Tunnel fire-fighting monitoring and early warning method, device and system based on internet of things sensing data analysis

Abstract

The application discloses a tunnel fire-fighting monitoring and early warning method, device and system based on Internet of Things sensing data analysis, relates to the fire-fighting early warning field, and solves the problem that the practicability of fire-fighting equipment in a tunnel cannot be effectively monitored. The method comprises the following steps: dividing different time periods according to the shooting time of equipment images; analyzing the pixel points of the equipment images in different time periods to obtain a rate acceleration time period and a rate deceleration time period; analyzing the average humidity and total exhaust emission of the tunnel interior in different time periods to obtain actual influence parameters in the tunnel; analyzing the corresponding average humidity or total exhaust emission in different time periods according to different actual influence parameters to obtain a predicted generation rate of dirt pixel points; analyzing the position of the dirt pixel points in real-time equipment images; and analyzing the early warning time of the fire-fighting equipment in the tunnel by using the predicted generation rate. The application realizes effective monitoring of the practicability of the fire-fighting equipment in the tunnel.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of fire warning, and particularly relates to a tunnel fire monitoring and early warning method, device and system based on Internet of Things sensing data analysis. BACKGROUND

[0002] A tunnel is a narrow channel constructed in a mountain, underground or under water, and its core function is to cross terrain obstacles, ensure traffic continuity or meet special purposes, and the tunnel has the characteristics of being closed and narrow, having a controllable environment and strong anti-interference, and as a key infrastructure in the fields of transportation and municipal administration, the structure and operation environment of the tunnel determine that the fire-fighting technology must break through the limitations of ordinary building fire-fighting.

[0003] In the prior art, the tunnel fire monitoring and early warning method is mostly achieved by identifying the flame smoke in the tunnel, however, as an important means of fire rescue, when the fire-fighting equipment in the tunnel cannot be normally used, it will cause difficulties to the fire rescue, and at the same time, due to the high humidity in the tunnel and the corrosion of the exhaust gas dissolved in water, the practicability of the fire-fighting equipment in the tunnel cannot be effectively monitored.

[0004] Therefore, the application provides a tunnel fire monitoring and early warning method, device and system based on Internet of Things sensing data analysis. SUMMARY

[0005] The application aims to provide a tunnel fire monitoring and early warning method, device and system based on Internet of Things sensing data analysis, so as to solve the problem that the practicability of the fire-fighting equipment in the tunnel cannot be effectively monitored.

[0006] In order to achieve the above-mentioned purpose, the application adopts the following technical scheme:

[0007] In a first aspect, the tunnel fire monitoring and early warning method based on Internet of Things sensing data analysis comprises the following steps:

[0008] Step S1, dividing different time periods according to the shooting time of the equipment image;

[0009] Step S2, analyzing the pixel points of the equipment image in different time periods, and obtaining the rate acceleration time period and the rate deceleration time period through analysis;

[0010] Step S3, analyzing the average humidity and the total exhaust emission in the tunnel in different time periods, and obtaining the actual influence parameter in the tunnel through analysis;

[0011] Step S4, analyzing the corresponding average humidity or total exhaust emission in different time periods according to different actual influence parameters, and obtaining the predicted generation rate of the dirt pixel points through analysis;

[0012] Step S5, the position of the dirt pixel point in the real-time device image is analyzed, and the warning time of the fire-fighting device inside the tunnel is analyzed by using the predicted generation rate.

[0013] Further, the division process in step S1 includes the following sub-steps:

[0014] Step S101, the designated fire-fighting device inside the tunnel is photographed at a first time interval, and the images are sequentially recorded as a first device image, a second device image, a third device image, …, and an n-th device image in ascending order of the photographing time, n being the number of the device images;

[0015] Step S102, the image taken when the fire-fighting device inside the tunnel is put into use is obtained and recorded as an initial device image, the pixel points in the initial device image are recorded as initial pixel points, and the pixel points in the first device image, the second device image, …, and the n-th device image are recorded as actual pixel points;

[0016] Step S103, the time period between taking the initial device image and taking the first device image is recorded as a first time period, the time period between taking the first device image and taking the second device image is recorded as a second time period, and similarly, the time period between taking the n-1-th device image and taking the n-th device image is recorded as an n-th time period.

[0017] Further, the analysis process in step S2 includes the following sub-steps:

[0018] Step S201, the initial device image is subjected to a gray-scale processing to obtain an initial gray-scale image, and all the device images are subjected to a gray-scale processing to obtain the gray-scale images corresponding to the device images;

[0019] Step S202, the gray-scale values corresponding to different initial pixel points in the initial gray-scale image are obtained, and the gray-scale values corresponding to the initial pixel points are recorded as initial gray-scale values; the gray-scale values corresponding to different actual pixel points in all the device images are obtained, and the gray-scale values corresponding to the actual pixel points are recorded as actual gray-scale values;

[0020] Step S203, the gray-scale image corresponding to the first device image is selected as an analysis object and recorded as a first gray-scale image, and the actual gray-scale values of the actual pixel points in the first gray-scale image are compared with the initial gray-scale values of the corresponding initial pixel points;

[0021] If the actual gray-scale value of any actual pixel point in the first gray-scale image is different from the initial gray-scale value of the corresponding initial pixel point, the corresponding actual pixel point in the first gray-scale image is recorded as a dirt pixel point;

[0022] If the actual gray scale values of all the actual pixel points in the first gray scale image are the same as the initial gray scale values of the corresponding initial pixel points, no operation is performed;

[0023] Similarly, the actual gray scale values of the actual pixel points in the different gray scale images are compared with the initial gray scale values of the corresponding initial pixel points, and the dirt pixel points in the different gray scale images are obtained by comparison;

[0024] In step S204, the number of the dirt pixel points in the different gray scale images is counted and recorded as the number of the dirt pixel points, and the number of the dirt pixel points in the first gray scale image is divided by the first time interval to obtain the generation rate of the dirt pixel points in the first time period;

[0025] In step S205, the number of the dirt pixel points in the second gray scale image is subtracted from the number of the dirt pixel points in the first gray scale image, and then divided by the first time interval to obtain the generation rate of the dirt pixel points in the second time period;

[0026] Similarly, the number of the dirt pixel points in the nth gray scale image is subtracted from the number of the dirt pixel points in the (n-1)th gray scale image, and then divided by the first time interval to obtain the generation rate of the dirt pixel points in the nth time period;

[0027] In step S206, the time period in which the generation rate of the dirt pixel points is greater than the corresponding generation rate in the last time period is recorded as the rate acceleration time period, and the time period in which the generation rate of the dirt pixel points is less than the corresponding generation rate in the last time period is recorded as the rate deceleration time period.

[0028] Further, the analysis process in step S3 includes the following sub-steps:

[0029] In step S301, real-time air data inside the tunnel is collected at a second time interval; wherein the real-time air data is the real-time exhaust gas concentration at the tunnel entrance, the real-time exhaust gas concentration at the tunnel exit, and the real-time wind speed at different positions inside the tunnel;

[0030] In step S302, the real-time wind speeds at different positions inside the tunnel are added and averaged to obtain the average wind speed inside the tunnel at the current time node, the cross-sectional area of the tunnel is obtained, and the cross-sectional area is divided by the average wind speed to obtain the real-time air flow rate inside the tunnel at the current time node;

[0031] In step S303, the real-time exhaust gas concentration at the tunnel exit is subtracted from the real-time exhaust gas concentration at the tunnel entrance to obtain the real-time exhaust gas concentration difference between the tunnel entrance and exit at the current time node, the real-time exhaust gas concentration difference is taken as an absolute value, multiplied by the real-time air flow rate, and then multiplied by the second time interval to obtain the exhaust emission of the vehicle inside the tunnel at the current time node;

[0032] Step S304, adding up the exhaust emission amounts of the vehicles inside the tunnel at different time nodes in the first time period to obtain the total exhaust emission amount of the vehicles inside the tunnel in the corresponding time period;

[0033] Similarly, adding up the exhaust emission amounts of the vehicles inside the tunnel at different time nodes in any time period to obtain the total exhaust emission amount of the vehicles inside the tunnel in the corresponding time period.

[0034] Further, the analysis process in step S3 further includes the following sub-steps:

[0035] Step S305, obtaining the real-time humidity inside the tunnel at different time nodes in any time period, and adding up the real-time humidity inside the tunnel at different time nodes to obtain the average humidity inside the tunnel in the corresponding time period;

[0036] Step S306, subtracting the total exhaust emission amount in the previous time period from the total exhaust emission amount in the corresponding time period, and dividing the total exhaust emission amount in the previous time period to obtain the total exhaust emission change rate in the corresponding time period;

[0037] Subtracting the average humidity in the previous time period from the average humidity in the corresponding time period, and dividing the average humidity in the previous time period to obtain the average humidity change rate in the corresponding time period;

[0038] Step S307, analyzing the total exhaust emission change rate and the average humidity change rate in the rate acceleration time period to obtain the positive feedback parameter corresponding to the rate acceleration time period, and the analysis process is specifically as follows:

[0039] If the total exhaust emission change rate in the rate acceleration time period is greater than or equal to zero, but the average humidity change rate is less than zero, then the total exhaust emission amount is taken as the positive feedback parameter corresponding to the rate acceleration time period; if the total exhaust emission change rate in the rate acceleration time period is less than zero, but the average humidity change rate is greater than or equal to zero, then the average humidity is taken as the positive feedback parameter corresponding to the rate acceleration time period; if the total exhaust emission change rate and the average humidity change rate in the rate acceleration time period are both less than zero, then no operation is performed; if the total exhaust emission change rate and the average humidity change rate in the rate acceleration time period are both greater than or equal to zero, then step S308 is entered;

[0040] Step S308, when the total exhaust emission change rate in the rate acceleration time period is greater than or equal to the average humidity change rate, then the total exhaust emission amount is taken as the positive feedback parameter of the rate acceleration time period;

[0041] When the total exhaust emission change rate in the rate acceleration time period is less than the average humidity change rate, then the average humidity is taken as the positive feedback parameter of the rate acceleration time period;

[0042] Similarly, the change rate of the total exhaust emission and the average humidity change rate in the rate reduction period are analyzed, and the positive feedback parameter of the rate reduction period is obtained;

[0043] In step S309, the number of time periods with the average humidity as the positive feedback parameter is counted and recorded as the humidity time period number, the number of time periods with the total exhaust emission as the positive feedback parameter is counted and recorded as the exhaust time period number, and the humidity time period number is compared with the exhaust time period number;

[0044] If the humidity time period number is greater than or equal to the exhaust time period number, the average humidity is taken as the actual impact parameter inside the tunnel;

[0045] If the humidity time period number is less than the exhaust time period number, the total exhaust emission is taken as the actual impact parameter inside the tunnel.

[0046] Further, the analysis process in step S4 includes the following sub-steps:

[0047] In step S41, when the actual impact parameter is the average humidity, the mode of the average humidity in different time periods is taken as the predicted average humidity, and the time period corresponding to the mode of the average humidity is recorded as the characteristic time period;

[0048] In step S42, when the actual impact parameter is the total exhaust emission, the characteristic time period is analyzed, and the analysis process is as follows:

[0049] The total exhaust emission in different time periods is added and averaged to obtain the average exhaust emission, and the absolute value of the difference between the average exhaust emission and the total exhaust emission in different time periods is obtained to obtain the exhaust emission deviation in different time periods;

[0050] The different exhaust emission deviations are compared to obtain the minimum value of the exhaust emission deviation, and the time period corresponding to the minimum value of the exhaust emission deviation is recorded as the characteristic time period;

[0051] In step S43, the generation rate of the dirt pixel points in different characteristic time periods is compared to obtain the maximum value of the generation rate, which is recorded as the predicted generation rate of the dirt pixel points.

[0052] Further, the analysis process in step S5 includes the following sub-steps:

[0053] In step S51, the device image corresponding to the fire-fighting equipment inside the tunnel at the current time node is obtained and recorded as the real-time device image, and the real-time device image is placed in a plane rectangular coordinate system;

[0054] In step S52, the coordinates of different water outlets on the surface of the fire-fighting equipment are obtained and recorded as the water hole position coordinates, and the coordinates of different dirt pixel points in the real-time device image are obtained and recorded as the dirt point coordinates;

[0055] Step S53, compare the dirt point coordinates with the water hole position coordinates;

[0056] If the dirt point coordinates of any dirt pixel point are the same as the water hole position coordinates, immediately issue a warning;

[0057] If the dirt point coordinates of all dirt pixel points are not the same as the water hole position coordinates, go to step S54;

[0058] Step S54, calculate the straight-line distance between different dirt pixel points and different water outlets by the distance formula, traverse and compare different straight-line distances to get the minimum straight-line distance, mark the dirt pixel point corresponding to the minimum straight-line distance as the potential diffusion point, and mark the water outlet corresponding to the minimum straight-line distance as the potential blockage hole;

[0059] Step S55, connect the potential blockage hole and the potential diffusion point using a line segment, count the number of pixel points crossed by the line segment and mark it as the minimum number of pixel points, and divide the minimum number of pixel points by the predicted generation rate to get the predicted diffusion duration;

[0060] Step S56, add the time corresponding to the current time node to the predicted diffusion duration to get the warning time of the tunnel internal fire-fighting equipment.

[0061] In a second aspect, a tunnel fire-fighting monitoring and warning device based on Internet of Things sensing data analysis includes a data acquisition module, an image analysis module, a parameter analysis module, a data prediction module, and a comprehensive analysis module.

[0062] The data acquisition module is used to acquire device images of tunnel internal fire-fighting equipment at different time nodes and send them to the image analysis module; the image analysis module is used to analyze pixel points in the device images in different time periods, analyze the rate acceleration period and the rate deceleration period, and send them to the parameter analysis module; the data acquisition module is also used to acquire humidity and tail gas emission at different positions inside the tunnel and send them to the parameter analysis module.

[0063] The parameter analysis module is used to analyze the average humidity and total tail gas emission inside the tunnel in different time periods, analyze the actual influence parameters inside the tunnel, and send them to the data prediction module; the data prediction module is used to analyze the average humidity or total tail gas emission in different time periods according to different actual influence parameters, analyze the predicted generation rate of dirt pixel points, and send them to the comprehensive analysis module; the comprehensive analysis module is used to analyze the position of dirt pixel points in the device image and analyze the warning time of the fire-fighting equipment using the predicted generation rate.

[0064] In a third aspect, the tunnel fire-fighting monitoring and early warning system based on Internet of Things sensing data analysis comprises:

[0065] a memory storing a computer program;

[0066] a processor connected in communication with the memory, and when the computer program is executed by the processor, the tunnel fire-fighting monitoring and early warning method based on Internet of Things sensing data analysis is realized.

[0067] In a fourth aspect, a computer readable storage medium stores a computer program, and when the program is executed by a processor, the tunnel fire-fighting monitoring and early warning method based on Internet of Things sensing data analysis is realized.

[0068] Compared with the prior art, the present application has the following advantages:

[0069] 1. The method first photographs the designated fire-fighting equipment inside the tunnel at different times, then analyzes the generation rate of the dirt pixel points on the surface of the fire-fighting equipment in different time periods, obtains the rate acceleration time period and the quantity slowing time period, and analyzes the humidity and tail gas emission amount inside the tunnel in different time periods, so as to analyze the actual influence parameters affecting the generation rate of the dirt pixel points, and realize the analysis of the influence parameters affecting the generation rate of the dirt inside the tunnel.

[0070] 2. The generation rate of the dirt pixel points on the surface of the fire-fighting equipment is estimated based on the actual influence parameters, the position of the dirt pixel points is analyzed with the position of the water outlet hole on the surface of the fire-fighting equipment, so as to determine whether the water outlet hole is blocked, and the maintenance warning time of the fire-fighting equipment is calculated based on the estimated generation rate, and the practicability of the fire-fighting equipment inside the tunnel is effectively analyzed. BRIEF DESCRIPTION OF DRAWINGS

[0071] In order to facilitate the understanding of those skilled in the art, the present application will be further described below with reference to the accompanying drawings.

[0072] Figure 1 The method flowchart of the present application;

[0073] Figure 2 The schematic diagram of the potential diffusion point and the potential blocked hole in the present application;

[0074] Figure 3 The structure schematic diagram of the tunnel fire-fighting monitoring and early warning system based on Internet of Things sensing data analysis in the present application. DETAILED DESCRIPTION

[0075] The technical solutions of the present application will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0076] Embodiment one: please refer to Figure 1 and Figure 2 The technical solution provided by the present application is: a tunnel fire-fighting monitoring and early warning method based on Internet of Things sensing data analysis. The method first photographs designated fire-fighting equipment inside the tunnel at different times, and the fire-fighting equipment is a sprinkler with water holes. Then, the generation rate of dirt pixel points on the surface of the fire-fighting equipment in different time periods is analyzed, and the rate acceleration time period and the quantity slowing time period are obtained. At the same time, the humidity and tail gas emission in the tunnel in different time periods are analyzed, so as to analyze the actual influence parameters affecting the generation rate of dirt pixel points. Then, the generation rate of dirt pixel points on the surface of the fire-fighting equipment is estimated based on the actual influence parameters. Finally, the position of the dirt pixel points and the position of the water hole on the surface of the fire-fighting equipment are analyzed to determine whether the water hole is blocked, and the maintenance warning time of the fire-fighting equipment is calculated based on the estimated generation rate.

[0077] In this embodiment, the tunnel fire-fighting monitoring and early warning method comprises the following steps:

[0078] Step S1, dividing different time periods according to the photographing time of the equipment image;

[0079] In this embodiment, the division process in step S1 comprises the following sub-steps:

[0080] Step S101, photographing the designated fire-fighting equipment inside the tunnel with a first time interval, and sequentially recording the images as a first equipment image, a second equipment image, a third equipment image, …, and an n-th equipment image according to the ascending order of photographing time, where n is the number of the equipment image;

[0081] Step S102, obtaining the image photographed when the fire-fighting equipment inside the tunnel is put into use and recording it as an initial equipment image, recording the pixel points in the initial equipment image as initial pixel points, and recording the pixel points in the first equipment image, the second equipment image, …, and the n-th equipment image as actual pixel points;

[0082] Step S103, recording the time period between photographing the initial equipment image and photographing the first equipment image as a first time period, recording the time period between photographing the first equipment image and photographing the second equipment image as a second time period, and similarly, recording the time period between photographing the (n-1)-th equipment image and photographing the n-th equipment image as an n-th time period;

[0083] In the embodiment, the number of the time period is the same as the number of the device image.

[0084] In step S2, the pixel points of the device images in different time periods are analyzed to obtain the time period of accelerated rate and the time period of decelerated rate.

[0085] In the embodiment, the analysis process in step S2 includes the following sub-steps:

[0086] In step S201, the initial device image is subjected to gray processing to obtain an initial gray image, and all the device images are subjected to gray processing to obtain the gray images corresponding to the device images.

[0087] In step S202, the gray values corresponding to different initial pixel points in the initial gray image are obtained, and the gray values corresponding to the initial pixel points are recorded as initial gray values; the gray values corresponding to different actual pixel points in all the device images are obtained, and the gray values corresponding to the actual pixel points are recorded as actual gray values.

[0088] In the embodiment, each actual pixel point in all the gray images has a corresponding initial pixel point in the initial gray image.

[0089] In step S203, the gray image corresponding to the first device image is selected as the analysis object and recorded as the first gray image, and the actual gray values of the actual pixel points in the first gray image are compared with the initial gray values of the corresponding initial pixel points.

[0090] If the actual gray value of any actual pixel point in the first gray image is different from the initial gray value of the corresponding initial pixel point, the corresponding actual pixel point in the first gray image is recorded as a dirt pixel point.

[0091] If the actual gray values of all the actual pixel points in the first gray image are the same as the initial gray values of the corresponding initial pixel points, no operation is performed.

[0092] Similarly, the actual gray values of the actual pixel points in different gray images are compared with the initial gray values of the corresponding initial pixel points to obtain the dirt pixel points in different gray images.

[0093] In step S204, the number of the dirt pixel points in different gray images is counted and recorded as the number of the dirt pixel points, and the number of the dirt pixel points in the first gray image is divided by the first time interval to obtain the generation rate of the dirt pixel points in the first time period.

[0094] In step S205, the number of the dirt pixel points in the second gray image is subtracted from the number of the dirt pixel points in the first gray image, and then divided by the first time interval to obtain the generation rate of the dirt pixel points in the second time period.

[0095] Similarly, the number of dirt pixels in the nth gray image is subtracted from the number of dirt pixels in the (n-1)th gray image, and then divided by the first time interval to obtain the generation rate of dirt pixels in the nth time period;

[0096] In this embodiment, the number of dirt pixels in the nth gray image is greater than or equal to the number of dirt pixels in the (n-1)th gray image; it needs to be explained that the humidity inside the tunnel is larger and changes less than outside the tunnel, and at the same time, the exhaust gas emitted by the car when driving inside the tunnel contains certain nitrogen oxides and sulfur oxides, which are corrosive after dissolving in water, so the dirt pixels in this embodiment are considered to be rust spots on the fire-fighting equipment, which will only increase over time without human intervention;

[0097] Step S206, the time period in which the generation rate of dirt pixels is greater than the corresponding generation rate in the last time period is recorded as the rate acceleration time period, and the time period in which the generation rate of dirt pixels is less than the corresponding generation rate in the last time period is recorded as the rate deceleration time period.

[0098] Step S3, analyzing the average humidity inside the tunnel and the total exhaust emission in different time periods to obtain the actual influence parameters inside the tunnel;

[0099] In this embodiment, the analysis process in step S3 includes the following sub-steps:

[0100] Step S301, collecting real-time air data inside the tunnel at a second time interval; wherein the real-time air data is the real-time exhaust concentration at the tunnel entrance, the real-time exhaust concentration at the tunnel exit, and the real-time wind speed at different positions inside the tunnel;

[0101] In this embodiment, the first time interval is greater than the second time interval, and the real-time exhaust concentration can be collected by installing a gas concentration sensor at the tunnel entrance and the tunnel exit, and the real-time wind speed can be collected by installing a wind speed sensor at different positions inside the tunnel;

[0102] Step S302, summing and averaging the real-time wind speed at different positions inside the tunnel to obtain the average wind speed inside the tunnel at the current time node, obtaining the cross-sectional area of the tunnel, and dividing the cross-sectional area by the average wind speed to obtain the real-time air flow inside the tunnel at the current time node;

[0103] In this embodiment, the cross-sectional area of the tunnel can be obtained from the design drawings of the tunnel;

[0104] Step S303, subtracting the real-time exhaust concentration at the tunnel entrance from the real-time exhaust concentration at the tunnel exit to obtain the real-time exhaust concentration difference between the tunnel entrance and exit at the current time node, taking the absolute value of the real-time exhaust concentration difference, multiplying the real-time air flow, and multiplying the second time interval to obtain the exhaust emission of the vehicle inside the tunnel at the current time node;

[0105] Step S304, adding and summing the exhaust emissions of the vehicle inside the tunnel at different time nodes in the first time period to obtain the total exhaust emission of the vehicle inside the tunnel in the corresponding time period;

[0106] Similarly, adding and summing the exhaust emissions of the vehicle inside the tunnel at different time nodes in any time period to obtain the total exhaust emission of the vehicle inside the tunnel in the corresponding time period;

[0107] Step S305, obtaining the real-time humidity inside the tunnel at different time nodes in any time period, and adding and averaging the real-time humidity inside the tunnel at different time nodes to obtain the average humidity inside the tunnel in the corresponding time period;

[0108] Step S306, subtracting the total exhaust emission in the previous time period from the corresponding total exhaust emission in any time period and dividing by the total exhaust emission in the previous time period to obtain the total exhaust emission change rate in the corresponding time period;

[0109] Subtracting the average humidity in the previous time period from the corresponding average humidity in any time period and dividing by the average humidity in the previous time period to obtain the average humidity change rate in the corresponding time period;

[0110] Step S307, analyzing the total exhaust emission change rate and the average humidity change rate in the rate acceleration time period, and obtaining the positive feedback parameter corresponding to the rate acceleration time period through analysis, and the analysis process is specifically as follows:

[0111] If the total exhaust emission change rate in the rate acceleration time period is greater than or equal to zero, but the average humidity change rate is less than zero, the total exhaust emission is taken as the positive feedback parameter corresponding to the rate acceleration time period; if the total exhaust emission change rate in the rate acceleration time period is less than zero, but the average humidity change rate is greater than or equal to zero, the average humidity is taken as the positive feedback parameter corresponding to the rate acceleration time period; if the total exhaust emission change rate and the average humidity change rate in the rate acceleration time period are both less than zero, no operation is performed; if the total exhaust emission change rate and the average humidity change rate in the rate acceleration time period are both greater than or equal to zero, step S308 is entered;

[0112] It needs to be explained that when the total exhaust emission rate and the average humidity change rate are both less than zero, it is considered that the generation rate of the dirt pixel point is accelerated by other factors, which is not discussed in this embodiment;

[0113] Step S308, when the total exhaust emission change rate in the rate acceleration time period is greater than or equal to the average humidity change rate, the total exhaust emission is taken as the positive feedback parameter of the rate acceleration time period;

[0114] When the total exhaust emission change rate in the rate acceleration time period is less than the average humidity change rate, the average humidity is taken as the positive feedback parameter of the rate acceleration time period;

[0115] Similarly, the total exhaust emission change rate and the average humidity change rate in different rate deceleration time periods are analyzed, and the positive feedback parameter of the rate deceleration time period is obtained;

[0116] It should be explained that when the positive feedback parameter of the rate deceleration time period is analyzed, the total exhaust emission change rate or the average humidity change rate less than zero is taken as the positive feedback parameter, when both are less than zero, the smaller one is taken as the positive feedback parameter, and when both are greater than or equal to zero, it is considered that the generation rate of the dirt pixel point is decelerated by other factors;

[0117] Step S309, the number of time periods with the average humidity as the positive feedback parameter is counted and recorded as the humidity time period number, the number of time periods with the total exhaust emission as the positive feedback parameter is counted and recorded as the exhaust time period number, and the humidity time period number and the exhaust time period number are compared;

[0118] If the humidity time period number is greater than or equal to the exhaust time period number, the average humidity is taken as the actual influence parameter inside the tunnel;

[0119] If the humidity time period number is less than the exhaust time period number, the total exhaust emission is taken as the actual influence parameter inside the tunnel.

[0120] Step S4, according to different actual influence parameters, the corresponding average humidity or total exhaust emission in different time periods is analyzed, and the predicted generation rate of the dirt pixel point is obtained;

[0121] In this embodiment, the analysis process in step S4 includes the following sub-steps:

[0122] Step S41, when the actual influence parameter is the average humidity, the mode of the average humidity in different time periods is taken as the predicted average humidity, and the time period corresponding to the mode of the average humidity is recorded as the characteristic time period;

[0123] Step S42, when the actual influence parameter is the total exhaust emission, the characteristic time period is analyzed, and the analysis process is specifically:

[0124] The tail gas average emission amount is obtained by adding and averaging the total tail gas emission amounts in different time periods, and the tail gas emission deviation amount in different time periods is obtained by subtracting the total tail gas emission amount in different time periods from the tail gas average emission amount and taking the absolute value.

[0125] The minimum value of the tail gas emission deviation amount is obtained by traversing and comparing different tail gas emission deviation amounts, and the time period corresponding to the minimum value of the tail gas emission deviation amount is recorded as a characteristic time period.

[0126] Step S43: The generation rate of the dirt pixel points in different characteristic time periods is traversed and compared to obtain the maximum value of the generation rate, which is recorded as the predicted generation rate of the dirt pixel points.

[0127] Step S5: The position of the dirt pixel points in the real-time device image is analyzed, and the warning time of the fire-fighting device inside the tunnel is analyzed using the predicted generation rate.

[0128] In this embodiment, the analysis process in step S5 includes the following sub-steps:

[0129] Step S51: Obtain the device image corresponding to the fire-fighting device inside the tunnel at the current time node and record it as a real-time device image, and place the real-time device image in a plane rectangular coordinate system.

[0130] Step S52: Obtain the coordinates of different water outlets on the surface of the fire-fighting device and record them as water hole position coordinates, and obtain the coordinates of different dirt pixel points in the real-time device image and record them as dirt point coordinates.

[0131] Step S53: Compare the dirt point coordinates with the water hole position coordinates.

[0132] If the dirt point coordinates of any dirt pixel point are the same as the water hole position coordinates, a warning is immediately issued.

[0133] If the dirt point coordinates of all dirt pixel points are different from the water hole position coordinates, step S54 is entered.

[0134] Step S54: The straight-line distances between different dirt pixel points and different water outlets are calculated by a distance formula, the minimum value of the straight-line distances is obtained by traversing and comparing different straight-line distances, the dirt pixel point corresponding to the minimum value of the straight-line distances is recorded as a potential diffusion point, and the water outlet corresponding to the minimum value of the straight-line distances is recorded as a potential blocked hole.

[0135] Step S55, please refer to Figure 2 The number of pixel points through which the line segment passes is counted and recorded as the minimum number of pixel points, and the predicted diffusion duration is obtained by dividing the minimum number of pixel points by the predicted generation rate.

[0136] For example, asFigure 2 As shown, the line segment between the potential clogging hole and the potential diffusion point passes through 4 pixel points, and the minimum number of pixel points is equal to 4 at this time;

[0137] In step S56, the time corresponding to the current time node is added to the predicted diffusion time to obtain the early warning time of the fire-fighting equipment inside the tunnel.

[0138] In this embodiment, when the early warning time is reached, the corresponding fire-fighting equipment inside the tunnel needs to be overhauled.

[0139] Embodiment Two: Based on the same invention, another concept is also proposed, which is a tunnel fire-fighting monitoring and early warning device based on Internet of Things sensing data analysis, including a data acquisition module, an image analysis module, a parameter analysis module, a data prediction module, and a comprehensive analysis module.

[0140] The data acquisition module is used to acquire the device images of the fire-fighting equipment inside the tunnel at different time nodes and send them to the image analysis module. The image analysis module is used to analyze the pixel points in the device images in different time periods, analyze the rate acceleration time period and the rate deceleration time period, and send them to the parameter analysis module. The data acquisition module is also used to acquire the humidity and tail gas emission at different positions inside the tunnel and send them to the parameter analysis module.

[0141] The parameter analysis module is used to analyze the average humidity and total tail gas emission inside the tunnel in different time periods, analyze the actual influence parameters inside the tunnel, and send them to the data prediction module. The data prediction module is used to analyze the corresponding average humidity or total tail gas emission in different time periods according to different actual influence parameters, analyze the predicted generation rate of the dirt pixel points, and send them to the comprehensive analysis module. The comprehensive analysis module is used to analyze the position of the dirt pixel points in the device image and analyze the early warning time of the fire-fighting equipment using the predicted generation rate.

[0142] Embodiment Three: As Figure 3As shown, the embodiment provides a tunnel fire-fighting monitoring and early warning system based on Internet of Things sensing data analysis, which can include a processor, a communications interface, a memory and a communications bus, wherein the processor, the communications interface and the memory complete mutual communication through the communications bus. The processor can call logical instructions in the memory to execute a tunnel fire-fighting monitoring and early warning method based on Internet of Things sensing data analysis, which includes: dividing different time periods according to the shooting time of the device image; analyzing the pixel points of the device image in different time periods to obtain the rate acceleration time period and the rate deceleration time period; analyzing the average humidity inside the tunnel and the total exhaust emission in different time periods to obtain the actual influence parameters inside the tunnel; analyzing the corresponding average humidity or total exhaust emission in different time periods according to different actual influence parameters to obtain the predicted generation rate of the dirt pixel points; analyzing the position of the dirt pixel points in the real-time device image, and analyzing the early warning time of the fire-fighting equipment inside the tunnel using the predicted generation rate.

[0143] In addition, the logical instructions in the memory described above can be implemented in the form of a software functional unit and sold or used as an independent product, which can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various program code storage media.

[0144] Embodiment four: the application also provides a computer program product, the computer program product comprises a computer program stored on a computer readable storage medium, the computer program comprises program instructions, when the program instructions are executed by a computer, the computer can execute the tunnel fire monitoring and early warning method based on the Internet of Things sensing data analysis provided by each of the above methods, the method comprises: dividing different time periods according to the shooting time of the device image; analyzing the pixel points of the device image in different time periods, and obtaining the rate acceleration time period and the rate deceleration time period; analyzing the average humidity inside the tunnel and the total exhaust emission in different time periods, and obtaining the actual influence parameter inside the tunnel; analyzing the corresponding average humidity or total exhaust emission in different time periods according to different actual influence parameters, and obtaining the predicted generation rate of the dirt pixel points; analyzing the position of the dirt pixel points in the real-time device image, and analyzing the early warning time of the fire-fighting equipment inside the tunnel by using the predicted generation rate.

[0145] Embodiment five: the application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the tunnel fire monitoring and early warning method based on the Internet of Things sensing data analysis provided by each of the above methods, the method comprises: dividing different time periods according to the shooting time of the device image; analyzing the pixel points of the device image in different time periods, and obtaining the rate acceleration time period and the rate deceleration time period; analyzing the average humidity inside the tunnel and the total exhaust emission in different time periods, and obtaining the actual influence parameter inside the tunnel; analyzing the corresponding average humidity or total exhaust emission in different time periods according to different actual influence parameters, and obtaining the predicted generation rate of the dirt pixel points; analyzing the position of the dirt pixel points in the real-time device image, and analyzing the early warning time of the fire-fighting equipment inside the tunnel by using the predicted generation rate.

[0146] The device embodiments described above are only schematic, wherein the units shown as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0147] Those skilled in the art can clearly understand the implementation of the various embodiments by means of software and the necessary general hardware platform from the above description of the embodiments, and of course, the embodiments can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that contributes to the technical solutions can be embodied in the form of a software product. The computer software product can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0148] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacement for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A tunnel fire monitoring and early warning method based on Internet of Things sensing data analysis, characterized in that, The method comprises: Step S1, dividing different time periods according to the shooting time of the equipment image; Step S2, analyzing the pixel points of the equipment image in different time periods to obtain the rate acceleration time period and the rate deceleration time period; The analysis process in step S2 comprises the following sub-steps: Step S201, performing gray processing on the initial equipment image to obtain an initial gray image, and performing gray processing on all equipment images to obtain the gray images corresponding to the equipment images; Step S202, obtaining the gray values corresponding to different initial pixel points in the initial gray image, and recording the gray values corresponding to the initial pixel points as initial gray values; obtaining the gray values corresponding to different actual pixel points in all equipment images, and recording the gray values corresponding to the actual pixel points as actual gray values; Step S203, selecting the gray image corresponding to the first equipment image as an analysis object and recording it as a first gray image, and comparing the actual gray values of the actual pixel points in the first gray image with the initial gray values of the corresponding initial pixel points; If the actual gray value of any actual pixel point in the first gray image is different from the initial gray value of the corresponding initial pixel point, the corresponding actual pixel point in the first gray image is recorded as a dirt pixel point; If the actual gray values of all actual pixel points in the first gray image are the same as the initial gray values of the corresponding initial pixel points, no operation is performed; Similarly, the actual gray values of the actual pixel points in different gray images are compared with the initial gray values of the corresponding initial pixel points, and the dirt pixel points in different gray images are obtained by comparison; Step S204, counting the number of dirt pixel points in different gray images and recording it as the number of dirt pixel points, and dividing the number of dirt pixel points in the first gray image by the first time interval to obtain the generation rate of dirt pixel points in the first time period; Step S205, dividing the number of dirt pixel points in the second gray image by the first time interval after subtracting the number of dirt pixel points in the first gray image, to obtain the generation rate of dirt pixel points in the second time period; Similarly, the number of dirt pixel points in the nth gray image is divided by the first time interval after subtracting the number of dirt pixel points in the (n-1)th gray image, to obtain the generation rate of dirt pixel points in the nth time period; Step S206, recording the time period in which the generation rate of dirt pixel points is greater than the corresponding generation rate in the last time period as the rate acceleration time period, and recording the time period in which the generation rate of dirt pixel points is less than the corresponding generation rate in the last time period as the rate deceleration time period; Step S3, analyzing the average humidity inside the tunnel and the total exhaust emission in different time periods to obtain the actual influence parameters inside the tunnel; Step S4, analyzing the corresponding average humidity or total exhaust emission in different time periods according to different actual influence parameters to obtain the predicted generation rate of dirt pixel points; Step S5, analyzing the position of the dirt pixel points in the real-time equipment image, and analyzing the warning time of the fire-fighting equipment inside the tunnel by using the predicted generation rate; The analysis process in step S5 comprises the following sub-steps: Step S51, obtain the device image corresponding to the tunnel internal fire-fighting equipment at the current time node and mark it as a real-time device image, and place the real-time device image in a plane rectangular coordinate system; Step S52, obtain the coordinates of different water outlet holes on the surface of the fire-fighting equipment and mark them as water hole position coordinates, and obtain the coordinates of different dirt pixel points in the real-time device image and mark them as dirt point coordinates; Step S53, compare the dirt point coordinates with the water hole position coordinates; If the dirt point coordinates of any dirt pixel point are the same as the water hole position coordinates, an early warning is immediately issued; If the dirt point coordinates of all dirt pixel points are different from the water hole position coordinates, step S54 is entered; Step S54, calculate the straight-line distance between different dirt pixel points and different water outlet holes by a distance formula, traverse and compare different straight-line distances to obtain a minimum value of the straight-line distance, mark the dirt pixel point corresponding to the minimum value of the straight-line distance as a potential diffusion point, and mark the water outlet hole corresponding to the minimum value of the straight-line distance as a potential blockage hole; Step S55, connect the potential blockage hole and the potential diffusion point using a line segment, count the number of pixel points crossed by the line segment and mark it as a minimum number of pixel points, and divide the minimum number of pixel points by a predicted generation rate to obtain a predicted diffusion time length; Step S56, add the time corresponding to the current time node to the predicted diffusion time length to obtain the early warning time of the tunnel internal fire-fighting equipment. 2.The tunnel fire monitoring and early warning method based on Internet of Things sensing data analysis according to claim 1, characterized in that, The division process in step S1 includes the following sub-steps: Step S101, take pictures of the designated fire-fighting equipment inside the tunnel at a first time interval, and sequentially mark the images as a first device image, a second device image, a third device image, …, and an n-th device image according to the ascending order of the shooting time, where n is the number of the device images; Step S102, obtain an image taken when the fire-fighting equipment inside the tunnel is put into use and mark it as an initial device image, mark the pixel points in the initial device image as initial pixel points, and mark the pixel points in the first device image, the second device image, …, and the n-th device image as actual pixel points; Step S103, mark the time period between taking the initial device image and taking the first device image as a first time period, mark the time period between taking the first device image and taking the second device image as a second time period, and similarly, mark the time period between taking the n-1-th device image and taking the n-th device image as an n-th time period. 3.The tunnel fire monitoring and early warning method based on Internet of Things sensing data analysis according to claim 1, characterized in that, The analysis process in step S3 includes the following sub-steps: Step S301, collect real-time air data inside the tunnel at a second time interval; wherein the real-time air data is the real-time exhaust gas concentration at the tunnel entrance, the real-time exhaust gas concentration at the tunnel exit, and the real-time wind speed at different positions inside the tunnel; Step S302, add and average the real-time wind speeds at different positions inside the tunnel to obtain the average wind speed inside the tunnel at the current time node, obtain the cross-sectional area of the tunnel, and divide the cross-sectional area by the average wind speed to obtain the real-time air flow inside the tunnel at the current time node; Step S303, subtracting the real-time exhaust concentration at the tunnel entrance from the real-time exhaust concentration at the tunnel exit to obtain the real-time exhaust concentration difference between the tunnel entrance and exit at the current time node, taking the absolute value of the real-time exhaust concentration difference, multiplying the real-time air flow, and then multiplying the second time interval to obtain the exhaust emission of the vehicle inside the tunnel at the current time node; Step S304, adding and summing the exhaust emissions of the vehicle inside the tunnel at different time nodes in the first time period to obtain the total exhaust emission of the vehicle inside the tunnel in the corresponding time period; Similarly, adding and summing the exhaust emissions of the vehicle inside the tunnel at different time nodes in any time period to obtain the total exhaust emission of the vehicle inside the tunnel in the corresponding time period. 4.The tunnel fire monitoring and early warning method based on Internet of Things sensing data analysis according to claim 3, characterized in that, The analysis process in step S3 further includes the following sub-steps: Step S305, obtaining the real-time humidity inside the tunnel at different time nodes in any time period, and adding and averaging the real-time humidity inside the tunnel at different time nodes to obtain the average humidity inside the tunnel in the corresponding time period; Step S306, subtracting the total exhaust emission in the previous time period from the total exhaust emission in the corresponding time period and then dividing by the total exhaust emission in the previous time period to obtain the total exhaust emission change rate in the corresponding time period; Subtracting the average humidity in the previous time period from the corresponding average humidity in any time period and then dividing by the average humidity in the previous time period to obtain the average humidity change rate in the corresponding time period; Step S307, analyzing the total exhaust emission change rate and the average humidity change rate in the rate acceleration time period to obtain the positive feedback parameter corresponding to the rate acceleration time period, and the analysis process is as follows: If the total exhaust emission change rate in the rate acceleration time period is greater than or equal to zero, but the average humidity change rate is less than zero, then the total exhaust emission is taken as the positive feedback parameter of the corresponding rate acceleration time period; if the total exhaust emission change rate in the rate acceleration time period is less than zero, but the average humidity change rate is greater than or equal to zero, then the average humidity is taken as the positive feedback parameter of the corresponding rate acceleration time period; if the total exhaust emission change rate and the average humidity change rate in the rate acceleration time period are both less than zero, then no operation is performed; if the total exhaust emission change rate and the average humidity change rate in the rate acceleration time period are both greater than or equal to zero, then step S308 is entered; Step S308, when the total exhaust emission change rate in the rate acceleration time period is greater than or equal to the average humidity change rate, then the total exhaust emission is taken as the positive feedback parameter of the rate acceleration time period; When the total exhaust emission change rate in the rate acceleration time period is less than the average humidity change rate, then the average humidity is taken as the positive feedback parameter of the rate acceleration time period; Similarly, the total exhaust emission change rate and the average humidity change rate in different rate deceleration time periods are analyzed to obtain the positive feedback parameter of the rate deceleration time period; Step S309, counting the number of time periods with the average humidity as the positive feedback parameter and recording it as the humidity time period number, counting the number of time periods with the total exhaust emission as the positive feedback parameter and recording it as the exhaust time period number, and comparing the humidity time period number with the exhaust time period number; If the number of humidity time periods is greater than or equal to the number of tail gas time periods, the average humidity is taken as the actual influencing parameter inside the tunnel; If the number of humidity time periods is less than the number of tail gas time periods, the total tail gas emission is taken as the actual influencing parameter inside the tunnel. 5.The tunnel fire monitoring and early warning method based on the Internet of Things sensing data analysis according to claim 4, characterized in that, The analysis process in the step S4 includes the following sub-steps: Step S41, when the actual influencing parameter is the average humidity, the mode of the average humidity in different time periods is taken as the predicted average humidity, and the time period corresponding to the mode of the average humidity is recorded as the characteristic time period; Step S42, when the actual influencing parameter is the total tail gas emission, the characteristic time period is analyzed, and the analysis process is specifically as follows: The total tail gas emission in different time periods is added and averaged to obtain the average tail gas emission, and the absolute value of the average tail gas emission minus the total tail gas emission in different time periods is obtained to obtain the tail gas emission deviation in different time periods; Different tail gas emission deviations are traversed and compared to obtain the minimum value of the tail gas emission deviation, and the time period corresponding to the minimum value of the tail gas emission deviation is recorded as the characteristic time period; Step S43, the generation rate of the dirt pixel points in different characteristic time periods is traversed and compared to obtain the maximum value of the generation rate and record it as the predicted generation rate of the dirt pixel points.

6. A tunnel fire monitoring and early warning device based on Internet of Things sensing data analysis, characterized in that, The tunnel fire-fighting monitoring and early warning method based on Internet of Things sensing data analysis according to any one of claims 1-5, comprising a data acquisition module, an image analysis module, a parameter analysis module, a data prediction module, and a comprehensive analysis module; The data acquisition module is used to acquire device images of fire-fighting equipment inside the tunnel at different time nodes and send them to the image analysis module; the image analysis module is used to analyze the pixel points in the device images in different time periods to obtain the rate acceleration time period and the rate deceleration time period and send them to the parameter analysis module; the data acquisition module is also used to acquire the humidity and tail gas emission at different positions inside the tunnel and send them to the parameter analysis module; The parameter analysis module is used to analyze the average humidity and the total tail gas emission inside the tunnel in different time periods to obtain the actual influencing parameter inside the tunnel and send it to the data prediction module; the data prediction module is used to analyze the corresponding average humidity or total tail gas emission in different time periods according to different actual influencing parameters to obtain the predicted generation rate of the dirt pixel points and send it to the comprehensive analysis module; the comprehensive analysis module is used to analyze the position of the dirt pixel points in the device images and analyze the early warning time of the fire-fighting equipment using the predicted generation rate.

7. A tunnel fire monitoring and early warning system based on Internet of Things sensing data analysis, characterized in that, The tunnel fire-fighting monitoring and early warning system comprises: A memory storing a computer program; A processor in communication with the memory, when the computer program is executed by the processor, the method according to any one of claims 1-5 is realized.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to realize the method according to any one of claims 1-5. The program is executed by the processor to realize the method according to any one of claims 1-5.

Images