Coal mine dust prevention and control dynamic monitoring method and system

Abstract

A coal mine dust prevention and control dynamic monitoring method comprises the following steps that original monitoring data of personnel are obtained, and the original monitoring data comprise personnel position data and personnel image data; personnel are grouped based on a preset management and control area position and the personnel position data, and a dust risk weight is given to each group of personnel; correcting preset standard protective measure data by using the dust risk weight to obtain reference protective measure data; analyzing the personnel image data to obtain personnel protection measure data; and generating a monitoring result corresponding to the personnel based on a ratio of the personnel protection measure data to the reference protection measure data. According to the coal mine dust prevention and control dynamic monitoring method and system provided by the invention, whether the personnel have the risk of dust invasion or not can be comprehensively judged by combining the position of the personnel, the time of the personnel in a certain area and the prevention and control measures of the personnel, and the accurate monitoring of the dust prevention and control state of the personnel is realized.

Description

Technical Field The present invention relates to the technical field of coal mine dust prevention and control, and in particular to a method and system for dynamic monitoring of coal mine dust prevention and control. Background Art Coal mine dust has three major characteristics: high concentration, small particle size, and high free silica content, which can cause serious harm to personnel. In order to achieve the prevention and control of coal mine dust, it is necessary to carry out from multiple directions simultaneously, including dust suppression, stable operation of ventilation systems, and individual protection of personnel. Although the treatment of equipment and environment can effectively reduce the dust concentration in the environment, it is impossible to completely eliminate dust. Therefore, personal dust prevention and control is a more effective means to ensure individual safety. At present, personal dust prevention and control mainly adopts the method of wearing protective equipment including masks and face masks. However, because these protective equipment can cause many physiological discomforts, such as difficulty breathing and stuffiness, many personnel are not very motivated. The existing technology lacks the means to monitor personnel dust prevention and control measures, and most of them only use manual inspection and reminder methods, which are very limited in effect. Summary of the invention In order to address the deficiencies in the prior art, the present invention provides a dynamic monitoring method and system for coal mine dust control, which can comprehensively determine whether a person is at risk of dust infestation based on the person's location, the time the person is in a certain area, and the person's prevention and control measures, thereby achieving accurate monitoring of the person's dust control status. In order to achieve the above object, the specific scheme adopted by the present invention is: A method for dynamic monitoring of coal mine dust prevention and control, comprising the following steps: Acquire original monitoring data of a person, wherein the original monitoring data includes person location data and person image data; Grouping personnel based on the preset control area location and the personnel location data, and assigning a dust risk weight to each group of personnel; Using the dust risk weight, the preset standard protective measures data are modified to obtain reference protective measures data; Analyzing the personnel image data to obtain personnel protection measures data; A monitoring result corresponding to the personnel is generated based on a ratio of the personnel protection measure data to the reference protection measure data. Preferably, the method for obtaining the personnel location data includes: Use the positioning device carried by the personnel to collect the dynamic location of the personnel; Clustering the dynamic positions, and generating a plurality of candidate position clusters based on the clustering results; Screening the candidate location clusters based on time to obtain multiple key location clusters; The key location clusters are simplified to obtain a plurality of personnel location data. Preferably, when the positioning device is used to collect the dynamic position of a person, the collection is performed according to a preset collection cycle; The method for clustering the dynamic locations includes: Traversing all the dynamic positions of the personnel, and calculating the dynamic distance between any two dynamic positions; The dynamic distances are screened to delete all dynamic distances whose values ​​reach a preset distance threshold; The dynamic position associated with the dynamic distance having a number exceeding a preset first threshold is used as an anchor point; The dynamic positions whose dynamic distances to the anchor point are smaller than the distance threshold are combined with the anchor point to form the candidate position cluster. Preferably, the method for screening the candidate position clusters based on time includes: Obtaining the collection time of each of the dynamic positions in the candidate position cluster; Determine the length of stay of personnel corresponding to the candidate location cluster based on the range of the collection time; When the length of time the person stays reaches a preset length threshold, the candidate location cluster is used as the key location cluster. Preferably, the method for simplifying the data of the key location cluster includes: Extracting the dynamic position located at the edge from the key position cluster as the edge position; Using the edge positions to perform graphic fitting to obtain a personnel activity area corresponding to the key position cluster; Determine the geometric center of the personnel activity area; The distance between the dynamic position and the geometric center is calculated, and the dynamic position closest to the geometric center is used as the personnel position data. Preferably, the method for obtaining the personnel image data includes: Collect personnel surveillance video; Performing frame analysis on the personnel monitoring video to obtain multiple monitoring images; Extracting a personnel area image from the surveillance image; The personnel area images are grouped based on the identity marking devices carried by the personnel to obtain the personnel image data corresponding to the personnel. Preferably, the method for analyzing the personnel image data includes: Performing pixel analysis on the personnel area image in the personnel image data to determine the personnel eye portion and the protective equipment portion; Determining the coverage of the protective equipment based on the distance between the eye portion of the person and the protective equipment portion; The coverage of all the protective equipment is integrated into the personnel protection measures data. Preferably, the dust risk weight ranges from 0 to 1. Preferably, the monitoring results include high risk, medium risk and low risk. A coal mine dust prevention and control dynamic monitoring system, used to implement the above-mentioned coal mine dust prevention and control dynamic monitoring method, the system comprises: A position acquisition subsystem, used to obtain the personnel position data, including a plurality of positioning devices corresponding to the personnel; An image acquisition subsystem, used to obtain the image data of the personnel, including a plurality of adjustable surveillance cameras at fixed positions; A data transmission subsystem, used for transmitting the personnel position data and the personnel image data, including an underground wireless communication device and an above-ground wired communication device; The data processing subsystem is used to generate the monitoring result. The present invention can comprehensively judge whether a person is at risk of dust infestation based on the person's location, the time the person is in a certain area, and the person's prevention and control measures, thereby achieving accurate monitoring of the person's dust prevention and control status, and then being able to promptly remind or admonish the person, thereby improving the person's safety. BRIEF DESCRIPTION OF THE DRAWINGS In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work. Figure 1 is a flow chart of the method of the present invention; Figure 2 is a flow chart of S1 in the embodiment; Figure 3 It is a structural block diagram of the system of the present invention. DETAILED DESCRIPTION The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. like Figure 1 and 2As shown, a dynamic monitoring method for coal mine dust prevention and control includes S1 to S5. S1. Obtain the original monitoring data of personnel, which includes personnel location data and personnel image data. Among them, personnel location data is used to determine whether the personnel is in an area with high dust volume, and personnel impact data is used to determine the current dust protection status of the personnel. The two work together to determine the risk level of the personnel. The method for obtaining personnel location data includes steps up to S14. S11. Use the positioning device carried by the personnel to collect the dynamic position of the personnel. Considering that the underground is a closed environment, it is impossible to use GPS positioning or Beidou positioning. Existing indoor positioning technologies, such as WIFI positioning and other technologies, can be used. It should be noted that because the coverage of WIFI signals is prioritized, it is difficult to directly apply them in the underground environment. According to the range to be monitored, multiple small-scale WIFI networks can be selected to form a large-scale integrated network for positioning. Considering that the position of personnel is constantly changing and there are many people in the coal mine, if the personnel position data is collected in real time, the amount of personnel position data will be too large, which will increase the energy consumption of the positioning device and increase the pressure of data transmission. Therefore, when using the positioning device to collect the dynamic position of the personnel, it is collected according to the preset collection period. By determining a suitable collection period to periodically collect personnel position data, the data volume and transmission load of personnel position data can be significantly reduced. S12, clustering the dynamic positions, and generating multiple candidate position clusters based on the clustering results. Because it is necessary to judge the risk level of personnel based on whether they are in an area with a large amount of dust, and personnel will be mobile, for example, in the process of going up and down the well, personnel need to pass through a large number of areas, and a lot of personnel position data will be generated accordingly. However, personnel will not stay for a long time in most positions, so even if the dust volume of the position passed is large, the risk of personnel will not be significantly increased because of the short residence time. Therefore, the present invention first clusters the dynamic positions to determine the areas where personnel stay for a long time, and deletes the dynamic positions corresponding to the areas where personnel pass for a short time, thereby reducing the complexity of subsequent data processing and improving the execution efficiency of the entire method. The method for clustering dynamic locations includes S121 to S124. S121. Traverse all dynamic positions of the personnel and calculate the dynamic distance between any two dynamic positions. If the personnel works in a certain area for a long time, multiple dynamic positions with close distances will be generated in the area. When the personnel passes through a certain area, the distance between the dynamic positions generated in the area is large. Therefore, based on the distance between the dynamic positions, the area where the personnel spends a long time can be determined. S122. Filter the dynamic distances and delete all dynamic distances whose values ​​reach the preset distance threshold. Because the dynamic positions are collected based on the collection cycle, if the person is moving quickly, the dynamic distance between two adjacent dynamic positions will be significantly greater than the dynamic distance between two adjacent dynamic positions when the person is moving in an area. Therefore, the dynamic distance with a larger value can be deleted first, and the two dynamic positions associated with the deleted dynamic distances can be deleted. After the dynamic distances exceeding the distance threshold are deleted and the associated dynamic positions are deleted, all dynamic distances associated with all remaining dynamic positions do not exceed the distance threshold. S123. The dynamic position whose number of associated dynamic distances exceeds the preset first threshold is used as an anchor point. During the production process, although the position of the personnel will change slightly, the change will not be too large. The personnel will generally be in a small range. In this small range, the personnel will roughly move around a point. The dynamic position of the point is the anchor point. For example, when a person performs an operation around a device, although the position of the person will change slightly, it will generally be centered on the device.

[0001] S124, the dynamic positions whose dynamic distances to the anchor point are less than the distance threshold are combined with the anchor point to form a candidate position cluster. In the candidate position cluster, the dynamic distances between the anchor point and all other dynamic positions are less than the distance threshold, and the range determined by all dynamic positions in the candidate position cluster is the stable working area of ​​the personnel. S13. Screen the candidate location clusters based on time to obtain multiple key location clusters. In S12, areas where personnel activities are relatively stable are determined. If these areas are areas with large amounts of dust, the risk of personnel in these areas is higher. However, in addition to regional factors, the length of time a person stays in an area will also directly affect the degree of risk. Therefore, it is also necessary to screen the candidate location clusters based on time, further extract areas where personnel stay for a long time, and introduce the time factor to further accurately judge the risk level of personnel. The method for screening candidate location clusters based on time includes S131 to S133. S131. Obtain the collection time of each dynamic position in the candidate position cluster. S132. Determine the length of stay of personnel corresponding to the candidate location cluster based on the range of the collection time. S133: When the duration of a person's stay reaches a preset duration threshold, the candidate location cluster is used as a key location cluster. After the key location cluster is obtained, the area corresponding to the key location cluster is an area where the activities of people are relatively stable and the stay time is relatively long. If the amount of dust in this area is large, the risk level of the person is the highest. S14, simplifying the key location clusters to obtain multiple personnel location data. After determining the key location clusters, because each key location cluster includes multiple dynamic locations, if each dynamic location is processed in the subsequent process, the amount of data to be processed is too large, the load is too high, and the delay is also higher. Therefore, it is necessary to simplify the key location clusters to reduce the amount of data to be processed subsequently. The method for simplifying data of the key location cluster includes S141 to S144. S141. Extract the dynamic position located at the edge from the key position cluster as the edge position. S142. Use edge positions to perform graphic fitting to obtain a personnel activity area corresponding to the key position cluster. S143. Determine the geometric center of the personnel activity area. S144. Calculate the distance between the dynamic position and the geometric center, and use the dynamic position closest to the geometric center as the personnel position data. It has been explained in S123 that if the activities of personnel in a certain area are relatively stable, they will move roughly around a point, which is also the anchor point of the alternative location cluster. Although the use of anchor points as personnel location data can be used to judge the risk level of personnel, there are still shortcomings. The main one is that the position of the anchor point may be the edge of the area where the personnel activities are stable. If the anchor point is used as the personnel location data, it will be difficult to reflect the location of the area, and it will be difficult to compare with the preset control area. Therefore, it is necessary to use the geometric center of the geometric figure determined by all dynamic positions in the key location cluster as a reference, and use the dynamic position closest to the geometric center as the personnel location data, which can more accurately reflect the specific area where the person is located. The method for acquiring personnel image data includes S15 to S18. S15. Collect personnel surveillance video. S16: Frame analysis is performed on the personnel monitoring video to obtain a plurality of monitoring images. S17, extracting a personnel area image from the monitoring image. The personnel area image can be extracted from the monitoring image using an existing neural network-based algorithm, which is a mature existing technology and will not be described in detail again. S18. Grouping personnel area images based on the identity tag devices carried by the personnel to obtain personnel image data corresponding to the personnel. So far, the obtained personnel position data and personnel image data are both corresponding to the personnel and are both discrete. S2. Group the personnel based on the preset control area location and personnel location data, and assign a dust risk weight to each group of personnel. The dust risk weight ranges from 0 to 1. If the area where the personnel stay for a long time and the activities are relatively stable, which is finally determined in S14, is located in the control area, it means that the risk level of the personnel in this area is the highest, and the required protective measures are also the highest. At this time, the dust risk weight is set to 1. If the area where the personnel stay for a long time and the activities are relatively stable is not in the control area, it means that the risk level of the personnel in this area is low, and the required protective measures can also be reduced. At this time, the dust risk weight can be reduced. The specific value can be determined according to the actual environmental conditions of the coal mine, which will not be repeated here. S3. Use the dust risk weight to modify the preset standard protection measures data to obtain reference protection measures data. S4. Analyze the personnel image data to obtain personnel protection measures data. The method for analyzing the personnel image data includes S41 to S43. S41. Perform pixel analysis on the personnel area image in the personnel image data to determine the personnel eye part and the protective equipment part. In coal mines, the protective equipment used to protect against dust is mainly masks or face shields, both of which partially cover the face of the personnel, and the personnel's eyes are exposed for normal work. Therefore, the position of the protective equipment part can be determined based on the personnel eye part. The method of extracting the personnel vision part and the protective equipment part from the personnel area image can also adopt the existing neural network-based image processing method, which is a mature existing technology and will not be repeated here. S42. Determine the coverage of the protective equipment based on the distance between the eye part of the person and the protective equipment part. The coverage of the protective equipment refers to the proportion of the part covered by the protective equipment relative to the face of the person. The higher the coverage, the higher the degree of protection of the person. S43. Integrate all protective equipment coverage into personnel protection measures data. S5. Generate monitoring results corresponding to personnel based on the ratio of personnel protection measures data and reference protection measures data. If the personnel protection measures data is greater than or equal to the reference protection measures data, it means that the personnel's current protection measures can meet the needs, otherwise it means that the personnel's current protection measures cannot meet the needs. The personnel protection measures data and the reference heatstroke prevention measures data are essentially the coverage of protective equipment. In order to facilitate dust protection guidance for personnel based on the monitoring results, the monitoring results include high risk, medium risk and low risk. like Figure 3As shown, the present invention further provides a coal mine dust control dynamic monitoring system, which is used to implement the above-mentioned coal mine dust control dynamic monitoring method. The system includes a position acquisition subsystem, an image acquisition subsystem, a data transmission subsystem and a data processing subsystem. The location acquisition subsystem is used to obtain personnel location data, including multiple positioning devices corresponding to personnel. It should be noted that for underground areas, safety needs to be considered. Generally, electronic products are prohibited from entering underground, so the positioning device needs to have sufficient safety. The positioning device can be encapsulated in a rubber body and fully isolated from the surrounding environment during the underground movement, thereby avoiding safety accidents caused by the internal current of the positioning device. On this basis, the positioning device can be charged wirelessly to complete power replenishment. The image acquisition subsystem is used to obtain personnel image data, including multiple adjustable surveillance cameras in fixed positions. The data transmission subsystem is used to transmit personnel location data and personnel image data, including underground wireless communication devices and above-ground wired communication devices. The data processing subsystem is used to generate monitoring results. The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other. The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for dynamic monitoring of coal mine dust prevention and control, characterized in that: The steps include: Acquire original monitoring data of a person, wherein the original monitoring data includes person location data and person image data; Grouping personnel based on the preset control area location and the personnel location data, and assigning a dust risk weight to each group of personnel; Using the dust risk weight, the preset standard protective measures data are modified to obtain reference protective measures data; Analyzing the personnel image data to obtain personnel protection measures data; A monitoring result corresponding to the personnel is generated based on a ratio of the personnel protection measure data to the reference protection measure data.

2. A method for dynamic monitoring of coal mine dust prevention and control as claimed in claim 1, characterized in that: The method for obtaining the personnel location data includes: Use the positioning device carried by the personnel to collect the dynamic location of the personnel; Clustering the dynamic positions, and generating a plurality of candidate position clusters based on the clustering results; Screening the candidate location clusters based on time to obtain multiple key location clusters; The key location clusters are simplified to obtain a plurality of personnel location data.

3. A method for dynamic monitoring of coal mine dust prevention and control as claimed in claim 2, characterized in that: When the positioning device is used to collect the dynamic position of the personnel, the collection is performed according to a preset collection cycle; The method for clustering the dynamic locations includes: Traversing all the dynamic positions of the personnel, and calculating the dynamic distance between any two dynamic positions; The dynamic distances are screened to delete all dynamic distances whose values ​​reach a preset distance threshold; The dynamic position associated with the dynamic distance having a number exceeding a preset first threshold is used as an anchor point; The dynamic positions whose dynamic distances to the anchor point are smaller than the distance threshold are combined with the anchor point to form the candidate position cluster.

4. A method for dynamic monitoring of coal mine dust prevention and control as claimed in claim 2, characterized in that: The method for screening the candidate position clusters based on time includes: Obtaining the collection time of each of the dynamic positions in the candidate position cluster; Determine the length of stay of personnel corresponding to the candidate location cluster based on the range of the collection time; When the length of time the person stays reaches a preset length threshold, the candidate location cluster is used as the key location cluster.

5. A method for dynamic monitoring of coal mine dust prevention and control as claimed in claim 2, characterized in that: The method for simplifying the data of the key location cluster includes: Extracting the dynamic position located at the edge from the key position cluster as the edge position; Using the edge positions to perform graphic fitting to obtain a personnel activity area corresponding to the key position cluster; Determine the geometric center of the personnel activity area; The distance between the dynamic position and the geometric center is calculated, and the dynamic position closest to the geometric center is used as the personnel position data.

6. A method for dynamic monitoring of coal mine dust prevention and control as claimed in claim 1, characterized in that: The method for obtaining the personnel image data includes: Collect personnel surveillance video; Performing frame analysis on the personnel monitoring video to obtain multiple monitoring images; Extracting a personnel area image from the surveillance image; The personnel area images are grouped based on the identity marking devices carried by the personnel to obtain the personnel image data corresponding to the personnel.

7. A method for dynamic monitoring of coal mine dust prevention and control as claimed in claim 6, characterized in that: The method for analyzing the personnel image data includes: Performing pixel analysis on the personnel area image in the personnel image data to determine the personnel eye portion and the protective equipment portion; Determining the coverage of the protective equipment based on the distance between the eye portion of the person and the protective equipment portion; The coverage of all the protective equipment is integrated into the personnel protection measures data.

8. A method for dynamic monitoring of coal mine dust prevention and control as claimed in claim 1, characterized in that: The dust risk weight ranges from 0 to 1.

9. A method for dynamic monitoring of coal mine dust prevention and control as claimed in claim 1, characterized in that: The monitoring results include high risk, medium risk and low risk.

10. A coal mine dust prevention and control dynamic monitoring system, characterized in that: The system is used to implement a method for dynamic monitoring of coal mine dust prevention and control as claimed in any one of claims 1 to 9, the system comprising: A position acquisition subsystem, used to obtain the personnel position data, including a plurality of positioning devices corresponding to the personnel; An image acquisition subsystem, used to obtain the image data of the personnel, including a plurality of adjustable surveillance cameras at fixed positions; A data transmission subsystem, used for transmitting the personnel position data and the personnel image data, including an underground wireless communication device and an above-ground wired communication device; The data processing subsystem is used to generate the monitoring result.

Images