Intelligent competitive prevention and control method and system for coal mine thermodynamic disasters

Abstract

The invention provides an intelligent competitive prevention and control method and system for coal mine thermodynamic disasters, and belongs to the technical field of coal mine disaster prevention and control, and the method comprises the steps: carrying out the feature extraction of multi-source target information data, and obtaining the disaster type of a coal mine target region; determining a disaster grade corresponding to the disaster type based on the disaster type and the key data associated with the disaster type; the key data is data in the multi-source target information data; selecting at least one type of fire preventing and extinguishing materials from a disaster prevention and control knowledge base based on disaster types, wherein the types of the fire preventing and extinguishing materials comprise liquid, gas and solid; and determining the ratio of different types of fire prevention and extinguishing materials based on the disaster grade to obtain a prevention and control strategy, and performing fire extinguishing prevention and control on the coal mine based on the prevention and control strategy. According to the intelligent competitive prevention and control method and system for the coal mine thermodynamic disasters, coal mine safety production and personal and property safety can be guaranteed.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of coal mine disaster prevention and control, and more particularly to a coal mine thermal dynamic disaster intelligent competitive prevention and control method and system. BACKGROUND

[0002] In the coal mining industry, coal thermal dynamic disasters such as coal spontaneous combustion, gas combustion, dust explosion, etc. seriously threaten the safety production and personal safety. At present, most of the prevention and control means have limitations. The existing technology often relies on a single means, for example, a large-flow nitrogen making machine mainly aims at coal spontaneous combustion, and is difficult to cope with instantaneous high-energy disasters such as gas explosion, and has narrow applicability. Thus, the safety production and personal and property safety of the coal mine cannot be effectively guaranteed. SUMMARY

[0003] The purpose of the present application is to provide a coal mine thermal dynamic disaster intelligent competitive prevention and control method and system to guarantee the safety production and personal and property safety of the coal mine.

[0004] The first aspect of the embodiment of the present application provides a coal mine thermal dynamic disaster intelligent competitive prevention and control method, comprising: performing feature extraction on multi-source target information data to obtain a disaster type of a target area of a coal mine; the multi-source target information data is data obtained by preprocessing and standardizing multi-source original information data, and the multi-source target data includes environmental data, visual data and geological data of the target area of the coal mine; determining a disaster grade corresponding to the disaster type based on the disaster type and key data associated with the disaster type; the key data is data in the multi-source target information data; selecting at least one type of fire extinguishing material from a disaster prevention and control knowledge base based on the disaster type, the types of the fire extinguishing material including liquid, gas and solid; determining a proportioning of different types of the fire extinguishing material based on the disaster grade, obtaining a prevention and control strategy, and performing fire extinguishing and prevention and control on the coal mine based on the prevention and control strategy.

[0005] The second aspect of the embodiment of the present application provides a coal mine thermal dynamic disaster intelligent competitive prevention and control system, comprising: a disaster type determination module configured to perform feature extraction on multi-source target information data to obtain a disaster type of a target area of a coal mine; the multi-source target information data is data obtained by preprocessing and standardizing multi-source original information data, and the multi-source target data includes environmental data, visual data and geological data of the target area of the coal mine; a disaster grade determination module configured to determine a disaster grade corresponding to the disaster type based on the disaster type and key data associated with the disaster type; the key data is data in the multi-source target information data; The fire extinguishing material selection module is configured to select at least one type of fire extinguishing material from the disaster prevention and control knowledge base based on the disaster type, and the type of fire extinguishing material includes liquid, gas and solid; The fire extinguishing and prevention module is configured to determine the proportion of different types of fire extinguishing materials based on the disaster level, obtain a prevention and control strategy, and perform fire extinguishing and prevention on the coal mine based on the prevention and control strategy.

[0006] In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the coal mine thermal dynamic disaster intelligent competitive prevention and control method are implemented.

[0007] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the coal mine thermal dynamic disaster intelligent competitive prevention and control method are implemented.

[0008] The coal mine thermal dynamic disaster intelligent competitive prevention and control method and system provided by the embodiments of the present application have the following beneficial effects: The present application determines the disaster type by preprocessing, standardizing and feature extraction of multi-source raw data, comprehensively integrates environmental, visual and geological information, and accurately identifies potential disasters. Based on the disaster type and key data, the disaster level is determined to accurately assess the severity of the disaster. According to the disaster type, the fire extinguishing material is selected from the knowledge base to ensure the material specificity. Then, the material ratio is determined according to the disaster level to form a prevention and control strategy, and precise fire extinguishing and prevention are realized. The scientificity, accuracy and efficiency of prevention and control can be effectively improved, the risk of coal mine thermal dynamic disaster can be reduced to the greatest extent, and the safety of coal mine production and personal and property safety can be ensured. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creating any creative labor.

[0010] Figure 1 A flowchart of a coal mine thermal dynamic disaster intelligent competitive prevention and control method provided by an embodiment of the present application is shown in the figure. Figure 2 A structure block diagram of a coal mine thermal dynamic disaster intelligent competitive prevention and control system provided by an embodiment of the present application is shown in the figure. Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0011] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known methods, processes, systems, circuits and methods are not set forth in order to avoid obscuring the description of the present application.

[0012] In order to make the purposes, technical solutions and advantages of the present application clearer, the following will be described by specific embodiments in conjunction with the accompanying drawings.

[0013] Reference will be made to Figure 1 , Figure 1 A flowchart of a coal mine thermal dynamic disaster intelligent competitive prevention and control method provided by an embodiment of the present application can be executed by an electronic device, and the method can include: S101: performing feature extraction on multi-source target information data to obtain a disaster type of a coal mine target area; the multi-source target information data is data obtained by preprocessing and standardizing multi-source original information data, and the multi-source target data includes environmental data, visual data and geological data of the coal mine target area.

[0014] In the embodiment, the coal mine thermal dynamic disaster prevention and control relies on multi-source original information data, including environmental data (such as temperature, humidity, gas concentration, oxygen content, etc., which can reflect the current physical environment state of the coal mine and is directly related to disaster occurrence), visual data (such as images collected by a camera in the coal mine, which can intuitively show the device running status, whether there is an open fire, etc.) and geological data (such as coal seam structure, rock characteristics, etc., which can affect the possibility of disaster occurrence and the propagation mode).

[0015] In the embodiment, the multi-source original information data has different formats, units and magnitudes, and the preprocessing step can include data cleaning, and the standardization converts different data to a unified scale. For example, temperature data is standardized to the interval [0, 1].

[0016] In the embodiment, a feature extraction algorithm based on machine learning, such as a convolutional neural network, can be used to process visual data to extract key features, or a statistical analysis method can be used to extract disaster-related features from environmental and geological data. Feature extraction is performed on the preprocessed and standardized multi-source target information data, and these features can reflect the correlation between the current state of the coal mine and potential disasters, and further determine the disaster type of the coal mine target area, such as coal spontaneous combustion, gas explosion, dust explosion, etc.

[0017] S102: Determine a disaster level corresponding to the disaster type based on the disaster type and key data associated with the disaster type; the key data is data in the multi-source target information data.

[0018] In this embodiment, after determining the disaster type, key data closely associated with the disaster type is screened from the multi-source target information data. For example, for coal spontaneous combustion disaster, the key data can include temperature change rate, carbon monoxide generation rate, etc.; for gas explosion disaster, gas concentration change trend, pressure change, etc. These key data can quantify the severity and development trend of the disaster.

[0019] In this embodiment, the pre-established rules can be used to determine the disaster level corresponding to the disaster type based on the screened key data. For example, in coal spontaneous combustion disaster, the temperature change rate is within a certain range, which is low level, and exceeds a certain threshold, which is medium level or high level, so as to accurately classify the severity of the disaster.

[0020] S103: Select at least one type of fire extinguishing material based on the disaster type from the disaster prevention and control knowledge base, the type of fire extinguishing material including liquid, gas and solid.

[0021] In this embodiment, the disaster prevention and control knowledge base is pre-constructed, which stores the fire extinguishing material information applicable to different disaster types.

[0022] Once the disaster type is determined, at least one type of fire extinguishing material is selected from the disaster prevention and control knowledge base. Since different fire extinguishing materials have different inhibitory effects on different disaster types, for example, for coal spontaneous combustion disaster, nitrogen (gas), water (liquid), fireproof paint (solid) can be selected; for gas explosion disaster, explosion suppressant (liquid or solid) can be selected, so as to ensure that the selected material can effectively cope with the corresponding disaster.

[0023] S104: Determine the proportion of different types of fire extinguishing materials based on the disaster level, obtain the control strategy, and control the fire in the coal mine based on the control strategy.

[0024] In this embodiment, for different disaster levels, considering the severity and development speed of the disaster, the proportion of different types of fire extinguishing materials is determined. In this embodiment, the higher the disaster level, the more efficient fire extinguishing material combination is needed, and the amount may be larger. For example, in low-level coal spontaneous combustion disaster, lower concentration of nitrogen gas mixed with appropriate amount of water can be used for prevention and control; while in high-level disaster, the concentration of nitrogen gas can be increased, and more fireproof solid materials can be used.

[0025] In this embodiment, according to the determined material ratio, a complete prevention and control strategy is formulated, including the material delivery mode (such as spraying, perfusion, etc.), delivery time and location, etc. Then, based on the prevention and control strategy, the coal mine is prevented and controlled, and through reasonable material use and operation mode, the development of the disaster is effectively inhibited as much as possible, and the safety of coal production is ensured.

[0026] From the above, it can be concluded that the present embodiment determines the disaster type through pre-processing, standardization and feature extraction of multi-source raw data, comprehensively integrates environmental, visual and geological information, and accurately identifies potential disasters. Based on the disaster type and key data, the disaster level is determined, which can accurately evaluate the severity of the disaster. According to the disaster type, the fire extinguishing materials are selected from the knowledge base to ensure the pertinence of the materials. Then, the material ratio is determined according to the disaster level to form a prevention and control strategy, and precise fire extinguishing and prevention are realized. This method is closely linked, effectively improves the scientificity, accuracy and efficiency of prevention and control, maximally reduces the risk of coal thermal dynamic disasters, and ensures the safety of coal production and personal and property safety.

[0027] In an embodiment of the present application, feature extraction is performed on multi-source target information data to obtain the disaster type of the target area of the coal mine, including: Feature extraction is performed on the environmental data of the target area of the coal mine to obtain an environmental feature vector; Feature extraction is performed on the visual data of the target area of the coal mine to obtain a visual feature vector; Feature extraction is performed on the geological data of the target area of the coal mine to obtain a geological feature vector; The environmental feature vector, the visual feature vector and the geological feature vector are spliced to obtain a multi-source data feature long vector; The multi-source data feature long vector is classified based on a support vector machine to obtain the disaster type of the target area of the coal mine.

[0028] In this embodiment, the environmental data of the target area of the coal mine contains various parameters, such as temperature, humidity, gas concentration, oxygen content, etc. These parameters reflect the real-time physical environmental conditions of the coal mine underground, and are closely related to the occurrence and development of thermal dynamic disasters.

[0029] In this embodiment, the environmental data can be processed by a specific algorithm to extract features. For example, the rate of change of temperature with time is calculated, which can reflect the dynamic change trend of temperature in the process of coal spontaneous combustion; the mean and variance of gas concentration in a period of time are calculated, the mean can reflect the overall concentration level of gas, and the variance can reflect the stability of gas emission. These extracted features are combined into an environmental feature vector, which condenses the key information related to disasters in the environmental data.

[0030] In this embodiment, the visual data mainly comes from images collected by cameras installed in the coal mine underground. The images contain rich scene information, such as the running state of equipment, the presence of open flames, the distribution of smoke, etc. These information is crucial for determining the disaster type.

[0031] This embodiment can use a convolutional neural network (CNN). CNN extracts image features of different scales, such as edges and textures, by sliding the convolution kernel in the convolution layer over the image. The pooling layer reduces the dimensionality of the feature map, reducing the amount of computation while preserving the main features. After multiple convolution and pooling operations, the resulting feature map is flattened to form a visual feature vector, which represents the visual features related to disasters in the visual data.

[0032] In this embodiment, geological data describes the stratum structure and coal seam characteristics of the coal mine area, which has an important influence on the occurrence and propagation of thermodynamic disasters. For example, the thickness, inclination, and coal quality characteristics of the coal seam, as well as the mechanical properties of the rock, are all related to the disaster type.

[0033] This embodiment can extract geological data features through data mining methods. For numerical geological parameters, such as coal seam thickness, normalization can be performed, and the correlation coefficient with other geological parameters can be calculated as a feature. For categorical data, such as coal seam type, one-hot encoding is used to convert it into a numerical vector, and then clustering analysis or other methods are used to extract features, ultimately forming a geological feature vector.

[0034] In this embodiment, the environmental feature vector, visual feature vector, and geological feature vector are concatenated to form a multi-source data feature long vector. This concatenation operation integrates information from different data sources, making the long vector contain multi-aspect disaster-related feature information of the target area of the coal mine, fully reflecting the actual situation of the coal mine.

[0035] Support vector machines are a type of supervised machine learning algorithm that aims to find an optimal hyperplane in the feature space that separates different classes of data as much as possible, maximizing the classification margin.

[0036] In this embodiment, the multi-source data feature long vector is used as the input of the support vector machine, which uses the classification rules learned during the training process to classify the input vector. In the training phase, the support vector machine learns from historical multi-source data feature vectors with disaster type labels, adjusting the model parameters to find the optimal hyperplane. When a new multi-source data feature long vector is input, the support vector machine determines its disaster type category based on the hyperplane, thus obtaining the disaster type of the target area of the coal mine. In this way, intelligent identification of the thermodynamic disaster type of the coal mine based on multi-source data is achieved.

[0037] From the above, the embodiment can provide comprehensive basis for judging disaster type by respectively extracting environmental, visual, and geological data feature vectors and splicing and integrating multi-source information. Based on support vector machine classification, the data features can be effectively utilized to achieve accurate classification and accurately identify the disaster type of the target region of the coal mine.

[0038] In an embodiment of the present application, the disaster level corresponding to the disaster type is determined based on the disaster type and the key data associated with the disaster type, including: The correlation between the disaster type and each target information data in the multi-source target information data is calculated based on the Pearson correlation coefficient to obtain a plurality of correlation coefficients; The key data associated with the disaster type is determined based on the plurality of correlation coefficients and the correlation coefficient threshold; The key data is input into the trained random forest model to classify the key data, and the disaster level corresponding to the disaster type is obtained.

[0039] The Pearson correlation coefficient is used to measure the strength and direction of the linear relationship between two variables. In the embodiment, the Pearson correlation coefficient is calculated for each target information data (such as temperature, gas concentration, and coal seam thickness, each as a variable) in the multi-source target information data and a specific disaster type (such as coal spontaneous combustion and gas explosion, which can be regarded as a variable).

[0040] For each pair of variables (disaster type variable and certain target information data variable), the correlation coefficient r is calculated by the Pearson correlation coefficient formula: where n is the number of data samples, and are the values of the two variables at the i-th sample, and are the means of the two variables. Through this calculation, a plurality of coefficients representing the correlation between the disaster type and each target information data are obtained.

[0041] In the embodiment, a correlation coefficient threshold is pre-set. The correlation coefficient threshold can be determined based on the experience in the field of coal mine thermodynamic disasters and the analysis of a large amount of historical data, and is used to screen data with strong correlation with the disaster type.

[0042] The plurality of correlation coefficients calculated are compared with the threshold. If the correlation coefficient between a certain target information data and the disaster type is greater than (or less than, depending on the actual analysis requirement) the threshold, it is considered that the target information data is closely related to the disaster type, and thus the target information data is determined as the key data associated with the disaster type. For example, if the correlation coefficient between gas concentration and gas explosion disaster type is higher than the threshold, the gas concentration is determined as the key data.

[0043] In this embodiment, the random forest model is an ensemble learning model composed of multiple decision trees. Before use, it has been trained with a large amount of historical critical data with disaster level labels. During training, the random forest model builds multiple decision trees by learning the characteristics of the critical data, and each decision tree is split based on the input critical data to predict the disaster level as accurately as possible.

[0044] The currently determined critical data is input into the trained random forest model. Each decision tree in the model classifies the input critical data according to the rules it has learned, and predicts a disaster level. Then, the random forest model synthesizes the prediction results of each decision tree through a voting mechanism, and finally determines the disaster level corresponding to the disaster type. For example, if most decision trees predict a gas explosion as a high-level disaster, the final disaster level is determined to be high. In this way, accurate determination of the disaster level based on critical data is achieved.

[0045] From the above, it can be seen that in this embodiment, the Pearson correlation coefficient is used to determine the correlation between the disaster type and each data, and the critical data is selected to provide a core basis for determining the disaster level. Then, the trained random forest model is used to classify the critical data, which can effectively mine data value and accurately determine the disaster level. In an embodiment of the present application, the determination method of the correlation coefficient threshold value includes: constructing a correlation matrix based on critical data and disaster levels; clustering the correlation matrix to obtain a clustering tree diagram; determining the correlation coefficient threshold value based on the height of the clustering tree diagram.

[0047] In this embodiment, the correlation coefficients between all critical data and disaster levels are arranged into a matrix, i.e. a correlation matrix. Each element in the correlation matrix represents the correlation between a critical data and a disaster level, reflecting the quantitative relationship between different critical data and disaster levels.

[0048] In this embodiment, for the constructed correlation matrix, the hierarchical clustering algorithm can be used for processing. The hierarchical clustering algorithm calculates the distance between data points (in this embodiment, the distance is calculated based on the correlation coefficient, and the higher the correlation, the closer the distance), and gradually merges similar data points to form a clustering structure.

[0049] During the clustering process, the hierarchical clustering algorithm generates a cluster dendrogram. This dendrogram shows how data points are gradually merged into clusters at different levels. Each node represents a cluster, and the lines connecting the nodes indicate the merging relationships between clusters. The height of the dendrogram (represented as a distance measure when two clusters merge) reflects the similarities or differences between clusters.

[0050] In this embodiment, the height of the cluster dendrogram intuitively reflects the degree of similarity or difference between the data points. When determining the correlation coefficient threshold, it is necessary to observe the structure and height information of the dendrogram.

[0051] If at a certain height in the dendrogram, the data points can be clearly divided into several clusters with obvious distinction, and these clusters are consistent with the actual disaster level or the importance grouping of key data, then the correlation coefficient corresponding to this height can be used as the correlation coefficient threshold.

[0052] For example, at a certain height, the clustering results divide key data into two groups: one with a high correlation with high-level disasters and the other with a high correlation with low-level disasters. The correlation coefficient value corresponding to this height can be used as a threshold. Data above this threshold is considered to have a strong correlation with the disaster level and is considered to be the more important part of the key data for determining the disaster level. Data below this threshold is relatively weakly correlated with the disaster level. In this way, the correlation coefficient threshold determined based on the height of the cluster dendrogram can scientifically and rationally screen the data most critical for determining the disaster level, improving the accuracy and reliability of subsequent disaster level judgments based on key data.

[0053] As can be seen above, this embodiment constructs a correlation matrix to comprehensively present the relationship between key data and disaster levels. Clustering creates a dendrogram, visually displaying data distribution characteristics. Determining the correlation coefficient threshold based on the height of the dendrogram allows for scientific and objective screening of key data, avoiding the blindness of subjective settings and improving the accuracy of disaster level determination.

[0054] In one embodiment of the present application, the correlation between the disaster type and each target information data in the multi-source target information data is calculated based on the Pearson correlation coefficient to obtain multiple correlation coefficients, including: Calculate the correlation between the disaster type and each target information data in the multi-source target information data based on the first formula to obtain multiple correlation coefficients; The first formula is:

[0055] in, represents the correlation coefficient, n represents the number of target information data, represents the disaster-related characteristic value in the i-th target information data, the mean value of the target information data, the result of the numerical value of the disaster level corresponding to the i-th target information data, the mean value of the disaster level, the weight coefficient corresponding to the i-th target information data.

[0056] In this embodiment, the multi-source target information data can include coal mine environment, vision and geology, etc., containing a large number of disaster-related characteristic values. This embodiment can record the disaster-related characteristic values in each target information data as , such as temperature, gas concentration, etc.; after the corresponding disaster level is numerically valued, it is taken as , for example, low level is 1, medium level is 2, and high level is 3. n represents the number of target information data, and the association between disaster type and each characteristic value is mined through analysis of these data.

[0057] The traditional Pearson correlation coefficient assumes that each data point contributes equally to the overall correlation, but in the coal mine disaster scenario, different target information data have different importance in judging the disaster type. Therefore, this embodiment introduces a weight coefficient , which can give different weights to each target information data according to actual conditions, such as the reliability of data source, the timeliness of data impact on disaster, etc. For example, data collected recently or from key monitoring areas may be given higher weight to highlight its role in correlation calculation.

[0058] Molecular part The weighted sum of of each data point is carried out through the weight coefficient . The deviation of the i-th target information data characteristic value from the mean value is measured, The deviation of the corresponding disaster level from the average disaster level is measured, and the product of the two reflects the synergy of the characteristic value and the change of the disaster level of the data point. The weighted sum comprehensively considers the synergistic effect of all data points.

[0059] Molecular part Similarly, the weighted sum of and is carried out and then the square root is taken. and measure the fluctuation of the target information data characteristic value and the disaster level relative to the respective mean value, respectively. The square root result of the weighted value is used to standardize the molecule, so that the value range of the correlation coefficient R is between-1 and 1, which is convenient for comparing the correlation strength of different target information data and disaster types.

[0060] In this embodiment, the weight coefficient can be determined based on the time characteristics of the target information data .

[0061] Considering the dynamic changes of the coal mining environment and disaster risks, the recent data can better reflect the current actual situation. For time series data, such as temperature, gas concentration and other data monitored over time, the closer the data is to the current time, the higher the weight is given. For example, an exponential decay function can be used to determine the weight, ω i = α t , where a is the decay factor (0 < a < 1), and t is the time interval between the data sampling time and the current time (calculated in a certain fixed time unit, such as days). In this way, newer data has a higher weight, and older data has a gradually decreasing weight.

[0062] From the above, it can be seen that the embodiment calculates the correlation by the improved Pearson correlation coefficient formula, and by introducing the weight coefficient, the important data can be highlighted according to the actual situation. Precise quantification of the correlation between disaster types and each target information data improves the scientificity and accuracy of determining the disaster grade.

[0063] In an embodiment of the present application, the ratio of different types of fire extinguishing materials is determined based on the disaster grade to obtain a control strategy, including: Selecting an initial ratio of the ratio of a plurality of fire extinguishing materials from the disaster control knowledge base based on the disaster grade; Filtering the plurality of initial ratios based on the plurality of initial ratios and the environmental data and geological data of the target area of the coal mine to obtain a control strategy.

[0064] In this embodiment, a large amount of knowledge and experience about different disaster grades and fire extinguishing material ratios are accumulated in advance and stored in the disaster control knowledge base. The knowledge base is constructed based on long-term theoretical research, experimental data and actual coal mine disaster control cases.

[0065] After determining the disaster grade of the target area of the coal mine, the embodiment can retrieve and select a plurality of corresponding fire extinguishing material ratios from the disaster control knowledge base as initial ratios according to the grade. For example, for low-grade coal spontaneous combustion disasters, the knowledge base stores several recommended fire extinguishing material combinations and ratios for this grade, such as mixing nitrogen gas with a lower concentration and an appropriate amount of water, or a certain proportion of fire retardant paint and inerting agent, etc. These are selected as the basis for further filtering.

[0066] In this embodiment, the environmental data of the target area of the coal mine includes temperature, humidity, gas concentration, oxygen content, etc. Different environmental conditions will affect the performance and effect of the fire extinguishing material. For example, in a high-temperature environment, some liquid fire extinguishing materials may be more volatile, affecting their sustained fire extinguishing ability; high gas concentration environment has special requirements for the fire resistance and explosion resistance of the fire extinguishing material. Therefore, these environmental factors need to be considered for initial proportioning screening. If the environmental data shows that the gas concentration is high, the material combination with good explosion suppression performance should be preferentially selected in the initial proportioning, and the proportion of the corresponding material may need to be adjusted to enhance the prevention and control of gas explosion risk.

[0067] The geological data describes the stratum structure, coal seam characteristics, etc. of the coal mine area. The thickness, dip angle, coal quality characteristics of the coal seam, and the mechanical properties of the rock will all have an impact on the fire extinguishing work. For example, a thicker coal seam requires more fire extinguishing materials to cover and suppress the disaster; different coal qualities have different adsorption and reactivity to certain fire extinguishing materials, which will affect the actual use effect of the materials. If the geological data shows that the coal seam is thick and the coal quality is flammable, when screening the initial proportioning, a material combination that can provide more persistent and extensive coverage effect should be selected, and the amount of material should be appropriately increased.

[0068] In this embodiment, the environmental data and geological data of the target area of the coal mine are comprehensively considered, and multiple initial proportionings selected from the knowledge base are evaluated and screened one by one. By comparing the applicability, effectiveness, cost-effectiveness, etc. of different initial proportionings under the current environmental and geological conditions, the unsuitable proportionings are excluded, and finally a fire extinguishing material proportioning that best fits the current actual situation of the coal mine is determined as the prevention and control strategy. This prevention and control strategy can make full use of the environmental and geological conditions and maximize the effectiveness of the fire extinguishing material to achieve the best disaster prevention and control effect.

[0069] From the above, it can be concluded that the initial proportioning is selected from the knowledge base according to the disaster level, and the screening is combined with the environmental and geological data of the coal mine, which can take into account different disaster levels and actual conditions. Ensure that the selected prevention and control strategy adapts to the specific coal mine scene, improve the use efficiency of the fire extinguishing material, accurately respond to disasters, avoid material waste or insufficient prevention and control, and effectively improve the scientificity and economy of coal mine disaster prevention and control.

[0070] In an embodiment of the present application, after determining the proportioning of different types of fire extinguishing materials based on the disaster level, obtaining the prevention and control strategy, and conducting fire extinguishing and prevention and control of the coal mine based on the prevention and control strategy, the following steps are further included: determining a new disaster level corresponding to the disaster type based on a preset time period after the fire extinguishing and prevention and control; in response to the new disaster level being greater than or equal to the disaster level, adjusting the proportioning of different types of fire extinguishing materials to obtain a new prevention and control strategy, and conducting fire extinguishing and prevention and control of the coal mine based on the new prevention and control strategy.

[0071] After implementing the fire prevention and control measures, a specific preset time period is set for evaluating the prevention and control effect. The selection of this time period should consider the characteristics of coal mine thermal dynamic disasters and the action time of fire prevention and control materials. For example, for coal spontaneous combustion disasters, one week can be set, because coal spontaneous combustion is a relatively slow process, and one week is enough to observe whether the prevention and control measures can effectively inhibit the development of spontaneous combustion; for gas explosion risk prevention and control, the preset time period is shorter, such as one day, because the gas concentration changes quickly, and the control of the prevention and control measures on the gas explosion hazard can be reflected in a short time.

[0072] In this embodiment, after the preset time period ends, the relevant data of the target area of the coal mine are re-collected, including but not limited to environmental data (such as temperature, gas concentration, oxygen content, etc.), visual data (whether there is still open fire, smoke, etc.), and geological data (whether the coal seam state has changed, etc.). Based on these data, the method for determining the disaster level (such as by feature extraction on multi-source data, inputting the trained model, etc.) is used to re-determine the new disaster level corresponding to the disaster type. The purpose is to objectively and accurately measure the actual situation of the disaster after the implementation of the fire prevention and control measures.

[0073] In this embodiment, the newly determined disaster level is compared with the disaster level before the implementation of the prevention and control strategy. If the new disaster level is greater than or equal to the previous disaster level, it indicates that the current prevention and control strategy has failed to effectively reduce the disaster risk, and even the disaster has a tendency to intensify. For example, after taking the prevention and control measures, the coal body temperature does not decrease in the preset time period, and even continues to rise, and the newly determined disaster level remains unchanged or increases, which requires adjustment of the prevention and control strategy.

[0074] In this embodiment, for the case where the disaster level does not decrease, the proportioning of different types of fire prevention and control materials is adjusted. This adjustment process can refer to the disaster prevention and control knowledge base and the specific data of the target area of the coal mine. For example, if it is found that the gas concentration is still high, the proportion of materials that can reduce the gas concentration (such as high-efficiency gas adsorbent) can be increased in the original proportioning of fire prevention and control materials, or the material combination more suitable for the current gas concentration and distribution can be replaced. Through the adjustment of the proportioning, a new prevention and control strategy is formed.

[0075] In this embodiment, based on the new prevention and control strategy, the coal mine is re-prevented and controlled, and it is expected that the new strategy can more effectively cope with the disaster, reduce the disaster level, and achieve effective control of the coal mine thermal dynamic disaster. This cyclic process embodies the dynamic adjustment and optimization of the coal mine disaster prevention and control, ensuring that the prevention and control measures always adapt to the development and change of the disaster.

[0076] From the above, the embodiment determines the new disaster level by the preset time period evaluation, and adjusts the ratio of fire extinguishing materials if it is not reduced. This dynamic adjustment mechanism can adapt to disaster changes in real time, ensure that the prevention and control strategy is always effective, avoid the failure of prevention and control due to fixed strategy, significantly improve the precision and sustainability of coal mine fire extinguishing and prevention, and ensure the safety of coal mine.

[0077] A coal mine thermodynamic disaster intelligent competitive prevention and control method corresponding to the above embodiment, Figure 2 The structural block diagram of a coal mine thermodynamic disaster intelligent competitive prevention and control system provided for an embodiment of the present application. For ease of illustration, only parts related to the embodiments of the present application are shown. For reference Figure 2 The coal mine thermodynamic disaster intelligent competitive prevention and control system 20 includes a disaster type determination module 21, a disaster level determination module 22, a fire extinguishing material selection module 23, and a fire extinguishing and prevention module 24.

[0078] The disaster type determination module 21 is configured to perform feature extraction on multi-source target information data to obtain the disaster type of the target area of the coal mine; the multi-source target information data is data obtained by preprocessing and standardizing multi-source original information data, and the multi-source target data includes environmental data, visual data, and geological data of the target area of the coal mine; The disaster level determination module 22 is configured to determine the disaster level corresponding to the disaster type based on the disaster type and key data associated with the disaster type; the key data is data in the multi-source target information data; The fire extinguishing material selection module 23 is configured to select at least one type of fire extinguishing material from a disaster prevention and control knowledge base based on the disaster type, and the types of fire extinguishing materials include liquid, gas, and solid; The fire extinguishing and prevention module 24 is configured to determine the ratio of different types of fire extinguishing materials based on the disaster level, obtain a prevention and control strategy, and perform fire extinguishing and prevention on the coal mine based on the prevention and control strategy.

[0079] In an embodiment of the present application, the disaster type determination module 21 is specifically configured to: perform feature extraction on the environmental data of the target area of the coal mine to obtain an environmental feature vector; perform feature extraction on the visual data of the target area of the coal mine to obtain a visual feature vector; perform feature extraction on the geological data of the target area of the coal mine to obtain a geological feature vector; splice the environmental feature vector, the visual feature vector, and the geological feature vector to obtain a multi-source data feature long vector; classify the multi-source data feature long vector based on a support vector machine to obtain the disaster type of the target area of the coal mine.

[0080] In an embodiment of the present application, the disaster grade determination module 22 is specifically configured to: calculate the correlation between the disaster type and each target information data in the multi-source target information data based on the Pearson correlation coefficient, to obtain a plurality of correlation coefficients; determine the key data associated with the disaster type based on the plurality of correlation coefficients and the correlation coefficient threshold value; input the key data into the trained random forest model to classify the key data, to obtain the disaster grade corresponding to the disaster type.

[0081] In an embodiment of the present application, the disaster grade determination module 22 is specifically further configured to: construct a correlation matrix based on the key data and the disaster grade; cluster the correlation matrix to obtain a cluster tree diagram; determine the correlation coefficient threshold value based on the height of the cluster tree diagram.

[0082] In an embodiment of the present application, the disaster grade determination module 22 is specifically further configured to: calculate the correlation between the disaster type and each target information data in the multi-source target information data based on the first formula, to obtain a plurality of correlation coefficients; The first formula is:

[0083] wherein, represents the correlation coefficient, n represents the number of target information data, represents the feature value related to the disaster in the i-th target information data, represents the mean value of the target information data, represents the result of the i-th target information data after numerical valueization corresponding to the disaster grade, represents the mean value of the disaster grade, represents the weight coefficient corresponding to the i-th target information data.

[0084] In an embodiment of the present application, the fire extinguishing and prevention module 24 is specifically configured to: select the initial proportion of the proportion of a plurality of fire extinguishing materials from the disaster prevention and control knowledge base based on the disaster grade; filter the plurality of initial proportions based on the plurality of initial proportions and the environmental data and geological data of the coal mine target area, to obtain the prevention and control strategy.

[0085] In an embodiment of the present application, a coal mine thermal dynamic disaster intelligent competitive prevention and control system 20 further comprises an adjustment module, which is specifically configured to: determine the new disaster grade corresponding to the disaster type based on a preset time period after fire extinguishing and prevention; In response to the new disaster level being greater than or equal to the disaster level, the ratio of different types of fire prevention and extinguishing materials is adjusted to obtain a new prevention and control strategy, and fire extinguishing and control are carried out in the coal mine based on the new prevention and control strategy.

[0086] See also Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided in one embodiment of the present application. Figure 3 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules in the above-mentioned system embodiments, such as Figure 2 The functions of the disaster type determination module 21, the disaster level determination module 22, the fire extinguishing material selection module 23, and the fire extinguishing prevention and control module 24 are shown.

[0087] It should be understood that in the embodiment of the present application, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0088] The input device 302 may include a touchpad, a fingerprint collection sensor (for collecting user fingerprint information and fingerprint direction information), a microphone, etc. The output device 303 may include a display (LCD, etc.), a speaker, etc.

[0089] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store information such as a disaster prevention and control knowledge base and correlation coefficient thresholds.

[0090] In specific implementation, the processor 301, the input device 302 and the output device 303 described in the embodiments of the present application can execute the implementation manner of the coal mine thermal power disaster intelligent competitive prevention and control method provided by the embodiments of the present application, and can also execute the implementation manner of the electronic device described in the embodiments of the present application, which will not be described here.

[0091] In another embodiment of the present application, a computer readable storage medium is provided, which stores a computer program. The computer program includes program instructions, which are executed by a processor to implement all or part of the processes of the above-mentioned embodiments. The computer program can also be used to instruct related hardware to complete the processes. The computer program can be stored in a computer readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium can include any entity or system capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0092] The computer readable storage medium can be an internal storage unit of the electronic device, such as a hard disk or a memory of the electronic device. The computer readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer readable storage medium can include both the internal storage unit and the external storage device of the electronic device. The computer readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0093] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been described in general terms in the foregoing description. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0094] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0095] In several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interfaces or units, and can also be electrical, mechanical or other form of connection.

[0096] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0097] In addition, the functional modules in each embodiment of the present application can be integrated in one processing unit, or each module can be physically present alone, or two or more modules can be integrated in one unit. The integrated unit can be realized in the form of hardware or software functional unit.

[0098] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An intelligent competitive prevention and control method for thermal power disasters in coal mines, characterized by: include: Extracting features from multi-source target information data to obtain disaster types in the target area of ​​the coal mine; the multi-source target information data is pre-processed and standardized from the multi-source original information data, and the multi-source target data includes environmental data, visual data, and geological data of the target area of ​​the coal mine; Determining a disaster level corresponding to the disaster type based on the disaster type and key data associated with the disaster type; the key data being data in the multi-source target information data; Selecting at least one type of fire extinguishing material from a disaster prevention and control knowledge base based on the disaster type, wherein the fire extinguishing material includes liquid, gas, and solid; The proportions of different types of fire prevention and extinguishing materials are determined based on the disaster level, a prevention and control strategy is obtained, and fire extinguishing and prevention and control are carried out in the coal mine based on the prevention and control strategy.

2. The intelligent competitive prevention and control method for thermal and dynamic disasters in coal mines according to claim 1, characterized in that: The feature extraction of multi-source target information data is performed to obtain the disaster type of the target area of ​​the coal mine, including: Extract features from the environmental data of the target area of ​​the coal mine to obtain the environmental feature vector; Extract features from the visual data of the target area of ​​the coal mine and obtain visual feature vectors; Extract features from geological data of the target area of ​​the coal mine to obtain geological feature vectors; splicing the environmental feature vector, the visual feature vector, and the geological feature vector to obtain a multi-source data feature long vector; The multi-source data feature long vectors are classified based on a support vector machine to obtain the disaster type of the target area of ​​the coal mine.

3. The intelligent competitive prevention and control method for thermal and dynamic disasters in coal mines according to claim 1, characterized in that: Determining a disaster level corresponding to the disaster type based on the disaster type and key data associated with the disaster type includes: Calculating the correlation between the disaster type and each target information data in the multi-source target information data based on the Pearson correlation coefficient to obtain multiple correlation coefficients; determining key data associated with the disaster type based on a plurality of correlation coefficients and correlation coefficient thresholds; The key data are input into a trained random forest model to classify the key data and obtain the disaster level corresponding to the disaster type.

4. The intelligent competitive prevention and control method for thermal and dynamic disasters in coal mines according to claim 3, characterized in that: The correlation coefficient threshold is determined by: constructing a correlation matrix based on the key data and disaster levels; Clustering the correlation matrix to obtain a cluster dendrogram; The correlation coefficient threshold is determined based on the height of the cluster dendrogram.

5. The intelligent competitive prevention and control method for thermal and dynamic disasters in coal mines according to claim 3, characterized in that: The correlation between the disaster type and each target information data in the multi-source target information data is calculated based on the Pearson correlation coefficient to obtain multiple correlation coefficients, including: Calculating the correlation between the disaster type and each target information data in the multi-source target information data based on the first formula to obtain multiple correlation coefficients; The first formula is: in, represents the correlation coefficient, n represents the number of target information data, represents the disaster-related characteristic value in the i-th target information data, represents the mean of the target information data, It represents the numerical result of the disaster level corresponding to the i-th target information data. represents the mean value of the disaster level, Represents the weight coefficient corresponding to the i-th target information data.

6. The intelligent competitive prevention and control method for thermal and dynamic disasters in coal mines according to claim 1, characterized in that: The method of determining the ratio of different types of fire extinguishing materials based on the disaster level to obtain a prevention and control strategy includes: Selecting, based on the disaster level, an initial ratio of multiple fire extinguishing materials from a disaster prevention and control knowledge base; The multiple initial proportions are screened based on the multiple initial proportions and the environmental data and geological data of the target area of ​​the coal mine to obtain a prevention and control strategy.

7. The intelligent competitive prevention and control method for thermal and dynamic disasters in coal mines according to claim 1, characterized in that: After determining the ratio of different types of fire prevention and extinguishing materials based on the disaster level, obtaining a prevention and control strategy, and performing fire prevention and control on the coal mine based on the prevention and control strategy, the method further includes: Determining a new disaster level corresponding to the disaster type based on a preset time period after fire extinguishing and prevention; In response to the new disaster level being greater than or equal to the disaster level, the ratio of different types of fire prevention and extinguishing materials is adjusted to obtain a new prevention and control strategy, and fire extinguishing and control are performed on the coal mine based on the new prevention and control strategy.

8. An intelligent competitive prevention and control system for thermal and dynamic disasters in coal mines, characterized by: include: The disaster type determination module is used to extract features from multi-source target information data to obtain the disaster type of the target area of ​​the coal mine; The multi-source target information data is data obtained by preprocessing and standardizing the multi-source original information data, and the multi-source target data includes environmental data, visual data and geological data of the target area of ​​the coal mine; A disaster level determination module, configured to determine a disaster level corresponding to the disaster type based on the disaster type and key data associated with the disaster type; the key data being data in the multi-source target information data; a fire extinguishing material selection module, configured to select at least one type of fire extinguishing material from a disaster prevention and control knowledge base based on the disaster type, wherein the types of fire extinguishing materials include liquid, gas, and solid; The fire prevention and control module is used to determine the ratio of different types of fire prevention and extinguishing materials based on the disaster level, obtain a prevention and control strategy, and perform fire prevention and control on the coal mine based on the prevention and control strategy.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images