An intelligent supervision method based on big data

Abstract

The present invention relates to the field of intelligent supervision technology, and specifically to an intelligent supervision method based on big data, comprising the following steps: collecting mineral gas data through gas sensors, obtaining the mineral gas data collected by the gas sensors, and preprocessing the mineral gas data; using machine learning to analyze and mine the mineral gas data, obtaining relevant data of methane gas, carbon monoxide gas and hydrogen sulfide gas from the mineral gas data, and establishing a mineral gas data prediction model; providing visual analysis results, providing real-time monitoring and alarm functions, and timely discovering abnormal mineral gas emissions; formulating an intelligent scheduling algorithm to obtain the distribution of mineral gas based on the intelligent scheduling algorithm, and further identifying the distribution of minerals based on the distribution; so as to provide data-driven decision support for regulatory departments.

Description

Technical Field

[0001] The present invention relates to the field of intelligent supervision technology, and in particular to an intelligent supervision method based on big data. Background Art

[0002] Mineral gases play a very important role in safeguarding the development of the economic environment. With the continuous improvement of urban economic development, the continuous increase in population, the continued steady growth of mineral development and factory construction, the pollution congestion caused by mineral gas emissions has become more and more serious.

[0003] As the city develops rapidly, some problems that need to be solved have also arisen, mainly manifested in: there is no effective information management method between pollution sources and the basic pollution data cannot be displayed. With the continuous improvement of information technology, the construction of a mineral gas management platform with industry supervision, large-screen display, data collection, and public information services as the main functions has become a major problem to be solved in the construction of mineral gas informatization. Summary of the invention

[0004] The present invention aims at solving the technical problems existing in the prior art and provides an intelligent supervision method based on big data to improve the efficiency of mineral development.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: an intelligent supervision method based on big data, comprising the following steps:

[0006] 101. Collect mineral gas data through gas sensors, the mineral gas data including methane gas, carbon monoxide gas and hydrogen sulfide gas, obtain the mineral gas data collected by the gas sensors, and pre-process the mineral gas data;

[0007] 102. Use machine learning to analyze and mine mineral gas data, obtain relevant data on methane gas, carbon monoxide gas, and hydrogen sulfide gas from mineral gas data, and establish a mineral gas data prediction model;

[0008] 103. Provide visual analysis results, real-time monitoring and alarm functions, and timely detect abnormal mineral gas conditions;

[0009] 104. Formulate an intelligent scheduling algorithm to obtain the distribution of mineral gas based on the intelligent scheduling algorithm, and further identify the distribution of minerals based on the distribution.

[0010] In a preferred embodiment, in the 101, sensor equipment is deployed, including gas sensors and GNSS equipment, and data related to mineral gas is collected by acquiring relevant data from the gas sensors. GNSS positioning equipment is installed on the mineral gas emission port to monitor the route and speed of the mineral mining vehicle, monitor and evaluate the emission of mineral gas. The GNSS positioning equipment continuously obtains the location information of the mineral mining vehicle, sends the mineral gas emission situation and location information to the monitoring system for processing, cleans and organizes the collected data, and uses the box plot method to calculate the upper and lower quartiles and the inner limit to determine the range of abnormal values. Data beyond this range is identified as abnormal values. The specific calculation steps are as follows:

[0011] S=Q3+K1*IQR

[0012] X=Q1-K1*IQR

[0013] Among them, S represents the upper limit of the data outlier, X represents the lower limit of the data outlier, Q1 represents the lower quartile, Q3 represents the upper quartile, lQR represents the interquartile range, and K1 represents the constant, which is used to determine the range of outliers and delete the data beyond the range of outliers from the data.

[0014] In a preferred embodiment, in 102, the mineral gas data prediction model obtains relevant data of methane gas, carbon monoxide gas and hydrogen sulfide gas from the mineral gas data, divides the relevant data of mineral gas emissions into a training set and a test set, establishes a mineral gas data prediction model through a linear regression algorithm, and fits the model by minimizing the residual sum of squares. The specific calculation formula is as follows:

[0015] Y=w0+w1x1+w2x2+...+wn*xn

[0016] Among them, x1, x2, ..., xn are the input data related to the mining gas emission, Y represents the output result, w0, w1, ..., wn are the parameters of the model, the trained model is verified through the verification set, and the model is tuned according to the verification results. The model parameters are adjusted by calculating the evaluation indicators to improve the model performance. The specific calculation method of the evaluation indicators is as follows:

[0017]

[0018] Among them, yi is the actual value, Represents the predicted value, n represents the number of samples, and the least squares method is used to minimize the residual sum of squares between the actual output value and the predicted value. The residual is defined and expressed as: Among them, yi represents the actual output value of the i-th sample, Represents the predicted value of the sample. By minimizing the residual sum of squares, the model parameters w0, w1, ..., wn are solved. The specific calculation steps for solving the model parameters are as follows:

[0019] S1. For each model parameter w j (j=0, 1, ..., n), the partial derivative of the residual sum of squares is calculated as follows:

[0020]

[0021] Among them, S represents the residual sum of squares, which represents the sum of squares of the error between the model prediction value and the actual value, wj represents the jth parameter in the linear regression model, Represents the partial derivative of the jth parameter of the model's output value for the i-th data sample;

[0022] S2. Set all partial derivatives to 0 and obtain a set of linear equations:

[0023]

[0024]

[0025] S3, solve the linear equations and obtain the estimated values ​​of the model parameters w0, w1, ..., w n , for new input data, use the trained model to make predictions.

[0026] In a preferred embodiment, in 103, the mineral gas data is analyzed, the mineral gas emission index collected by the mining vehicles in the area is calculated, and the location data of the index calculation result is mapped to the visual map. Specifically, the mineral gas emission index collected by the mining vehicles is calculated as follows:

[0027] P_j=Zj / Zs

[0028] Among them, Zj represents the mineral gas emissions collected by the vehicle, and Zs represents the average speed of the mining vehicle. Specifically, the specific calculation formula for the mineral gas emissions collected by the vehicle for one hour is as follows:

[0029] Zj=L*n*60 / 2

[0030] Among them, L represents the actual mineral gas emission collected by the mining vehicle, n represents the engine speed, and the specific calculation method of the emission index is as follows:

[0031] D=W1*C1+W2*C2+W3*C3

[0032] Among them, W1, W2, and W3 represent the weight coefficients of various mineral gases, reflecting the toxicity and influencing factors of mineral gases. C1, C2, and C3 represent the concentrations of different mineral gases. A heat map is used to display the emission level in the current area, and early warning of emissions is issued by updating data in real time.

[0033] In a preferred embodiment, in 104, the mineral gas distribution path is converted into a gas network topology map, and the distribution path is divided into different areas. The shortest path of the mineral gas emission area is found through a search algorithm, and the heuristic function, the cost function and the evaluation function are calculated. The specific calculation method of the specific heuristic function is as follows:

[0034] h(n)=|N_Z-M_Z|+|N_H-M_H|

[0035] Wherein, N_Z represents the ordinate of the mineral area where the mineral gas is emitted, M_Z represents the ordinate of the current starting point, N_H represents the abscissa of the mineral area where the mineral gas is emitted, and M_H represents the abscissa of the current starting point;

[0036] W1. Define the cost function. The cost function is used to represent the actual cost from the starting node to the current node n. For each node n, the cost function is calculated by accumulating the weights of the sections passed. Assuming that the parent node of node n is p and the weight of the section (n, p) is w, the cost function is defined as:

[0037] g(n)=g(p)+w

[0038] W2. Calculate the evaluation function: The evaluation function comprehensively considers the heuristic function and the cost function to evaluate the priority of node n. The evaluation function is defined as:

[0039] f(n)=g(n)+h(n)

[0040] The evaluation function represents the cost estimate from the start node to the target node through node n. The optimal path creates an open list and a closed list, adds the start node to the open list, and sets the g value of the start node to 0. When the open list is not empty, execute the following loop:

[0041] A1. Select the node n with the smallest f value from the open list as the current node;

[0042] A2. If the current node is the target node, it means the shortest path has been found and the search ends.

[0043] A3. Remove the current node from the open list and add it to the closed list;

[0044] A4. For each neighbor node m of the current node, calculate its cost function and evaluation function. If m is already in the closed list, ignore the node;

[0045] A4. If m is not in the open list, add it to the open list, set the parent node of m to the current node n, and update the q value and f value of m.

[0046] A5. When m is already in the open list, compare the new g value of m with the current g value. If the new g value is smaller, update the parent node of m to the current node n, and update the g value and f value of m.

[0047] The beneficial effects of the present invention are as follows: the present invention monitors mineral gas data, discovers potential mineral resources, issues early warnings, analyzes a large amount of regulatory data, can discover mineral data therein, provide data-driven decision support for regulatory authorities, can make decisions and plans on mineral gas emissions and minerals, and help improve the efficiency of mineral development. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 The figure is a flow chart of an intelligent supervision method based on big data. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0050] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0051] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0052] like Figure 1 This embodiment provides an intelligent supervision method based on big data, which specifically includes the following steps:

[0053] 101. Collect mineral gas data through gas sensors, the mineral gas data including methane gas, carbon monoxide gas and hydrogen sulfide gas, obtain the mineral gas data collected by the gas sensors, and pre-process the mineral gas data;

[0054] 102. Use machine learning to analyze and mine mineral gas data, obtain relevant data on methane gas, carbon monoxide gas, and hydrogen sulfide gas from mineral gas data, and establish a mineral gas data prediction model;

[0055] 103. Provide visual analysis results, real-time monitoring and alarm functions, and timely detect abnormal mineral gas conditions;

[0056] 104. Formulate an intelligent scheduling algorithm to obtain the distribution of mineral gas based on the intelligent scheduling algorithm, and further identify the distribution of minerals based on the distribution.

[0057] In this embodiment, what needs to be specifically explained is 101. In the above 101, sensor equipment is deployed, including gas sensors and GNSS equipment. Data related to mineral gas is collected by acquiring relevant data from the gas sensors, and GNSS positioning equipment is installed on the mineral gas emission port to monitor the driving route and speed of the mineral mining vehicle, monitor and evaluate the mineral gas emission in the mineral area, and the GNSS positioning equipment continuously obtains the location information of the mineral mining vehicle, sends the mineral gas emission situation and location information to the monitoring system for processing, cleans and organizes the collected data, and uses the box plot method to calculate the upper and lower quartiles and the inner limit to determine the range of abnormal values. Data beyond this range is identified as abnormal values. The specific calculation steps are as follows:

[0058] S=Q3+K1*IQR

[0059] X=Q1-K1*IQR

[0060] Among them, S represents the upper limit of the data outlier, X represents the lower limit of the data outlier, Q1 represents the lower quartile, Q3 represents the upper quartile, IQR represents the interquartile range, and K1 represents the constant, which is used to determine the range of outliers and delete the data that exceeds the outlier range from the data.

[0061] In this embodiment, what needs to be specifically explained is 102. In 102, the mineral gas data prediction model obtains relevant data of methane gas, carbon monoxide gas and hydrogen sulfide gas from the mineral gas data, divides the relevant data of mineral gas emissions into a training set and a test set, establishes a mineral gas data prediction model through a linear regression algorithm, and fits the model by minimizing the residual sum of squares. The specific calculation formula is as follows:

[0062] Y=w0+w1x1+w2x2+...+wn*xn

[0063] Among them, x1, x2, ..., xn are the input data related to the mining gas emission, Y represents the output result, w0, w1, ..., wn are the parameters of the model, the trained model is verified through the verification set, and the model is tuned according to the verification results. The model parameters are adjusted by calculating the evaluation indicators to improve the model performance. The specific calculation method of the evaluation indicators is as follows:

[0064]

[0065] Among them, yi is the actual value, Represents the predicted value, n represents the number of samples, and the least squares method is used to minimize the residual sum of squares between the actual output value and the predicted value. The residual is defined and expressed as: Among them, yi represents the actual output value of the i-th sample, Represents the predicted value of the sample. By minimizing the residual sum of squares, the model parameters w0, w1, ..., wn are solved. The specific calculation steps for solving the model parameters are as follows:

[0066] S1. For each model parameter w j (j=0, 1, ..., n), the partial derivative of the residual sum of squares is calculated as follows:

[0067]

[0068] Among them, S represents the residual sum of squares, which represents the sum of squares of the error between the model prediction value and the actual value, wj represents the jth parameter in the linear regression model, Represents the partial derivative of the jth parameter of the model's output value for the i-th data sample;

[0069] S2. Set all partial derivatives to 0 and obtain a set of linear equations:

[0070]

[0071] S3, solve the linear equations and obtain the estimated values ​​of the model parameters w0, w1, ..., w n , for new input data, use the trained model to make predictions.

[0072] In this embodiment, what needs to be specifically explained is 103. In the above 103, the mineral gas data is analyzed, the mineral gas emission index collected by the mineral mining vehicles in the area is calculated, and the location data of the index calculation result is mapped to the visual map. Specifically, the mineral gas emission coefficient collected by the mineral mining vehicle is specifically calculated as follows:

[0073] P_j=Zj / Zs

[0074] Among them, Zj represents the mineral gas emissions collected by the vehicle, and Zs represents the average speed of the mining vehicle. Specifically, the specific calculation formula for the mineral gas emissions collected by the vehicle for one hour is as follows:

[0075] Zj=L*n*60 / 2

[0076] Where L represents the actual mineral gas emission collected by the mining vehicle, n represents the engine speed, and the specific calculation method of the emission index is as follows:

[0077] D=W1*C1+W2*C2+W3*C3

[0078] Among them, W1, W2, and W3 represent the weight coefficients of various mineral gases, reflecting the toxicity and influencing factors of mineral gases. C1, C2, and C3 represent the concentrations of different mineral gases. A heat map is used to display the emission level in the current area, and early warning of emissions is issued by updating data in real time.

[0079] In this embodiment, it is necessary to specifically explain that 104, the mineral gas distribution path is converted into a gas network topology map, and the distribution path is divided into different areas. Through the search algorithm, the shortest path of the mineral gas emission area is found, and the heuristic function, the cost function and the evaluation function are calculated. The specific calculation method of the specific heuristic function is as follows:

[0080] h(n)=|N_Z-M_Z|+|N_H-M_H|

[0081] Among them, N_Z represents the ordinate of the mineral area where the mineral gas is emitted, M_Z represents the ordinate of the current starting point, N_H represents the abscissa of the mineral area where the mineral gas is emitted, and M_H represents the abscissa of the current starting point.

[0082] W1. Define the cost function. The cost function is used to represent the actual cost from the starting node to the current node n. For each node n, the cost function is calculated by accumulating the weights of the sections passed. Assuming that the parent node of node n is p and the weight of the section (n, p) is w, the cost function is defined as:

[0083] g(n)=g(p)+w

[0084] W2. Calculate the evaluation function: The evaluation function comprehensively considers the heuristic function and the cost function to evaluate the priority of node n. The evaluation function is defined as:

[0085] f(n)=g(n)+h(n)

[0086] The evaluation function represents the cost estimate from the start node to the target node through node n. The optimal path creates an open list and a closed list, adds the start node to the open list, and sets the g value of the start node to 0. When the open list is not empty, execute the following loop:

[0087] A1. Select the node n with the smallest f value from the open list as the current node;

[0088] A2. If the current node is the target node, it means the shortest path has been found and the search ends.

[0089] A3. Remove the current node from the open list and add it to the closed list;

[0090] A4. For each neighbor node m of the current node, calculate its cost function and evaluation function. If m is already in the closed list, ignore the node;

[0091] A4. If m is not in the open list, add it to the open list, set the parent node of m to the current node n, and update the q value and f value of m.

[0092] A5. When m is already in the open list, compare the new g value of m with the current g value. If the new g value is smaller, update the parent node of m to the current node n, and update the g value and f value of m.

[0093] The residual in the present invention represents the difference between the actual output value of each data castration version and the corresponding predicted value. Specifically, it should be noted that the output result of the model is the predicted value obtained after predicting the input traffic data, and the output result is the predicted value of traffic flow in a certain period of time in the future.

[0094] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0095] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0096] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0097] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0099] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0100] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent supervision method based on big data, characterized in that: The following steps are involved:

101. Collect mineral gas data through gas sensors, the mineral gas data including methane gas, carbon monoxide gas and hydrogen sulfide gas, obtain the mineral gas data collected by the gas sensors, and pre-process the mineral gas data; Deploy sensor equipment, including gas sensors and GNSS equipment, collect mineral gas related data by obtaining relevant data from gas sensors, and install GNSS positioning equipment on mineral gas emission outlets to monitor the driving route and speed of mineral mining vehicles, monitor and evaluate mineral gas emissions. GNSS positioning equipment continuously obtains the location information of mineral mining vehicles, sends mineral gas emission conditions and location information to the monitoring system for processing, cleans and organizes the collected data, and uses the box plot method to calculate the upper and lower quartiles and inner limits to determine the range of outliers. Data outside this range is identified as outliers. The specific calculation steps are as follows: S=Q3+K1*IIQR X=Q1-K1*IIQR Among them, S represents the upper limit of the data outlier, X represents the lower limit of the data outlier, Q1 represents the lower quartile, Q3 represents the upper quartile, IQR represents the interquartile range, and K1 represents the position constant, which is used to determine the range of outliers and delete the data beyond the range of outliers from the data; 102. Use machine learning to analyze and mine mineral gas data, obtain relevant data on methane gas, carbon monoxide gas, and hydrogen sulfide gas from mineral gas data, and establish a mineral gas data prediction model; 103. Provide visual analysis results, real-time monitoring and alarm functions, and timely detect abnormal mineral gas conditions; 104. Formulate an intelligent scheduling algorithm to obtain the distribution of mineral gas based on the intelligent scheduling algorithm, and further identify the distribution of minerals based on the distribution.

2. According to claim 1, a smart supervision method based on big data is characterized in that: In 102, the mineral gas data prediction model obtains relevant data of methane gas, carbon monoxide gas and hydrogen sulfide gas from the mineral gas data, divides the relevant data of mineral gas emissions into a training set and a test set, establishes a mineral gas data prediction model through a linear regression algorithm, and fits the model by minimizing the residual sum of squares. The specific calculation formula is as follows: Y=w0+w1x1+w2x2+...wn*xn Among them, x1, x2, ..., xn are the input data related to mineral gas emissions, Y represents the output result, w0, w1, ..., wn are the parameters of the model, the trained model is verified through the verification set, and the model is tuned according to the verification results, and the model parameters are adjusted by calculating the evaluation indicators.

3. According to claim 2, a smart supervision method based on big data is characterized in that: The specific calculation method of the evaluation index is as follows: Among them, yi is the actual value, Represents the predicted value, n represents the number of samples, and the least squares method is used to minimize the residual sum of squares between the actual output value and the predicted value. The residual is defined and expressed as: Among them, yi represents the actual output value of the i-th sample, Represents the predicted value of the sample, and the model parameters w0, w1, ..., wn are solved by minimizing the residual sum of squares.

4. The intelligent supervision method based on big data according to claim 3 is characterized in that: The solution model parameters, for each model parameter w j (j=0, 1, ..., n), the partial derivative of the residual sum of squares is calculated as follows: Among them, S represents the residual sum of squares, which represents the sum of squares of the error between the model prediction value and the actual value, wj represents the jth parameter in the linear regression model, Represents the partial derivative of the jth parameter of the model's output value for the i-th data sample.

5. The intelligent supervision method based on big data according to claim 4 is characterized in that: The calculation steps of the partial derivative are as follows: S1. Set all partial derivatives to 0 and obtain a set of linear equations: S2. Solve the linear equations to obtain the estimated values ​​of the model parameters w0, w1, ..., w n , for new input data, use the trained model to make predictions.

6. The intelligent supervision method based on big data according to claim 1 is characterized in that: In the above 103, the mineral gas data is analyzed, the mineral gas emission index collected by the mining vehicles in the area is calculated, and the location data of the index calculation result is mapped to the visual map. Specifically, the mineral gas emission index collected by the mining vehicles is calculated as follows: P_j=Zj / Zs Among them, Zj represents the mineral gas emissions collected by the vehicle, and Zs represents the average speed of the mining vehicle. Specifically, the specific calculation formula for the mineral gas emissions collected by the vehicle for one hour is as follows: Zj=L*n*60 / 2 Where L represents the actual mineral gas displacement collected by the mineral excavation vehicle, and n represents the engine speed.

7. The intelligent supervision method based on big data according to claim 6 is characterized in that: The specific calculation method of the emission coefficient is as follows: D=W1*C1+W2*C2+W3*C3 Among them, W1, W2, and W3 represent the weight coefficients of various mineral gases, reflecting the toxicity and influencing factors of mineral gases. C1, C2, and C3 represent the concentrations of different mineral gases. A heat map is used to display the emission level in the current area, and early warning of emissions is issued by updating data in real time.

8. The intelligent supervision method based on big data according to claim 1 is characterized in that: In the above 104, the mineral gas distribution path is converted into a gas network topology map, and the distribution path is divided into different areas. The shortest path of the mineral gas emission area is found through a search algorithm, and the heuristic function, the cost function and the evaluation function are calculated. The specific calculation method of the specific heuristic function is as follows: h(n)=|N_Z-M_Z|+|NH-M_H| Among them, N_Z represents the ordinate of the mineral area where mineral gas is emitted, M_Z represents the ordinate of the current starting point, N_H represents the abscissa of the mineral area where mineral gas is emitted, and M_H represents the abscissa of the current starting point.

9. The intelligent supervision method based on big data according to claim 8 is characterized in that: The specific calculation steps of the cost function and the evaluation function are as follows: W1. Define the cost function. The cost function is used to represent the actual cost from the starting node to the current node n. For each node n, the cost function is calculated by accumulating the weights of the sections passed. Assuming that the parent node of node n is p and the weight of the section (n, p) is w, the cost function is defined as: g(n)=g(p)+w W2. Calculate the evaluation function: The evaluation function comprehensively considers the heuristic function and the cost function to evaluate the priority of node n. The evaluation function is defined as: f(n)=g(n)+h(n) The evaluation function represents the cost estimate from the start node to the target node through node n. The optimal path is created by creating an open list and a closed list, adding the start node to the open list, and setting the g value of the start node to 0.

Images