Closed coal shed fog gun linkage control method and system based on image AI

Abstract

The invention relates to a closed coal shed fog gun linkage control method and system based on image AI, and belongs to the field of fog gun control. The method comprises the following steps: acquiring an initial image of a closed coal shed, and preprocessing to obtain a corrected image of the closed coal shed; carrying out binarization processing on the closed coal shed correction image to obtain a closed coal shed detection image; according to the closed coal shed detection image, closed coal shed dust raising information is obtained; obtaining the humidity information of the closed coal shed according to the corrected image of the closed coal shed; closed coal shed sensing information is obtained according to the monitoring period; obtaining the weight information of the closed coal shed through a weight sensor; triggering a fog gun primary starting instruction, a fog gun secondary starting instruction and a fog gun closing instruction according to the closed coal shed warning information; and the closed coal shed dust raising information, the closed coal shed humidity information, the closed coal shed sensing information, the closed coal shed weight information, the fog gun primary starting instruction and the fog gun secondary starting instruction are synchronized to a user terminal. Whether the closed coal shed needs to start the water pump for dust prevention and cooling is rapidly judged by the AI.

Description

Technical Field

[0001] The present invention belongs to the technical field of fog cannon control, and in particular relates to a closed coal shed fog cannon linkage control method and system based on image AI. Background Art

[0002] Dust is prone to exceed the standard in closed coal sheds, which affects work efficiency and workers' health. Fog cannons can atomize water into fine particles through high pressure to form water mist to reduce dust in the air, significantly improve the pollution phenomenon in closed coal sheds, increase the humidity in the coal sheds, and reduce the temperature in the coal sheds. Fog cannons use less water resources and energy, achieving significant environmental improvement effects, meeting the requirements of energy conservation and emission reduction. At present, there is no effective means to intelligently judge when and under what circumstances the fog cannon should be turned on in closed coal sheds, and no effective measures have been taken to prevent the dust pollution caused by mobile equipment such as large load vehicles entering the closed coal sheds. The naive Bayes classifier is a classification algorithm based on Bayes' theorem and the conditional independence assumption of features. It assumes that all features are independent of each other, which makes the calculation simpler, more efficient, and more stable. It can be used to determine whether dust pollution occurs in closed coal sheds. Summary of the invention

[0003] In order to solve the above problems existing in the prior art, the present invention provides a closed coal shed fog cannon linkage control method and system based on image AI.

[0004] The purpose of the present invention can be achieved through the following technical solutions:

[0005] A closed coal shed fog cannon linkage control method based on image AI, the implementation of the closed coal shed fog cannon linkage control method comprises the following steps:

[0006] Preset a monitoring cycle, collect an initial image of the closed coal shed through an industrial camera according to the monitoring cycle, pre-process the initial image of the closed coal shed to obtain a closed coal shed correction image, and the wavelength of the industrial camera is less than 700nm;

[0007] Binarizing the closed coal shed correction image to obtain a closed coal shed detection image;

[0008] Obtaining closed coal shed dust information according to the closed coal shed detection image, wherein the closed coal shed dust information includes closed coal shed dust pollution information and closed coal shed dust non-pollution information;

[0009] Obtaining closed coal shed humidity information according to the closed coal shed correction image, wherein the closed coal shed humidity information includes closed coal shed suitable humidity information and closed coal shed insufficient humidity information;

[0010] Acquire closed coal shed sensor information according to the monitoring period, the closed coal shed sensor information includes closed coal shed temperature information and closed coal shed directional wind speed information, the closed coal shed temperature information includes closed coal shed temperature exceeding standard information and closed coal shed temperature reaching standard information, the closed coal shed directional wind speed information includes closed coal shed wind speed positive feedback information and closed coal shed wind speed negative feedback information;

[0011] Acquire the weight information of the closed coal shed by means of a weight sensor, wherein the weight information of the closed coal shed includes overweight information of the closed coal shed and non-overweight information of the closed coal shed;

[0012] When 3 or more closed coal shed warning information is output within one monitoring cycle, the first-level start instruction of the fog cannon is triggered; when more than 0 but less than 3 closed coal shed warning information is output, the second-level start instruction of the fog cannon is triggered; when 0 closed coal shed warning information is output, the fog cannon shutdown instruction is triggered, and the closed coal shed warning information includes the closed coal shed dust pollution information, the closed coal shed insufficient humidity information, the closed coal shed temperature exceeding the standard information, the closed coal shed wind speed negative feedback information, and the closed coal shed overweight information;

[0013] The dust information of the closed coal shed, the humidity information of the closed coal shed, the sensor information of the closed coal shed, the weight information of the closed coal shed, the first-level start-up instruction of the fog cannon, and the second-level start-up instruction of the fog cannon are synchronized to the user terminal.

[0014] Preferably, the binarization processing of the closed coal shed correction image to obtain the closed coal shed detection image comprises:

[0015] Preset a segmentation grayscale threshold, and segment the closed coal shed correction image into a closed coal shed foreground and a closed coal shed background according to the segmentation grayscale threshold;

[0016] Obtaining the foreground proportion, background proportion, foreground average gray value, and background average gray value of the closed coal shed foreground and the closed coal shed background;

[0017] Calculating the total average gray value of the closed coal shed correction image;

[0018] Calculate the foreground and background variance according to the total average gray value;

[0019] When the foreground-background variance reaches a maximum value, the corresponding segmentation grayscale threshold is an optimal segmentation threshold, and the closed coal shed correction image is segmented according to the optimal segmentation threshold to obtain the closed coal shed detection image.

[0020] Preferably, obtaining the closed coal shed dust information according to the closed coal shed detection image comprises:

[0021] By constructing a gray-level co-occurrence matrix, the closed coal shed detection image is subjected to feature extraction to obtain a three-dimensional feature vector, wherein the three-dimensional feature vector includes an energy value, an entropy value, and an inverse moment;

[0022] The dust information of the closed coal shed is obtained through a naive Bayes classifier according to the three-dimensional feature vector.

[0023] Preferably, extracting features from the closed coal shed detection image by constructing a gray level co-occurrence matrix to obtain a three-dimensional feature vector comprises:

[0024] The closed coal shed detection image is divided into windows, and the gray-level co-occurrence matrix is ​​constructed for each window;

[0025] Obtaining a histogram eigenvalue of the gray level co-occurrence matrix, and calculating the energy value according to the histogram eigenvalue;

[0026] Calculating the entropy value according to the histogram eigenvalue;

[0027] The inverse moment is calculated according to the histogram eigenvalues.

[0028] Preferably, obtaining the closed coal shed humidity information according to the closed coal shed correction image comprises:

[0029] A closed coal shed humidity control point is preset, wherein the closed coal shed humidity control point is located at a fixed position of the closed coal shed and at the far edge of the shooting range of the industrial camera;

[0030] Locate the position of the closed coal shed humidity control point in the closed coal shed correction image, and calculate the clarity of the closed coal shed humidity control point according to the gray value of the closed coal shed humidity control point;

[0031] Obtaining the clarity of the dry coal shed, wherein the clarity of the dry coal shed is the clarity of the humidity control point of the closed coal shed in a dry environment;

[0032] The humidity information of the closed coal shed is obtained by comparing the clarity of the humidity control point of the closed coal shed with the clarity of the dry coal shed. When the clarity of the humidity control point of the closed coal shed is less than 80% of the clarity of the dry coal shed, the suitable humidity information of the closed coal shed is output. When the clarity of the humidity control point of the closed coal shed is greater than or equal to 80% of the clarity of the dry coal shed, the insufficient humidity information of the closed coal shed is output.

[0033] Preferably, the acquiring of closed coal shed sensor information according to the monitoring period includes:

[0034] The temperature of the closed coal shed is obtained by the temperature sensor, and a closed coal shed temperature threshold is preset. When the temperature of the closed coal shed is greater than or equal to the closed coal shed temperature threshold, information that the closed coal shed temperature exceeds the standard is output; when the temperature of the closed coal shed is less than the closed coal shed temperature threshold, information that the closed coal shed temperature meets the standard is output;

[0035] The directional wind speed of the closed coal shed is obtained through the wind speed sensor and the wind direction sensor. The directional wind speed of the closed coal shed is the wind speed in the direction of water discharge from the fog cannon. A closed coal shed wind speed threshold is preset. When the directional wind speed of the closed coal shed is greater than or equal to the closed coal shed wind speed threshold, the closed coal shed wind speed positive feedback information is output. When the directional wind speed of the closed coal shed is less than the closed coal shed wind speed threshold, the closed coal shed wind speed negative feedback information is output.

[0036] Preferably, the obtaining the weight information of the closed coal shed by means of a weight sensor comprises:

[0037] The weight of the mobile equipment of the closed coal shed is obtained by weight sensors arranged around the edge of the closed coal shed, and a weight threshold of the closed coal shed is preset. When the weight of the mobile equipment of the closed coal shed is greater than or equal to the weight threshold of the closed coal shed, the overweight information of the closed coal shed is output; when the weight of the mobile equipment of the closed coal shed is less than the weight threshold of the closed coal shed, the non-overweight information of the closed coal shed is output.

[0038] An image AI-based closed coal shed fog cannon linkage control system, used to execute the closed coal shed fog cannon linkage control method described above, comprising an image processing module, a closed coal shed warning module, and a fog cannon command trigger module;

[0039] The image processing module is used to preset a monitoring cycle, collect an initial image of a closed coal shed through an industrial camera according to the monitoring cycle, pre-process the initial image of the closed coal shed to obtain a closed coal shed correction image, and binarize the closed coal shed correction image to obtain a closed coal shed detection image;

[0040] The closed coal shed warning module is used to obtain the dust information of the closed coal shed according to the closed coal shed detection image, and the closed coal shed dust information includes the closed coal shed dust pollution information and the closed coal shed dust non-pollution information; obtain the closed coal shed humidity information according to the closed coal shed correction image, and the closed coal shed humidity information includes the closed coal shed humidity suitable information and the closed coal shed humidity insufficient information; obtain the closed coal shed sensor information through the sensor according to the monitoring period, and the closed coal shed sensor information includes the closed coal shed temperature information and the closed coal shed directional wind speed information, and the closed coal shed temperature information includes the closed coal shed temperature exceeding the standard information and the closed coal shed temperature reaching the standard information, and the closed coal shed directional wind speed information includes the closed coal shed wind speed positive feedback information and the closed coal shed wind speed negative feedback information; obtain the closed coal shed weight information through the weight sensor, and the closed coal shed weight information includes the closed coal shed overweight information and the closed coal shed not overweight information;

[0041] The fog cannon command trigger module is used to trigger the fog cannon first-level start command when 3 or more closed coal shed warning information is output within one monitoring cycle, trigger the fog cannon second-level start command when more than 0 but less than 3 closed coal shed warning information is output, and trigger the fog cannon shutdown command when 0 closed coal shed warning information is output. The closed coal shed warning information includes dust pollution information of the closed coal shed, insufficient humidity information of the closed coal shed, temperature exceeding the standard of the closed coal shed, negative feedback information of wind speed of the closed coal shed, and overweight information of the closed coal shed.

[0042] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned closed coal shed fog cannon linkage control method when executing the program.

[0043] A storage medium containing computer executable instructions, which are used to execute the above-mentioned closed coal shed fog cannon linkage control method when executed by a computer processor.

[0044] The beneficial effects of the present invention are:

[0045] (1) By collecting the initial image of the closed coal shed and obtaining the closed coal shed correction image and closed coal shed detection image through AI processing, the closed coal shed warning information is finally obtained to trigger the fog cannon start command, so as to realize the rapid and intelligent judgment of the closed coal shed status and realize the fully automated trigger command, so as to timely warn and control the pollution and other conditions in the closed coal shed;

[0046] (2) The initial image of the closed coal shed is collected by an industrial camera with a wavelength less than 700 nm. The wavelength at this time cannot penetrate the water mist. When the air humidity is high, the image clarity will be reduced, which is convenient for judging whether the humidity of the closed coal shed is insufficient;

[0047] (3) The closed coal shed correction image is processed by binarization to obtain the closed coal shed detection image, and the optimal segmentation threshold is reasonably selected to make the image foreground and background significantly different, which is convenient for subsequent image analysis;

[0048] (4) By constructing a gray-level co-occurrence matrix, the features of the closed coal shed detection image are extracted to obtain a three-dimensional feature vector. According to the three-dimensional feature vector, the naive Bayes classifier is used to obtain the dust information of the closed coal shed. The trained model is used to quickly classify the image into two categories: polluted and unpolluted. The classification method is reasonable and efficient.

[0049] (5) Obtain the directional wind speed of the closed coal shed through the wind speed sensor and wind direction sensor. The directional wind speed of the closed coal shed is the wind speed in the direction of the fog cannon's water discharge. When the directional wind speed is large, it can assist the water mist of the fog cannon to diffuse in the closed coal shed. At this time, the operation intensity or frequency of the fog cannon can be appropriately reduced to achieve resource conservation;

[0050] (6) The weight of the mobile equipment in the closed coal shed is obtained by placing weight sensors around the edge of the closed coal shed. When overweight equipment enters the closed coal shed, an early warning can be given to avoid dust caused by the movement of overweight equipment, thus playing a preventive role. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0052] Figure 1 The present invention is a flowchart of the steps of a closed coal shed fog cannon linkage control method based on image AI. DETAILED DESCRIPTION

[0053] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, characteristics and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0054] The working principle and use process of the present invention:

[0055] See also Figure 1 , a closed coal shed fog cannon linkage control method based on image AI, comprising:

[0056] S1: Preset a monitoring period, collect an initial image of the closed coal shed through an industrial camera according to the monitoring period, pre-process the initial image of the closed coal shed to obtain a corrected image of the closed coal shed, the wavelength of the industrial camera is less than 700nm, and the pre-processing includes but is not limited to image denoising, gamma correction, edge enhancement, and color correction;

[0057] S2: Binarizing the closed coal shed correction image to obtain a closed coal shed detection image;

[0058] S3: obtaining dust information of the closed coal shed according to the closed coal shed detection image, wherein the dust information of the closed coal shed includes dust pollution information of the closed coal shed and dust non-pollution information of the closed coal shed;

[0059] S4: obtaining closed coal shed humidity information according to the closed coal shed correction image, wherein the closed coal shed humidity information includes closed coal shed suitable humidity information and closed coal shed insufficient humidity information;

[0060] S5: acquiring closed coal shed sensing information through sensors according to the monitoring period, wherein the sensors include temperature sensors, wind speed sensors, and wind direction sensors, wherein the closed coal shed sensing information includes closed coal shed temperature information and closed coal shed directional wind speed information, wherein the closed coal shed temperature information includes closed coal shed temperature exceeding standard information and closed coal shed temperature reaching standard information, and the closed coal shed directional wind speed information includes closed coal shed wind speed positive feedback information and closed coal shed wind speed negative feedback information;

[0061] S6: Obtaining weight information of the closed coal shed through a weight sensor, wherein the weight information of the closed coal shed includes overweight information of the closed coal shed and non-overweight information of the closed coal shed;

[0062] S7: When 3 or more closed coal shed warning information is output within one monitoring cycle, the first-level start instruction of the fog cannon is triggered; when more than 0 and less than 3 closed coal shed warning information is output, the second-level start instruction of the fog cannon is triggered; when 0 closed coal shed warning information is output, the fog cannon shutdown instruction is triggered. The closed coal shed warning information includes the closed coal shed dust pollution information, the closed coal shed insufficient humidity information, the closed coal shed temperature exceeding the standard information, the closed coal shed wind speed negative feedback information, and the closed coal shed overweight information. When the first-level start instruction of the fog cannon is triggered, the operation intensity and frequency of the fog cannon are high; when the second-level start instruction of the fog cannon is triggered, the operation intensity and frequency of the fog cannon are low;

[0063] S8: Synchronize the dust information of the closed coal shed, the humidity information of the closed coal shed, the sensor information of the closed coal shed, the weight information of the closed coal shed, the first-level start-up instruction of the fog cannon, and the second-level start-up instruction of the fog cannon to the user terminal.

[0064] In this embodiment, the closed coal shed correction image is binarized to obtain the closed coal shed detection image, which can be specifically implemented by the following steps:

[0065] S201: Preset a segmentation grayscale threshold, and segment the closed coal shed correction image into a closed coal shed foreground and a closed coal shed background according to the segmentation grayscale threshold;

[0066] S202: Obtaining a foreground proportion, a background proportion, a foreground average grayscale value, and a background average grayscale value of the closed coal shed foreground and the closed coal shed background, wherein the foreground proportion is the proportion of the closed coal shed foreground to the closed coal shed corrected image, and the background proportion is the proportion of the closed coal shed background to the closed coal shed corrected image;

[0067] S203: Calculate the total average gray value of the closed coal shed correction image, the calculation formula is u=w0u0+w1u1, wherein u is the total average gray value, w0 is the foreground proportion, u0 is the foreground average gray value, w1 is the background proportion, and u1 is the background average gray value;

[0068] S204: Calculate the foreground and background variance according to the total average gray value, and the calculation formula is S 2 =w0(u0-u) 2 +w1(u1-u) 2 , where S 2 is the foreground-background variance;

[0069] S205: When the foreground-background variance reaches the maximum value, the corresponding segmentation grayscale threshold is the optimal segmentation threshold. The closed coal shed correction image is segmented according to the optimal segmentation threshold to obtain the closed coal shed detection image, so that the image foreground and background are significantly distinguished, which is convenient for subsequent image analysis.

[0070] In this embodiment, the closed coal shed dust information is obtained according to the closed coal shed detection image, and the closed coal shed dust information includes closed coal shed dust pollution information and closed coal shed dust non-pollution information, which can be specifically implemented by the following steps:

[0071] S301: extracting features of the closed coal shed detection image by constructing a gray level co-occurrence matrix to obtain a three-dimensional feature vector, wherein the three-dimensional feature vector includes an energy value, an entropy value, and an inverse difference moment;

[0072] S302: Obtaining dust information of the closed coal shed through a naive Bayes classifier according to the three-dimensional feature vector;

[0073] The posterior probability is obtained through the prior probability, conditional probability and marginal probability, the prior probability is the probability of the closed coal shed dust pollution information and the closed coal shed dust-free information when it does not depend on the three-dimensional feature vector, the conditional probability is the probability of the three-dimensional feature vector appearing under the closed coal shed dust pollution information and the closed coal shed dust-free information, the marginal probability is the total probability of the three-dimensional feature vector appearing, the posterior probability is the probability of the closed coal shed dust pollution information and the closed coal shed dust-free information appearing given the three-dimensional feature vector, when the posterior probability of the closed coal shed detection image about the closed coal shed dust pollution information is greater, the closed coal shed dust pollution information is output, and when the posterior probability of the closed coal shed detection image about the closed coal shed dust-free information is greater, the closed coal shed dust-free information is output.

[0074] In this embodiment, a gray-level co-occurrence matrix is ​​constructed to extract features of the closed coal shed detection image to obtain a three-dimensional feature vector, wherein the three-dimensional feature vector includes an energy value, an entropy value, and an inverse moment, which can be implemented by the following steps:

[0075] S301-1: Divide the closed coal shed detection image into windows of 16×16 pixel size, and construct the gray level co-occurrence matrix for each window. The direction angle of the gray level co-occurrence matrix is ​​0 degree, the sliding window step is 3, and the gray value range is [0-16];

[0076] S301-2: Obtain the histogram eigenvalues ​​of the gray level co-occurrence matrix, where the histogram eigenvalues ​​include but are not limited to brightness distribution, contrast, and saturation, and calculate the energy value according to the histogram eigenvalues. The calculation formula is: Among them, E is the energy value, H is the histogram eigenvalue, L is the maximum value of the gray value range, the value is 16, and i is the gray value;

[0077] S301-3: Calculate the entropy value according to the histogram feature value, and the calculation formula is: Where, T is the entropy value;

[0078] S301-4: Calculate the inverse moment according to the histogram eigenvalues, and the calculation formula is: Among them, D is the inverse moment, d is the sliding window step size, θ is the direction angle, and i and j are two adjacent different grayscale values.

[0079] In this embodiment, the closed coal shed humidity information is obtained according to the closed coal shed correction image, and the closed coal shed humidity information includes closed coal shed suitable humidity information and closed coal shed insufficient humidity information, which can be specifically implemented by the following steps:

[0080] S401: Preset a humidity control point in the closed coal shed, where the humidity control point is located at a fixed position in the closed coal shed and at the far edge of the shooting range of the industrial camera, and can be a point on the ground, a point on a fixed device, a point on a sticker, or a point on a lamp;

[0081] S402: Locate the position of the closed coal shed humidity control point in the closed coal shed correction image, and calculate the clarity of the closed coal shed humidity control point according to the gray value of the closed coal shed humidity control point. The calculation formula is Y=∑ x ∑ y [f(x+2,y)-f(x,y)] 2 , where Y is the clarity of the closed coal shed humidity control point, f(x,y) is the grayscale value of the closed coal shed humidity control point, and f(x+2,y) is the grayscale value of the 2 unit points away from the closed coal shed humidity control point;

[0082] S403: Acquire the clarity of the dry coal shed, where the clarity of the dry coal shed is the clarity of the humidity control point of the closed coal shed in a dry environment;

[0083] S404: The humidity information of the closed coal shed is obtained by comparing the clarity of the humidity control point of the closed coal shed with the clarity of the dry coal shed. Wavelengths below 700nm cannot penetrate water mist. When the air humidity is high, the image clarity will be reduced, which is convenient for judging whether the humidity of the closed coal shed is insufficient. When the clarity of the humidity control point of the closed coal shed is less than 80% of the clarity of the dry coal shed, the suitable humidity information of the closed coal shed is output. When the clarity of the humidity control point of the closed coal shed is greater than or equal to 80% of the clarity of the dry coal shed, the insufficient humidity information of the closed coal shed is output.

[0084] In this embodiment, the closed coal shed sensor information is obtained through the sensor according to the monitoring period, which can be specifically implemented through the following steps:

[0085] S501: Acquire the temperature of the closed coal shed through the temperature sensor, preset a closed coal shed temperature threshold, and when the temperature of the closed coal shed is greater than or equal to the closed coal shed temperature threshold, output the closed coal shed temperature exceeding standard information; when the temperature of the closed coal shed is less than the closed coal shed temperature threshold, output the closed coal shed temperature reaching standard information;

[0086] S502: The directional wind speed of the closed coal shed is obtained through the wind speed sensor and the wind direction sensor. The directional wind speed of the closed coal shed is the wind speed in the direction of water discharge from the fog cannon. When the wind direction is opposite to the direction of water discharge from the fog cannon, the directional wind speed of the closed coal shed is negative. A closed coal shed wind speed threshold is preset. The closed coal shed wind speed threshold is greater than 0. When the directional wind speed of the closed coal shed is greater than or equal to the closed coal shed wind speed threshold, the positive feedback information of the closed coal shed wind speed is output. When the directional wind speed of the closed coal shed is less than the closed coal shed wind speed threshold, the negative feedback information of the closed coal shed wind speed is output. When the directional wind speed is larger, the water mist of the fog cannon can be assisted to diffuse in the closed coal shed. At this time, the operation intensity or frequency of the fog cannon can be appropriately reduced to achieve resource saving.

[0087] In this embodiment, the weight information of the closed coal shed is obtained by a weight sensor, and the weight information of the closed coal shed includes overweight information of the closed coal shed and non-overweight information of the closed coal shed, which can be specifically implemented by the following steps:

[0088] The weight of the mobile equipment in the closed coal shed is obtained by weight sensors arranged around the edge of the closed coal shed. When overweight equipment enters the closed coal shed, an early warning can be given to avoid dust caused by the movement of overweight equipment, thereby playing a preventive role. The weight of the mobile equipment in the closed coal shed is the weight of the mobile equipment entering the closed coal shed, and the mobile equipment includes but is not limited to load-carrying vehicles, boxes, work vehicles, mobile equipment and facilities. A weight threshold of the closed coal shed is preset. When the weight of the mobile equipment in the closed coal shed is greater than or equal to the weight threshold of the closed coal shed, the overweight information of the closed coal shed is output. When the weight of the mobile equipment in the closed coal shed is less than the weight threshold of the closed coal shed, the information that the closed coal shed is not overweight is output.

[0089] A closed coal shed fog cannon linkage control system based on image AI, including an image processing module, a closed coal shed warning module, and a fog cannon command trigger module;

[0090] The image processing module is used to preset a monitoring cycle, collect an initial image of a closed coal shed through an industrial camera according to the monitoring cycle, pre-process the initial image of the closed coal shed to obtain a closed coal shed correction image, and binarize the closed coal shed correction image to obtain a closed coal shed detection image;

[0091] The closed coal shed warning module is used to obtain the dust information of the closed coal shed according to the closed coal shed detection image, and the closed coal shed dust information includes the closed coal shed dust pollution information and the closed coal shed dust non-pollution information; obtain the closed coal shed humidity information according to the closed coal shed correction image, and the closed coal shed humidity information includes the closed coal shed humidity suitable information and the closed coal shed humidity insufficient information; obtain the closed coal shed sensor information through the sensor according to the monitoring period, and the closed coal shed sensor information includes the closed coal shed temperature information and the closed coal shed directional wind speed information, and the closed coal shed temperature information includes the closed coal shed temperature exceeding the standard information and the closed coal shed temperature reaching the standard information, and the closed coal shed directional wind speed information includes the closed coal shed wind speed positive feedback information and the closed coal shed wind speed negative feedback information; obtain the closed coal shed weight information through the weight sensor, and the closed coal shed weight information includes the closed coal shed overweight information and the closed coal shed not overweight information;

[0092] The fog cannon command trigger module is used to trigger the fog cannon first-level start command when 3 or more closed coal shed warning information is output within one monitoring cycle, trigger the fog cannon second-level start command when more than 0 but less than 3 closed coal shed warning information is output, and trigger the fog cannon shutdown command when 0 closed coal shed warning information is output. The closed coal shed warning information includes dust pollution information of the closed coal shed, insufficient humidity information of the closed coal shed, temperature exceeding the standard of the closed coal shed, negative feedback information of wind speed of the closed coal shed, and overweight information of the closed coal shed.

[0093] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0094] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0095] The program code contained on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0096] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A closed coal shed fog cannon linkage control method based on image AI, characterized in that: The implementation of the closed coal shed fog cannon linkage control method comprises the following steps: Preset a monitoring cycle, collect an initial image of the closed coal shed through an industrial camera according to the monitoring cycle, pre-process the initial image of the closed coal shed to obtain a closed coal shed correction image, and the wavelength of the industrial camera is less than 700nm; Binarizing the closed coal shed correction image to obtain a closed coal shed detection image; Obtaining closed coal shed dust information according to the closed coal shed detection image, wherein the closed coal shed dust information includes closed coal shed dust pollution information and closed coal shed dust non-pollution information; Obtaining closed coal shed humidity information according to the closed coal shed correction image, wherein the closed coal shed humidity information includes closed coal shed suitable humidity information and closed coal shed insufficient humidity information; Acquire closed coal shed sensor information according to the monitoring period, the closed coal shed sensor information includes closed coal shed temperature information and closed coal shed directional wind speed information, the closed coal shed temperature information includes closed coal shed temperature exceeding standard information and closed coal shed temperature reaching standard information, the closed coal shed directional wind speed information includes closed coal shed wind speed positive feedback information and closed coal shed wind speed negative feedback information; Acquire the weight information of the closed coal shed by means of a weight sensor, wherein the weight information of the closed coal shed includes overweight information of the closed coal shed and non-overweight information of the closed coal shed; When 3 or more closed coal shed warning information is output within one monitoring cycle, the first-level start instruction of the fog cannon is triggered; when more than 0 but less than 3 closed coal shed warning information is output, the second-level start instruction of the fog cannon is triggered; when 0 closed coal shed warning information is output, the fog cannon shutdown instruction is triggered, and the closed coal shed warning information includes the closed coal shed dust pollution information, the closed coal shed insufficient humidity information, the closed coal shed temperature exceeding the standard information, the closed coal shed wind speed negative feedback information, and the closed coal shed overweight information; The dust information of the closed coal shed, the humidity information of the closed coal shed, the sensor information of the closed coal shed, the weight information of the closed coal shed, the first-level start-up instruction of the fog cannon, and the second-level start-up instruction of the fog cannon are synchronized to the user terminal.

2. The closed coal shed fog cannon linkage control method according to claim 1 is characterized in that: The binarization processing of the closed coal shed correction image to obtain the closed coal shed detection image comprises: Preset a segmentation grayscale threshold, and segment the closed coal shed correction image into a closed coal shed foreground and a closed coal shed background according to the segmentation grayscale threshold; Obtaining the foreground proportion, background proportion, foreground average gray value, and background average gray value of the closed coal shed foreground and the closed coal shed background; Calculating the total average gray value of the closed coal shed correction image; Calculate the foreground and background variance according to the total average gray value; When the foreground-background variance reaches a maximum value, the corresponding segmentation grayscale threshold is an optimal segmentation threshold, and the closed coal shed correction image is segmented according to the optimal segmentation threshold to obtain the closed coal shed detection image.

3. The closed coal shed fog cannon linkage control method according to claim 1 is characterized in that: The obtaining of dust information of the closed coal shed according to the closed coal shed detection image comprises: By constructing a gray-level co-occurrence matrix, the closed coal shed detection image is subjected to feature extraction to obtain a three-dimensional feature vector, wherein the three-dimensional feature vector includes an energy value, an entropy value, and an inverse moment; The dust information of the closed coal shed is obtained through a naive Bayes classifier according to the three-dimensional feature vector.

4. The closed coal shed fog cannon linkage control method according to claim 3 is characterized in that: The extracting features of the closed coal shed detection image by constructing a gray level co-occurrence matrix to obtain a three-dimensional feature vector comprises: The closed coal shed detection image is divided into windows, and the gray-level co-occurrence matrix is ​​constructed for each window; Obtaining a histogram eigenvalue of the gray level co-occurrence matrix, and calculating the energy value according to the histogram eigenvalue; Calculating the entropy value according to the histogram eigenvalue; The inverse moment is calculated according to the histogram eigenvalues.

5. The closed coal shed fog cannon linkage control method according to claim 1 is characterized in that: The obtaining of the closed coal shed humidity information according to the closed coal shed correction image comprises: A closed coal shed humidity control point is preset, wherein the closed coal shed humidity control point is located at a fixed position of the closed coal shed and at the far edge of the shooting range of the industrial camera; Locate the position of the closed coal shed humidity control point in the closed coal shed correction image, and calculate the clarity of the closed coal shed humidity control point according to the gray value of the closed coal shed humidity control point; Obtaining the clarity of the dry coal shed, wherein the clarity of the dry coal shed is the clarity of the humidity control point of the closed coal shed in a dry environment; The humidity information of the closed coal shed is obtained by comparing the clarity of the humidity control point of the closed coal shed with the clarity of the dry coal shed. When the clarity of the humidity control point of the closed coal shed is less than 80% of the clarity of the dry coal shed, the suitable humidity information of the closed coal shed is output. When the clarity of the humidity control point of the closed coal shed is greater than or equal to 80% of the clarity of the dry coal shed, the insufficient humidity information of the closed coal shed is output.

6. The closed coal shed fog cannon linkage control method according to claim 1, characterized in that: The obtaining of closed coal shed sensor information according to the monitoring cycle includes: The temperature of the closed coal shed is obtained by the temperature sensor, and a closed coal shed temperature threshold is preset. When the temperature of the closed coal shed is greater than or equal to the closed coal shed temperature threshold, information that the closed coal shed temperature exceeds the standard is output; when the temperature of the closed coal shed is less than the closed coal shed temperature threshold, information that the closed coal shed temperature meets the standard is output; The directional wind speed of the closed coal shed is obtained through the wind speed sensor and the wind direction sensor. The directional wind speed of the closed coal shed is the wind speed in the direction of water discharge from the fog cannon. A closed coal shed wind speed threshold is preset. When the directional wind speed of the closed coal shed is greater than or equal to the closed coal shed wind speed threshold, the closed coal shed wind speed positive feedback information is output. When the directional wind speed of the closed coal shed is less than the closed coal shed wind speed threshold, the closed coal shed wind speed negative feedback information is output.

7. The closed coal shed fog cannon linkage control method according to claim 1, characterized in that: The method of obtaining the weight information of the closed coal shed by using the weight sensor includes: The weight of the mobile equipment of the closed coal shed is obtained by weight sensors arranged around the edge of the closed coal shed, and a weight threshold of the closed coal shed is preset. When the weight of the mobile equipment of the closed coal shed is greater than or equal to the weight threshold of the closed coal shed, the overweight information of the closed coal shed is output; when the weight of the mobile equipment of the closed coal shed is less than the weight threshold of the closed coal shed, the non-overweight information of the closed coal shed is output.

8. A closed coal shed fog cannon linkage control system based on image AI, characterized in that: The system is applied to the closed coal shed fog cannon linkage control method as described in any one of claims 1 to 7, comprising an image processing module, a closed coal shed warning module, and a fog cannon command trigger module; The image processing module is used to preset a monitoring cycle, collect an initial image of a closed coal shed through an industrial camera according to the monitoring cycle, pre-process the initial image of the closed coal shed to obtain a closed coal shed correction image, and binarize the closed coal shed correction image to obtain a closed coal shed detection image; The closed coal shed warning module is used to obtain the dust information of the closed coal shed according to the closed coal shed detection image, and the closed coal shed dust information includes the closed coal shed dust pollution information and the closed coal shed dust non-pollution information; obtain the closed coal shed humidity information according to the closed coal shed correction image, and the closed coal shed humidity information includes the closed coal shed humidity suitable information and the closed coal shed humidity insufficient information; obtain the closed coal shed sensor information through the sensor according to the monitoring period, and the closed coal shed sensor information includes the closed coal shed temperature information and the closed coal shed directional wind speed information, and the closed coal shed temperature information includes the closed coal shed temperature exceeding the standard information and the closed coal shed temperature reaching the standard information, and the closed coal shed directional wind speed information includes the closed coal shed wind speed positive feedback information and the closed coal shed wind speed negative feedback information; obtain the closed coal shed weight information through the weight sensor, and the closed coal shed weight information includes the closed coal shed overweight information and the closed coal shed not overweight information; The fog cannon command trigger module is used to trigger the fog cannon first-level start command when 3 or more closed coal shed warning information is output within one monitoring cycle, trigger the fog cannon second-level start command when more than 0 but less than 3 closed coal shed warning information is output, and trigger the fog cannon shutdown command when 0 closed coal shed warning information is output. The closed coal shed warning information includes dust pollution information of the closed coal shed, insufficient humidity information of the closed coal shed, temperature exceeding the standard of the closed coal shed, negative feedback information of wind speed of the closed coal shed, and overweight information of the closed coal shed.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the closed coal shed fog cannon linkage control method as described in any one of claims 1-7 is implemented.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, are used to execute the closed coal shed fog cannon linkage control method as described in any one of claims 1-7.

Images