An intelligent coal flow management system based on autonomous decision-making of visual AI

Abstract

The present invention discloses an intelligent coal flow management system based on visual AI autonomous decision-making, which relates to the technical field of coal flow management and includes the following modules: a visual monitoring module that takes pictures of the coal flow on the conveyor belt to obtain multiple consecutive reference pictures, obtains a visual coal flow coefficient through visual analysis of multiple reference pictures, establishes a visual database, and incorporates the visual coal flow coefficient and the reference pictures into the visual database; takes pictures of the coal flow through the visual detection module, and obtains a visual coal flow coefficient through visual analysis of multiple reference pictures, so as to facilitate predicting the amount of coal on the conveyor belt through visual pictures, and further facilitate adjusting the rotation speed of the conveyor belt drive motor according to the predicted amount of coal, and further facilitate adjusting the transportation speed of the conveyor belt according to the actual amount of transported coal.

Description

Technical Field

[0001] The present invention relates to the technical field of coal flow management, and specifically to an intelligent coal flow management system based on visual AI autonomous decision-making. Background Art

[0002] With the rapid development of China's industry, underground coal energy extraction has become an important research direction. Coal flow refers to the flow and transportation of crushed underground coal through a conveyor belt. The smoothness of coal flow transportation is directly related to the production efficiency and supply stability of coal. Efficient coal flow management can ensure that coal is transported to the demand side in a timely and accurate manner, providing strong support for industrial production and energy supply. At the same time, with the continuous progress of technology, modern coal flow monitoring and control systems are also constantly developing to improve the safety and reliability of coal flow.

[0003] The following problems exist during the transportation of coal through the conveyor belt:

[0004] First, the conveyor belt for transporting coal flow is driven by an electric motor. However, the amount of coal stacked on the conveyor belt is not constant. As the progress of underground coal extraction and crushing changes, the amount of coal on the conveyor belt is sometimes more, sometimes less, and sometimes there is even no coal being transported. A large amount of coal on the conveyor belt means that the coal extraction and crushing efficiency is high at this time, so it is necessary to increase the coal transportation and conveyor speed to prevent blockage of the transported coal after mining. A small amount of coal on the conveyor belt means that the coal extraction and crushing efficiency is low at this time. If the conveyor belt still maintains a high-speed transportation state, not only will electricity be wasted, but also the service life of the conveyor belt and rollers will be wasted due to friction.

[0005] Second, during the transportation of coal flow, while the coal moves with the conveyor belt, the stacked coal will roll down under jolting. Therefore, some coal will approach the edge of the conveyor belt or even roll off the conveyor belt. The coal that rolls off is not only not effectively transported but also has the risk of injuring workers or mining equipment. In coal flow management, in order to facilitate the intelligent management of the transportation speed of the coal flow conveyor belt and to avoid coal from rolling off the conveyor belt, we propose an intelligent coal flow management system based on visual AI autonomous decision-making. Summary of the Invention

[0006] (1) Technical Problems to be Solved

[0007] In view of the deficiencies of the prior art, the present invention provides an intelligent coal flow management system based on visual AI autonomous decision-making to solve the above problems in the prior art.

[0008] (2) Technical Solutions

[0009] To achieve the above objectives, the present invention is realized through the following technical solutions: An intelligent coal flow management system based on visual AI autonomous decision-making includes the following modules:

[0010] A visual monitoring module takes multiple consecutive reference pictures of the coal flow on the conveyor belt, obtains a visual coal flow coefficient through visual analysis of multiple reference pictures, establishes a visual database, and incorporates the visual coal flow coefficient and the reference pictures into the visual database;

[0011] A data correction module obtains the running speed of the conveyor belt and the instantaneous power of the driving motor, obtains a conveyor belt load value through the running speed of the conveyor belt and the instantaneous power of the driving motor, sets a preset threshold value for the conveyor belt load value, obtains a load difference coefficient by taking the difference between the conveyor belt load value and the preset threshold value of the conveyor belt load value, and obtains a coal flow transportation coefficient through the load difference coefficient and the visual coal flow coefficient;

[0012] A speed regulation module sets a preset threshold value for the coal flow transportation coefficient and adjusts the rotation speed of the driving motor by comparing the coal flow transportation coefficient with the preset threshold value of the coal flow transportation coefficient;

[0013] An offset alarm module obtains the distance of the coal edge in the reference picture, sets a preset threshold value for the edge safety distance, and determines whether to turn on an alarm to remind the management personnel by comparing the coal edge distance with the preset threshold value of the edge safety distance.

[0014] Preferably, in the visual monitoring module, the visual coal flow coefficient is obtained through visual analysis of multiple reference pictures. Specifically:

[0015] Step 1: Classify all reference pictures according to the top view angle and the side view angle, then perform gray-scale processing on all reference pictures, obtain the brightness information of each reference picture after gray-scale processing, set a preset threshold range for brightness, capture the brightness areas within the preset threshold range in each top-view reference picture and mark them as the coal top-view areas, and capture the brightness areas within the preset threshold range in each side-view reference picture and mark them as the coal side-view areas;

[0016] Step 2: Perform repeated area comparison and deletion on all coal top-view areas to obtain the final coal top-view areas, respectively obtain the area of each final coal top-view area, perform repeated area comparison and deletion on all coal side-view areas to obtain the final coal side-view areas, respectively obtain the height of each final coal side-view area, arrange the heights of all final coal side-view areas in ascending order and select the maximum value and mark it as the height of the final coal side-view area;

[0017] Step 3: Set a preset threshold value for the area ratio, and obtain the visual coal flow coefficient through the preset threshold value for the area ratio, the areas of all final coal top-view areas, and the height of the final coal side-view area.

[0018] Preferably, the calculation method of the visual coal flow coefficient is specifically:

[0019]

[0020] Among them, Sx represents the visual coal flow coefficient, Mj represents the preset threshold of the area ratio, Fs represents the area of the final coal top view area, Es represents the height of the final coal side view area, and n represents the number of the areas of the final coal top view area, where n = 1, 2, 3, ….

[0021] Preferably, the running speed of the conveyor belt is obtained in the data correction module, specifically:

[0022] Step 1: Obtain two consecutive reference pictures taken by the visual monitoring module, obtain the shooting interval time, and identify and capture multiple common reference objects in the two reference pictures by brightness, contrast, area and shape;

[0023] Step 2: Overlap the two reference pictures, measure the spacing of each group of common reference objects respectively to obtain multiple spacing values, arrange the multiple spacing values in ascending order and delete the minimum value and the maximum value, sum and average the remaining multiple spacing values to obtain the reference spacing, set the preset threshold of the distance ratio, and obtain the running speed of the conveyor belt through the reference distance, the preset threshold of the distance ratio and the shooting time interval.

[0024] Preferably, the calculation method of the running speed of the conveyor belt is specifically:

[0025]

[0026] Among them, Sd represents the running speed of the conveyor belt, Cj represents the reference distance, Jy represents the preset threshold of the distance ratio, and Sj represents the shooting time interval.

[0027] Preferably, the conveyor belt load value is obtained in the data correction module through the running speed of the conveyor belt and the instantaneous power of the driving motor, specifically:

[0028] Step 1: Obtain the running speeds of the conveyor belt at multiple different instants, obtain the instantaneous powers of the driving motor at multiple corresponding instants, and obtain multiple traction forces of the conveyor belt by dividing the instantaneous powers of multiple driving motors by the running speeds of the conveyor belt at multiple corresponding instants respectively;

[0029] Step 2: Arrange the multiple traction forces of the conveyor belt in ascending order and take the median to obtain the reference traction force, obtain the friction coefficient between the conveyor belt and the coal flow, and obtain the conveyor belt load value by dividing the reference traction force by the friction coefficient between the conveyor belt and the coal flow.

[0030] Preferably, the calculation method of the coal flow transportation coefficient is specifically:

[0031]

[0032] Among them, My represents the coal flow transportation coefficient, Sx represents the visual coal flow coefficient, and Fh represents the load difference coefficient. and are both weights.

[0033] Preferably, the speed control module is specifically as follows:

[0034] Step 1: Obtain the coal flow transportation coefficient, set a preset threshold for the coal flow transportation coefficient, and obtain the transportation coefficient difference by subtracting the preset threshold of the coal flow transportation coefficient from the coal flow transportation coefficient.

[0035] Step 2: Set the comparison period to 10 seconds and set the driving motor speed adjustment range. Compare the size relationship between the transportation coefficient difference and 0 every 10 seconds. If the transportation coefficient difference is greater than 0, control the conveyor belt driving motor to increase the speed based on the driving motor speed adjustment range. If the transportation coefficient difference is less than 0, control the conveyor belt driving motor to decrease the speed based on the driving motor speed adjustment range.

[0036] Preferably, the offset alarm module is specifically as follows:

[0037] Step 1: Obtain the reference picture in the visual monitoring module, obtain the coal top-down area in the grayscale-processed reference picture, obtain the brightness of the conveyor belt edge, capture the position of the conveyor belt edge in the grayscale-processed reference picture through the brightness of the conveyor belt edge, and measure the distances between the coal top-down area and the conveyor belt edge position to obtain multiple margin values.

[0038] Step 2: Set a preset threshold for the margin ratio. Multiply the preset threshold for the margin ratio by multiple margin values respectively to obtain multiple margin reference values. Arrange the multiple margin reference values in ascending order, and obtain the minimum margin value and the mode margin value of the margin reference values.

[0039] Step 3: Set a preset threshold for the edge safety distance. Compare the size relationship between the preset threshold for the edge safety distance and the minimum margin value and the mode margin value respectively. If both the minimum margin value and the mode margin value are greater than the preset threshold for the edge safety distance, it is marked that the coal position is safe. If both the minimum margin value and the mode margin value are less than the preset threshold for the edge safety distance, it is marked that the coal position is dangerous and an alarm is issued to remind the management staff.

[0040] (III) Beneficial effects

[0041] The present invention provides an intelligent coal flow management system based on visual AI autonomous decision-making, having the following beneficial effects:

[0042] (1) In this solution, the visual detection module takes pictures of the coal flow. By visually analyzing multiple reference pictures, the visual coal flow coefficient is obtained, which facilitates predicting the amount of coal on the conveyor belt through visual pictures. Furthermore, it is convenient to adjust the rotation speed of the conveyor belt drive motor according to the predicted amount of coal, and then adjust the transportation speed of the conveyor belt according to the actual amount of transported coal. This is beneficial to accelerating the transportation efficiency when the amount of coal is large, and also convenient to reduce the ineffective workload of the conveyor belt and the drive motor when the amount of coal is low, thus avoiding wasting electricity while wasting the service life of the conveyor belt and the rollers. Moreover, it is convenient to intelligently manage the transportation speed of the coal flow conveyor belt in coal flow management.

[0043] (2) In this solution, the data correction module combines the running speed of the conveyor belt and the instantaneous power of the drive motor to obtain the load value of the conveyor belt. Then, the load difference coefficient is obtained by subtracting the preset threshold value of the conveyor belt load value from the conveyor belt load value. Finally, the coal flow transportation coefficient is obtained through the load difference coefficient and the visual coal flow coefficient, which facilitates a more accurate prediction of the amount of coal by combining visual monitoring information, conveyor belt speed, and drive motor power. This is beneficial to improving the accuracy of the predicted result of the amount of coal. Furthermore, it is convenient to adjust the rotation speed of the drive motor according to the predicted result, and then adjust the transportation speed according to the actual amount of transported coal.

[0044] (3) In this solution, the offset alarm module further analyzes the reference pictures in the visual detection module to estimate the distance between the coal and the edge of the conveyor belt. When the distance is too small, an alarm is triggered to remind the management staff to intervene and clean the coal at the edge, which is beneficial to preventing the coal from falling off the conveyor belt during transportation and injuring workers or mining equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic structural diagram of an intelligent coal flow management system based on visual AI autonomous decision-making of the present invention;

[0046] Figure 2 It is a flow block diagram of an intelligent coal flow management system based on visual AI autonomous decision-making of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0048] Please refer to Figure 1 - Figure 2, the present invention provides an intelligent coal flow management system based on visual AI autonomous decision-making, including the following modules:

[0049] A visual monitoring module takes multiple consecutive reference pictures of the coal flow on the conveyor belt, obtains the visual coal flow coefficient through visual analysis of multiple reference pictures, establishes a visual database, and incorporates the visual coal flow coefficient and the reference pictures into the visual database;

[0050] A data correction module obtains the running speed of the conveyor belt and the instantaneous power of the driving motor, obtains the conveyor belt load value through the running speed of the conveyor belt and the instantaneous power of the driving motor, sets a preset threshold value for the conveyor belt load value, obtains a load difference coefficient by taking the difference between the conveyor belt load value and the preset threshold value of the conveyor belt load value, and obtains a coal flow transportation coefficient through the load difference coefficient and the visual coal flow coefficient;

[0051] A speed regulation module sets a preset threshold value for the coal flow transportation coefficient and adjusts the rotation speed of the driving motor by comparing the coal flow transportation coefficient with the preset threshold value of the coal flow transportation coefficient;

[0052] An offset alarm module obtains the distance of the coal edge in the reference picture, sets a preset threshold value for the edge safety distance, and determines whether to turn on the alarm to remind the management personnel by comparing the coal edge distance with the preset threshold value of the edge safety distance;

[0053] The calculation method of the coal flow transportation coefficient is specifically as follows:

[0054]

[0055] Wherein, My represents the coal flow transportation coefficient, Sx represents the visual coal flow coefficient, and Fh represents the load difference coefficient, and are both weights,

[0056] In this embodiment, in this solution, the visual detection module takes pictures of the coal flow, obtains the visual coal flow coefficient through visual analysis of multiple reference pictures, so as to facilitate predicting the quantity of coal on the conveyor belt through visual pictures, and further facilitate adjusting the rotation speed of the conveyor belt driving motor according to the predicted quantity of coal, and further facilitate adjusting the transportation speed of the conveyor belt according to the actual quantity of transported coal, thus beneficial to accelerating the transportation efficiency when the quantity of coal is large, and also facilitating reducing the ineffective workload of the conveyor belt and the driving motor when the quantity of coal is low, thus beneficial to avoiding wasting electricity and the service life of the conveyor belt and the rollers, and further facilitating intelligent management of the transportation speed of the coal flow conveyor belt in coal flow management. By establishing a visual database, it is convenient to proofread and correct the predicted quantity of coal through historical reference pictures and historical visual coal flow coefficients during subsequent prediction, and further facilitate more accurate prediction of the quantity of coal;

[0057] In this solution, the data correction module combines the running speed of the conveyor belt and the instantaneous power of the driving motor to obtain the load value of the conveyor belt. Then, the load difference coefficient is obtained by subtracting the preset threshold value of the conveyor belt load value from the conveyor belt load value. Finally, the coal flow transportation coefficient is obtained by combining the load difference coefficient and the visual coal flow coefficient, which facilitates a more accurate prediction of the coal quantity by combining visual monitoring information, conveyor belt speed, and driving motor power. This is beneficial to improving the accuracy of the coal quantity prediction result. Furthermore, it is convenient to adjust the rotational speed of the driving motor according to the prediction result, and then it is convenient to adjust the transportation speed according to the actual coal transportation quantity. This further benefits in accelerating the transportation efficiency when the coal quantity is large, and also further facilitates reducing the ineffective workload of the conveyor belt and the driving motor when the coal quantity is low. This further benefits in avoiding wasting electricity while wasting the service life of the conveyor belt and the rollers. Furthermore, it is further convenient to intelligently manage the transportation speed of the coal flow conveyor belt in coal flow management;

[0058] In this solution, the speed control module compares the predicted coal flow transportation coefficient and adjusts the rotational speed of the driving motor according to the comparison result, which benefits in accelerating the transportation efficiency when the coal quantity is large, and also facilitates reducing the ineffective workload of the conveyor belt and the driving motor when the coal quantity is low. This benefits in avoiding wasting electricity while wasting the service life of the conveyor belt and the rollers. Furthermore, it is convenient to intelligently manage the transportation speed of the coal flow conveyor belt in coal flow management;

[0059] In this solution, the offset alarm module further analyzes the reference pictures in the visual detection module to estimate the distance between the coal and the edge of the conveyor belt. When the distance is too small, an alarm is turned on to remind the management staff to intervene and clean the coal at the edge, which benefits in avoiding the coal from falling off the conveyor belt and injuring workers or mining equipment during transportation;

[0060] It is worth mentioning that the weight values in this solution can be obtained through the analytic hierarchy process, and the preset threshold values in this solution can be obtained through the weight analysis method. There will be no further elaboration here.

[0061] In the visual monitoring module, the visual coal flow coefficient is obtained through visual analysis of multiple reference pictures. Specifically:

[0062] Step 1: Classify all the reference pictures according to the top view angle and the side view angle, and then perform gray-scale processing on all the reference pictures to obtain the brightness information of each reference picture after gray-scale processing. Set the range of the brightness preset threshold. In each top view reference picture, capture the brightness area within the brightness preset threshold range and mark it as the coal top view area. In each side view reference picture, capture the brightness area within the brightness preset threshold range and mark it as the coal side view area;

[0063] Step 2: Perform repeated area comparison and deletion on all the top-down views of coal to obtain the final top-down views of coal. Respectively obtain the area of each final top-down view of coal. Perform repeated area comparison and deletion on all the side views of coal to obtain the final side views of coal. Respectively obtain the height of each final side view of coal. Arrange the heights of all the final side views of coal in ascending order and select the maximum value and mark it as the height of the final side view of coal.

[0064] Step 3: Set a preset threshold for the area ratio. Obtain the visual coal flow coefficient through the preset threshold for the area ratio, the areas of all the final top-down views of coal, and the height of the final side view of coal.

[0065] The calculation method of the visual coal flow coefficient is specifically as follows:

[0066]

[0067] Among them, Sx represents the visual coal flow coefficient, Mj represents the preset threshold for the area ratio, Fs represents the area of the final top-down view of coal, Es represents the height of the final side view of coal, and n represents the number of areas of the final top-down views of coal, where n = 1, 2, 3, ….

[0068] In this embodiment, by performing grayscale processing on the captured pictures, then identifying the coal in the pictures through brightness, calculating the volume and quantity of coal by identifying the area of coal through the top-down view angle and the height of coal through the side view angle, so as to facilitate predicting the quantity of coal on the conveyor belt through visual monitoring, and further facilitating adjusting the rotational speed of the driving motor according to the prediction result, and further facilitating adjusting the coal transportation efficiency according to the actual coal transportation quantity.

[0069] Obtain the running speed of the conveyor belt in the data correction module, specifically as follows:

[0070] Step 1: Obtain two consecutive reference pictures captured in the visual monitoring module, obtain the shooting interval time, and identify and capture multiple common reference objects in the two reference pictures through brightness, contrast, area, and shape.

[0071] Step 2: Overlap the two reference pictures, respectively measure the distances between each group of common reference objects to obtain multiple distance values, arrange the multiple distance values in ascending order and delete the minimum value and the maximum value, sum and average the remaining multiple distance values to obtain the reference distance, set a preset threshold for the distance ratio, and obtain the running speed of the conveyor belt through the reference distance, the preset threshold for the distance ratio, and the shooting time interval.

[0072] The calculation method of the running speed of the conveyor belt is specifically as follows:

[0073]

[0074] Wherein, Sd represents the running speed of the conveyor belt, Cj represents the reference distance, Jy represents the preset threshold of the distance ratio, and Sj represents the shooting time interval.

[0075] In this embodiment, since the position of the shooting camera is fixed, the reference object is determined by comparing consecutive pictures, so as to facilitate calculating the moving speed of the conveyor belt according to the shooting time interval and the moving distance of the reference object, and further facilitate accurately predicting the quantity of coal transported on the conveyor belt subsequently.

[0076] In the data correction module, the conveyor belt load value is obtained through the running speed of the conveyor belt and the instantaneous power of the driving motor. Specifically:

[0077] Step 1: Obtain the running speeds of the conveyor belt at multiple different instants, obtain the instantaneous powers of the driving motor at multiple corresponding instants, and obtain the traction forces of multiple conveyor belts by dividing the instantaneous powers of multiple driving motors by the running speeds of the conveyor belt at multiple corresponding instants respectively.

[0078] Step 2: Arrange the traction forces of multiple conveyor belts in ascending order and take the median to obtain the reference traction force, obtain the friction coefficient between the conveyor belt and the coal flow, and obtain the conveyor belt load value by dividing the reference traction force by the friction coefficient between the conveyor belt and the coal flow.

[0079] In this embodiment, the running speed of the conveyor belt and the instantaneous power of the driving motor are combined to obtain the conveyor belt load value, so as to facilitate predicting the actual quantity of coal transported on the conveyor belt, and further facilitate adjusting the rotation speed of the conveyor belt driving motor according to the predicted quantity of coal subsequently, and then facilitate adjusting the transportation speed of the conveyor belt according to the actual quantity of coal transported, so as to be beneficial to increasing the transportation efficiency when the quantity of coal is large, and also facilitate reducing the ineffective workload of the conveyor belt and the driving motor when the quantity of coal is low, so as to be beneficial to avoiding wasting electricity while wasting the service life of the conveyor belt and the rollers, and further facilitate intelligently managing the transportation speed of the coal flow conveyor belt in coal flow management.

[0080] The speed regulation module is specifically:

[0081] Step 1: Obtain the coal flow transportation coefficient, set the preset threshold of the coal flow transportation coefficient, and obtain the transportation coefficient difference by subtracting the preset threshold of the coal flow transportation coefficient from the coal flow transportation coefficient.

[0082] Step 2: Set the comparison period to 10 seconds, set the driving motor speed adjustment range, compare the size relationship between the transportation coefficient difference and 0 every 10 seconds. If the transportation coefficient difference is greater than 0, control the conveyor belt driving motor to increase the speed based on the driving motor speed adjustment range; if the transportation coefficient difference is less than 0, control the conveyor belt driving motor to decrease the speed based on the driving motor speed adjustment range.

[0083] In this embodiment, by setting a comparison period and a rotational speed adjustment range, it is convenient to cyclically detect coal periodically and adjust the rotational speed of the drive motor, so as to facilitate the intelligent adjustment of the coal transportation speed according to the actual coal transportation volume.

[0084] The offset alarm module is specifically as follows:

[0085] Step 1: Obtain the reference picture in the visual monitoring module, obtain the top-view area of the coal in the reference picture after grayscale processing, obtain the brightness of the conveyor belt edge, capture the position of the conveyor belt edge in the reference picture after grayscale processing through the brightness of the conveyor belt edge, and measure the distances between the top-view area of the coal and the position of the conveyor belt edge to obtain multiple margin values;

[0086] Step 2: Set a preset threshold for the margin ratio. Multiply the preset threshold for the margin ratio by multiple margin values respectively to obtain multiple margin reference values. Arrange the multiple margin reference values in ascending order, and obtain the minimum margin value and the mode margin value of the margin reference values;

[0087] Step 3: Set a preset threshold for the edge safety distance. Compare the size relationships between the preset threshold for the edge safety distance and the minimum margin value and the mode margin value respectively. If both the minimum margin value and the mode margin value are greater than the preset threshold for the edge safety distance, it is marked that the coal position is safe. If both the minimum margin value and the mode margin value are less than the preset threshold for the edge safety distance, it is marked that the coal position is dangerous and an alarm is issued to remind the management personnel.

[0088] In this embodiment, by further analyzing the reference picture in the visual detection module, the distance between the coal and the conveyor belt edge is estimated. When the distance is too small, an alarm is turned on to remind the management personnel to intervene and clean the coal at the edge, which is beneficial to avoiding the coal from falling off the conveyor belt and injuring workers or mining equipment during transportation.

[0089] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution.

[0090] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0091] As described above, this is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application.

Claims

1. An intelligent coal flow management system based on autonomous decision-making of visual AI, characterized in that, It includes the following modules: A visual monitoring module that takes pictures of the coal flow on the conveyor belt to obtain multiple consecutive reference pictures, analyzes the multiple reference pictures visually to obtain a visual coal flow coefficient, establishes a visual database, and incorporates the visual coal flow coefficient and the reference pictures into the visual database; A data correction module that obtains the running speed of the conveyor belt, obtains the instantaneous power of the driving motor, obtains a conveyor belt load value based on the running speed of the conveyor belt and the instantaneous power of the driving motor, sets a preset threshold for the conveyor belt load value, obtains a load difference coefficient by taking the difference between the conveyor belt load value and the preset threshold of the conveyor belt load value, and obtains a coal flow transportation coefficient based on the load difference coefficient and the visual coal flow coefficient; A speed regulation module that sets a preset threshold for the coal flow transportation coefficient and adjusts the rotational speed of the driving motor by comparing the coal flow transportation coefficient with the preset threshold of the coal flow transportation coefficient; An offset alarm module that obtains the distance of the coal edge in the reference picture, sets a preset threshold for the edge safety distance, and determines whether to turn on an alarm to alert the management staff by comparing the coal edge distance with the preset threshold of the edge safety distance; The calculation method of the visual coal flow coefficient is specifically as follows: ; Among them, is expressed as the visual coal flow coefficient, is expressed as the preset threshold of the area ratio, is expressed as the area of the final coal top view area, is expressed as the height of the final coal side view area, is expressed as the number of areas of the final coal top view area, ; The calculation method of the running speed of the conveyor belt is specifically as follows: ; Among them, represents the running speed of the conveyor belt, represents the reference distance, represents the preset threshold of the distance ratio, represents the shooting time interval; In the data correction module, the conveyor belt load value is obtained based on the running speed of the conveyor belt and the instantaneous power of the driving motor, specifically as follows: Step 1: Obtain the running speeds of the conveyor belt at multiple different instants, obtain the instantaneous powers of the driving motor at multiple corresponding instants, and obtain multiple traction forces of the conveyor belt by dividing the instantaneous powers of the multiple driving motors by the running speeds of the conveyor belt at the multiple corresponding instants respectively; Step 2: Arrange the multiple traction forces of the conveyor belt in ascending order and take the median to obtain a reference traction force, obtain the friction coefficient between the conveyor belt and the coal flow, and obtain the conveyor belt load value by dividing the reference traction force by the friction coefficient between the conveyor belt and the coal flow; The calculation method of the coal flow transportation coefficient is specifically as follows: ; Among them, is expressed as the coal flow transportation coefficient, is expressed as the visual coal flow coefficient, is expressed as the load difference coefficient, and are both weights, , .

2. The intelligent coal flow management system based on visual AI autonomous decision-making according to claim 1, characterized in that: In the visual monitoring module, the visual coal flow coefficient is obtained by visually analyzing multiple reference pictures, specifically as follows: Step 1: Classify all the reference pictures according to the top view angle and the side view angle, then grayscale all the reference pictures, obtain the brightness information of each reference picture after grayscale processing, set a preset threshold range for the brightness, capture the brightness areas within the preset threshold range in each top view reference picture and mark them as the coal top view areas, and capture the brightness areas within the preset threshold range in each side view reference picture and mark them as the coal side view areas; Step 2: Compare and delete the overlapping areas of all the coal top view areas to obtain the final coal top view areas, obtain the area of each final coal top view area respectively, compare and delete the overlapping areas of all the coal side view areas to obtain the final coal side view areas, obtain the height of each final coal side view area respectively, arrange the heights of all the final coal side view areas in ascending order and select the maximum value and mark it as the height of the final coal side view area; Step 3: Set a preset threshold for the area ratio, and obtain the visual coal flow coefficient based on the preset threshold for the area ratio, the areas of all the final coal top view areas, and the height of the final coal side view area.

3. The intelligent coal flow management system based on visual AI autonomous decision-making according to claim 1, characterized in that: In the data correction module, the running speed of the conveyor belt is obtained, specifically as follows: Step 1: Obtain two consecutive reference pictures taken by the visual monitoring module, obtain the shooting interval time, and identify and capture multiple common reference objects in the two reference pictures by brightness, contrast, area, and shape; Step 2: Overlap the two reference pictures, measure the distances between each group of common reference objects to obtain multiple distance values, arrange the multiple distance values in ascending order and delete the minimum and maximum values, sum and average the remaining multiple distance values to obtain the reference distance, set the preset threshold of the distance ratio, and obtain the running speed of the conveyor belt through the reference distance, the preset threshold of the distance ratio, and the shooting time interval.

4. An intelligent coal flow management system based on visual AI autonomous decision-making according to claim 1, characterized in that: The speed regulation module is specifically: Step 1: Obtain the coal flow transportation coefficient, set the preset threshold of the coal flow transportation coefficient, and obtain the transportation coefficient difference by subtracting the preset threshold of the coal flow transportation coefficient from the coal flow transportation coefficient; Step 2: Set the comparison period to 10 seconds, set the adjustment range of the driving motor speed, compare the size relationship between the transportation coefficient difference and 0 every 10 seconds. If the transportation coefficient difference is greater than 0, control the conveyor belt driving motor to increase the speed based on the adjustment range of the driving motor speed. If the transportation coefficient difference is less than 0, control the conveyor belt driving motor to decrease the speed based on the adjustment range of the driving motor speed.

5. The intelligent coal flow management system based on visual AI autonomous decision-making according to claim 2, characterized in that: The offset alarm module is specifically: Step 1: Obtain the reference picture in the visual monitoring module, obtain the top-down view area of the coal in the reference picture after gray-scale processing, obtain the brightness of the conveyor belt edge, capture the position of the conveyor belt edge in the reference picture after gray-scale processing through the brightness of the conveyor belt edge, and measure the distances between the top-down view area of the coal and the position of the conveyor belt edge to obtain multiple edge distance values; Step 2: Set the preset threshold of the edge distance ratio, multiply the preset threshold of the edge distance ratio by the multiple edge distance values respectively to obtain multiple edge distance reference values, arrange the multiple edge distance reference values in ascending order, and obtain the minimum edge distance value and the mode edge distance value of the edge distance reference values; Step 3: Set the preset threshold of the edge safety distance, compare the size relationship between the preset threshold of the edge safety distance and the minimum edge distance value and the mode edge distance value respectively. If both the minimum edge distance value and the mode edge distance value are greater than the preset threshold of the edge safety distance, mark it as the coal position is safe. If both the minimum edge distance value and the mode edge distance value are less than the preset threshold of the edge safety distance, mark it as the coal position is dangerous and issue an alarm to remind the management personnel.

Images