A safety assessment method for deep stope structures based on joint drive of data and knowledge model

Abstract

The present invention provides a method for evaluating the safety of deep mine structures based on the joint drive of data and knowledge models, which relates to the technical field of deep mine structures. The specific steps include: continuously collecting geological parameters and environmental parameters related to deep mines, establishing and training a knowledge model based on geotechnical mechanics and environmental analysis, and simultaneously constructing and training a deformation response model. The geological condition coefficient, environmental risk coefficient, and deformation response coefficient are obtained using current data, and a comprehensive evaluation coefficient is generated through data processing and correlation analysis. The comprehensive evaluation coefficient is compared with a preset threshold to determine whether the mine structure is safe. When faced with the dynamic changes in geological conditions, environmental factors, and deformation responses during deep mine mining, the present invention utilizes real-time collected data and inputs it into pre-trained geomechanical models, environmental analysis models, and deformation response models to achieve dynamic updates of the evaluation results, thus avoiding the drawbacks of evaluation based on static data and fixed models.

Description

Technical Field

[0001] The present invention relates to the technical field of deep stope structures, and in particular to a deep stope structure safety evaluation method based on the joint drive of data and knowledge models. Background Art

[0002] As shallow mineral resources gradually decrease, deep mining has become an important means of obtaining them. However, due to the unique geological environment and mining conditions of deep stopes, structural safety issues are becoming increasingly complex and severe. Accurately assessing the structural safety status of deep stopes is crucial to ensuring the smooth progress of mining operations and the safety of personnel.

[0003] Existing assessment methods have the following shortcomings:

[0004] First, focusing solely on the impact of a single factor on stope structural safety—for example, analyzing only geological parameters—ignored the complex interactions between environmental factors and deformation responses. This one-sided assessment approach fails to truly reflect the complex realities of deep stopes, resulting in inaccurate assessment results.

[0005] Second, during the mining process in deep stopes, geological conditions, environmental factors, and the deformation response of the stope itself are all in dynamic flux. However, existing assessment methods, mostly based on static data and fixed models, fail to update and adapt to these dynamic changes. For example, as mining depth increases and the mining area expands, factors such as ground stress and groundwater levels change. However, traditional assessment methods are unable to adjust their results in real time, thus hindering the accurate assessment of stope structural safety.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0007] The purpose of the present invention is to provide a deep stope structure safety assessment method based on a joint drive of data and knowledge models to solve the problems raised in the above background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A deep stope structure safety assessment method based on a joint drive of data and knowledge models includes the following steps:

[0010] S1. Continuously collect multiple data related to the area where the deep stope is located, including historical and current geological parameters, environmental parameters, and deformation response data;

[0011] S2. Constructing a knowledge model based on geotechnical mechanics and environmental analysis, the knowledge model comprising a geomechanics model and an environmental analysis model, evaluating past geological parameters based on an expert scoring method to generate geological condition coefficients for evaluating the quality of geological factors, combining past geological parameters and corresponding geological condition coefficients to train the geomechanics model, and evaluating past environmental parameters based on an expert scoring method to generate environmental risk coefficients for evaluating the quality of environmental factors, combining past environmental parameters and corresponding environmental risk coefficients to train the environmental analysis model, and inputting current geological parameters and environmental parameters into the geomechanics model and the environmental analysis model, respectively, to obtain current geological condition coefficients and environmental risk coefficients;

[0012] S3. Construct a deformation response model, using historical deformation response data as input and deformation response coefficients of previous deep stopes as labels. The deformation response coefficients are determined by an expert group, and the deformation response model is trained.

[0013] S4. Input the current deformation response data into the trained deformation response model to obtain the deformation response coefficient of the current deep stope;

[0014] S5. Perform data processing and correlation analysis on the geological condition coefficient, environmental risk coefficient, and deformation response coefficient of the current deep stope to generate a comprehensive evaluation coefficient for comprehensively evaluating the structural safety of the deep stope;

[0015] S6. Compare the comprehensive evaluation coefficient with the pre-set structural safety threshold to determine whether the current deep stope structure meets the safety standards.

[0016] Furthermore, the geological parameters include rock density, rock porosity and rock thickness, the environmental parameters include CO concentration, temperature, humidity and groundwater level in the deep mining area, and the deformation response data includes horizontal displacement, vertical displacement, stress and strain.

[0017] Furthermore, based on the geomechanical model, the expression of the geological condition coefficient is as follows:

[0018] ;

[0019] in, is the geological condition coefficient of the current deep stope;

[0020] Where, is the current rock mass density, is the current rock porosity, is the current rock mass thickness;

[0021] is the regression coefficient of rock mass density, is the regression coefficient of rock porosity, is the regression coefficient of rock mass thickness, On the basis of .

[0022] Furthermore, based on the environmental analysis model, the expression of the environmental risk coefficient is as follows:

[0023] ;

[0024] in, is the environmental risk factor of the current deep stope;

[0025] Where, is the interaction term between the CO concentration and temperature in the current deep stope, is the interaction term between the current humidity in the deep stope and the groundwater level;

[0026] is the regression coefficient of the interaction term between CO concentration and temperature, is the regression coefficient of the interaction term between humidity and groundwater level, On the basis of .

[0027] Furthermore, the geological condition coefficient, environmental risk coefficient and deformation response coefficient of the current deep stope are processed and correlated to generate a comprehensive evaluation coefficient based on the following formula:

[0028] ;

[0029] in, is the comprehensive evaluation coefficient of the current deep stope, is the geological condition coefficient of the current deep stope, is the environmental risk coefficient of the current deep stope, is the deformation response coefficient of the current deep stope;

[0030] Where, 、 and are the weight coefficients of geological condition coefficient, environmental risk coefficient and deformation response coefficient respectively, and 、 and The specific value of is determined by the hierarchical analysis method.

[0031] Furthermore, the specific process of step S6 is as follows:

[0032] when , the current deep stope structure meets safety standards;

[0033] when , the current deep stope structure does not meet safety standards;

[0034] is the safety threshold of deep stope structure, indicating the critical value of deep stope structure safety.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] By continuously collecting data covering both past and current geological parameters, environmental parameters, and deformation response data, this method overcomes the limitations of existing technologies that focus solely on a single factor. It comprehensively considers the numerous key factors and their complex interactions that affect the safety of deep stope structures, significantly improving assessment accuracy. Faced with the dynamic changes in geological conditions, environmental factors, and deformation response during deep stope mining, this method utilizes real-time collected data and inputs it into pre-trained geomechanical models, environmental analysis models, and deformation response models to obtain the corresponding geological condition coefficients, environmental risk coefficients, and deformation response coefficients in real time, enabling dynamic updates of assessment results and avoiding the drawbacks of assessments based on static data and fixed models.

[0037] At the same time, the present invention constructs professional knowledge models and conducts targeted training, builds various models based on professional theories and a large amount of data, compares them with the coefficients determined by the expert scoring method, and uses an optimization algorithm to iteratively update the model coefficients to minimize the loss function, thereby enhancing the reliability of the evaluation.

[0038] By comparing the comprehensive evaluation coefficient with the pre-set structural safety threshold, a clear decision-making basis is provided for deep mine mining operations, ensuring the smooth progress of mining operations and personnel safety, and effectively improving the scientificity, accuracy and practicality of deep mine structural safety assessments. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Schematic diagram of the overall method flow of the present invention;

[0040] Figure 2 is a fitting curve diagram of rock mass density and geological condition coefficient of the present invention;

[0041] Figure 3 is a fitting curve diagram of rock mass thickness and geological condition coefficients of the present invention;

[0042] Figure 4 is a fitting curve diagram of the rock mass porosity and geological condition coefficient of the present invention;

[0043] Figure 5 is a fitting curve diagram of the interaction term between humidity and groundwater level and the environmental risk coefficient of the present invention;

[0044] Figure 6This is a fitting curve diagram of the interaction term between CO concentration and humidity and the environmental risk coefficient of the present invention;

[0045] Figure 7 is a fitting curve diagram of the geological condition coefficient and the comprehensive evaluation coefficient of the present invention;

[0046] Figure 8 It is a fitting curve diagram of the environmental risk coefficient and comprehensive evaluation coefficient of the present invention;

[0047] Figure 9 It is a fitting curve diagram of the deformation response coefficient and comprehensive evaluation coefficient of the present invention. DETAILED DESCRIPTION

[0048] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0049] It should be noted that, unless otherwise defined, the technical or scientific terms used in the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0050] Example 1:

[0051] See also Figure 1 , the present invention provides a technical solution:

[0052] A deep stope structure safety assessment method based on a joint drive of data and knowledge models includes the following steps:

[0053] S1. Continuously collect multiple data related to the area where the deep stope is located, including historical and current geological parameters, environmental parameters, and deformation response data. The geological parameters include rock density, rock porosity, and rock thickness; the environmental parameters include CO concentration, temperature, humidity, and groundwater level in the deep stope; and the deformation response data includes horizontal displacement, vertical displacement, stress, and strain.

[0054] Based on the above embodiment, the structure of the deep stope described in S1 mainly refers to various support, enclosure and transportation systems established in deep projects such as underground mines or tunnels for resource mining or transportation.

[0055] Based on the above embodiment, the method and equipment for collecting geological parameters, environmental parameters and deformation response data are as follows:

[0056] Through the core sampling method, core samples are taken from the underground rock formations and laboratory analysis is performed to determine the density of the rock mass in the area where the deep mining site is located.

[0057] Using the water saturation method, the core sample is immersed in clean water, ensuring it is completely submerged. The sample is allowed to absorb water until its mass no longer changes. The pore volume of the sample is calculated by measuring the volume of water displaced by the sample. Porosity = (pore volume / sample volume) x 100%. Ultrasonic detectors are deployed in the deep mining area. The ultrasonic transmitter sends an ultrasonic signal into the rock mass and records the time it takes for the signal to reflect back. The rock mass thickness is calculated based on the speed of sound waves in the rock.

[0058] The CO concentration in deep mining areas is monitored using electrochemical sensors.

[0059] Temperature sensors are used to continuously record temperature changes to obtain the temperature of the deep mining area.

[0060] Use humidity sensors to measure humidity in deep stopes.

[0061] Water level gauges are installed in areas where deep mining sites are located. Usually, bubble water level gauges or electronic water level gauges are used. The data of the water level gauges are read regularly to monitor changes in groundwater levels.

[0062] Electronic levels are used to measure horizontal and vertical displacements of rocks in areas where deep stopes are located.

[0063] Strain gauges are installed on the rock surface in the deep mining area. The strain gauges can monitor the stress changes inside the rock in real time and transmit the data to the recording system.

[0064] The strain gauge is pasted on the rock surface and the area with relatively concentrated force is selected to obtain effective data. The strain gauge can monitor the tiny deformation of the surface in real time and convert the strain signal into an electrical signal. The recorded data is collected and analyzed to evaluate the strain state of the rock under different conditions.

[0065] After collecting density, porosity, thickness, CO2 concentration, temperature, humidity, groundwater level, horizontal displacement, vertical displacement, stress, and strain, these parameters were normalized to their maximum and minimum values. The normalized data were then used for subsequent analysis and processing. This ensured that all data were analyzed and processed in the same dimension, avoiding the problem of some data being neglected due to different dimensions.

[0066] Among them, the equipment for measuring rock density and porosity, ultrasonic detectors, electrochemical sensors, temperature sensors, humidity sensors, water level gauges, electronic levels, stress gauges, and strain gauges can all use models of existing equipment and are not limited here.

[0067] Equipment for measuring rock density and porosity, including ultrasonic detectors, electrochemical sensors, temperature sensors, humidity sensors, water level gauges, electronic levels, stress gauges, and strain gauges, are collected in multiple groups (e.g., three groups). Density, porosity, thickness, CO2 concentration, temperature, humidity, groundwater level, horizontal displacement, vertical displacement, stress, and strain are detected at different locations. The same data detected at different locations are then averaged, and the final average value is used as the corresponding data for density, porosity, thickness, CO2 concentration, temperature, humidity, groundwater level, horizontal displacement, vertical displacement, stress, and strain, so as to avoid accidental errors from individual point sampling.

[0068] S2. Constructing a knowledge model based on geotechnical mechanics and environmental analysis, the knowledge model comprising a geomechanics model and an environmental analysis model, evaluating past geological parameters based on an expert scoring method to generate geological condition coefficients for evaluating the quality of geological factors, combining past geological parameters and corresponding geological condition coefficients to train the geomechanics model, and evaluating past environmental parameters based on an expert scoring method to generate environmental risk coefficients for evaluating the quality of environmental factors, combining past environmental parameters and corresponding environmental risk coefficients to train the environmental analysis model, and inputting current geological parameters and environmental parameters into the geomechanics model and the environmental analysis model, respectively, to obtain current geological condition coefficients and environmental risk coefficients;

[0069] Table 1 shows the variation of geological condition coefficient with rock density, rock porosity and rock thickness.

[0070]

[0071] Based on the above embodiment, according to the data in Table 1, as the rock density gradually increases from 2.5 to 4.4, the geological condition coefficient increases continuously from 122.22 to 1448. That is, the greater the rock density, the greater the geological condition coefficient. Therefore, the rock density and the geological condition coefficient are positively correlated.

[0072] The rock porosity gradually decreases from 0.15 to 0.01, and the geological condition coefficient increases from 122.22 to 1448, indicating that the smaller the rock porosity, the larger the geological condition coefficient. Therefore, the rock porosity and the geological condition coefficient are negatively correlated.

[0073] The rock layer thickness gradually increases from 10 to 29, and the geological condition coefficient increases from 122.22 to 1448, which means that the thicker the rock layer, the larger the geological condition coefficient. Therefore, the rock layer thickness is positively correlated with the geological condition coefficient.

[0074] from Figure 2 The black squares of the geological condition coefficient data points are distributed near the black fitting curve, showing an upward trend, and the curve is obviously curved, indicating that the rock density and the geological condition coefficient have a nonlinear positive correlation. As the rock density increases, the geological condition coefficient increases, and the growth rate gradually accelerates, indicating that the influence of rock density on the geological condition coefficient is increasing.

[0075] Figure 3 In the figure, the black square data points rise along the nonlinear black fitted curve, reflecting the nonlinear positive correlation between rock layer thickness and the geological condition coefficient. As rock layer thickness increases, the geological condition coefficient increases, with a gradual increase followed by a rapid increase. This indicates that increasing rock layer thickness significantly increases the geological condition coefficient.

[0076] observe Figure 4 The black square data points rise along the black fitting curve as the rock porosity decreases, and the curve is nonlinear. This indicates that the rock porosity and the geological condition coefficient have a nonlinear negative correlation. That is, the smaller the rock porosity, the larger the geological condition coefficient. Moreover, when the porosity decreases by the same amount, the increase in the geological condition coefficient is more obvious in the early stage.

[0077] Based on the above embodiment, the geomechanical model is expressed as follows:

[0078] ;

[0079] in, It is the geological condition coefficient of the current deep mining site. The geological condition coefficient is used to comprehensively evaluate the structural stability and safety of the deep mining site by combining the rock density, porosity and rock thickness. The larger the geological condition coefficient is, the stronger the overall quality and bearing capacity of the rock mass is, and the higher the structural safety and stability of the deep mining site is.

[0080] Where, is the current rock mass density, is the current rock porosity, is the current rock mass thickness;

[0081] is the regression coefficient of rock mass density, is the regression coefficient of rock porosity, is the regression coefficient of rock mass thickness, which is used to reflect the influence of different geological parameters on the geological condition coefficient. These are the coefficients to be optimized in the model expression. They are iteratively optimized through model training. Specifically, the geological condition coefficients output by the geomechanical model and the geological condition coefficients determined by the expert scoring method are calculated to obtain the deviation between the two. The loss function is defined as the deviation between the two. The optimization algorithm (such as gradient descent) is used to iteratively update the , to minimize the loss function, use the mean square error as the loss function, when the mean square error is When within the range, complete the Optimization.

[0082] The input of the expression of the geomechanical model is rock density, rock porosity, and rock thickness, and the output is the geological condition coefficient.

[0083] On this basis, it should be noted that:

[0084] When the rock density An increase in density means a greater amount of rock material per unit volume, stronger interactions between atoms or molecules, and a denser rock mass. This directly enhances the rock's inherent strength and bearing capacity, enabling it to better withstand the various stresses induced by mining activities. For example, high-density rock is less susceptible to deformation and damage when subjected to overburden pressure and mining disturbance stresses, providing a more stable support structure for deep stopes. Deep stopes, in turn, have higher structural safety and stability, and thus a higher geological condition coefficient.

[0085] When the rock thickness When it increases, it is equivalent to increasing the bearing layer thickness of the mine's surrounding rock. Thicker rock can disperse the stress generated during mining and reduce stress concentration. For example, at the mine roof, thicker rock layers can act like a more solid "ceiling," better bearing the pressure above the roof and reducing the risk of roof collapse. At the same time, thicker rock provides stronger lateral support for the surrounding rock around the mine, helping to maintain the stability of the mine's overall structure and improving the structural safety and stability of deep mines. Therefore, the higher the geological condition coefficient, the better.

[0086] When the rock porosity An increase in the pore volume indicates the presence of more voids within the rock mass. These voids weaken the continuity and integrity of the rock mass, causing uneven stress transmission within the rock mass and potentially leading to stress concentration around the pores. Furthermore, the presence of pores reduces the effective bearing area of ​​the rock mass, reducing its overall strength. Rocks with more pores are more susceptible to fracture and deformation when subjected to external forces such as mining stress, resulting in reduced structural safety and stability in deep stopes. Consequently, the lower the pore volume coefficient, the lower the pore volume coefficient.

[0087] Therefore, the geological condition coefficient and rock mass density , rock mass thickness is positively correlated, and the geological condition coefficient and rock porosity Therefore, the geological condition coefficient is expressed in the form of a fraction: and rock mass density , rock porosity , rock mass thickness The functional relationship between them.

[0088] in, Size relationship setting standard:

[0089] Rock density It directly reflects the density and bearing capacity of the rock. Higher density usually means stronger compressive strength and better structural stability. Therefore, in many cases, density has a greater impact on the quality of the rock mass. Set the maximum;

[0090] Rock thickness Affects its overall stability and load distribution ability. Thicker rock mass can withstand greater external pressure and provide a better safety factor. Although the effect of thickness is important, it is usually smaller than that of density because increasing thickness does not always significantly increase the strength of the rock mass, especially when the density is low. Therefore, the regression coefficient of rock mass thickness is Lower than the regression coefficient of rock mass density ;

[0091] Porosity It refers to the ratio of the void volume in the rock mass to the total volume. A higher porosity will lead to a decrease in the strength and stability of the rock mass. The presence of pores will weaken the overall bearing capacity of the rock mass. In the formula, the porosity is in the denominator, which means that an increase in porosity will lead to In the overall evaluation, although the importance of porosity cannot be ignored, its impact is negative, so the regression coefficient The setup is relatively small.

[0092] In summary, the regression coefficient of rock density is greater than that of rock thickness, and the regression coefficient of rock thickness is greater than that of rock porosity. Therefore, The constraint condition is On the basis of .

[0093] Table 2 shows the changes in environmental risk coefficients with the interaction terms of CO concentration and temperature, and humidity and groundwater level.

[0094]

[0095] Based on the above example, according to the data in Table 2, as the interaction term between CO concentration and temperature gradually increases from 10 to 105, the environmental risk coefficient continuously increases from 22 to 117. In other words, the larger the value of the interaction term between CO concentration and temperature, the greater the environmental risk coefficient. Therefore, the interaction term between CO concentration and temperature and the environmental risk coefficient are positively correlated.

[0096] The interaction term between humidity and groundwater level gradually increased from 50 to 145, and the environmental risk coefficient increased from 22 to 117, indicating that the larger the interaction term, the greater the environmental risk coefficient. Therefore, the interaction term between humidity and groundwater level and the environmental risk coefficient are positively correlated.

[0097] observe Figure 5 The environmental risk coefficient data points in the black squares are also closely distributed on the black fitting curve, showing a straight upward trend. This demonstrates that the interaction term between humidity and groundwater level also has a linear positive correlation with the environmental risk coefficient. Specifically, the larger the value of the interaction term between humidity and groundwater level, the higher the environmental risk coefficient linearly increases at a fixed rate, indicating that the impact of this interaction term on the environmental risk coefficient also has a stable linear relationship.

[0098] from Figure 6 As can be seen, the black square data points represent the environmental risk coefficient, and the black curve is the fitted curve. The data points are closely distributed near the black fitted curve and exhibit a clear linear upward trend. This indicates a positive linear correlation between the interaction term between CO concentration and temperature and the environmental risk coefficient. In other words, as the value of the interaction term between CO concentration and temperature increases, the environmental risk coefficient increases linearly.

[0099] Based on the above embodiment, the expression of the environmental analysis model is as follows:

[0100] ;

[0101] in, is the environmental risk coefficient of the current deep mine. The environmental risk coefficient is used to comprehensively evaluate the environmental risk of the deep mine by combining the interaction terms of CO concentration and temperature, and the interaction terms of humidity and groundwater level. The larger the environmental risk coefficient, the greater the environmental risk of the deep mine.

[0102] Where, is the interaction term between CO concentration and temperature in deep stope, is the interaction term between the humidity in the deep stope and the groundwater level;

[0103] is the regression coefficient of the interaction term between CO concentration and temperature, is the regression coefficient of the interaction term between humidity and groundwater level, which is used to reflect the influence of different environmental parameters on the environmental risk coefficient. These are the coefficients to be optimized in the model expression. Model training is used for iterative optimization. Specifically, the environmental risk coefficient output by the environmental analysis model and the environmental risk coefficient determined by the expert scoring method are calculated to obtain the deviation between the two. The loss function is defined as the deviation between the two. The optimization algorithm (such as gradient descent) is used to iteratively update the environmental risk coefficient. , to minimize the loss function, use the mean square error as the loss function, when the mean square error is When within the range, complete the Optimization.

[0104] The input of the model expression of the environmental analysis model is CO concentration, temperature, humidity, and groundwater level, and the output is the environmental risk coefficient.

[0105] On this basis, it should be noted that:

[0106] When the interaction term between CO concentration and temperature increases, CO concentration rises in high-temperature environments, which accelerates CO diffusion and chemical reactivity. High CO concentrations not only pose a direct threat to the safety of underground workers and can easily lead to poisoning accidents, but CO also reacts with surrounding substances, potentially altering the physical and chemical properties of the rock mass. For example, it can corrode minerals or support materials, thereby affecting the stability of the stope structure. Furthermore, high temperatures themselves can degrade the mechanical properties of rock. These two factors interact to further increase the environmental risk in deep stopes, resulting in a higher environmental risk coefficient.

[0107] When the interaction term between humidity and groundwater level increases, it indicates rising groundwater levels and increased humidity. High humidity can easily cause clay minerals in the rock mass to expand, increasing its volume. This, in turn, creates additional stress on the surrounding rock mass, increasing the likelihood of deformation and failure. Rising groundwater levels can reduce the effective stress in the rock mass, weakening its shear strength and increasing the risk of disasters such as water inrush. Furthermore, high humidity and high groundwater levels can accelerate the corrosion of metal support materials, reducing their effectiveness. These combined factors significantly increase the environmental risk in deep mines, resulting in a higher environmental risk coefficient.

[0108] Therefore, the environmental risk coefficient is positively correlated with the interaction term between CO concentration and temperature, and the interaction term between humidity and groundwater level.

[0109] From a physical perspective, environmental factors such as CO concentration, temperature, humidity, and groundwater level do not affect deep stope environmental risks in isolation but rather interact with each other. A linear weighted function can intuitively reflect the combined impact of the interactions between CO concentration and temperature, and between humidity and groundwater level, on the environmental risk coefficient.

[0110] When the interaction term between CO concentration and temperature, as well as the interaction term between humidity and groundwater level, increases, their respective effects on environmental risk can be reflected in the linear weighted function as simple addition, reflecting the cumulative nature of environmental risk as various factors change.

[0111] in, Size relationship setting standard:

[0112] There is a strong positive correlation between CO concentration and temperature. For example, under certain environmental conditions, rising temperature will promote the release or concentration of CO. This strong correlation makes The value is larger because the interaction between the two factors has a more significant impact on environmental risk.

[0113] The groundwater level is mainly affected by factors such as precipitation, soil type, and pumping activities, while changes in humidity have a relatively small impact on the groundwater level. Therefore, the interaction term between humidity and groundwater level has little impact on environmental risks.

[0114] In summary, the regression coefficient of the interaction term between CO concentration and temperature is greater than the regression coefficient of the interaction term between humidity and groundwater level. On the basis of .

[0115] S3. Construct a deformation response model, using historical horizontal displacement, vertical displacement, stress, and strain as inputs and the deformation response coefficients of previous deep stopes as labels. The deformation response coefficients are determined by an expert group and used to train the deformation response model.

[0116] S4. Input the current horizontal displacement, vertical displacement, stress, and strain into the trained deformation response model to obtain the deformation response coefficient of the current deep stope;

[0117] Based on the above embodiment, the deformation response model is established based on historical data (such as previous horizontal displacement, vertical displacement, stress and strain). By learning and training a large amount of historical deformation data, the model can capture the complex relationship between deformation response and input parameters, thereby realizing the prediction of the current deformation state of the mining area. Therefore, the deformation response model is called a data model.

[0118] Based on the above embodiment, the deformation response model is constructed using a deep learning network based on a multilayer perceptron. The deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer. The first hidden layer, the second hidden layer, and the third hidden layer each have at least two neurons and each use ReLU as an activation function.

[0119] In this embodiment, the input features of the deep learning network of the multilayer perceptron include four features: horizontal displacement, vertical displacement, stress and strain.

[0120] The structure of the deep learning network of multilayer perceptron is:

[0121] Input layer: receives input of 4 features;

[0122] The first hidden layer has 64 neurons and uses ReLU as the activation function.

[0123] The second hidden layer has 32 neurons and also uses the ReLU activation function.

[0124] The third hidden layer has 16 neurons and uses the ReLU activation function.

[0125] Output layer: has 1 neuron, which outputs the deformation response coefficient of the deep stope.

[0126] The process of training the deformation response model is as follows:

[0127] The previous horizontal displacement, vertical displacement, stress and strain are used as input, and the deformation response coefficient of the previous deep stope is used as a label for training. The deformation response coefficient is determined by an expert group and is within the range of 1 to 9. The larger the deformation response coefficient, the lower the structural safety of the deep stope. The mean square error is used as the loss function. When the mean square error is When it is within the range, the training of the deformation response model is completed.

[0128] S5. Perform data processing and correlation analysis on the geological condition coefficient, environmental risk coefficient, and deformation response coefficient of the current deep stope to generate a comprehensive evaluation coefficient for comprehensively evaluating the structural safety of the deep stope;

[0129] Table 3 shows the changes of comprehensive evaluation coefficient with geological condition coefficient, environmental risk coefficient and deformation response coefficient

[0130]

[0131] Based on the above embodiment, according to the data in Table 3, the geological condition coefficient and the comprehensive evaluation coefficient are significantly positively correlated: when the geological condition coefficient increases from 1.7 to 15, the comprehensive evaluation coefficient increases from 1 to 13.35 simultaneously, indicating that the better the geological conditions, the higher the safety of the deep stope structure.

[0132] The environmental risk coefficient, deformation response coefficient and comprehensive evaluation coefficient are negatively correlated: when the environmental risk coefficient decreases from 34 to 15 and the deformation response coefficient decreases from 10 to 0.5, the comprehensive evaluation coefficient gradually increases, indicating that the lower the environmental risk and the smaller the deformation, the higher the safety of the mine.

[0133] In summary, changes in the comprehensive evaluation coefficient are the result of improved geological conditions, reduced environmental risks, and reduced deformation. For example, for every 0.7 increase in the geological condition coefficient, a 1 decrease in the environmental risk coefficient, and a 0.5 decrease in the deformation response coefficient, the comprehensive evaluation coefficient increases by approximately 0.65, reflecting the quantitative impact of each factor on stope safety.

[0134] from Figure 7 From the above, we can see that the black squares' comprehensive evaluation coefficient data points are closely distributed on the black fitting curve, showing a straight upward trend. This indicates a linear positive correlation between the geological condition coefficient and the comprehensive evaluation coefficient. Specifically, as the geological condition coefficient increases, the comprehensive evaluation coefficient increases linearly, reflecting the positive impact of the geological condition coefficient on the comprehensive evaluation coefficient. The higher the geological condition coefficient, the better the performance of deep stope structural safety in the comprehensive evaluation.

[0135] observe Figure 8 The black square data points follow a linear downward trend along the black fitting curve. This demonstrates a linear negative correlation between the environmental risk factor and the comprehensive evaluation coefficient. As the environmental risk factor increases, the comprehensive evaluation coefficient decreases linearly, indicating an inverse effect of the environmental risk factor on the comprehensive evaluation coefficient. The higher the environmental risk factor, the worse the safety of the deep stope structure in the comprehensive evaluation.

[0136] exist Figure 9In the figure, the black squares' comprehensive evaluation coefficient data points show a linear downward trend along the black fitting curve. This indicates a linear negative correlation between the deformation response coefficient and the comprehensive evaluation coefficient. As the deformation response coefficient increases, the comprehensive evaluation coefficient decreases linearly, indicating that the deformation response coefficient has an inverse effect on the comprehensive evaluation coefficient. Specifically, the higher the deformation response coefficient, the lower the safety of the deep stope structure in the comprehensive evaluation.

[0137] On the basis of the above embodiment, the geological condition coefficient, environmental risk coefficient and deformation response coefficient of the current deep stope are subjected to data processing and correlation analysis to generate a comprehensive evaluation coefficient based on the following formula:

[0138] ;

[0139] in, is the comprehensive evaluation coefficient of the current deep stope. The comprehensive evaluation coefficient is used to comprehensively score the safety of the current deep stope structure by combining the geological condition coefficient, environmental risk coefficient, and deformation response coefficient. The larger the comprehensive evaluation coefficient, the safer the deep stope structure.

[0140] It should be noted that, as can be seen from the above description, the geological condition coefficient The larger the size, the higher the safety and stability of the deep stope structure, and the higher the environmental risk factor. The larger the value, the greater the environmental risk of the deep stope, and the deformation response coefficient The larger the value, the lower the safety of the deep stope structure. Therefore, the comprehensive evaluation coefficient and geological condition coefficient Positive correlation, comprehensive evaluation coefficient and environmental risk factors , deformation response coefficient Both are negatively correlated;

[0141] The structural safety of deep stopes is the result of the interaction of multiple factors, including geological conditions, environmental factors, and deformation response. Through a weighted summation approach, the geological condition coefficient, environmental risk coefficient, and deformation response coefficient can be integrated into a comprehensive evaluation coefficient, fully reflecting the combined impact of each factor on deep stope structural safety. This approach captures the interrelationships between different factors and their overall contribution to stope structural safety, avoiding the limitation of considering a single factor in isolation while ignoring the impact of others.

[0142] Where, 、 and are the weight coefficients of geological condition coefficient, environmental risk coefficient and deformation response coefficient respectively, and 、 and The specific value of is determined by the hierarchical analysis method, and the specific logic is as follows:

[0143] The three indicators of geological condition coefficient, environmental risk coefficient and deformation response coefficient are marked, and the relative importance between them is determined by the nine-scale method to construct a judgment matrix, in which the index of geological condition coefficient is marked as 1, the index of environmental risk coefficient is marked as 2, and the index of deformation response coefficient is marked as 3. The constructed judgment matrix for:

[0144] ;

[0145] in, 、 denotes the index of the coefficient, and , , indicating that the index is The importance of the coefficient of index v to the comprehensive evaluation coefficient is The specific value is determined by relevant experts using a 1-9 scoring method. Indicates that the index is The coefficient of is extremely important to the comprehensive evaluation coefficient compared to the index of v. Indicates that the index is The coefficient of is extremely unimportant to the comprehensive evaluation coefficient compared to the coefficient with index v;

[0146] Each element value in the judgment matrix is ​​divided by the sum of its columns to obtain a normalized judgment matrix. The mean of the element values ​​in each row of the normalized judgment matrix is ​​calculated, and the mean of the element values ​​in the first row is used as the proportional coefficient of the geological condition coefficient, the mean of the element values ​​in the second row is used as the proportional coefficient of the environmental risk coefficient, and the mean of the element values ​​in the third row is used as the proportional coefficient of the deformation response coefficient. With the constraint that the sum of the scaled values ​​is equal to 1, the three proportional coefficients are scaled equally, and the values ​​obtained after scaling are used as the weights of the corresponding coefficients.

[0147] S6. Compare the comprehensive evaluation coefficient with the pre-set structural safety threshold to determine whether the current deep stope structure meets the safety standards.

[0148] Based on the above embodiment, the specific process of step S6 is as follows:

[0149] when , the current deep stope structure meets safety standards;

[0150] when , the current deep stope structure does not meet safety standards;

[0151] is the safety threshold of deep stope structure, which indicates the critical value of deep stope structure safety. The safety threshold can be determined by statistical analysis of a large amount of experimental data to determine the distribution of comprehensive evaluation coefficients. The statistical indicators such as maximum value, minimum value, mean value and standard deviation in historical data can be used to set the safety threshold. For example, Set to a certain standard deviation above the mean.

[0152] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0153] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art will appreciate that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by computer software, electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0154] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, and may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment as needed.

[0155] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A deep stope structure safety assessment method based on a joint drive of data and knowledge models, characterized by: The specific steps include: S1. Continuously collect multiple data related to the area where the deep stope is located, including historical and current geological parameters, environmental parameters, and deformation response data; S2. Constructing a knowledge model based on geotechnical mechanics and environmental analysis, the knowledge model comprising a geomechanics model and an environmental analysis model, evaluating past geological parameters based on an expert scoring method to generate geological condition coefficients for evaluating the quality of geological factors, combining past geological parameters and corresponding geological condition coefficients to train the geomechanics model, and evaluating past environmental parameters based on an expert scoring method to generate environmental risk coefficients for evaluating the quality of environmental factors, combining past environmental parameters and corresponding environmental risk coefficients to train the environmental analysis model, and inputting current geological parameters and environmental parameters into the geomechanics model and the environmental analysis model, respectively, to obtain current geological condition coefficients and environmental risk coefficients; S3. Construct a deformation response model, using historical deformation response data as input and deformation response coefficients of previous deep stopes as labels. The deformation response coefficients are determined by an expert group, and the deformation response model is trained. S4. Input the current deformation response data into the trained deformation response model to obtain the deformation response coefficient of the current deep stope; S5. Perform data processing and correlation analysis on the geological condition coefficient, environmental risk coefficient, and deformation response coefficient of the current deep stope to generate a comprehensive evaluation coefficient for comprehensively evaluating the structural safety of the deep stope; S6. Compare the comprehensive evaluation coefficient with a preset structural safety threshold to determine whether the current deep stope structure meets safety standards; The geological parameters include rock density, rock porosity and rock thickness; the environmental parameters include CO concentration, temperature, humidity and groundwater level in the deep stope; and the deformation response data include horizontal displacement, vertical displacement, stress and strain; Based on the geomechanical model, the expression of the geological condition coefficient is as follows: in, is the geological condition coefficient of the current deep stope; Where, is the current rock mass density, is the current rock porosity, is the current rock mass thickness; is the regression coefficient of rock mass density, is the regression coefficient of rock porosity, is the regression coefficient of rock mass thickness, On the basis of ; Based on the environmental analysis model, the expression of the environmental risk coefficient is as follows: in, is the environmental risk factor of the current deep stope; Where, is the interaction term between the CO concentration and temperature in the current deep stope, is the interaction term between the current humidity in the deep stope and the groundwater level; is the regression coefficient of the interaction term between CO concentration and temperature, is the regression coefficient of the interaction term between humidity and groundwater level, On the basis of ; The geological condition coefficient, environmental risk coefficient and deformation response coefficient of the current deep stope are processed and correlated to generate a comprehensive evaluation coefficient based on the following formula: in, is the comprehensive evaluation coefficient of the current deep stope, is the geological condition coefficient of the current deep stope, is the environmental risk coefficient of the current deep stope, is the deformation response coefficient of the current deep stope; Where, 、 and are the weight coefficients of geological condition coefficient, environmental risk coefficient and deformation response coefficient respectively, and 、 and The specific value of is determined by the hierarchical analysis method.

2. The deep stope structure safety assessment method based on the joint drive of data and knowledge model according to claim 1 is characterized by: The specific process of step S6 is as follows: when , the current deep stope structure meets safety standards; when , the current deep stope structure does not meet safety standards; is the safety threshold of deep stope structure, indicating the critical value of deep stope structure safety.

Images