A control method and system of dust suppressant spraying applied to a train and a medium

Abstract

The application relates to a dust suppressant spraying control method, system and medium applied to a train, and the method comprises the following steps: M1. A spraying vehicle drives into a platform and stops beside a train needing spraying, real-time image data information of a train spraying area is acquired based on a vehicle-mounted camera, spraying time length data information of each train is acquired based on a vehicle-mounted light sensing probe, and flow data information of the dust suppressant is acquired based on a vehicle-mounted turbine flow sensor; M2. Based on the image data information of the train spraying area, an improved HOG feature extraction algorithm is used to extract the pixel points of the image and construct an image pixel matrix of the train spraying area. The application can not only adaptively optimize and adjust the flow of spraying according to the spraying time length and the image of the train spraying area, thereby saving energy consumption, but also does not need manual participation in the spraying process, reduces labor cost, and improves the efficiency of train spraying.

Description

Technical Field

[0001] The present invention relates to the technical field of spraying dust suppressants on trains, and in particular to a control method, system and medium for spraying dust suppressants on trains. Background Art

[0002] Dust suppressants react with dust particles through their special chemical composition to form a protective film. The sprayed dust suppressant will form a protective film on the surface of the train or the dust suppressant will evenly penetrate the surface of the coal. During the evaporation process, the surface particles will be bonded together to form a solidified layer with a certain strength and toughness that can withstand strong winds.

[0003] Prior art patent (application number: 202111311639.8) discloses an intelligent mist spray dust suppression system and method for train unloading depots. The system comprises: a mist sprayer for spraying mist particles ≤10μm to capture and suppress dust; a host system for supplying air and water to the mist sprayer; at least one Hawkeye / Frogeye monitoring unit, located on the unloading side of the train along its length, capable of providing feedback on silo signals, visual recognition data, and dust detection signals; at least one dust detection unit, located around the Hawkeye / Frogeye monitoring unit, for collecting and providing feedback on dust concentration and size data; a visual recognition system; a dust detection system; a data processing system; a PLC control system; and a human-machine interface for operating the PLC control system. This solution fails to adaptively control, adjust, and optimize the dust suppressant flow rate based on the train's spraying area completion rate to ensure train spraying completion while conserving dust suppressant spraying, resulting in a waste of resources. Summary of the Invention

[0004] In view of the above problems, the present invention provides a control method, system and medium for dust suppressant spraying applied to trains. It can not only adaptively optimize and control the spray flow rate according to the spraying duration and the image of the train spraying area, thereby saving energy consumption, but also the spraying process does not require human participation, reducing labor costs and improving the efficiency of train spraying.

[0005] In order to achieve the above-mentioned and other related purposes, the present invention provides the following technical solutions:

[0006] A method for controlling dust suppressant spraying applied to a train, the method comprising:

[0007] M1. The spraying vehicle drives onto the platform and stops next to the train to be sprayed. The vehicle's onboard camera acquires real-time image data of the train spray area, uses the vehicle's onboard light sensor to obtain real-time data on the spray duration of each train section, and uses the vehicle's onboard turbine flow sensor to obtain real-time data on the flow rate of the sprayed dust suppressant.

[0008] M2. Based on the image data information of the train spray area, an improved HOG feature extraction algorithm is used to extract the pixels of the image and construct an image pixel matrix of the train spray area to obtain the image pixel matrix data information of the train spray area;

[0009] M3. Based on the image pixel matrix data information of the train spray area, construct a train spray completion model to predict the train spray completion and obtain the predicted train spray completion data information;

[0010] M4. Based on the predicted train spraying completion data information, the spraying duration data information of each train and the flow data information of the spraying dust suppressant, the improved Grey Wolf optimization algorithm is used to optimize the flow rate of the dust suppressant spraying to obtain the optimized dust suppressant spraying flow data information.

[0011] Furthermore, in step M2, extracting pixel points of the image using the improved HOG feature extraction algorithm and constructing an image pixel matrix of the train spray area includes:

[0012] M21. Based on the image data information of the train spray area, construct an image pixel gradient function G of the train spray area,

[0013] ,

[0014] Where x is the image data information of the train spray area, α1, α2, and α3 are the gradient weight factors of the image pixels, and the gradient value of each pixel in the train spray area image is calculated to obtain the gradient value data information of the image pixels in the train spray area;

[0015] M22. Based on the gradient value data information of the image pixels of the train spray area, establish the feature extraction function H of the image pixels,

[0016] ,

[0017] Where y is the gradient value data information of the image pixel in the train spray area, β1 is the first feature extraction factor, β2 is the second feature extraction factor, and β3 is the third feature extraction factor;

[0018] M23. Based on the feature extraction function H of the image pixel points, the pixel points of the image are extracted, and the image pixel matrix of the train spray area is constructed to obtain the image pixel matrix data information of the train spray area.

[0019] Furthermore, the first feature extraction factor β1 is,

[0020] ,

[0021] The second feature extraction factor β2 is,

[0022] ,

[0023] The third feature extraction factor β3 is,

[0024] .

[0025] Furthermore, the constraints of the first feature extraction factor β1, the second feature extraction factor β2 and the third feature extraction factor β3 are:

[0026] .

[0027] Furthermore, in step M3, the train spraying completion model is constructed to predict the spraying completion degree of the train, including:

[0028] M31. Based on the image pixel matrix data information of the train spray area, construct an image pixel training data set and a test data set for the train spray area;

[0029] M32. Input the image pixel training data set of the train spray area into the train spray completion model for training and learning, and determine the train spray completion decision function W,

[0030] ,

[0031] Among them, z is the image pixel training dataset of the train spray area, λ1, λ2 and λ3 are the train spray completion learning factors, and the trained train spray completion model is obtained;

[0032] M33. Based on the trained train spray completion model, input the image pixel test dataset of the train spray area, predict the train spray completion degree, and obtain the predicted train spray completion degree data information.

[0033] Furthermore, the constraints of the train spray completion learning factors λ1, λ2 and λ3 are:

[0034] .

[0035] Furthermore, in step M4, the optimization of the dust suppressant spraying flow rate using the improved Grey Wolf optimization algorithm includes:

[0036] M41. Based on the predicted train spraying completion data, the spraying duration data for each train, and the flow rate data of the spray dust suppressant, construct a gray wolf population and initialize its parameters, determine the maximum number of iterations for the population, and obtain initialized gray wolf population data;

[0037] M42. Based on the initialized gray wolf population data information, establish the fitness function S of the gray wolf population individuals,

[0038] ,

[0039] Among them, h is the initialized gray wolf population data information, ω1, ω2 and ω3 are the feedback adjustment factors of the gray wolf population individuals, and the fitness values ​​of the gray wolf population individuals are calculated to obtain the fitness value data information of the gray wolf population individuals;

[0040] M43. Based on the fitness data information of the gray wolf population individuals, establish a position update function Q of the gray wolf population,

[0041] ,

[0042] ,

[0043] ,

[0044] Among them, a is the fitness data information of the gray wolf population individuals, ρ1 and ρ2 are the position update optimization factors of the gray wolf population individuals, and the flow rate of dust suppressant spraying is optimized to obtain the optimized flow rate data information of dust suppressant spraying.

[0045] Furthermore, the method further comprises:

[0046] M5. Based on the optimized dust suppressant spray flow data information, establish the train dust suppressant spray control function R,

[0047] ,

[0048] Among them, c is the optimized flow data information of dust suppressant spraying, θ1 and θ2 are the control parameters of train dust suppressant spraying, and the spraying of train dust suppressant is controlled and adjusted to obtain the control data information of train dust suppressant spraying.

[0049] In order to achieve the above-mentioned and other related purposes, the present invention also provides a control system for spraying dust suppressants applied to trains, comprising a computer device programmed or configured to execute any one of the steps of the control method for spraying dust suppressants applied to trains.

[0050] In order to achieve the above-mentioned and other related purposes, the present invention also provides a computer-readable storage medium storing a computer program programmed or configured to execute any one of the control methods for spraying dust suppressants applied to trains.

[0051] The present invention has the following positive effects:

[0052] 1. The present invention uses an improved HOG feature extraction algorithm to extract pixel points of the image and construct an image pixel matrix of the train spray area. In combination with the construction of a train spray completion model, the train spray completion degree is predicted. This not only enables real-time monitoring of the train spray area, thereby ensuring the uniformity of the spraying, but also improves the accuracy of spray process monitoring and prevents the occurrence of repeated spraying.

[0053] 2. The present invention optimizes the flow rate of dust suppressant spraying by adopting an improved Gray Wolf optimization algorithm, and combines it with the control function R of the dust suppressant spraying of the train to accurately control the spraying process of the dust suppressant of the train. It can not only adaptively optimize and control and adjust the spraying flow rate according to the spraying duration and the image of the train spraying area, thereby saving energy consumption, but also the spraying process does not require human participation, reducing labor costs and improving the efficiency of train spraying. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 Schematic diagram of the method flow of the present invention;

[0055] Figure 2 Schematic diagram of the process of the improved HOG feature extraction algorithm of the present invention;

[0056] Figure 3 A schematic diagram of the process of constructing a train spray completion model of the present invention;

[0057] Figure 4 Schematic diagram of the flow of the improved gray wolf optimization algorithm of the present invention. DETAILED DESCRIPTION

[0058] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0059] Example 1: Figure 1 As shown, a control method for spraying dust suppressants applied to trains, the method comprising:

[0060] M1. The spraying vehicle drives onto the platform and stops next to the train to be sprayed. The vehicle's onboard camera acquires real-time image data of the train spray area, uses the vehicle's onboard light sensor to obtain real-time data on the spray duration of each train section, and uses the vehicle's onboard turbine flow sensor to obtain real-time data on the flow rate of the sprayed dust suppressant.

[0061] M2. Based on the image data information of the train spray area, an improved HOG feature extraction algorithm is used to extract the pixels of the image and construct an image pixel matrix of the train spray area to obtain the image pixel matrix data information of the train spray area;

[0062] M3. Based on the image pixel matrix data information of the train spray area, construct a train spray completion model to predict the train spray completion and obtain the predicted train spray completion data information;

[0063] M4. Based on the predicted train spraying completion data information, the spraying duration data information of each train and the flow data information of the spraying dust suppressant, the improved Grey Wolf optimization algorithm is used to optimize the flow rate of the dust suppressant spraying to obtain the optimized dust suppressant spraying flow data information.

[0064] In this embodiment, if Figure 2 As shown, in step M2, the use of the improved HOG feature extraction algorithm to extract pixel points of the image and construct an image pixel matrix of the train spray area includes:

[0065] M21. Based on the image data information of the train spray area, construct an image pixel gradient function G of the train spray area,

[0066] ,

[0067] Where x is the image data information of the train spray area, α1, α2, and α3 are the gradient weight factors of the image pixels, and the gradient value of each pixel in the train spray area image is calculated to obtain the gradient value data information of the image pixels in the train spray area;

[0068] M22. Based on the gradient value data information of the image pixels of the train spray area, establish the feature extraction function H of the image pixels,

[0069] ,

[0070] Where y is the gradient value data information of the image pixel in the train spray area, β1 is the first feature extraction factor, β2 is the second feature extraction factor, and β3 is the third feature extraction factor;

[0071] M23. Based on the feature extraction function H of the image pixel points, the pixel points of the image are extracted, and the image pixel matrix of the train spray area is constructed to obtain the image pixel matrix data information of the train spray area.

[0072] In this embodiment, the first feature extraction factor β1 is,

[0073] ,

[0074] The second feature extraction factor β2 is,

[0075] ,

[0076] The third feature extraction factor β3 is,

[0077] .

[0078] In this embodiment, the constraints of the first feature extraction factor β1, the second feature extraction factor β2, and the third feature extraction factor β3 are:

[0079] .

[0080] Example 2: Based on the control method for spraying dust suppressants applied to trains in Example 1, the present invention is further illustrated and described below.

[0081] like Figure 1 As shown, a control method for spraying dust suppressants applied to trains, the method comprising:

[0082] M1. The spraying vehicle drives onto the platform and stops next to the train to be sprayed. The vehicle's onboard camera acquires real-time image data of the train spray area, uses the vehicle's onboard light sensor to obtain real-time data on the spray duration of each train section, and uses the vehicle's onboard turbine flow sensor to obtain real-time data on the flow rate of the sprayed dust suppressant.

[0083] M2. Based on the image data information of the train spray area, an improved HOG feature extraction algorithm is used to extract the pixels of the image and construct an image pixel matrix of the train spray area to obtain the image pixel matrix data information of the train spray area;

[0084] M3. Based on the image pixel matrix data information of the train spray area, construct a train spray completion model to predict the train spray completion and obtain the predicted train spray completion data information;

[0085] M4. Based on the predicted train spraying completion data information, the spraying duration data information of each train and the flow data information of the spraying dust suppressant, the improved Grey Wolf optimization algorithm is used to optimize the flow rate of the dust suppressant spraying to obtain the optimized dust suppressant spraying flow data information.

[0086] In this embodiment, if Figure 3 As shown, in step M3, the train spraying completion model is constructed to predict the spraying completion degree of the train, including:

[0087] M31. Based on the image pixel matrix data information of the train spray area, construct an image pixel training data set and a test data set for the train spray area;

[0088] M32. Input the image pixel training data set of the train spray area into the train spray completion model for training and learning, and determine the train spray completion decision function W,

[0089] ,

[0090] Among them, z is the image pixel training dataset of the train spray area, λ1, λ2 and λ3 are the train spray completion learning factors, and the trained train spray completion model is obtained;

[0091] M33. Based on the trained train spray completion model, input the image pixel test dataset of the train spray area, predict the train spray completion degree, and obtain the predicted train spray completion degree data information.

[0092] In this embodiment, the constraints of the train spray completion learning factors λ1, λ2, and λ3 are:

[0093] .

[0094] In this embodiment, if Figure 4 As shown, in step M4, the optimization of the dust suppressant spraying flow rate using the improved gray wolf optimization algorithm includes:

[0095] M41. Based on the predicted train spraying completion data, the spraying duration data for each train, and the flow rate data of the spray dust suppressant, construct a gray wolf population and initialize its parameters, determine the maximum number of iterations for the population, and obtain initialized gray wolf population data;

[0096] M42. Based on the initialized gray wolf population data information, establish the fitness function S of the gray wolf population individuals,

[0097] ,

[0098] Among them, h is the initialized gray wolf population data information, ω1, ω2 and ω3 are the feedback adjustment factors of the gray wolf population individuals, and the fitness values ​​of the gray wolf population individuals are calculated to obtain the fitness value data information of the gray wolf population individuals;

[0099] M43. Based on the fitness data information of the gray wolf population individuals, establish a position update function Q of the gray wolf population,

[0100] ,

[0101] ,

[0102] ,

[0103] Among them, a is the fitness data information of the gray wolf population individuals, ρ1 and ρ2 are the position update optimization factors of the gray wolf population individuals, and the flow rate of dust suppressant spraying is optimized to obtain the optimized flow rate data information of dust suppressant spraying.

[0104] In this embodiment, the method further includes:

[0105] M5. Based on the optimized dust suppressant spray flow data information, establish the train dust suppressant spray control function R,

[0106] ,

[0107] Among them, c is the optimized flow data information of dust suppressant spraying, θ1 and θ2 are the control parameters of train dust suppressant spraying, and the spraying of train dust suppressant is controlled and adjusted to obtain the control data information of train dust suppressant spraying.

[0108] In this embodiment, the present invention provides a control system for spraying dust suppressants applied to trains, including a computer device programmed or configured to execute any one of the steps of the control method for spraying dust suppressants applied to trains.

[0109] In this embodiment, the present invention provides a computer-readable storage medium storing a computer program programmed or configured to execute any one of the control methods for spraying dust suppressants applied to trains.

[0110] Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0111] In summary, the present invention can not only adaptively optimize and control the spray flow rate according to the spray duration and the image of the train spray area, thereby saving energy consumption, but also the spray process does not require human participation, reducing labor costs and improving the efficiency of train spraying.

[0112] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A control method for spraying dust suppressants on trains, characterized in that: The method comprises: M1. The spraying vehicle drives onto the platform and stops next to the train to be sprayed. The vehicle's onboard camera acquires real-time image data of the train spray area, uses the vehicle's onboard light sensor to obtain real-time data on the spray duration of each train section, and uses the vehicle's onboard turbine flow sensor to obtain real-time data on the flow rate of the sprayed dust suppressant. M2. Based on the image data information of the train spray area, an improved HOG feature extraction algorithm is used to extract the pixels of the image and construct an image pixel matrix of the train spray area to obtain the image pixel matrix data information of the train spray area; M3. Based on the image pixel matrix data information of the train spray area, construct a train spray completion model to predict the train spray completion and obtain the predicted train spray completion data information; M4. Based on the predicted train spray completion data, the spray duration data for each train, and the dust suppressant spray flow data, an improved Gray Wolf optimization algorithm is used to optimize the dust suppressant spray flow rate to obtain optimized dust suppressant spray flow data; In step M4, the optimization of the dust suppressant spraying flow rate using the improved Grey Wolf optimization algorithm includes: M41. Based on the predicted train spraying completion data, the spraying duration data for each train, and the flow rate data of the spray dust suppressant, construct a gray wolf population and initialize its parameters, determine the maximum number of iterations for the population, and obtain initialized gray wolf population data; M42. Based on the initialized gray wolf population data information, establish the fitness function S of the gray wolf population individuals, ， Among them, h is the initialized gray wolf population data information, ω1, ω2 and ω3 are the feedback adjustment factors of the gray wolf population individuals, and the fitness values ​​of the gray wolf population individuals are calculated to obtain the fitness value data information of the gray wolf population individuals; M43. Based on the fitness data information of the gray wolf population individuals, establish a position update function Q of the gray wolf population, ， ， ， Among them, a is the fitness data information of the gray wolf population individuals, ρ1 and ρ2 are the position update optimization factors of the gray wolf population individuals, and the flow rate of dust suppressant spraying is optimized to obtain the optimized flow rate data information of dust suppressant spraying.

2. The control method for spraying dust suppressants applied to trains according to claim 1, characterized in that: In step M2, the use of the improved HOG feature extraction algorithm to extract pixel points of the image and construct an image pixel matrix of the train spray area includes: M21. Based on the image data information of the train spray area, construct an image pixel gradient function G of the train spray area, ， Where x is the image data information of the train spray area, α1, α2, and α3 are the gradient weight factors of the image pixels, and the gradient value of each pixel in the train spray area image is calculated to obtain the gradient value data information of the image pixels in the train spray area; M22. Based on the gradient value data information of the image pixels of the train spray area, establish the feature extraction function H of the image pixels, ， Where y is the gradient value data information of the image pixel in the train spray area, β1 is the first feature extraction factor, β2 is the second feature extraction factor, and β3 is the third feature extraction factor; M23. Based on the feature extraction function H of the image pixel points, the pixel points of the image are extracted, and the image pixel matrix of the train spray area is constructed to obtain the image pixel matrix data information of the train spray area.

3. The method for controlling dust suppressant spraying applied to trains according to claim 2, characterized in that: The first feature extraction factor β1 is, ， The second feature extraction factor β2 is, ， The third feature extraction factor β3 is, 。 4. The method for controlling dust suppressant spraying applied to trains according to claim 3, characterized in that: The constraints of the first feature extraction factor β1, the second feature extraction factor β2 and the third feature extraction factor β3 are: 。 5. The control method for spraying dust suppressant applied to trains according to claim 1, characterized in that: In step M3, the train spraying completion model is constructed to predict the spraying completion degree of the train, including: M31. Based on the image pixel matrix data information of the train spray area, construct an image pixel training data set and a test data set for the train spray area; M32. Input the image pixel training data set of the train spray area into the train spray completion model for training and learning, and determine the train spray completion decision function W, ， Among them, z is the image pixel training dataset of the train spray area, λ1, λ2 and λ3 are the train spray completion learning factors, and the trained train spray completion model is obtained; M33. Based on the trained train spray completion model, input the image pixel test dataset of the train spray area, predict the train spray completion degree, and obtain the predicted train spray completion degree data information.

6. The method for controlling dust suppressant spraying applied to trains according to claim 5, characterized in that: The constraints of the train spray completion learning factors λ1, λ2 and λ3 are: 。 7. The control method for spraying dust suppressant applied to trains according to claim 1, characterized in that: The method further comprises: M5. Based on the optimized dust suppressant spray flow data information, establish the train dust suppressant spray control function R, ， Among them, c is the optimized flow data information of dust suppressant spraying, θ1 and θ2 are the control parameters of train dust suppressant spraying, and the spraying of train dust suppressant is controlled and adjusted to obtain the control data information of train dust suppressant spraying.

8. A control system for spraying dust suppressants on trains, comprising computer equipment, characterized in that: The computer device is programmed or configured to execute the steps of the method for controlling dust suppressant spraying applied to trains as claimed in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program programmed or configured to execute the method for controlling dust suppressant spraying applied to a train according to any one of claims 1 to 7.

Images