A comprehensive intelligent production safety management and control method and system

Abstract

The present invention relates to the field of intelligent control processing, and more specifically, to a comprehensive safe production intelligent management and control method and system, the method comprising: obtaining historical environmental parameter data related to the production and mining operation area and constructing a data set, obtaining the nearest neighbor data point set of any environmental parameter data in the data set, and calculating the local density of the environmental parameter data; obtaining the degree of deviation based on the difference between the local density and the nearest neighbor data point set, and analyzing the degree of change of each data point; adjusting the size of the nearest neighbor by the ratio between the degree of change and the degree of deviation, using the nearest neighbor algorithm to obtain the anomaly score of each environmental parameter data, combining the anomaly score and the air volume size of the equipment at the corresponding moment of the data point, and controlling the control parameters of the air volume in the current area. By dynamically adjusting the size of the nearest neighbor, the present invention enables the system to better adapt to the data distribution characteristics in different environments, ensuring that the air volume control of the ventilation equipment is more accurate.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control processing. More specifically, the present invention relates to a comprehensive intelligent safety production management and control method and system. Background Art

[0002] During mining operations in coal and non-coal mines, the crushing, excavation, and blasting of ore layers can release harmful gases (carbon monoxide, carbon dioxide, and methane concentrations) from the ground into the work environment. Ventilation is crucial to ensuring the timely discharge of these gases. Insufficient ventilation can easily lead to the accumulation of harmful gases in the mine, posing a serious threat to miners' lives and disrupting normal production. Therefore, it's crucial to monitor abnormal changes in parameter data throughout the production process.

[0003] A Chinese patent application, currently published with publication number CN117288825A, discloses a method and system for coal mine equipment safety management and control, relating to the technical field of coal mine equipment safety management and control. The system includes the following steps: S1. Measuring the gas concentration value based on the current generated by the electrochemical reaction between the gas and the electrodes of the electrochemical sensor; S2. Acquiring data information from several measurement processes during the gas concentration measurement, including electrochemical characteristic information and dynamic response characteristic information. The application monitors the gas concentration measurement process of a gas detector. When the gas detector has a hidden danger of being unable to accurately monitor the gas concentration, it issues an early warning, notifies relevant personnel of the situation, and promptly arranges for relevant maintenance work on the gas detector. If anomalies in the measurement accuracy of the gas detector are detected, the gas detector is promptly maintained and managed to ensure that the gas detector accurately monitors the gas concentration, effectively avoiding explosion accidents caused by inaccurate gas concentration monitoring.

[0004] This application document collects several real-time measurement accuracy assessment values ​​from gas concentration measurements during maintenance and management of gas concentration accuracy anomalies, performs a comprehensive analysis, and determines the maintenance and management status. Currently, when monitoring environmental parameter anomalies, the nearest neighbor algorithm sets a fixed nearest neighbor size and analyzes the distance between each data point and its nearest neighbor as the anomaly score. However, the complexity of the actual underground mine environment leads to different distribution characteristics for different parameters. An inappropriate neighborhood size setting can easily lead to misjudgment of concentrated anomaly data. Summary of the Invention

[0005] To address the problem that setting a fixed nearest neighbor size in the nearest neighbor algorithm leads to different distribution characteristics in the underground mine environment, and inappropriate neighborhood size setting easily leads to misjudgment of concentrated abnormal data, the present invention provides solutions in the following aspects.

[0006] In a first aspect, a comprehensive safe production intelligent management and control method includes: obtaining historical environmental parameter data related to a production and mining operation area and constructing a data set, wherein the environmental parameter data include: gas concentration, carbon monoxide concentration, and carbon dioxide concentration; obtaining a nearest neighbor data point set of any environmental parameter data in the data set, and calculating the local density of the environmental parameter data based on the distance between the environmental parameter data and each data point in the nearest neighbor data point set; obtaining the degree of deviation of each data point based on the difference between the local density of each data point and each data in the nearest neighbor data point set, and analyzing the degree of change of each data point in the nearest neighbor data point set based on the difference between any two data points in the nearest neighbor data point set of each data point; multiplying the ratio between the degree of change and the degree of deviation by the size of an initial preset neighborhood and rounding up as the size of the nearest neighbor of the data point, using a nearest neighbor algorithm to obtain an anomaly score of each environmental parameter data, and using the anomaly score of the data point corresponding to different environmental parameters and the air volume of the equipment at the corresponding time of the data point as a control parameter for controlling the air volume in the current area; wherein the control parameter satisfies the following relationship: Where, Indicates the The control parameters of the ventilation equipment at each moment, Indicates the The wind volume at a certain moment, Indicates the Parameters The anomaly score of each data point, Indicates the number of environmental parameters, Indicates the index of the environment parameter, Represents the standard normalization function.

[0007] The effect is that by dynamically adjusting the size of the nearest neighbor, acquiring historical environmental parameter data for the production and mining area and constructing a dataset, the local density and deviation of each data point, as well as the degree of data variation within the nearest neighbor data point set, can more accurately identify anomalous data points. This not only improves the accuracy of anomaly detection but also better adapts to data distribution characteristics in different environments. By combining the anomaly scores of different environmental parameters with real-time air volume, it achieves intelligent control of ventilation equipment air volume, ensuring that the air quality in the working environment remains within a safe range and optimizing the operating efficiency of the ventilation equipment.

[0008] Preferably, obtaining the nearest neighbor data point set of any environmental parameter data in the data set includes:

[0009] Taking any environmental parameter data in the data set as a marked data point, a preset number of data points with the smallest Euclidean distance between the marked data point and each data point in the data set are taken as the nearest neighbor data point set of the marked data point.

[0010] The effect is that by selecting a preset number of data points with the smallest Euclidean distance, the local neighborhood structure of the marked data points can be accurately identified, thereby more accurately reflecting the distribution of the data points in space.

[0011] Preferably, the calculating the local density of the environmental parameter data includes:

[0012] Taking any environmental parameter data in the dataset as a marked data point, the nearest neighbor data point set of the marked data point is obtained, and the inverse of the sum of the absolute values ​​of the distance differences between the marked data point and each data point in the nearest neighbor data point set is calculated to obtain the local density of the marked data point.

[0013] The effect is that by calculating the local density, it can accurately reflect the density of data points in their neighborhood, which not only enhances the sensitivity to abnormal data points and adapts to different data distributions, but also provides quantitative indicators and supports dynamic adjustment of the nearest neighbor size, thereby improving the accuracy and computational efficiency of anomaly detection.

[0014] Preferably, calculating the degree of deviation of each data point includes:

[0015] Taking any environmental parameter data in the data set as the marked data point, the mean of the local density of the marked data point is calculated, and the mean of the local density is divided by the local density of the marked data point to obtain the degree of deviation of the marked data point.

[0016] The effect is that by calculating the degree of deviation of the marked data points, the abnormality of the marked data points can be quantified, which not only improves the accuracy of anomaly detection, but also can effectively identify anomalies that are inconsistent with the distribution characteristics of surrounding data points, and adapts to different data distributions, which is conducive to dynamically adjusting the size of the nearest neighbor.

[0017] Preferably, obtaining the degree of deviation of each data point further includes:

[0018] Taking any environmental parameter data in the data set as the marked data point, the mean and standard deviation of the nearest neighbor data point set of the marked data point are calculated, and the difference between the marked data point and the mean of the nearest neighbor data point set is divided by the standard deviation to obtain the degree of deviation of the marked data point.

[0019] Preferably, analyzing the degree of change of data in the set of nearest neighboring data points of each data point includes:

[0020] Taking any environmental parameter data in the data set as the marked data point, calculate the change rate of the concentration value of any group of data points in the nearest neighbor data point set of the marked data point, sum the change rates between all pairs of data points in the nearest neighbor data point set, and normalize them as the degree of change of the marked data point.

[0021] The effect is that by calculating the rate of change of the concentration value of each pair of data points in the nearest neighbor data point set of the marked data point, the degree of change of the marked data point is obtained. This is conducive to capturing the dynamic changes of data points in the local neighborhood, thereby enhancing sensitivity to potential abnormal situations.

[0022] In a second aspect, a comprehensive intelligent management and control system for safe production includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned comprehensive intelligent management and control method for safe production is implemented.

[0023] The present invention has the following effects:

[0024] 1. This invention dynamically adjusts the size of the nearest neighbor by calculating the local density and deviation of each data point, taking into account the degree of data variability. This facilitates more accurate identification of early abnormal signals and avoids the misjudgment of traditional fixed nearest neighbor size methods when processing data with varying distribution characteristics. By adaptively adjusting the neighborhood size, data point anomalies can be more accurately assessed, thereby improving the accuracy of anomaly detection.

[0025] 2. This invention not only considers the local density and deviation of data points, but also incorporates the local variability of data points. By dynamically adjusting the size of the nearest neighbor, the system can better adapt to data distribution characteristics in different environments. This allows the control system to more flexibly adjust parameters in complex underground mine environments, ensuring more precise air volume control for ventilation equipment, thereby improving the overall performance and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a method flow chart of steps S1 to S3 in a comprehensive intelligent management and control method for safe production according to an embodiment of the present invention.

[0027] Figure 2 This is a structural block diagram of a comprehensive intelligent safety production management and control system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0029] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0030] Reference Figure 1A comprehensive intelligent production safety management and control method includes steps S1 to S3, which are as follows:

[0031] S1: Obtain historical environmental parameter data related to the production and mining operation area and construct a data set, where the environmental parameter data includes: gas concentration, carbon monoxide concentration, and carbon dioxide concentration; obtain the nearest neighbor data point set of any environmental parameter data in the data set, and calculate the local density of the environmental parameter data based on the distance between the environmental parameter data and each data point in the nearest neighbor data point set.

[0032] It should be noted that an environmental detector is placed in the coal mine excavation operation area to obtain real-time environmental parameter data of the current operation area, where the environmental parameter data includes but is not limited to: gas concentration, carbon monoxide concentration, and carbon dioxide concentration. The number of the nearest ventilation equipment is obtained through the location information of the environmental detector, and the air volume of the nearest ventilation equipment in the operation area is obtained. In this embodiment, it is preset to collect environmental parameter data every 5 seconds.

[0033] Further analysis based on real-world scenarios reveals that the complexity of underground mining environments leads to varying distribution patterns in parameter data across different dimensions. For example, coal seam cutting releases significant gas concentrations, while carbon monoxide and carbon dioxide are often emitted by diesel equipment or blasting devices used within the mine. Under normal mine conditions, ventilation equipment exhausts these gases, maintaining stable concentrations in the working area and preventing accumulation. Therefore, it's necessary to analyze whether each parameter significantly deviates from the others. Large deviations indicate the potential for unsafe accumulation.

[0034] Among them, obtaining the nearest neighbor data point set includes:

[0035] Taking any environmental parameter data in the data set as a marked data point, a preset number of data points with the smallest Euclidean distance between the marked data point and each data point in the data set are taken as the nearest neighbor data point set of the marked data point.

[0036] For example, the preset number is 10, which can be adjusted according to actual conditions.

[0037] Get the local density of environmental parameter data, including:

[0038] Taking any environmental parameter data in the dataset as a marked data point, the nearest neighbor data point set of the marked data point is obtained, and the inverse of the sum of the absolute values ​​of the distance differences between the marked data point and each data point in the nearest neighbor data point set is calculated to obtain the local density of the marked data point.

[0039] Specifically, the local density satisfies the following relationship:

[0040] ;

[0041] Where, Indicates the Parameters The local density of the data points, Indicates the Parameters data points, Indicates the Parameters The data point corresponds to the nearest neighbor data point in the set data points, Represents the index value of the data point in the nearest neighbor data point set, Represents the number of data points in the nearest neighbor data point set.

[0042] That is to say, Reflects the Parameters data point and the nearest neighbor data point The distance difference between the two data points. The smaller the distance, the closer the two data points are in space.

[0043] Indicates the Parameters The local density of a data point. The smaller the value, the greater the distance between the data point and its neighboring data points, and the more dispersed it is in the spatial representation.

[0044] S2: Based on the difference between the local density of each data point and each data in the nearest neighbor data point set, the deviation degree of each data point is calculated. Based on the difference between any two data points in the nearest neighbor data point set of each data point, the degree of change of the data of each data point in the nearest neighbor data point set is analyzed.

[0045] Obtaining the degree of deviation for each data point includes:

[0046] Taking any environmental parameter data in the data set as the marked data point, the mean of the local density of the marked data point is calculated, and the mean of the local density is divided by the local density of the marked data point to obtain the degree of deviation of the marked data point.

[0047] Specifically, the degree of deviation satisfies the following relationship:

[0048] ;

[0049] Where, Indicates the Parameters The degree of deviation of the data points, Indicates the Parameters The data point corresponds to the nearest neighbor data point in the set The local density of the data points, Indicates the Parameters The local density of the data points, Represents the index value of the data point in the nearest neighbor data point set, Represents the number of data points in the nearest neighbor data point set.

[0050] That is to say, Indicates the Parameters The degree of deviation of a data point is that if the mean of the local density of all its neighboring data points is larger, it means that the distribution of the neighbors of each data point is denser. Once the neighbor distribution of a data point is more dispersed, it means that there is a significant difference in the distribution of the data point and its neighboring data points in the feature space, and it is considered that the degree of deviation of the data point is greater.

[0051] In addition, another embodiment further includes:

[0052] Taking any environmental parameter data in the data set as the marked data point, the mean and standard deviation of the nearest neighbor data point set of the marked data point are calculated, and the difference between the marked data point and the mean of the nearest neighbor data point set is divided by the standard deviation to obtain the degree of deviation of the marked data point.

[0053] Specifically, the degree of deviation satisfies the following relationship:

[0054] ;

[0055] Where, Indicates the Parameters The degree of deviation of the data points, Indicates the Parameters data points, Indicates the The mean of the set of nearest neighbor data points of the parameter, Indicates the The standard deviation of the set of nearest neighbor data points for the parameter.

[0056] That is to say, It can reflect the center position of the nearest neighbor data point set. It reflects the degree of discreteness of the nearest neighbor data point set, that is, the average difference between each data point and the mean in the nearest neighbor data set. The greater the degree of deviation, the greater the difference between the mean of the marked data point and the nearest neighbor data point set, which means that the marked data point is an outlier relative to the nearest neighbor data point set, otherwise it is a normal value.

[0057] Further analysis shows that once accumulation occurs in actual mines due to untimely ventilation or inappropriate air volume, the monitored concentration will show an increasing trend. This means that at the initial abnormal moment, the deviation of the data point is relatively large, and the possibility of an abnormality is high. However, as the increasing trend changes, the distance difference between the abnormal change data point and its nearest neighbor data points becomes less obvious, and the deviation of the abnormal change data point obtained at this time will be smaller, which is inconsistent with the actual environmental change characteristics. Therefore, it is necessary to analyze the rate of change of each data point in the nearest neighbor data point set. If the rate of change between the data points in the nearest neighbor data point set is relatively large, it means that the nearest neighbor data point has shown a significant change characteristic.

[0058] Obtain the degree of change of each data point in the set of nearest neighboring data points, including:

[0059] Taking any environmental parameter data in the data set as the marked data point, calculate the change rate of the concentration value of any group of data points in the nearest neighbor data point set of the marked data point, sum the change rates between all pairs of data points in the nearest neighbor data point set, and normalize them as the degree of change of the marked data point.

[0060] Specifically, the degree of change satisfies the following relationship:

[0061] ;

[0062] Where, Indicates the Parameters The degree of change of the data in the nearest neighbor data point corresponding to each data point. Indicates the Parameters The data point corresponds to the nearest neighbor data point in the set The data points correspond to concentration values. Indicates the Parameters The data point corresponds to the nearest neighbor data point in the set The data points correspond to concentration values. Indicates the nearest neighbor data point except the The index values ​​of other data points besides data points, Represents the index value of the data point in the nearest neighbor data point set, represents the number of data points in the nearest neighbor data point set, Represents the standard normalization function.

[0063] That is to say, It represents the rate of change of concentration values ​​between a pair of data points, reflecting the relative difference between the concentrations of the two data points;

[0064] Indicates the Parameters The sum of the concentration change rates of any two data points in the nearest neighbor data point set. The larger the value, the more significant the difference in concentration data in the nearest neighbor data point set. This means that a rapid change process may be underway. The greater the degree of change in the data set of the nearest neighbor data points corresponding to each data point.

[0065] Further analysis shows that the traditional nearest neighbor algorithm uses a fixed neighborhood size to obtain the distance between a data point and its nearest neighboring data point to evaluate anomalies. The larger the distance, the more abnormal the data point. However, due to the influence of the actual underground mine environment, once the ventilation effect is poor, the concentration data will accumulate abnormalities. Due to the gradual nature of the mining process, the concentration data will show a gradual increase. If the degree of change in the data in the nearest neighbor data point set corresponding to a data point monitored in the current operating area is greater, this may mean that there may be continuous abnormal data in the nearest neighbor data point set. If the neighborhood is too small, the obtained nearest neighbor data set will be a continuous abnormality, while the actual abnormal concentration is gradually changing, thereby underestimating the degree of deviation of the original abnormal data point. If the neighborhood is too large, each data point needs to traverse the distance to its nearest neighbor data points. For data points in its neighboring area that are relatively stable, the calculation time will undoubtedly increase. Therefore, the neighborhood size needs to be dynamically adjusted. The specific steps are as follows:

[0066] S3: The ratio of the degree of change to the degree of deviation is multiplied by the size of the initial preset neighborhood and rounded up as the size of the nearest neighbor of the data point. The nearest neighbor algorithm is used to obtain the anomaly score of each environmental parameter data. The anomaly score of the data point corresponding to the different environmental parameters and the air volume of the equipment at the corresponding time of the data point are used as the control parameters for controlling the air volume in the current area.

[0067] Specifically, the size of the nearest neighbor is dynamically adjusted to satisfy the following relationship:

[0068] ;

[0069] Where, Indicates the Parameters The nearest neighbor size of a data point, represents the initial preset neighborhood size, Indicates the Parameters The degree of change of the data in the nearest neighbor data point corresponding to each data point. Indicates the Parameters The degree of deviation of a data point.

[0070] That is to say, Indicates the Parameters The nearest neighbor size weight of a data point is used. If the degree of change in the data in the nearest neighbor data point set corresponding to the data point is greater, it means that the nearest neighbor data point set may contain continuous abnormal data points. Under this condition, if the deviation of the data point is smaller, that is, the distribution of the data point and its nearest neighbor data points in the feature space is more concentrated, it can be considered that there are more abnormal data points in the nearest neighbor data point set of the data point. A larger weight should be given to increase the neighborhood size to include more data points.

[0071] Further analysis reveals that fixed ventilation equipment is often installed within specific areas of mines to ensure fresh air is supplied to the work area to dilute harmful gases and exhaust them, maintaining safe air quality. Therefore, it is necessary to adjust the air volume of this equipment based on real-time concentration monitoring to avoid accidents caused by concentration accumulation.

[0072] Specifically, the control parameters satisfy the following relationship:

[0073] ;

[0074] Where, Indicates the The control parameters of the ventilation equipment at each moment, Indicates the The wind volume at a certain moment, Indicates the Parameters The anomaly score of each data point, Indicates the number of environmental parameters, Indicates the index of the environment parameter, Represents the standard normalization function.

[0075] That is to say, Indicates the different parameters The sum of the anomaly scores of the data points. The larger the value, the higher the harmful concentration in the current working environment. It is necessary to increase the air volume of the ventilation equipment in the current area to exhaust the harmful gases in time.

[0076] The sum of the anomaly scores is normalized and mapped to Within the range, It is a baseline value to ensure that the control parameter will not be less than the air volume By adding the sum of the normalized anomaly scores to An adjustment factor is obtained, which is used to dynamically adjust the air volume.

[0077] If the sum of the anomaly scores at the current moment is high, the normalized value is close to 1, and the adjustment factor will be close to 1.5, thereby significantly increasing the air volume of the ventilation equipment and timely exhausting harmful gases to ensure the safety of the working environment; if the sum of the anomaly scores at the current moment is low, the normalized value is close to 0, and the adjustment factor will be close to 0.5, and the air volume of the ventilation equipment will be maintained at a low level to save energy and maintain normal ventilation in the working environment.

[0078] By Quantification in If the corresponding concentration at the current moment is too high, the control parameter result of the ventilation equipment will be larger.

[0079] The present invention also provides a comprehensive intelligent management and control system for safe production. Figure 2 As shown, the system includes a processor and a memory, and the memory stores computer program instructions. When the computer program instructions are executed by the processor, a comprehensive safe production intelligent management and control method according to the first aspect of the present invention is implemented.

[0080] The system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and therefore will not be described in detail here.

[0081] In the present invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium can be part of, accessible to, or connectable to a device. Any application or module described in the present invention can be implemented by computer-readable / executable instructions stored or otherwise retained by such a computer-readable medium.

[0082] In the description of this specification, "multiple" and "several" mean at least two, such as two, three or more, etc., unless otherwise clearly defined.

[0083] While several embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, variations, and alternatives will occur to those skilled in the art without departing from the concept and spirit of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in practicing the present invention.

Claims

1. A comprehensive intelligent management and control method for safe production, characterized in that: include: Obtain historical environmental parameter data related to the production mining operation area and construct a data set, where the environmental parameter data includes: gas concentration, carbon monoxide concentration, and carbon dioxide concentration; obtain the nearest neighbor data point set for any environmental parameter data in the data set, and calculate the local density of the environmental parameter data based on the distance between the environmental parameter data and each data point in the nearest neighbor data point set; Based on the difference between the local density of each data point and each data in the nearest neighbor data point set, the deviation degree of each data point is calculated. Based on the difference between any two data points in the nearest neighbor data point set of each data point, the degree of change of the data of each data point in the nearest neighbor data point set is analyzed. The ratio of the degree of change to the degree of deviation is multiplied by the size of the initial preset neighborhood and rounded up to obtain the size of the nearest neighbor of the data point. The nearest neighbor algorithm is used to obtain the anomaly score of each environmental parameter data. The anomaly score of the data point corresponding to the different environmental parameters and the air volume of the equipment at the corresponding time of the data point are used as the control parameters for controlling the air volume in the current area. The control parameters satisfy the following relationship: Where, Indicates the The control parameters of the ventilation equipment at each moment, Indicates the The wind volume at a certain moment, Indicates the Parameters The anomaly score of each data point, Indicates the number of environmental parameters, Indicates the index of the environment parameter, Represents the standard normalization function.

2. A comprehensive intelligent management and control method for safe production according to claim 1, characterized in that: Get the nearest neighbor data point set of any environmental parameter data in the dataset, including: Taking any environmental parameter data in the data set as a marked data point, a preset number of data points with the smallest Euclidean distance between the marked data point and each data point in the data set are taken as the nearest neighbor data point set of the marked data point.

3. A comprehensive intelligent management and control method for safe production according to claim 1, characterized in that: The calculating the local density of the environmental parameter data includes: Taking any environmental parameter data in the dataset as a marked data point, the nearest neighbor data point set of the marked data point is obtained, and the inverse of the sum of the absolute values ​​of the distance differences between the marked data point and each data point in the nearest neighbor data point set is calculated to obtain the local density of the marked data point.

4. A comprehensive intelligent management and control method for safe production according to claim 1, characterized in that: The calculation of the deviation degree of each data point includes: Taking any environmental parameter data in the data set as the marked data point, the mean of the local density of the marked data point is calculated, and the mean of the local density is divided by the local density of the marked data point to obtain the degree of deviation of the marked data point.

5. A comprehensive intelligent management and control method for safe production according to claim 1, characterized in that: Obtaining the degree of deviation of each data point further includes: Taking any environmental parameter data in the data set as the marked data point, the mean and standard deviation of the nearest neighbor data point set of the marked data point are calculated, and the difference between the marked data point and the mean of the nearest neighbor data point set is divided by the standard deviation to obtain the degree of deviation of the marked data point.

6. A comprehensive intelligent management and control method for safe production according to claim 1, characterized in that: The analysis of the degree of change of data in the set of nearest neighboring data points of each data point includes: Taking any environmental parameter data in the data set as the marked data point, calculate the change rate of the concentration value of any group of data points in the nearest neighbor data point set of the marked data point, sum the change rates between all pairs of data points in the nearest neighbor data point set, and normalize them as the degree of change of the marked data point.

7. A comprehensive intelligent safety production management and control system, characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the comprehensive intelligent management and control method for safe production according to any one of claims 1 to 6 is implemented.

Images