A smart mine management system

Abstract

The present invention belongs to the technical field of mining engineering, and discloses a smart mine management system; the system comprises: a region division module, which is used for dividing a mine into regions; a data acquisition module, which is used for acquiring mine environment data of each region; an adjustment analysis module, which is used for analyzing the mine environment data and identifying the region to be adjusted; a collaborative analysis module, which is used for analyzing the mine environment data of the region to be adjusted and identifying the collaborative adjustment region in the region to be adjusted; a ventilation optimization module, which dynamically optimizes the fan speed based on the mine environment data of the region to be adjusted and the collaborative adjustment region; the present invention realizes the automatic control of the mine ventilation system, improves the accuracy and efficiency of mine ventilation, thereby improving the intelligence level and management efficiency of mine ventilation; ensures that the internal environment of the mine is always in a safe and comfortable state, provides miners with safer and more reliable working conditions, and thus improves the mine safety management level.

Description

Technical Field

[0001] The present invention relates to the field of mining engineering technology, and more specifically, to a smart mine management system. Background Art

[0002] Mine ventilation system is a key component to ensure safe and efficient operation of mines. During mining, due to the closed underground space, air circulation inside the mine is restricted, and miners are affected by environmental factors such as air quality, temperature and humidity, and gas concentration when working. If the mine ventilation system is not properly managed, it will lead to safety hazards such as insufficient oxygen, gas accumulation, and excessive dust inside the mine. In severe cases, it may even cause catastrophic accidents (such as gas explosions, landslides, etc.). Therefore, the design, control and adjustment of the ventilation system are crucial. Traditional mine ventilation systems often rely on manual operation and basic equipment. However, due to the complex and changeable mining environment, manual operation has the problems of slow response speed and poor predictability, and it is difficult to achieve precise control and real-time optimization. Therefore, traditional ventilation systems often have problems such as delayed gas concentration monitoring, low ventilation efficiency, and poor environmental adaptability.

[0003] With the rapid development of intelligent technology, mine ventilation systems have gradually changed; by introducing advanced technologies such as the Internet of Things, sensor technology, big data analysis, and artificial intelligence, the monitoring, control, and adjustment capabilities of mine ventilation systems have been greatly improved, enabling more accurate, safe, and efficient ventilation management; for example, a patent application with publication number CN114895618A discloses a remote centralized control system for fans in a deep mine ventilation system; including: management and operation layer, network transmission layer, core control layer, and field equipment layer; the management and operation layer includes a surface control room host computer and an underground control room host computer. The core control layer includes a PLC control system, which is connected to the network transmission layer; the field equipment layer includes field detection sensors, fan frequency conversion speed control cabinet, field manual start and stop operation box and fan, and is controlled by the PLC control system; this invention adopts a PC+PLC control architecture, with three control modes: field operation box manual, field PLC human-machine interface control and surface (underground) centralized control, which meet the different needs of fan inspection and maintenance, network abnormality emergency and normal operation, and realize remote centralized automatic control of fans in the whole mine and unmanned operation on site underground.

[0004] However, although the above technology can realize automatic control of the fan, it relies on the comparison of wind speed setting signals and sensor data to adjust the fan, and cannot fully consider other important factors in the mine environment, such as temperature, gas concentration, airflow resistance and other complex factors; therefore, it is impossible to comprehensively calculate the optimal parameters of the fan in real time, resulting in difficulty in achieving optimal ventilation adjustment under rapidly changing environmental conditions, resulting in insufficient response speed and adjustment flexibility of the fan.

[0005] In view of this, the present invention proposes a smart mine management system to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: a smart mine management system, comprising: The area division module is used to divide the mine into areas; the method for dividing the mine into areas includes: Get the maximum wind speed of each fan in the mine; add the maximum wind speeds of each fan in turn to get the total wind speed; divide the maximum wind speed of each fan by the total wind speed to get the weighted wind speed; get the mine area, multiply the weighted wind speed of each fan by the mine area to get the weighted area corresponding to each fan; divide the mine into regions according to the weighted area to get There are regions, each region corresponds to a wind turbine, and the area of ​​each region is the weighted area of ​​the corresponding wind turbine; Data acquisition module, used to collect mine environment data of each area; mine environment data includes ambient wind speed, ambient temperature, gas concentration, oxygen concentration and air flow resistance; The adjustment analysis module is used to analyze the mine environment data and identify the area to be adjusted. The step of identifying the area to be adjusted includes: Step S101: set a digital label for each region in turn and mark it as a region label. The range of the region label is ; Set digital labels for each type of data in the mine environment data in turn and mark them as data labels. The range of data labels is ; Step S102: Select the area label and mark it as the current area. ; Step S103: Select the data label from the mine environment data corresponding to the current area. Anomaly detection on the data ; Step S104: ; Step S105: looping steps S103 to S104 until all the mine environment data corresponding to the current area have completed abnormal detection, the loop ends, and the process proceeds to step S106; Step S106: ; Step S107: looping steps S102 to S106 until all regions are marked as current regions, the loop ends, and the process proceeds to step S108; Step S108: taking the area with abnormal data in the mine environment data as the area to be adjusted; A collaborative analysis module, used to analyze the mine environment data of the area to be regulated and identify the collaborative regulation area in the area to be regulated; The ventilation optimization module dynamically optimizes the fan speed based on the mine environmental data of the area to be adjusted and the coordinated adjustment area.

[0007] Furthermore, in step S103, the method for abnormality detection includes: Mark the data for anomaly detection as elements, and mark the elements collected in real time as real-time elements; obtain Historical elements, historical elements are normal elements of the current area collected at historical moments, and normal elements are elements within the normal range. is an integer greater than 1; The historical elements are added in sequence and then divided by , get the mean historical element; according to the mean historical element, calculate the covariance matrix corresponding to the historical element; the expression of the covariance matrix is: ; In the formula, is the covariance matrix, For the historical elements, is the mean historical element, for The transpose of ; According to the covariance matrix, calculate the covariance distance corresponding to the real-time element; the expression of covariance distance is: ; In the formula, is the covariance distance, For real-time elements; Set the significance level; obtain the data dimension corresponding to the element, where the data dimension is the number of data types in the element; obtain the distance threshold based on the significance level and data dimension; square the covariance distance to obtain the square distance, and compare the square distance with the distance threshold; if the square distance is greater than the distance threshold, mark the data corresponding to the corresponding element as abnormal data; if the square distance is less than or equal to the distance threshold, do not mark the data corresponding to the corresponding element.

[0008] Furthermore, the method for identifying the coordinated adjustment region in the region to be adjusted includes: Obtain the data label of the abnormal data corresponding to each area to be adjusted, and mark it as an abnormal label; take the area area, covariance matrix and an abnormal label of each area to be adjusted as a group of analysis data; input each group of analysis data into the trained threshold prediction model, and predict the fluctuation threshold corresponding to the abnormal label in the corresponding area to be adjusted; compare the abnormal data corresponding to the abnormal label in each area to be adjusted with the corresponding fluctuation threshold; if the abnormal data is greater than or equal to the fluctuation threshold, the area to be adjusted corresponding to the abnormal data is used as a coordinated adjustment area; if the abnormal data is less than the fluctuation threshold, the area to be adjusted corresponding to the abnormal data is not used as a coordinated adjustment area; The training process of the threshold prediction model includes: Pre-collection Group analysis data, The corresponding fluctuation threshold is set for each group of analysis data. is an integer greater than 1, converting the analysis data and the corresponding fluctuation threshold into a corresponding set of feature vectors; taking each set of feature vectors as the input of the threshold prediction model, the threshold prediction model takes a set of predicted fluctuation thresholds corresponding to each set of analysis data as the output, and takes the actual fluctuation threshold corresponding to each set of analysis data as the prediction target, and the actual fluctuation threshold is the pre-set fluctuation threshold corresponding to the analysis data; minimizing the sum of the prediction errors of all analysis data is taken as the training target; the threshold prediction model is trained until the sum of the prediction errors converges and the training is stopped; the threshold prediction model is a deep neural network model.

[0009] Furthermore, the step of dynamically optimizing the wind speed of the fan includes: Step S201: marking both the area to be adjusted and the coordinated adjustment area as analysis areas; Step S202: selecting an analysis area where fan parameters are not optimized, and marking it as an optimization area; Step S203: if the optimized area is a coordinated adjustment area, proceed to step S204; if the optimized area is an area to be adjusted, proceed to step S205; Step S204: Mark the coordinated adjustment area and the adjacent area of ​​the coordinated adjustment area as coordinated areas; obtain the maximum wind speed and wind speed of each coordinated area, and construct the wind speed range corresponding to each coordinated area; construct a wind speed set according to the wind speed range of each coordinated area; set a different digital label for each wind speed set and mark it as a set label; randomly generate an initial antibody group, the antibodies in the initial antibody group correspond to the set label one by one, and enter step S206; Step S205: obtaining the maximum wind speed and fan wind speed of the area to be adjusted, and constructing a wind speed range corresponding to the area to be adjusted; randomly generating an initial antibody group, wherein the antibodies in the initial antibody group correspond one-to-one to the wind speeds in the wind speed range corresponding to the area to be adjusted; Step S206: define a fitness function; Step S207: performing antibody screening on the initial antibody group to generate a memory antibody group; Step S208: calculating the corresponding clone size for each antibody in the memory antibody group, and cloning to generate a clone antibody group; Step S209: calculating the selection probability of each antibody in the cloned antibody group, and selecting antibodies according to the selection probability to generate a selected antibody group; Step S210: performing antibody recombination on antibodies in the cloned antibody group to generate a recombinant antibody group; Step S211: merging the selected antibody group and the recombinant antibody group to generate a merged antibody group; Step S212: Determine whether the iteration is finished; if so, obtain the antibody with the largest fitness in the combined antibody group and mark it as the optimal antibody, optimize the wind speed of the fan in the coordinated area according to the wind speed set corresponding to the set label corresponding to the optimal antibody, or adjust the wind speed of the fan in the area to be adjusted according to the wind speed corresponding to the maximum antibody; if not, perform antibody screening on the combined antibody group, regenerate the memory antibody group, and return to step S208; Step S213: looping steps S202 to S212 until all analysis areas have completed the fan speed optimization, and then the loop ends.

[0010] Furthermore, in step S204, the method for constructing the wind speed set is: randomly selecting a wind speed from the wind speed range of each collaborative area to construct a set of wind speed sets, and constructing a total of M wind speed sets, and the M wind speed sets are all different; The size of the initial antibody population was , that is, the initial antibody group includes antibodies, and the range of each antibody is the set label corresponding to the M wind speed sets; the number of iterations t of the initial antibody group is 0; In the step S205, the range of each antibody is the wind speed range corresponding to the area to be adjusted; In step S206, the fitness function is expressed as: ; In the formula, For fitness, The method for obtaining the ventilation effect is as follows: if the optimized area is a collaborative adjustment area, the wind speed set corresponding to the antibody corresponding set label and the mine environment data corresponding to the collaborative adjustment area are taken as the first data, and the first data are input into the trained ventilation evaluation model to evaluate the corresponding ventilation effect; if the optimized area is an area to be adjusted, the wind speed corresponding to the antibody and the mine environment data corresponding to the area to be adjusted are taken as the second data, and the second data are input into the trained ventilation evaluation model to evaluate the corresponding ventilation effect; the ventilation evaluation model is a neural network model.

[0011] Furthermore, in step S207, the method for antibody screening is: calculating the fitness corresponding to each antibody in the initial antibody group, and screening out the antibodies from the initial antibody group. The antibody with the highest fitness, ; In step S208, the method for calculating the cloning scale includes: ; ; In the formula, is the clone size of the ith antibody, Int is the rounding function, is the initial antibody population size, is the affinity of the ith antibody, is the fitness of the ith antibody, min is the minimum function, exp is the natural exponential function, is the Euclidean distance between the ith antibody and the jth antibody, is the ith antibody, is the jth antibody, , , .

[0012] Furthermore, in step S209, the method for generating the selected antibody group includes: Calculate the fitness of each antibody in the cloned antibody group, and add them up in sequence to obtain the total antibody fitness, divide the fitness of each antibody by the total antibody fitness, and obtain the selection probability of each antibody; sort the selection probability of each antibody from large to small, and replace each selection probability in positive order with the sum of each selection probability and all selection probabilities before the corresponding selection probability; obtain all selection probabilities after replacement and mark them as replacement probabilities; the antibody corresponding to the replacement probability is consistent with the antibody corresponding to the selection probability before replacement; take every two adjacent replacement probabilities as an analysis set in positive order; mark the replacement probability with a large value in each analysis set as the first probability, and mark the replacement probability with a small value as the second probability; construct the probability screening range corresponding to each analysis set according to the first probability and the second probability of each analysis set, wherein the first probability is the maximum value of the probability screening range, the second probability is the minimum value of the probability screening range, and the minimum value is an open interval, and the maximum value is a closed interval; each analysis set corresponds to the antibody corresponding to the second probability; wherein the minimum value of the probability screening range corresponding to the first antibody is 0, and the maximum value is the corresponding selection probability; randomly generate indivual A random number between The probability of the random number in the screening range corresponds to the antibody, and a selection antibody group is generated.

[0013] Furthermore, in step S210, the antibody recombination method includes: Randomly selected from a population of clonal antibodies The antibody is used as the parent antibody for antibody recombination to generate the progeny antibody , until the number of unselected antibodies in the cloned antibody population is less than When , antibody recombinant is completed; Progeny Antibodies The calculation methods include: ; In the formula, For the Parent antibody, For the scaling factors, which are randomly generated real numbers and The scale factors are not all zero; In step S212, the method for determining whether the iteration is completed includes: Preset Iteration Threshold , the number of iterations t and the iteration threshold For comparison; if , the iteration ends; if , the iteration continues.

[0014] Technical effects and advantages of a smart mine management system of the present invention: By dividing the mine into regions, collecting mine environmental data from each area, identifying the areas to be adjusted and the areas for coordinated adjustment, and dynamically optimizing the fan speed for these areas; it can comprehensively consider multiple factors such as wind speed, temperature, gas concentration, etc. in the mine environment, and use artificial intelligence technology for data analysis, so as to dynamically optimize the fan speed, realize the automatic control of the mine ventilation system, and improve the accuracy and efficiency of mine ventilation, thereby improving the intelligence level and management efficiency of mine ventilation; compared with the traditional method that relies on manual adjustment, it can quickly respond to environmental changes and adjust fan parameters in time to ensure that the internal environment of the mine is always in a safe and comfortable state, provide miners with safer and more reliable working conditions, and thus improve the level of mine safety management. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a schematic diagram of a smart mine management system according to Embodiment 1 of the present invention; Figure 2 This is a flow chart of the method for dynamically optimizing wind speed of a wind turbine according to Example 1 of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Example 1: Please refer to Figure 1 As shown, a smart mine management system described in this embodiment includes a region division module, a data acquisition module, a regulation analysis module, a collaborative analysis module and a ventilation optimization module; each module is connected by wired and / or wireless means to realize data transmission between modules.

[0018] The area division module is used to divide the mine into areas.

[0019] Methods for zoning mines include: Obtain the maximum wind speed of each fan in the mine; wind speed is the flow speed of air when the fan is running, which affects the flow efficiency and ventilation effect of air in the mine; the maximum wind speed of the fan is obtained by technical personnel in this field through the relevant technical parameters of the fan; the maximum wind speed of each fan is added in sequence to obtain the total wind speed; the maximum wind speed of each fan is divided by the total wind speed to obtain the weighted wind speed; obtain the mine area, which is obtained by technical personnel in this field through the mine plan or geological map and combined with actual measurements; multiply the weighted wind speed of each fan by the mine area to obtain the weighted area corresponding to each fan; divide the mine into regions according to the weighted area, and obtain There are regions, each region corresponds to a wind turbine one by one, and the area of ​​each region is the weighted area of ​​the corresponding wind turbine.

[0020] The data acquisition module is used to collect the mine environment data of each area.

[0021] Mine environment data include ambient wind speed, ambient temperature, gas concentration, oxygen concentration and air flow resistance; The ambient wind speed is the speed of air flow inside the mine, which is obtained through wind speed sensors (such as hot wire anemometers, impeller anemometers, ultrasonic anemometers, etc.) installed in various areas. It helps to determine whether the airflow inside the mine is normal and whether the fan needs to increase the wind speed.

[0022] The ambient temperature is the temperature inside the mine, which is obtained through temperature sensors (such as thermocouple sensors, RTD temperature sensors, digital temperature sensors, etc.) installed in various areas. It helps to determine whether the mine is in a suitable operating temperature range. When the temperature is too high, the fan speed needs to be increased to improve ventilation, thereby improving the mine temperature.

[0023] Gas concentration refers to the volume of gas per unit volume of air in a mine, and is obtained through gas sensors (such as methane gas sensors, infrared gas sensors, electrochemical gas sensors, etc.) installed in various areas. Gas concentration is one of the important indicators of mine safety. Excessive gas concentration can lead to explosion or fire hazards. If the gas concentration is too high, the wind speed of the fan needs to be increased to accelerate gas dilution and reduce gas accumulation.

[0024] Oxygen concentration refers to the volume of oxygen per unit volume of air in a mine, and is obtained through oxygen sensors (such as electrochemical oxygen sensors, infrared oxygen sensors, etc.) installed in various areas. Changes in oxygen concentration in a mine will affect the safety and health of miners. If the oxygen concentration is too low, it will cause suffocation or discomfort to miners. The wind speed of the fan needs to be increased to increase the oxygen supply, thereby ensuring that the air quality in the mine meets safety requirements.

[0025] Airflow resistance is the resistance to airflow in the mine, which is obtained through differential pressure sensors installed in various areas. When the airflow resistance increases, the fan speed needs to be increased to overcome the greater airflow resistance and ensure ventilation efficiency. When the airflow resistance decreases, the fan speed can be reduced to reduce the fan load.

[0026] The adjustment analysis module is used to analyze the mine environment data and identify the areas to be adjusted; The steps to identify the area to be adjusted include: Step S101: set a digital label for each region in turn and mark it as a region label. The range of the region label is ; Set digital labels for each type of data in the mine environment data in turn and mark them as data labels. The range of data labels is ; Step S102: Select the area label and mark it as the current area. ; Step S103: Select the data label from the mine environment data corresponding to the current area. Anomaly detection on the data ; Step S104: ; Step S105: looping steps S103 to S104 until all the mine environment data corresponding to the current area have completed abnormal detection, the loop ends, and the process proceeds to step S106; Step S106: ; Step S107: looping steps S102 to S106 until all regions are marked as current regions, the loop ends, and the process proceeds to step S108; Step S108: taking the area with abnormal data in the mine environment data as the area to be adjusted.

[0027] In the above step S103, the method for abnormality detection includes: Mark the data for anomaly detection as elements, and mark the elements collected in real time as real-time elements; obtain Historical elements, historical elements are normal elements of the current area collected at historical moments, and normal elements are elements within the normal range. is an integer greater than 1. The historical elements are obtained through the database integrated in the mine management system. The historical elements are added in sequence and then divided by , get the mean historical element; according to the mean historical element, calculate the covariance matrix corresponding to the historical element; the expression of the covariance matrix is: ; In the formula, is the covariance matrix, For the historical elements, is the mean historical element, for The transpose of ; According to the covariance matrix, calculate the covariance distance corresponding to the real-time element; the expression of covariance distance is: ; In the formula, is the covariance distance, For real-time elements; Set the significance level, which is preset by technical personnel in this field according to actual conditions, and is usually 0.01 (indicating a 1% confidence level) or 0.05 (indicating a 5% confidence level); obtain the data dimension corresponding to the element, where the data dimension is the number of types of data in the element; obtain the distance threshold by consulting the chi-square distribution table according to the significance level and the data dimension; square the covariance distance to obtain the square distance, and compare the square distance with the distance threshold; if the square distance is greater than the distance threshold, mark the data corresponding to the corresponding element as abnormal data; if the square distance is less than or equal to the distance threshold, do not mark the data corresponding to the corresponding element.

[0028] A collaborative analysis module, used to analyze the mine environment data of the area to be regulated and identify the collaborative regulation area in the area to be regulated; The method for identifying the co-regulation region in the region to be regulated includes: Obtain the data label of the abnormal data corresponding to each area to be adjusted, and mark it as an abnormal label; take the area area, covariance matrix and an abnormal label of each area to be adjusted as a group of analysis data; input each group of analysis data into the trained threshold prediction model respectively, and predict the fluctuation threshold corresponding to the abnormal label in the corresponding area to be adjusted; compare the abnormal data corresponding to the abnormal label in each area to be adjusted with the corresponding fluctuation threshold; if the abnormal data is greater than or equal to the fluctuation threshold, the area to be adjusted corresponding to the abnormal data is used as a coordinated adjustment area, indicating that the abnormal degree of the abnormal data is large, and the ventilation problem cannot be solved by adjusting the wind speed of the fan in the corresponding area to be adjusted. Therefore, it is necessary to coordinate the wind speed of the fans in multiple areas to be adjusted to ensure the balance and optimization of the overall ventilation effect and ensure the safety in the mine; if the abnormal data is less than the fluctuation threshold, the area to be adjusted corresponding to the abnormal data is not used as a coordinated adjustment area.

[0029] The training process of the threshold prediction model includes: Pre-collection Group analysis data, The corresponding fluctuation threshold is set for each group of analysis data. is an integer greater than 1, and the analysis data and the corresponding fluctuation threshold are converted into a corresponding set of feature vectors; the fluctuation threshold corresponding to the analysis data is collected by technical personnel in the process of historical detection of mine ventilation conditions. Combined with the actual situation and practical experience, the fluctuation threshold corresponding to the data under the conditions of each group of analysis data is determined in turn. The corresponding fluctuation thresholds are set for the group analysis data in turn; Each set of feature vectors is used as the input of the threshold prediction model. The threshold prediction model uses a set of predicted fluctuation thresholds corresponding to each set of analysis data as output, and uses the actual fluctuation threshold corresponding to each set of analysis data as the prediction target. The actual fluctuation threshold is the pre-set fluctuation threshold corresponding to the analysis data. The training target is to minimize the sum of the prediction errors of all analysis data. The calculation formula of the prediction error is: ,in is the prediction error, is the group number of the eigenvector corresponding to the analyzed data, For the The predicted fluctuation threshold corresponding to the group analysis data, For the The actual fluctuation threshold corresponding to the group analysis data; the threshold prediction model is trained until the sum of the prediction errors reaches convergence and the training is stopped.

[0030] The above threshold prediction model is specifically a deep neural network model; it includes an input layer, a hidden layer and an output layer; each hidden layer includes multiple neurons, each neuron is connected to the neurons in the next layer, and the connection contains weights, which determine the importance and influence of data transmission in the neural network; an activation function is applied to each neuron between the hidden layer and the output layer, and the activation function introduces nonlinearity, allowing the network to learn more complex patterns and features.

[0031] The ventilation optimization module dynamically optimizes the fan speed based on the mine environmental data of the area to be adjusted and the coordinated adjustment area.

[0032] like Figure 2 As shown, the steps of dynamically optimizing the fan speed include: Step S201: marking both the area to be adjusted and the coordinated adjustment area as analysis areas; Step S202: selecting an analysis area where fan parameters are not optimized, and marking it as an optimization area; Step S203: if the optimized area is a coordinated adjustment area, proceed to step S204; if the optimized area is an area to be adjusted, proceed to step S205; Step S204: Mark the coordinated adjustment area and the adjacent area of ​​the coordinated adjustment area as coordinated areas; obtain the maximum wind speed and wind speed of each coordinated area, and construct the wind speed range corresponding to each coordinated area; construct a wind speed set according to the wind speed range of each coordinated area; set a different digital label for each wind speed set and mark it as a set label; randomly generate an initial antibody group, the antibodies in the initial antibody group correspond to the set label one by one, and enter step S206; Step S205: obtaining the maximum wind speed and fan wind speed of the area to be adjusted, and constructing a wind speed range corresponding to the area to be adjusted; randomly generating an initial antibody group, wherein the antibodies in the initial antibody group correspond one-to-one to the wind speeds in the wind speed range corresponding to the area to be adjusted; Step S206: define a fitness function; Step S207: performing antibody screening on the initial antibody group to generate a memory antibody group; Step S208: calculating the corresponding clone size for each antibody in the memory antibody group, and cloning to generate a clone antibody group; Step S209: calculating the selection probability of each antibody in the cloned antibody group, and selecting antibodies according to the selection probability to generate a selected antibody group; Step S210: performing antibody recombination on antibodies in the cloned antibody group to generate a recombinant antibody group; Step S211: merging the selected antibody group and the recombinant antibody group to generate a merged antibody group; Step S212: Determine whether the iteration is finished; if so, obtain the antibody with the largest fitness in the combined antibody group and mark it as the optimal antibody, optimize the wind speed of the fan in the coordinated area according to the wind speed set corresponding to the set label corresponding to the optimal antibody, or adjust the wind speed of the fan in the area to be adjusted according to the wind speed corresponding to the maximum antibody; if not, perform antibody screening on the combined antibody group, regenerate the memory antibody group, and return to step S208; Step S213: looping steps S202 to S212 until all analysis areas have completed the fan speed optimization, and then the loop ends.

[0033] In the above step S204, the method for constructing the wind speed set is: randomly selecting a wind speed from the wind speed range of each collaborative area to construct a set of wind speed sets, and constructing a total of M wind speed sets, and the M wind speed sets are all different; The size of the initial antibody population was , that is, the initial antibody group includes antibodies, and the range of each antibody is the set label corresponding to the M groups of wind speed sets; the number of iterations t of the initial antibody group is 0.

[0034] In the above step S205, the range of each antibody is the wind speed range corresponding to the area to be adjusted.

[0035] In the above step S206, the fitness function is expressed as: ; In the formula, For fitness, is the ventilation effect; the method for obtaining the ventilation effect is: if the optimized area is a coordinated adjustment area, the wind speed set corresponding to the antibody corresponding set label and the mine environment data corresponding to the coordinated adjustment area are used as the first data, and the first data are input into the trained ventilation evaluation model to evaluate the corresponding ventilation effect; if the optimized area is an area to be adjusted, the wind speed corresponding to the antibody and the mine environment data corresponding to the area to be adjusted are used as the second data, and the second data are input into the trained ventilation evaluation model to evaluate the corresponding ventilation effect; the ventilation evaluation model is a neural network model; The training process of the ventilation assessment model includes: Pre-collection Group evaluation data, including collection labels and mine environment data; Each group of evaluation data is set with corresponding ventilation effects. is an integer greater than 1, and the evaluation data and the corresponding ventilation effect are converted into a corresponding set of feature vectors; the ventilation effect corresponding to the evaluation data is collected by technical personnel in the process of historical detection of mine ventilation conditions. Combined with the actual situation and practical experience, the ventilation effect corresponding to the data under the conditions of each group of evaluation data is judged in turn. The group evaluation data sets the corresponding ventilation effects in turn; Each set of feature vectors is used as the input of the ventilation evaluation model. The ventilation evaluation model takes a set of predicted ventilation effects corresponding to each set of evaluation data as output, and takes the actual ventilation effect corresponding to each set of evaluation data as the prediction target. The actual ventilation effect is the pre-set ventilation effect corresponding to the evaluation data. The training target is to minimize the sum of the prediction errors of all evaluation data. The calculation formula of the prediction error is: ,in is the prediction error, is the group number of the eigenvector corresponding to the evaluation data, For the The predicted ventilation effect corresponding to the group evaluation data, For the The actual ventilation effect corresponding to the group evaluation data is obtained; the ventilation evaluation model is trained until the sum of the prediction errors reaches convergence and the training is stopped.

[0036] In the above step S207, the method of antibody screening is: calculating the fitness corresponding to each antibody in the initial antibody group, and screening out the antibodies from the initial antibody group. The antibody with the highest fitness, .

[0037] In the above step S208, the method for calculating the cloning scale includes: ; ; In the formula, is the clone size of the ith antibody, Int is the rounding function, is the initial antibody population size, is the affinity of the ith antibody, is the fitness of the ith antibody, min is the minimum function, exp is the natural exponential function, is the Euclidean distance between the ith antibody and the jth antibody, is the ith antibody, is the jth antibody, , , .

[0038] It should be noted that when calculating the Euclidean distance between the ith antibody and the jth antibody, normalization is performed so that .

[0039] In the above step S209, the method for generating the selected antibody group includes: Calculate the fitness of each antibody in the cloned antibody group, and add them up in sequence to obtain the total antibody fitness, divide the fitness of each antibody by the total antibody fitness, and obtain the selection probability of each antibody; sort the selection probability of each antibody from large to small, and replace each selection probability in positive order with the sum of each selection probability and all selection probabilities before the corresponding selection probability; obtain all selection probabilities after replacement and mark them as replacement probabilities; the antibody corresponding to the replacement probability is consistent with the antibody corresponding to the selection probability before replacement; take every two adjacent replacement probabilities as an analysis set in positive order; mark the replacement probability with a large value in each analysis set as the first probability, and mark the replacement probability with a small value as the second probability; construct the probability screening range corresponding to each analysis set according to the first probability and the second probability of each analysis set, wherein the first probability is the maximum value of the probability screening range, the second probability is the minimum value of the probability screening range, and the minimum value is an open interval, and the maximum value is a closed interval; each analysis set corresponds to the antibody corresponding to the second probability; wherein the minimum value of the probability screening range corresponding to the first antibody is 0, and the maximum value is the corresponding selection probability; randomly generate indivual A random number between The probability of the random number in the screening range corresponds to the antibody, and a selection antibody group is generated.

[0040] For example, the selection probabilities of the three antibodies are 0.5, 0.3, and 0.2, respectively; since there is no value before 0.5, 0.5 is still 0.5 after replacement; since 0.3 is preceded by 0.5, 0.3 is replaced by 0.3+0.5=0.8, and since 0.2 is preceded by 0.3 and 0.5, 0.2 is replaced by 0.2+0.3+0.5=1; therefore, the replacement probabilities are 0.5, 0.8, and 1, respectively; 0.5 and 0.8 are an analysis set, and the probability screening range corresponding to the second antibody is ; 0.8 and 1 are also an analysis set, then the probability screening range corresponding to the third antibody is ; The probability screening range corresponding to the first antibody is ; If the randomly generated random number is 0.7, since 0.7 is in Therefore, a second antibody was selected.

[0041] In the above step S210, the method for antibody recombination includes: Randomly selected from a population of clonal antibodies The antibody is used as the parent antibody for antibody recombination to generate the progeny antibody , until the number of unselected antibodies in the cloned antibody population is less than When the antibody recombination is completed; the preferred embodiment of this invention 3; the recombinant antibody group includes multiple progeny antibodies .

[0042] Progeny Antibodies The calculation methods include: ; In the formula, For the Parent antibody, For the scaling factors, which are randomly generated real numbers and The scale factors are not all zero.

[0043] In the above step S212, the method for determining whether the iteration is finished includes: Preset Iteration Threshold , iterative threshold It is pre-set by those skilled in the art according to the required algorithm accuracy; the number of iterations t and the iteration threshold For comparison; if , the iteration ends; if , the iteration continues.

[0044] This embodiment divides the mine into regions, collects mine environmental data from each region, identifies the areas to be adjusted and the areas for coordinated adjustment, and dynamically optimizes the wind speed of the fan for these areas; it can comprehensively consider multiple factors in the mine environment, such as wind speed, temperature, and gas concentration, and use artificial intelligence technology to perform data analysis, thereby dynamically optimizing the fan speed, realizing automated control of the mine ventilation system, and improving the accuracy and efficiency of mine ventilation, thereby improving the intelligence level and management efficiency of mine ventilation; compared with the traditional method that relies on manual adjustment, it can quickly respond to environmental changes and adjust fan parameters in a timely manner to ensure that the internal environment of the mine is always in a safe and comfortable state, providing miners with safer and more reliable working conditions, thereby improving the level of mine safety management.

[0045] Embodiment 2: The present application also provides an electronic device. The electronic device may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are executed by one or more processors, a smart mine management system as described above may be executed.

[0046] The method or system according to the implementation mode of the present application can also be implemented with the help of the architecture of the electronic device shown in the present application. The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, input / output, a hard disk, etc. A storage device in the electronic device, such as a ROM or a hard disk, can store a smart mine management system provided by the present application. Furthermore, the electronic device may also include a user interface. Of course, the architecture shown in the present application is only exemplary. When implementing different devices, one or more components in the electronic device shown in the present application may be omitted according to actual needs.

[0047] Example 3: One embodiment of the present application discloses a computer-readable storage medium. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, a smart mine management system according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache). Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0048] In addition, according to the implementation of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided in the present application, for example: a smart mine management system. When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0049] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0050] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A smart mine management system, characterized in that: include: The regional division module is used to divide the mine into regions; Methods for zoning mines include: Get the maximum wind speed of each fan in the mine; add the maximum wind speeds of each fan in turn to get the total wind speed; divide the maximum wind speed of each fan by the total wind speed to get the weighted wind speed; get the mine area, multiply the weighted wind speed of each fan by the mine area to get the weighted area corresponding to each fan; divide the mine into regions according to the weighted area to get There are regions, each region corresponds to a wind turbine, and the area of ​​each region is the weighted area of ​​the corresponding wind turbine; Data acquisition module, used to collect mine environment data of each area; mine environment data includes ambient wind speed, ambient temperature, gas concentration, oxygen concentration and air flow resistance; The adjustment analysis module is used to analyze the mine environment data and identify the area to be adjusted. The step of identifying the area to be adjusted includes: Step S101: Set a digital label for each region in turn and mark it as a region label. The range of the region label is ; Set digital labels for each type of data in the mine environment data in turn and mark them as data labels. The range of data labels is ; Step S102: Select the area label and mark it as the current area. ; Step S103: Select the data label from the mine environment data corresponding to the current area. Anomaly detection on the data ; Step S104: ; Step S105: looping steps S103 to S104 until all the mine environment data corresponding to the current area have completed abnormal detection, the loop ends, and the process proceeds to step S106; Step S106: ; Step S107: looping steps S102 to S106 until all regions are marked as current regions, the loop ends, and the process proceeds to step S108; Step S108: taking the area with abnormal data in the mine environment data as the area to be adjusted; A collaborative analysis module, used to analyze the mine environment data of the area to be regulated and identify the collaborative regulation area in the area to be regulated; The ventilation optimization module dynamically optimizes the fan speed based on the mine environmental data of the area to be adjusted and the coordinated adjustment area.

2. A smart mine management system according to claim 1, characterized in that: In step S103, the method for abnormality detection includes: Mark the data for anomaly detection as elements, and mark the elements collected in real time as real-time elements; obtain Historical elements, historical elements are normal elements of the current area collected at historical moments, and normal elements are elements within the normal range. is an integer greater than 1; The historical elements are added in sequence and then divided by , get the mean historical element; according to the mean historical element, calculate the covariance matrix corresponding to the historical element; the expression of the covariance matrix is: ; In the formula, is the covariance matrix, For the historical elements, is the mean historical element, for The transpose of ; According to the covariance matrix, calculate the covariance distance corresponding to the real-time element; the expression of covariance distance is: ; In the formula, is the covariance distance, For real-time elements; Set the significance level; obtain the data dimension corresponding to the element, where the data dimension is the number of data types in the element; obtain the distance threshold based on the significance level and data dimension; square the covariance distance to obtain the square distance, and compare the square distance with the distance threshold; if the square distance is greater than the distance threshold, mark the data corresponding to the corresponding element as abnormal data; if the square distance is less than or equal to the distance threshold, do not mark the data corresponding to the corresponding element.

3. A smart mine management system according to claim 2, characterized in that: The method for identifying a coordinated adjustment region in a to-be-adjusted region comprises: Obtain the data label of the abnormal data corresponding to each area to be adjusted, and mark it as an abnormal label; take the area area, covariance matrix and an abnormal label of each area to be adjusted as a group of analysis data; input each group of analysis data into the trained threshold prediction model, and predict the fluctuation threshold corresponding to the abnormal label in the corresponding area to be adjusted; compare the abnormal data corresponding to the abnormal label in each area to be adjusted with the corresponding fluctuation threshold; if the abnormal data is greater than or equal to the fluctuation threshold, the area to be adjusted corresponding to the abnormal data is used as a coordinated adjustment area; if the abnormal data is less than the fluctuation threshold, the area to be adjusted corresponding to the abnormal data is not used as a coordinated adjustment area; The training process of the threshold prediction model includes: Pre-collection Group analysis data, The corresponding fluctuation threshold is set for each group of analysis data. is an integer greater than 1, converting the analysis data and the corresponding fluctuation threshold into a corresponding set of feature vectors; taking each set of feature vectors as the input of the threshold prediction model, the threshold prediction model takes a set of predicted fluctuation thresholds corresponding to each set of analysis data as the output, and takes the actual fluctuation threshold corresponding to each set of analysis data as the prediction target, and the actual fluctuation threshold is the pre-set fluctuation threshold corresponding to the analysis data; minimizing the sum of the prediction errors of all analysis data is taken as the training target; the threshold prediction model is trained until the sum of the prediction errors converges and the training is stopped; the threshold prediction model is a deep neural network model.

4. A smart mine management system according to claim 3, characterized in that: The step of dynamically optimizing the wind speed of the fan comprises: Step S201: marking both the area to be adjusted and the coordinated adjustment area as analysis areas; Step S202: selecting an analysis area where fan parameters are not optimized, and marking it as an optimization area; Step S203: if the optimized area is a coordinated adjustment area, proceed to step S204; if the optimized area is an area to be adjusted, proceed to step S205; Step S204: Mark the coordinated adjustment area and the adjacent area of ​​the coordinated adjustment area as coordinated areas; obtain the maximum wind speed and wind speed of each coordinated area, and construct the wind speed range corresponding to each coordinated area; construct a wind speed set according to the wind speed range of each coordinated area; set a different digital label for each wind speed set and mark it as a set label; randomly generate an initial antibody group, the antibodies in the initial antibody group correspond to the set label one by one, and enter step S206; Step S205: obtaining the maximum wind speed and fan wind speed of the area to be adjusted, and constructing a wind speed range corresponding to the area to be adjusted; randomly generating an initial antibody group, wherein the antibodies in the initial antibody group correspond one-to-one to the wind speeds in the wind speed range corresponding to the area to be adjusted; Step S206: define a fitness function; Step S207: performing antibody screening on the initial antibody group to generate a memory antibody group; Step S208: calculating the corresponding clone size for each antibody in the memory antibody group, and cloning to generate a clone antibody group; Step S209: calculating the selection probability of each antibody in the cloned antibody group, and selecting antibodies according to the selection probability to generate a selected antibody group; Step S210: performing antibody recombination on antibodies in the cloned antibody group to generate a recombinant antibody group; Step S211: merging the selected antibody group and the recombinant antibody group to generate a merged antibody group; Step S212: Determine whether the iteration is finished; if so, obtain the antibody with the largest fitness in the combined antibody group and mark it as the optimal antibody, optimize the wind speed of the fan in the coordinated area according to the wind speed set corresponding to the set label corresponding to the optimal antibody, or adjust the wind speed of the fan in the area to be adjusted according to the wind speed corresponding to the maximum antibody; if not, perform antibody screening on the combined antibody group, regenerate the memory antibody group, and return to step S208; Step S213: looping steps S202 to S212 until all analysis areas have completed the fan speed optimization, and then the loop ends.

5. A smart mine management system according to claim 4, characterized in that: In step S204, the method for constructing the wind speed set is: randomly selecting a wind speed from the wind speed range of each collaborative area to construct a set of wind speed sets, and constructing a total of M wind speed sets, and the M wind speed sets are all different; The size of the initial antibody population was , that is, the initial antibody group includes antibodies, and the range of each antibody is the set label corresponding to the M wind speed sets; the number of iterations t of the initial antibody group is 0; In the step S205, the range of each antibody is the wind speed range corresponding to the area to be adjusted; In step S206, the fitness function is expressed as: ; In the formula, For fitness, The method for obtaining the ventilation effect is as follows: if the optimized area is a collaborative adjustment area, the wind speed set corresponding to the antibody corresponding set label and the mine environment data corresponding to the collaborative adjustment area are taken as the first data, and the first data are input into the trained ventilation evaluation model to evaluate the corresponding ventilation effect; if the optimized area is an area to be adjusted, the wind speed corresponding to the antibody and the mine environment data corresponding to the area to be adjusted are taken as the second data, and the second data are input into the trained ventilation evaluation model to evaluate the corresponding ventilation effect; the ventilation evaluation model is a neural network model.

6. A smart mine management system according to claim 5, characterized in that: In step S207, the method for antibody screening is: calculating the fitness corresponding to each antibody in the initial antibody group, and screening out the antibodies from the initial antibody group. The antibody with the highest fitness, ; In step S208, the method for calculating the cloning scale includes: ； ； In the formula, is the clone size of the ith antibody, Int is the rounding function, is the initial antibody population size, is the affinity of the ith antibody, is the fitness of the ith antibody, min is the minimum function, exp is the natural exponential function, is the Euclidean distance between the ith antibody and the jth antibody, is the ith antibody, is the jth antibody, , , .

7. A smart mine management system according to claim 6, characterized in that: In step S209, the method for generating the selected antibody group includes: Calculate the fitness of each antibody in the cloned antibody group, and add them up in sequence to obtain the total antibody fitness, divide the fitness of each antibody by the total antibody fitness, and obtain the selection probability of each antibody; sort the selection probability of each antibody from large to small, and replace each selection probability in positive order with the sum of each selection probability and all selection probabilities before the corresponding selection probability; obtain all selection probabilities after replacement and mark them as replacement probabilities; the antibody corresponding to the replacement probability is consistent with the antibody corresponding to the selection probability before replacement; take every two adjacent replacement probabilities as an analysis set in positive order; mark the replacement probability with a large value in each analysis set as the first probability, and mark the replacement probability with a small value as the second probability; construct the probability screening range corresponding to each analysis set according to the first probability and the second probability of each analysis set, wherein the first probability is the maximum value of the probability screening range, the second probability is the minimum value of the probability screening range, and the minimum value is an open interval, and the maximum value is a closed interval; each analysis set corresponds to the antibody corresponding to the second probability; wherein the minimum value of the probability screening range corresponding to the first antibody is 0, and the maximum value is the corresponding selection probability; randomly generate indivual A random number between The probability of the random number in the screening range corresponds to the antibody, and a selection antibody group is generated.

8. The intelligent mine management system according to claim 7, characterized in that: In step S210, the antibody recombination method includes: Randomly selected from a population of clonal antibodies The antibody is used as the parent antibody for antibody recombination to generate the progeny antibody , until the number of unselected antibodies in the cloned antibody population is less than When , antibody recombinant is completed; Progeny Antibodies The calculation methods include: ； In the formula, For the Parent antibody, For the scaling factors, which are randomly generated real numbers and The scale factors are not all zero; In step S212, the method for determining whether the iteration is completed includes: Preset Iteration Threshold , the number of iterations t and the iteration threshold For comparison; if , the iteration ends; if , the iteration ends.

Images