to issue a warning.

[0065] In the above technical solution, the application provides the following technical effects and advantages:

[0066] The application integrates multi-source data monitoring and advanced numerical simulation technology to realize real-time and comprehensive evaluation of the roadway floor heave risk, and has the significant advantage of effectively improving the accuracy and timeliness of monitoring. By arranging a plurality of sensors to acquire real-time stress, displacement and other key data, and combining the discrete element method and the finite element method to construct micro and macro models, the method can not only deeply analyze the complex mechanical behavior inside the roadway, but also can perform risk prediction through the random forest algorithm to realize accurate early warning. Combined with comprehensive analysis of data of the monitoring points in abnormal conditions, the floor heave risk can be timely identified. This systematic analysis method provides a scientific basis for roadway safety management, helps to identify potential risks in advance, reduces the accident rate, enhances the safety and stability of mine operation, and has high application value. BRIEF DESCRIPTION OF DRAWINGS

[0067] Figure 1 The whole method flowchart of the present application is shown in the figure;

[0068] Figure 2 The system structure diagram of the present application is shown in the figure. DETAILED DESCRIPTION

[0069] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application is further described in detail below in combination with specific embodiments.

[0070] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present application should be the commonly understood meanings by those skilled in the art. The terms "first", "second" and similar words used in the present application do not represent any order, number or importance, but are only used to distinguish different components. The terms "include" or "contain" and similar words mean that the elements or objects before the words cover the elements or objects listed after the words and their equivalents, without excluding other elements or objects. The terms "connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "up", "down", "left", "right" and the like are only used to represent relative positional relationships, which may change accordingly when the absolute positions of the described objects change.

[0071] Embodiment:

[0072] Please refer to Figure 1 The present application provides a technical scheme:

[0073] A method for analyzing the mechanism of roadway floor heave, the specific steps comprising:

[0074] Step 1: arranging a plurality of monitoring points in the roadway to collect monitoring data, pressure, vibration, temperature and humidity data of the monitoring points at the current time, and to obtain historical monitoring data of the monitoring points at past historical times, the monitoring data including stress, displacement and material parameters;

[0075] In this embodiment, the specific logic for collecting data at the roadway monitoring points is as follows:

[0076] Starting from the starting point of the roadway, a monitoring point is arranged every 3 meters, and stress sensors, displacement sensors, pressure sensors, vibration sensors, temperature sensors and humidity sensors are arranged at the monitoring points to collect stress, displacement, pressure, vibration, temperature and humidity data at the monitoring points, the material parameters including normal stiffness, tangential stiffness, elastic modulus and Poisson's ratio of the material, which can be obtained through literature query or material database.

[0077] The monitoring points are set every 3 meters in the roadway, and various sensors are arranged, so that various types of environmental and mechanical data can be obtained comprehensively and in real time. The collection of multi-dimensional data can effectively reflect the complex state inside the roadway and improve the comprehensiveness and accuracy of monitoring. Secondly, the combination of real-time data and historical monitoring data can better identify trends and change rules, thereby providing a scientific basis for early warning of the risk of roadway floor heave. This step lays a solid foundation for subsequent risk assessment and development of management measures.

[0078] Step 2: Based on the monitoring data, a micro model and a macro model of the roadway are constructed, and the micro model and the macro model are coupled to obtain the contact force and total stress data of the particles in the roadway under the corresponding monitoring data;

[0079] In this embodiment, the specific logic for constructing the micro model and the macro model of the roadway is as follows:

[0080] The discrete element method is used to construct the micro soil model, and the contact force expression between particles in the model is as follows:

[0081] F ij =F n,ij +F t,ij =k n,ij ·δ n,ij +k t,ij ·δ t,ij

[0082] Wherein, F ij represents the contact force of particle i and particle j, F n,ij represents the normal force of particle i and particle j, F t,ij represents the tangential force of particle i and particle j, k n,ij is the normal stiffness of particle i and particle j, k t,ij is the tangential stiffness of particle i and particle j, δ n,ij is the normal displacement of particle i and particle j, δ t,ij is the tangential displacement of particle i and particle j, i and j are the indices of the particles;

[0083] The normal displacement of the particle is determined by the overlap amount of the contact points of the two particles, and the calculation formula is:

[0084] δ n,ij =R i +R j -d ij , d ij <R i +R j

[0085] Wherein, R i is the radius of particle i, Rj Let d be the radius of particle j. ij Let d be the distance between the centers of particle i and particle j, when d ij ≥R i +R j At that time, there is no contact between the particles, and the normal displacement δ n,ij =0; Tangential displacement is the relative displacement within the contact surface, which can be directly calculated and obtained in this discrete element method model. Furthermore, in the discrete element method model, the tangential force must satisfy the Coulomb friction condition:

[0086] F t ≤μ·F n

[0087] Where μ is the coefficient of friction, if the tangential force F t If the friction limit is exceeded, slippage will occur, and the tangential displacement needs to be readjusted. The friction coefficient can be obtained from recommended values ​​in literature or theoretical models, such as: quartz sand μ∈[0.3,0.6], steel particles: μ∈[0.1,0.2], soil particles μ∈[0.4,0.8]. If there is no experimental data or literature reference, it can be estimated based on the properties of the granular material. For example, coarse particles have a higher friction coefficient, usually μ>0.4, while smooth particles have a lower friction coefficient, usually μ≈[0.1,0.3].

[0088] The formula used to obtain the normal stiffness between particles is:

[0089]

[0090] Among them, E * For the equivalent elastic modulus, R * ij Let be the equivalent contact radius of particle i and particle j. The equivalent contact radius can be dynamically calculated from the radii of particle i and particle j in the discrete element method model.

[0091]

[0092] Among them, E i Let E be the elastic modulus of particle i. j Let v be the elastic modulus of particle j. i Let v be the Poisson's ratio of particle i. j Let be the Poisson's ratio of particle j;

[0093]

[0094] Among them, R i R is the radius of the contacting particle i. j Let be the radius of the contacting particle j;

[0095] Tangential stiffness is calculated using empirical ratios:

[0096] k t,ij =η·k n,ij

[0097] Wherein, η is a proportional coefficient, usually take η = 1 / 3;

[0098] The macro model uses the finite element method to describe the continuum mechanics behavior of the roadway, and the macro roadway structure model is constructed using the finite element method, and the formula for obtaining the stress matrix is as follows:

[0099] σ A =D·∈

[0100] Wherein, σ A Indicates the macro stress matrix, D is the elastic modulus matrix of the material, and ∈ is the strain matrix;

[0101] The formula for calculating the total stress in the macro model is as follows:

[0102]

[0103] Wherein, σ macro Indicates the total stress in the macro model, V indicates the volume of the macro model, F op Indicates the contact force of particle o and particle p in the micro model, n indicates the total number of particles in the macro model, o and p are the indexes of the particles, and o, p ∈ [1, n], o≠p;

[0104] The formula for coupling the micro model and the macro model and feeding back the contact force in the micro model to the macro model is as follows:

[0105]

[0106] Wherein, σ macro Indicates the total stress after coupling the micro model, k n,ab The normal stiffness of particle a and particle b, k t,ab The tangential stiffness of particle a and particle b, δ n,ab The normal displacement of particle a and particle b, δ t,ab The tangential displacement of particle a and particle b, N indicates the total number of particles in the micro model, a and b are the indexes of the particles, a, b ∈ [1, N], a≠b;

[0107] The formula for feeding back the macro stress to the micro model and correcting the contact force between particles is as follows:

[0108] F ij ′=k n,ij ·δ n,ij +k t,ij ·δ t,ij +σmacro ·A ij

[0109] where Fij represents the contact force between particle i and particle j after coupling the macroscopic model, Aij ij ij is the contact area between particle i and particle j;

[0110] For a spherical contact area, the contact radius is calculated by the formula:

[0111] A ij = π|R * ij ·δ n,ij |

[0112] where Rij * ii is the equivalent contact radius of particle i and particle j, which can be dynamically calculated in the discrete element method model from the radii of particle i and particle j.

[0113] Analyzing stress, displacement, and material parameters in historical monitoring data, and combining discrete element method and finite element method to build micro and macro models, can effectively achieve a deep understanding of the internal mechanical behavior of the roadway. The micro model simulates the contact force between particles in detail through the discrete element method, capturing subtle mechanical interactions, while the macro model provides the overall stress distribution of the structure through the finite element method. This multi-level modeling approach not only improves the accuracy of the model, but also more realistically reflects the response of the roadway under different conditions. Secondly, by coupling the micro and macro models, dynamic feedback between the two is achieved, effectively integrating the contact force information of micro particles into macro stress analysis. This coupling method allows mechanical behavior at different scales to interact, improving the comprehensiveness and reliability of the model, providing a more solid foundation for risk assessment. For example, changes in micro parameters such as normal stiffness and tangential stiffness can directly affect the calculation of macro stress, and vice versa, making the model more adaptable and able to cope with complex and changing geological conditions.

[0114] Step 3: Using expert scoring method, state evaluation is performed on the historical monitoring data of the monitoring points at the past historical time and the corresponding contact force total stress data, and the corresponding state labels are assigned, a risk prediction model is constructed based on the random forest algorithm, and the historical monitoring data and the corresponding contact force and total stress data are taken as input, and the state label is taken as label to train the risk prediction model, the state label includes normal state and abnormal state;

[0115] In this embodiment, the specific logic for constructing the risk prediction model is as follows:

[0116] ​The historical monitoring data of the monitoring points at the past historical time and the corresponding contact force and total stress data are evaluated by the expert scoring method, and a label of normal state or abnormal state is given, wherein the normal state is represented by a risk value B=0, and the abnormal state is represented by a risk value B=1. The historical monitoring data of the monitoring points at the past historical time and the corresponding contact force and total stress data are normalized and integrated into a sample data set, and the sample data set is divided into a training set and a test set with a division ratio of 7:3. A risk prediction model is constructed based on a random forest algorithm, the historical monitoring data, contact force and total stress data in the training set are used as input, and the corresponding state label is used as a label. The risk prediction model is trained, and the historical monitoring data, contact force and total stress in the test set are input to evaluate the performance of the model. The evaluation indexes include accuracy, precision and recall. If the change amplitudes of all evaluation indexes are less than 0.01 in five iterations, it is determined that the model training is completed. By evaluating the historical monitoring data of the monitoring points at the past historical time and the corresponding contact force and total stress data by the expert scoring method, the experience and knowledge of the field experts can be effectively combined to give each monitoring point a label of normal state or abnormal state. This process ensures the objectivity and scientificity of the state label, making the subsequent risk assessment and prediction more reliable. The abnormal value elimination and mean filling of the historical monitoring data, and the standardization processing by Z-score can effectively improve the data quality. This preprocessing ensures the stability and consistency of the input data set, lays a solid foundation for subsequent model training, and reduces the influence of noise on the performance of the model. The risk prediction model is constructed based on the random forest algorithm, and the stress, displacement, contact force and total stress data in the training set are used for training, which can fully exploit the complex relationships between the data. As an integrated learning method, the random forest has strong robustness and high prediction accuracy, is suitable for processing multi-dimensional data with nonlinear characteristics, and can effectively improve the accuracy of risk prediction.

[0117] Step 4: input the monitoring data, contact force and total stress data of each monitoring point at the current time into the risk prediction model to obtain the state label of each monitoring point at the current time;

[0118] In this embodiment, the specific logic for obtaining the model prediction of the state at the current time is as follows:

[0119] The monitoring data, contact force and total stress data of each monitoring point at the current time are normalized together with the historical data, and then input into the trained risk prediction model to obtain the risk value predicted by the model. If the risk value B=1, it is an abnormal state, and if the risk value B=0, it is a normal state. The abnormal state monitoring points are labeled.

[0120] Step 5: analyzing the monitoring point marked as an abnormal state, calculating the bottom drum risk index of the monitoring point at the current time, and comparing the bottom drum risk index with a preset risk threshold to determine whether to issue a warning;

[0121] In this embodiment, the specific logic for calculating the bottom drum risk index at the abnormal state monitoring point at the current time is as follows:

[0122] The stress, displacement, pressure, vibration, temperature, and humidity data at the monitoring point marked as an abnormal state are obtained, and the formula for obtaining the bottom drum risk index is as follows:

[0123]

[0124] wherein R is the bottom drum risk index, P is the pressure, E is the stress, D is the displacement, V is the vibration amplitude, T is the temperature, T is the ideal temperature value, which can be set to 20℃, H is the humidity, H is the ideal humidity value, which can be set to 50%, ω1, ω2, ω3, ω4, and ω5 are weight coefficients of the respective terms, 0<ω1<ω5<ω4<ω2<ω3<1, and ω1+ω2+ω3+ω4+ω5=1; the vibration amplitude at the current time is obtained by obtaining the vibration signal of the monitoring point in a time period before the current time and processing the vibration signal to obtain the vibration amplitude in the time period, and the vibration amplitude is taken as the vibration amplitude at the current time;

[0125] The bottom drum risk index at the current time is compared with the preset risk threshold, if the bottom drum risk index at the current time is lower than the preset risk threshold, the monitoring is continued, and if the bottom drum risk index at the current time is higher than the preset risk threshold, the corresponding monitoring point is abnormal, and a danger warning is issued.

[0126] The pressure P data is processed using a logarithmic function because the change of the pressure usually has a nonlinear characteristic, the pressure is positively proportional to the bottom drum risk index in the early stage, and when the pressure reaches a certain level, the influence on the risk increase will weaken, so the logarithmic function can effectively balance this nonlinear relationship. Although the pressure has an influence on the bottom drum risk, the influence is relatively linear, and in some cases (such as higher than a certain threshold), the influence degree may weaken. The change of the pressure is processed using a logarithmic function, which further reduces the weight, so the weight is the smallest. The stress reflects the internal force state of the material or structure caused by external action, which is usually related to the strength and carrying capacity of the material. The displacement represents the deformation degree of the structure caused by the stress. Excessive displacement may mean damage or instability of the structure; the square of the stress (E 2) emphasizes the non-linear impact of stress on the risk index. Higher stress can significantly affect the risk, which is consistent with the yield strength and fatigue limit theory in material science. Excessive stress can lead to material failure, so squaring it helps to emphasize the risk in high stress situations. Dividing the square of stress by displacement (D+1) helps to consider the moderating effect of displacement on risk. The larger the displacement, the more likely it is that the structure has undergone some degree of deformation. As the displacement increases, the carrying capacity of the material usually decreases, so the impact of stress on risk will be relatively reduced as the displacement increases. The ratio of stress to displacement reflects the stiffness of the material or structure. The greater the stiffness, the more stable it is, and the smaller the risk of floor heave, i.e. inversely proportional to the risk index of floor heave. The impact of humidity can be represented by a linear difference, as the impact of humidity on materials is relatively simple. Higher humidity increases the risk of floor heave. Humidity affects the risk of floor heave, but usually does not increase the risk as sharply as other factors such as vibration and stress, so its weight is only higher than that of pressure. The impact of temperature on the risk of floor heave is usually non-linear. High temperature environment can cause material fatigue and degradation, so the square difference is used to reflect the impact of temperature deviation from the reference value, which can reasonably quantify this risk. The impact of temperature on the risk of floor heave cannot be ignored, but its weight is higher than that of humidity because temperature changes can have a significant impact on the strength and stability of materials, especially in extreme temperature conditions. The impact of temperature on risk is non-linear, so a relatively high weight is set. The square form of stress E reflects the significant impact of stress on the risk of floor heave, especially in high stress situations, where the risk will rise sharply. Therefore, its weight is only lower than that of vibration, reflecting the key role of stress in risk assessment. At the same time, in order to consider the effect of displacement D, it is normalized by adding 1 to the displacement to ensure that the impact on risk is not amplified too much when the displacement increases. The square form of vibration V is used to show the linear relationship between vibration level and floor heave risk, i.e. the greater the vibration intensity, the higher the risk. The square relationship enhances the risk judgment in high vibration situations. Vibration can directly affect the stability of the roadway structure, especially during mining, where there is a strong correlation between vibration frequency and intensity and the risk of floor heave. Therefore, a higher weight is set to reflect its direct impact on risk.

[0127] Please refer to Figure 2 The application further provides a roadway floor heave mechanism analysis system for implementing the roadway floor heave mechanism analysis method, comprising:

[0128] A data acquisition module is configured to arrange a plurality of monitoring points in the roadway to acquire monitoring data, pressure, vibration, temperature and humidity data of the monitoring points at the current time, and obtain historical monitoring data of the monitoring points at past historical times, wherein the monitoring data includes stress, displacement and material parameters.

[0129] A multiscale model construction module is configured to construct a micro model and a macro model of the roadway based on the monitoring data, and couple the micro model with the macro model to obtain contact force and total stress data of particles in the roadway under corresponding monitoring data;

[0130] A risk prediction model construction module is configured to perform state evaluation on historical monitoring data of the monitoring points and corresponding contact force and total stress data at past time points by using an expert scoring method, and assign corresponding state labels, construct a risk prediction model based on a random forest algorithm, and train the risk prediction model by taking the historical monitoring data and corresponding contact force and total stress data as inputs and the state labels as labels, wherein the state labels include a normal state and an abnormal state.

[0131] A real-time state prediction module is configured to input monitoring data, contact force and total stress data of each monitoring point at a current time point into the risk prediction model to obtain state labels of each monitoring point at the current time point.

[0132] An abnormal state analysis module is configured to analyze the monitoring points labeled as the abnormal state, calculate a floor heave risk index of the monitoring point at the current time point, and compare the floor heave risk index with a preset risk threshold to determine whether to issue a warning.

[0133] The above formulas are all dimensionless numerical calculations, the formulas are obtained by software simulation of a large amount of data to obtain a formula of the nearest real situation, and preset parameters in the formulas are set by a person skilled in the art according to actual conditions.

[0134] The above embodiments can be realized wholly or partially by software, hardware, firmware or any combination thereof. When realized by software, the above embodiments can be realized in the form of a computer program product wholly or partially. Those skilled in the art can realize that units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized by hardware or software methods depends on specific application and design constraints of the technical solutions.

[0135] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, which can be located in one place or distributed on multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiments according to actual needs.

[0136] The above is merely specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A method of analyzing a mechanism of a roadway floor heave, characterized by, The specific steps include: Step 1: arranging a plurality of monitoring points in the roadway to collect monitoring data, pressure, vibration, temperature and humidity data of the monitoring points at the current time, and to obtain historical monitoring data of the monitoring points at past historical times, the monitoring data including stress, displacement and material parameters; Step 2: constructing a micro model and a macro model of the roadway based on the monitoring data, and coupling the micro model with the macro model to obtain contact force and total stress data of particles in the roadway corresponding to the monitoring data; Step 3: using expert scoring method to evaluate the state of the historical monitoring data of the monitoring points at the past historical times and the corresponding contact force and total stress data, and giving corresponding state labels, constructing a risk prediction model based on a random forest algorithm, and taking the historical monitoring data and the corresponding contact force and total stress data as inputs and the state labels as labels to train the risk prediction model, the state labels including normal state and abnormal state; Step 4: inputting the monitoring data, contact force and total stress data of each monitoring point at the current time into the risk prediction model to obtain the state labels of each monitoring point at the current time; Step 5: analyzing the monitoring points with the abnormal state labels, calculating the floor heave risk index of the monitoring points at the current time, and comparing the floor heave risk index with a preset risk threshold to determine whether to issue a warning.

2. The method of claim 1, wherein, The specific logic for collecting data at the roadway monitoring points is as follows: Starting from the starting point of the roadway, a monitoring point is set every 3 meters, and stress sensors, displacement sensors, pressure sensors, vibration sensors, temperature sensors and humidity sensors are arranged at the monitoring points to collect stress, displacement, pressure, vibration, temperature and humidity data at the monitoring points, the material parameters including normal stiffness, tangential stiffness, elastic modulus and Poisson's ratio of the material.

3. The method of claim 2, wherein the roof fall mechanism is analyzed by, The specific logic for constructing the micro model and the macro model of the roadway is as follows: A micro soil model is constructed using the discrete element method, and the contact force expression between particles in the model is as follows: F ij = F n,ij + F t,ij = k n,ij • δ n,ij + k t,ij • δ t,ij where F ij represents the contact force between particle i and particle j, F n,ij represents the normal force between particle i and particle j, F t,ij represents the tangential force between particle i and particle j, k n,ij is the normal stiffness of particle i and particle j, k t,ij is the tangential stiffness of particle i and particle j, δ n,ij is the normal displacement of particle i and particle j, δ t,ij is the tangential displacement of particle i and particle j, i and j are the indices of the particles; The normal displacement of the particle is determined by the overlap of the contact points of the two particles, and the calculation formula is as follows: delta n,ij = R i + R j - d ij , d ij < R i + R j where R i is the radius of particle i, R j is the radius of particle j, d ij is the distance between the centers of particle i and particle j, when d ij ≥ R i + R j , there is no contact between the particles, the normal displacement δ n,ij = 0; the tangential displacement is the relative displacement within the contact surface, which can be directly calculated and obtained in the discrete element method model, and in the discrete element method model, the tangential force needs to satisfy the Coulomb friction condition: F t ≤ μ · F n where μ is the friction coefficient, and if the tangential force F t If the friction force limit is exceeded, slip occurs and the tangential displacement needs to be re-adjusted; The formula for obtaining the normal stiffness between particles is as follows: where E * is the equivalent elastic modulus, R * ij is the equivalent contact radius of particle i and particle j, which is dynamically calculated from the radii of particle i and particle j in the discrete element method model; where E i is the modulus of elasticity of particle i, E j is the modulus of elasticity of particle j, v i is the Poisson's ratio of particle i, v j is the Poisson's ratio of particle j; wherein R i is the radius of the contacting particle i, R j is the radius of the contacting particle j; The tangential stiffness is calculated using an empirical ratio: k t,ij = η · k n,ij Wherein, η is the proportionality coefficient; A macro roadway structure model is constructed using the finite element method, and the formula for obtaining the stress matrix is as follows: σ A = D · ∈ where σ A is the macroscopic stress matrix, D is the elastic modulus matrix of the material, and ∈ is the strain matrix. The formula for calculating the total stress in the macro model is as follows: where σ macro represents the total stress in the macroscopic model, V represents the volume of the macroscopic model, F op represents the contact force between particle o and particle p in the microscopic model, n represents the total number of particles in the macroscopic model, o and p are indices of the particles, and o, p ∈ [1, n], o ≠ p; The formula for coupling the micro model and the macro model and feeding back the contact force in the micro model to the macro model is as follows: where σ macro represents the total stress after coupling the micro-model, k n,ab is the normal stiffness of particle a and particle b, k t,ab is the tangential stiffness of particle a and particle b, δ n,ab is the normal displacement of particle a and particle b, δ t,ab is the tangential displacement of particle a and particle b, N represents the total number of particles in the micro-model, a and b are the indices of the particles, a, b ∈ [1, N], a ≠ b; The formula for feeding back the macro stress to the micro model and correcting the contact force between particles is as follows: F ij ′=k n,ij ·δ n,ij +k t,ij ·δ t,ij +σ macro ·A ij where Fij represents the contact force between particle i and particle j after coupling the macroscopic model, Aij represents the contact area between particle i and particle j, and Fij, Aij are calculated by the following equations: ij Fij = kij * (di - d0) + cij * vij ij Aij = 2 * r * r * (1 - cos(θ)) For spherical contact area, the contact radius is used to calculate, and the formula is as follows: A ij = π | R * ij · δ n,ij | where |R * ij ·δ n,ij | denotes the absolute value of the product.

4. The method of claim 3, wherein, The specific logic for constructing the risk prediction model is as follows: The historical monitoring data of the monitoring points at the past historical moments and the corresponding contact force and total stress data are evaluated by an expert scoring method, and are given a label of normal state or abnormal state, wherein the normal state is represented by a risk value B=0, and the abnormal state is represented by a risk value B=1. The historical monitoring data of the monitoring points at the past historical moments and the corresponding contact force and total stress data are normalized and integrated into a sample data set, and the sample data set is divided into a training set and a test set with a division ratio of 7:

3. A risk prediction model is constructed based on a random forest algorithm, the historical monitoring data, the contact force and the total stress data in the training set are taken as inputs, and the corresponding state label is taken as a label to train the risk prediction model. The historical monitoring data, the contact force and the total stress in the test set are input to evaluate the performance of the model, and the evaluation indexes include accuracy, precision and recall. If the change amplitudes of the evaluation indexes are all less than 0.01 in five iterations, it is determined that the model training is completed.

5. The method of claim 4, wherein, The specific logic for obtaining the state predicted by the model at the current moment is as follows: The monitoring data, the contact force and the total stress data of each monitoring point at the current moment are normalized and input into the trained risk prediction model to obtain the risk value predicted by the model. If the risk value B=1, it is an abnormal state, and if the risk value B=0, it is a normal state. The abnormal state monitoring point is labeled.

6. The method of claim 5, wherein, The specific logic for calculating the floor heave risk index of the abnormal state monitoring point at the current moment is as follows: The stress, displacement, pressure, vibration, temperature and humidity data of the monitoring point labeled as an abnormal state are obtained, and the formula for obtaining the floor heave risk index is as follows: Wherein, R is the risk index of bottom drum, P is pressure, E is stress, D is displacement, V is vibration amplitude, T is temperature, is the ideal value of temperature, H is humidity, is the ideal value of humidity, ω1, ω2, ω3, ω4, ω5 are weight coefficients of respective terms, 0 < ω1 < ω5 < ω4 < ω2 < ω3 < 1, and ω1 + ω2 + ω3 + ω4 + ω5 = 1; The floor heave risk index at the current moment is compared with the preset risk threshold. If the floor heave risk index at the current moment is lower than the preset risk threshold, the monitoring continues. If the floor heave risk index at the current moment is higher than the preset risk threshold, the corresponding monitoring point is abnormal, and a danger warning is issued.

7. A system for analyzing a mechanism of a roadway floor heave, characterized by, The roadway floor heave mechanism analysis system is used to implement the roadway floor heave mechanism analysis method of any one of claims 1-6, comprising: A data acquisition module is used to arrange a plurality of monitoring points in the roadway to acquire monitoring data, pressure, vibration, temperature and humidity data of the monitoring points at the current moment, and to obtain historical monitoring data of each monitoring point at the past historical moments. The monitoring data includes stress, displacement and material parameters. A multi-scale model construction module is used to construct a micro model and a macro model of the roadway based on the monitoring data, and to couple the micro model and the macro model to obtain the contact force and the total stress data of the particles in the roadway corresponding to the monitoring data. A risk prediction model construction module is used to evaluate the state of the historical monitoring data of the monitoring points at the past historical moments and the corresponding contact force and total stress data by an expert scoring method, and to give a corresponding state label. A risk prediction model is constructed based on a random forest algorithm, and the historical monitoring data and the corresponding contact force and total stress data are taken as inputs, and the state label is taken as a label to train the risk prediction model. The state label includes a normal state and an abnormal state. a real-time state prediction module, configured to input the monitoring data, the contact force and the total stress data of each monitoring point at the current time into a risk prediction model to obtain a state label of each monitoring point at the current time; an abnormal state analysis module, configured to analyze the monitoring point labeled as the abnormal state, calculate a floor heave risk index of the monitoring point at the current time, and compare the floor heave risk index with a preset risk threshold to determine whether to issue a warning.

Images