Control methods for dust suppression spray systems of scraper conveyor equipment

Abstract

This invention relates to the field of dust suppression technology in mines, and more particularly to a control method for a spray dust suppression system of a scraper conveyor. The spray dust suppression system includes a shower nozzle, a pressure sensor, and a dust concentration sensor. The control method can calculate the optimal spray pressure value under the current working environment using a pre-designed algorithm and based on the actual dust concentration data collected by the dust concentration sensor. Then, it controls the shower nozzle to perform spray dust suppression operations based on the optimal spray pressure value. This control method can also automatically adjust the optimal spray pressure value in the database based on the actual collected dust concentration deviation value. This invention can dynamically adjust the spray volume according to the actual working environment and the spray dust suppression effect, saving water and electricity resources and contributing to cost reduction and efficiency improvement.

Description

Technical Field

[0001] This invention relates to the field of dust suppression technology in mines, and in particular to a control method for a spray dust suppression system of a scraper conveyor. Background Technology

[0002] Coal mines are a vital part of the global energy industry. However, the underground working environment in coal mines is complex and high-risk. The transportation of coal generates large amounts of dust, which settles on rotating parts of machinery, increasing wear and tear and causing premature damage. This coal dust also floats in the work area, posing a serious threat to the health and safety of workers. Therefore, effectively controlling dust, reducing dust concentration, and improving the underground working environment to prevent coal dust explosions are crucial aspects of safe coal mine production. Currently, the dust suppression method used in mines is spray dust suppression, which is carried out at maximum spray volume, resulting in a significant waste of water and electricity resources.

[0003] To address the aforementioned technical problems, Chinese invention patent application CN114183201.A discloses a dust monitoring device and intelligent spray dust suppression system for fully mechanized mining faces. The system includes a dust monitoring module, an intelligent spray control device, and a ground monitoring and control system. The dust monitoring module comprises a dust particle size monitoring device and a dust data analysis system. The intelligent spray control device includes a sprayer housing and water and air supply pipelines, a water-air atomizing nozzle, and a chip control unit, all arranged within the sprayer housing. The water and air supply pipelines are equipped with water pressure regulating devices and air pressure regulating devices. The sprayer housing is an elliptical tube shell, with mounting rings on its upper surface for mounting on the top beam of the hydraulic support of the fully mechanized mining face. A water and air supply pipeline with its outlet facing outwards is installed at the front opening of the sprayer housing. The ends of the water and air supply pipelines are connected to the water-air atomizing nozzles facing the coal cutting dust-generating area via adapter elbows. The system features convenient automated operation, excellent dust suppression effect, high data accuracy, and comprehensive spray coverage.

[0004] However, the above-mentioned existing technologies have the following technical problems: When the above-mentioned solutions are used for dust suppression by spraying, the spray volume cannot be accurately controlled according to the actual coal dust concentration in the mine. This may result in a situation where the spray volume does not match the actual required spray volume, which may cause insufficient spray volume leading to slow dust suppression, or excessive spray volume leading to waste of water and electricity resources. Summary of the Invention

[0005] In view of this, it is necessary to provide a control method for a scraper conveyor spray dust suppression system that can accurately control the spray volume based on the coal dust concentration.

[0006] A control method for a dust suppression spray system of a scraper conveyor equipment is disclosed. The dust suppression spray system is located in a non-enclosed working area and includes a first shower nozzle, a first pressure sensor, and a dust concentration sensor. The control method is applied to the non-enclosed working area and includes the following steps:

[0007] Step 1: Real-time acquisition of the first spray pressure data of the first shower nozzle collected by the first pressure sensor, and the actual dust concentration data of the non-enclosed working area collected by the dust concentration sensor;

[0008] Step 2: Obtain the permissible safe dust concentration data for the non-enclosed work area;

[0009] Step 3: Based on the actual dust concentration data and the safe dust concentration data, determine the dust concentration deviation value, which represents the deviation between the actual and expected concentrations, and the dust concentration deviation change amount, which represents the rate of change of the dust concentration deviation value.

[0010] Step 4: Use the dust concentration deviation value and the change in dust concentration deviation as inputs to the pre-built fuzzy control model, and output the predicted spray pressure data;

[0011] Step 5: Control the opening of the first shower nozzle based on the predicted spray pressure data and the first spray pressure data.

[0012] Preferably, step 3 specifically includes:

[0013] The difference between the actual dust concentration data and the safe dust concentration data is calculated to obtain the dust concentration deviation value;

[0014] Calculate the difference between the dust concentration deviation at time t+1 and the dust concentration deviation at time t to obtain the change in dust concentration deviation at time t.

[0015] Preferably, in step 4, the method for constructing the fuzzy control model includes:

[0016] S401: The dust concentration deviation parameter is described using the Gaussian distribution function, and N membership functions corresponding to the dust concentration deviation parameter are obtained by defining N fuzzy sets; among them, the smaller the concentration deviation in the N membership functions corresponding to the dust concentration deviation parameter, the greater the accuracy of the membership function.

[0017] S402: The Gaussian distribution function is used to describe the parameter of dust concentration deviation change, and N membership functions corresponding to the dust concentration deviation change are obtained by defining N fuzzy sets; among them, the smaller the concentration deviation change in the N membership functions corresponding to the dust concentration deviation change, the greater the accuracy of the membership function.

[0018] S403: The spray pressure parameters of the first nozzle are described using the Gaussian distribution function, and N membership functions corresponding to the spray pressure of the first nozzle are obtained by defining N fuzzy sets; among them, the closer the spray pressure is to the center value within the range of the N membership functions corresponding to the spray pressure of the first nozzle, the greater the accuracy of the membership function.

[0019] S404: Based on the membership functions of the N corresponding dust concentration deviation parameters, the N corresponding dust concentration deviation changes, the N corresponding spray pressures of the first nozzle, and expert experience, a fuzzy control rule base is constructed; wherein, the fuzzy rule base contains N*N fuzzy control rules, and each fuzzy control rule contains a set of inputs that uniquely correspond to a fuzzy set of spray pressures, wherein the inputs consist of a fuzzy set corresponding to a dust concentration deviation parameter and a fuzzy set corresponding to a dust concentration deviation change;

[0020] S405: Based on the fuzzy control rule base, the membership function of the corresponding spray pressure is mapped to the predicted spray pressure data to obtain the fuzzy control model.

[0021] Preferably, in S405, the step of mapping the membership function corresponding to the spray pressure to the predicted spray pressure data to obtain the fuzzy control model includes: outputting the predicted spray pressure data using the following formula 1:

[0022]

[0023] In Formula 3, f(x) represents the output predicted spray pressure data, and M represents the number of fuzzy control rules in the fuzzy control rule base. The center value of the Gaussian distribution function is used to characterize the fuzzy set of the corresponding spray pressure parameter that follows the l-th fuzzy control rule, and n is used to characterize the number of fuzzy sets of the corresponding spray pressure parameter. and Membership parameters x, respectively, used to characterize the corresponding spray pressure i The width and center value of the Gaussian distribution function of the fuzzy set following the l-th fuzzy control rule, x i The membership value is used to characterize the fuzzy set that conforms to the i-th spray pressure parameter.

[0024] Preferably, after step 5, the method further includes:

[0025] S501: Obtain the current dust concentration value collected by the dust concentration sensor;

[0026] S502: Determine whether the current dust concentration value is greater than the preset dust concentration threshold; if so, execute the preset alarm operation.

[0027] Preferably, the control method of the dust suppression spray system of the scraper conveyor further includes: optimizing the fuzzy control model based on the parameter self-tuning principle.

[0028] Preferably, the optimization of the fuzzy control model based on the parameter self-tuning principle includes:

[0029] Obtain at least one set of sample training data; wherein each set of sample training data includes a dust concentration deviation value and a dust concentration deviation change as input, and an optimal spray pressure value as output;

[0030] Using the at least one set of sample training data as the input layer of the neural network, the output is the optimized parameter that optimizes the membership function of the dust concentration deviation parameter and the dust concentration deviation change parameter.

[0031] Based on the optimization parameters, the mean and variance of the membership functions of the dust concentration deviation parameter and the dust concentration deviation change parameter are iteratively optimized respectively.

[0032] Preferably, the optimization parameters for optimizing the membership functions of the dust concentration deviation parameter and the dust concentration deviation change parameter by using the at least one set of sample training data as the input layer output of the neural network include:

[0033] Each set of training data samples is calculated sequentially using the following set of formulas to obtain at least one set of primary optimization parameters:

[0034]

[0035]

[0036]

[0037]

[0038] In formulas 4 to 7, z l a, b, and f represent the initial optimization parameters, h represents the number of parameter updates, and x represents the number of times the parameters are updated. Ei and x Di Let these represent the dust concentration deviation value and the change in deviation under the i-th fuzzy set, respectively. This represents the center of the Gaussian distribution of the k-th fuzzy set after optimizing the spray pressure P according to the l-th fuzzy rule. Let represent the center and width of the Gaussian distribution function of the i-th fuzzy set after h optimizations of the dust concentration deviation value following the l-th fuzzy rule. Let represent the center and width of the Gaussian distribution function of the i-th fuzzy set after h optimizations of the dust concentration deviation change following the l-th fuzzy rule.

[0039] Preferably, the iterative optimization of the mean and variance of the membership functions of the dust concentration deviation parameter and the dust concentration deviation change parameter based on the optimization parameters includes:

[0040] The mean and variance of the membership functions of the dust concentration deviation parameter and the dust concentration deviation change parameter are iteratively calculated using the following set of formulas:

[0041]

[0042]

[0043]

[0044]

[0045]

[0046] In formulas 8 to 12, Let represent the center and width of the Gaussian distribution function of the i-th fuzzy set after h+1 optimizations of the dust concentration deviation value following the l-th fuzzy rule. Let represent the center and width of the Gaussian distribution function of the i-th fuzzy set after h+1 optimizations of the dust concentration deviation change following the l-th fuzzy rule.

[0047] Preferably, the spray dust suppression system is installed in an enclosed working area and includes a second shower nozzle, a second pressure sensor, and a touch sensor; the control method is applied to the enclosed working area and includes the following steps:

[0048] A1: Obtain the first coal flow data collected by the touch sensor and the second spray pressure data collected by the second pressure sensor;

[0049] A2: Determine whether the current coal flow rate is greater than the preset large coal flow threshold based on the first coal flow rate data; if yes, proceed to step A3; otherwise, return to step A1.

[0050] A3: The first preset duration of the timing is used, and after the first duration is reached, the second coal flow data collected by the touch sensor is acquired again;

[0051] A4: Determine whether the current coal flow rate is greater than the large coal flow threshold based on the second coal flow rate data; if yes, increase the opening of the second shower nozzle based on the second pressure spray data; if no, return to step A1.

[0052] In the control method of the above-mentioned dust suppression spray system for scraper conveyor equipment, the dust suppression spray system includes a shower nozzle, a pressure sensor, and a dust concentration sensor. The control method can calculate the optimal spray pressure value under the current working environment through a pre-designed algorithm and based on the actual dust concentration data collected by the dust concentration sensor. Then, it controls the shower nozzle to perform dust suppression spraying based on the optimal spray pressure value. The control method can also automatically adjust the optimal spray pressure value in the database based on the actual collected dust concentration deviation value. This invention can dynamically adjust the spray volume according to the actual working environment and the dust suppression spraying effect, saving water and electricity resources and helping to reduce costs and increase efficiency. Attached Figure Description

[0053] Figure 1 This is a flowchart of the control method for the spray dust suppression system of the scraper conveyor equipment of this application.

[0054] Figure 2 This is the membership function curve of the dust concentration deviation parameter in this application.

[0055] Figure 3 This is the membership function curve of the dust concentration deviation change parameter in this application.

[0056] Figure 4 This is the membership function curve of the spray pressure parameter in this application.

[0057] Figure 5 This is the fuzzy control rule table of this application.

[0058] Figure 6 This is a schematic diagram of the dust suppression spray system for the scraper conveyor equipment described in this application. Detailed Implementation

[0059] The technical solutions and effects of the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0060] A control method for a dust suppression spray system in a scraper conveyor is disclosed. The dust suppression spray system is located in a non-enclosed working area and includes a first shower nozzle, a first pressure sensor, and a dust concentration sensor. The first shower nozzle is a fine atomizing nozzle to improve spray accuracy, and an adjustable control valve is installed at the inlet of the first shower nozzle to control the spray volume. The control method is applied to the non-enclosed working area, such as the coal unloading point of a conveyor and the coal dropping point of a transfer conveyor, and includes the following steps:

[0061] Step 1: Real-time acquisition of the first spray pressure data of the first shower nozzle collected by the first pressure sensor, and the actual dust concentration data of the non-enclosed working area collected by the dust concentration sensor;

[0062] Step 2: Obtain the permissible safe dust concentration data for the non-enclosed work area. This data has different fixed values ​​under different work scenarios to adapt to different work scenarios;

[0063] Step 3: Based on the actual dust concentration data and the safe dust concentration data, determine the dust concentration deviation value, which represents the deviation between the actual and expected concentrations, and the dust concentration deviation change amount, which represents the rate of change of the dust concentration deviation value.

[0064] Step 4: Use the dust concentration deviation value and the change in dust concentration deviation as inputs to the pre-built fuzzy control model, and output the predicted spray pressure data;

[0065] Step 5: Control the opening of the first shower nozzle based on the predicted spray pressure data and the first spray pressure data.

[0066] Furthermore, step 3 specifically includes:

[0067] The difference between the actual dust concentration data and the safe dust concentration data is calculated to obtain the dust concentration deviation value, which can be calculated using the following formula 1:

[0068] Ec = Cm - Ca Formula 1

[0069] In Formula 1, Ec is the dust concentration deviation value, Cm is the actual dust concentration data, Ca is the safe dust concentration data, and the obtained dust concentration deviation value can be applied to the next step of calculation.

[0070] The difference between the dust concentration deviation at time t+1 and the dust concentration deviation at time t is calculated to obtain the change in dust concentration deviation at time t. This change in dust concentration deviation can be calculated using the following formula 2:

[0071] Dc = Ec(t+1) - Ec(t) Formula 2

[0072] In Formula 2, Dc is the change in dust concentration deviation, Ec(t) is the dust concentration deviation value at time t, Ec(t+1) is the dust concentration deviation value at time t+1, and the obtained change in dust concentration deviation can be applied to the next step of calculation.

[0073] Furthermore, in step 4, the method for constructing the fuzzy control model includes:

[0074] S401: The dust concentration deviation parameter is described using the Gaussian distribution function, and N membership functions corresponding to the dust concentration deviation parameter are obtained by defining N fuzzy sets; among them, the smaller the concentration deviation in the N membership functions corresponding to the dust concentration deviation parameter, the greater the accuracy of the membership function.

[0075] S402: The Gaussian distribution function is used to describe the parameter of dust concentration deviation change, and N membership functions corresponding to the dust concentration deviation change are obtained by defining N fuzzy sets; among them, the smaller the concentration deviation change in the N membership functions corresponding to the dust concentration deviation change, the greater the accuracy of the membership function.

[0076] S403: The spray pressure parameters of the first nozzle are described using the Gaussian distribution function, and N membership functions corresponding to the spray pressure of the first nozzle are obtained by defining N fuzzy sets; among them, the closer the spray pressure is to the center value within the range of the N membership functions corresponding to the spray pressure of the first nozzle, the greater the accuracy of the membership function.

[0077] S404: Based on the membership functions of the N corresponding dust concentration deviation parameters, the N corresponding dust concentration deviation changes, the N corresponding spray pressures of the first nozzle, and expert experience, a fuzzy control rule base is constructed; wherein, the fuzzy rule base contains N*N fuzzy control rules, and each fuzzy control rule contains a set of inputs that uniquely correspond to a fuzzy set of spray pressures, wherein the inputs consist of a fuzzy set corresponding to a dust concentration deviation parameter and a fuzzy set corresponding to a dust concentration deviation change;

[0078] S405: Based on the fuzzy control rule base, the membership function of the corresponding spray pressure is mapped to the predicted spray pressure data to obtain the fuzzy control model.

[0079] In this embodiment, based on the operator's actual operating experience, the dust concentration deviation parameter ranges from [0, 150] mg / m³. 3Furthermore, seven fuzzy sets were defined, namely Ec1, Ec2, Ec3, Ec4, Ec5, Ec6, and Ec7, and their membership function curves are shown in Figure 2.

[0080] In this embodiment, based on the operator's actual operating experience, the range of the dust concentration deviation change parameter is [-6, 6] mg / (m³). 3 ·s), and defined 7 fuzzy sets, namely Dc1, Dc2, Dc3, Dc4, Dc5, Dc6, and Dc7, whose membership function curves are shown in Figure 1. Figure 3 As shown;

[0081] In this embodiment, based on the operator's actual operating experience, the spray pressure parameter ranges from [2, 10] MPa, and seven fuzzy sets are defined as P1, P2, P3, P4, P5, P6, and P7, with their membership function curves as shown below. Figure 4 As shown;

[0082] In this embodiment, based on actual experience in dust suppression spraying and expert advice, a fuzzy rule base containing 49 fuzzy control rules was constructed. Its control condition statements can be described as follows:

[0083]

[0084] These control statements can be summarized as follows: Figure 5 The fuzzy control rule table is shown.

[0085] Furthermore, in S405, the fuzzy control model is obtained by mapping the membership function of the corresponding spray pressure to the predicted spray pressure data, including: outputting the predicted spray pressure data using the following calculation formula:

[0086]

[0087] In the formula, f(x) represents the output predicted spray pressure data, and M represents the number of fuzzy control rules in the fuzzy control rule base. The center value of the Gaussian distribution function is used to characterize the fuzzy set of the corresponding spray pressure parameter that follows the l-th fuzzy control rule, and n is used to characterize the number of fuzzy sets of the corresponding spray pressure parameter. and Membership parameters x, respectively, used to characterize the corresponding spray pressure i The width and center value of the Gaussian distribution function of the fuzzy set following the l-th fuzzy control rule, x i The membership value is used to characterize the fuzzy set that conforms to the i-th spray pressure parameter.

[0088] Furthermore, following step 5, the process further includes:

[0089] S501: Obtain the current dust concentration value collected by the dust concentration sensor;

[0090] S502: Determine whether the current dust concentration value is greater than the preset dust concentration threshold; if so, execute the preset alarm operation so that the operator can promptly detect and eliminate the fault of the spray dust suppression system.

[0091] Furthermore, the control method for the dust suppression spray system of the scraper conveyor equipment includes:

[0092] A self-tuning database is pre-constructed; wherein, the self-tuning database includes at least one set of optimal input-output, each set of optimal input-output includes a dust concentration deviation value and a dust concentration deviation change as input, and an optimal spray pressure value as output.

[0093] Each set of training data samples is calculated sequentially using the following set of formulas to obtain at least one set of primary optimization parameters:

[0094]

[0095]

[0096]

[0097]

[0098] In formulas 4 to 7, z l a, b, and f represent the initial optimization parameters, h represents the number of parameter updates, and x represents the number of times the parameters are updated. Ei and x Di Let these represent the dust concentration deviation value and the change in deviation under the i-th fuzzy set, respectively. This represents the center of the Gaussian distribution of the k-th fuzzy set after optimizing the spray pressure P according to the l-th fuzzy rule. Let represent the center and width of the Gaussian distribution function of the i-th fuzzy set after h optimizations of the dust concentration deviation value following the l-th fuzzy rule. Let represent the center and width of the Gaussian distribution function of the i-th fuzzy set after h optimizations of the dust concentration deviation change following the l-th fuzzy rule.

[0099] In this embodiment, to make the primary optimization parameters more accurate, multiple sets of sample training data are used to obtain multiple sets of primary optimization parameters, and the primary optimization parameters z are... l We perform weighted average operations on a, b, and f respectively, and obtain the weighted average z of the primary optimization parameters. l', a', b', f' are used as primary optimization parameters.

[0100] Furthermore, the iterative optimization of the mean and variance of the membership functions of the dust concentration deviation parameter and the dust concentration deviation change parameter based on the optimization parameters includes:

[0101] The mean and variance of the membership functions of the dust concentration deviation parameter and the dust concentration deviation change parameter are iteratively calculated using the following set of formulas:

[0102]

[0103]

[0104]

[0105]

[0106]

[0107]

[0108] In formulas 8 to 12, Let represent the center and width of the Gaussian distribution function of the i-th fuzzy set after h+1 optimizations of the dust concentration deviation value following the l-th fuzzy rule. Let represent the center and width of the Gaussian distribution function of the i-th fuzzy set after h+1 optimizations of the dust concentration deviation change following the l-th fuzzy rule.

[0109] In one embodiment, the spray dust suppression system is located in an enclosed working area and includes a second shower nozzle, a second pressure sensor, and a touch sensor; the control method is applied to the enclosed working area, for example, the crushing point of a crusher, and includes the following steps:

[0110] A1: Obtain the first coal flow data collected by the touch sensor and the second spray pressure data collected by the second pressure sensor;

[0111] A2: Determine whether the current coal flow rate is greater than the preset large coal flow threshold based on the first coal flow rate data; if yes, proceed to step A3; otherwise, return to step A1.

[0112] A3: The first preset duration of the timing is used, and after the first duration is reached, the second coal flow data collected by the touch sensor is acquired again;

[0113] A4: Determine whether the current coal flow rate is greater than the large coal flow threshold based on the second coal flow rate data; if yes, increase the opening of the second shower nozzle based on the second pressure spray data; if no, return to step A1.

[0114] In one embodiment, the spray dust suppression system includes a sensing unit, a control unit, and an execution unit. The sensing unit is connected to the control unit to provide detection data for calculation by the control unit. The control unit is also connected to the execution unit to control the execution unit to perform spray dust suppression operations. The sensing unit includes a dust concentration sensor, a touch sensor, and a pressure sensor. The control unit is a programmable electronic device, such as a microcontroller. The control unit is equipped with the control method. The execution unit includes a nozzle, a water supply pipe, and a water valve. The outlet end of the water supply pipe is connected to the nozzle. The water valve is located inside the water supply pipe and connected to the control unit to control the opening degree of the water valve through the control unit. The nozzle is located above the scraper conveyor for spray dust suppression.

[0115] In the non-enclosed working areas, such as the coal unloading points of conveyors and the coal dropping points of transfer machines, when using the spray dust suppression system, based on a pre-established framework according to expert advice, and using the actual dust concentration data detected in real time by the dust concentration sensor as the input value, the system outputs the optimal spray pressure value under the current dust concentration, and uses this to control the opening of the first shower nozzle for spray dust suppression operation. During spray dust suppression operation, the dust concentration sensor will feed back the real-time detected dust concentration data, and use this to calculate the current dust concentration deviation value and the amount of change in dust concentration deviation.

[0116] In the enclosed working area, such as the crushing point of the crusher, when using the spray dust suppression system, because the dust concentration sensor has a short service life in the enclosed working area and needs to be frequently replaced, a touch sensor is used instead of the dust concentration sensor to provide control signals for spray dust suppression. After the touch sensor detects the coal flow signal, it will increase the opening of the second shower nozzle after a first duration to carry out spray dust suppression. The first duration is the time required for the coal flow to reach the second shower nozzle after passing the touch sensor. The specific time of the first duration depends on the actual installation situation, for example, 3 seconds. During the spray dust suppression operation, the touch sensor will detect the coal flow signal again after a certain period of time, for example, 3 seconds. If the coal flow signal is detected, the spray dust suppression operation continues. If the coal flow signal is not detected, the coal flow signal will be cleared and the opening of the second shower nozzle will be reduced to interrupt the spray dust suppression operation. After clearing the coal flow signal, the touch sensor will continue to cyclically detect the coal flow signal to ensure timely spray dust suppression and ensure safe production in the mine.

[0117] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A control method of a blade conveyor equipment misting dust suppression system, characterized by, The spray dust suppression system is installed in a non-enclosed working area and includes a first shower nozzle, a first pressure sensor, and a dust concentration sensor; the control method is applied to the non-enclosed working area and includes the following steps: Step 1: Real-time acquisition of the first spray pressure data of the first shower nozzle collected by the first pressure sensor, and the actual dust concentration data of the non-enclosed working area collected by the dust concentration sensor; Step 2: Obtain the permissible safe dust concentration data for the non-enclosed work area; Step 3: Based on the actual dust concentration data and the safe dust concentration data, determine the dust concentration deviation value, which represents the deviation between the actual and expected concentrations, and the dust concentration deviation change amount, which represents the rate of change of the dust concentration deviation value. Step 4: Use the dust concentration deviation value and the change in dust concentration deviation as inputs to the pre-built fuzzy control model, and output the predicted spray pressure data; Step 5: Control the opening of the first shower nozzle based on the predicted spray pressure data and the first spray pressure data; In step 4, the method for constructing the fuzzy control model includes: S401: The dust concentration deviation parameter is described using the Gaussian distribution function, and N membership functions corresponding to the dust concentration deviation parameter are obtained by defining N fuzzy sets; among them, the smaller the concentration deviation in the N membership functions corresponding to the dust concentration deviation parameter, the greater the accuracy of the membership function. S402: The Gaussian distribution function is used to describe the parameter of dust concentration deviation change, and N membership functions corresponding to the dust concentration deviation change are obtained by defining N fuzzy sets; among them, the smaller the concentration deviation change in the N membership functions corresponding to the dust concentration deviation change, the greater the accuracy of the membership function. S403: The spray pressure parameters of the first nozzle are described using the Gaussian distribution function, and N membership functions corresponding to the spray pressure of the first nozzle are obtained by defining N fuzzy sets; among them, the closer the spray pressure is to the center value within the range of the N membership functions corresponding to the spray pressure of the first nozzle, the greater the accuracy of the membership function. S404: Based on the membership functions of the N corresponding dust concentration deviation parameters, the N corresponding dust concentration deviation changes, the N corresponding spray pressures of the first nozzle, and expert experience, a fuzzy control rule base is constructed; wherein, the fuzzy control rule base contains N*N fuzzy control rules, and each fuzzy control rule contains a set of inputs that uniquely correspond to a fuzzy set of spray pressures, wherein the inputs consist of a fuzzy set corresponding to a dust concentration deviation parameter and a fuzzy set corresponding to a dust concentration deviation change; S405: Based on the fuzzy control rule base, map the membership function of the corresponding spray pressure to the predicted spray pressure data to obtain the fuzzy control model; In S405, the step of mapping the membership function corresponding to the spray pressure to the predicted spray pressure data to obtain the fuzzy control model includes: outputting the predicted spray pressure data using the following formula 3: ； ...Formula 3 In Formula 3, f(x) represents the output predicted spray pressure data, and M represents the number of fuzzy control rules in the fuzzy control rule base. The center value of the Gaussian distribution function is used to characterize the fuzzy set of the corresponding spray pressure parameter that follows the l-th fuzzy control rule, and n is used to characterize the number of fuzzy sets of the corresponding spray pressure parameter. and Membership parameters used to characterize the corresponding spray pressure The width and center value of the Gaussian distribution function of the fuzzy set following the l-th fuzzy control rule. Membership values ​​used to characterize the fuzzy set that conforms to the i-th spray pressure parameter; The control method further includes: optimizing the fuzzy control model based on the parameter self-tuning principle; the optimization of the fuzzy control model based on the parameter self-tuning principle includes: Obtain at least one set of sample training data; wherein each set of sample training data includes a dust concentration deviation value and a dust concentration deviation change as input, and an optimal spray pressure value as output; Using the at least one set of sample training data as the input layer of the neural network, the output is the optimized parameter that optimizes the membership function of the dust concentration deviation parameter and the dust concentration deviation change parameter. Based on the optimization parameters, the mean and variance of the membership functions of the dust concentration deviation parameter and the dust concentration deviation change parameter are iteratively optimized respectively. The optimization parameters, obtained by using the at least one set of sample training data as the input layer output of the neural network to optimize the membership function of the dust concentration deviation parameter and the dust concentration deviation change parameter, include: Each set of training data samples is calculated sequentially using the following set of formulas to obtain at least one set of primary optimization parameters: ； ...Formula 4 ； ...Formula 5 ； ...Formula 6 ； ...Formula 7 In formulas 4-7, z l a, b, and f represent the initial optimization parameters, and h represents the number of parameter updates. and Let these represent the dust concentration deviation value and the change in dust concentration deviation under the i-th fuzzy set, respectively. This represents the center of the Gaussian distribution of the k-th fuzzy set after optimizing the spray pressure P according to the l-th fuzzy rule. , Let Ec and V represent the center and width of the Gaussian distribution function of the i-th fuzzy set after h optimizations, respectively, for the dust concentration deviation value Ec following the l-th fuzzy rule. , Let represent the center and width of the Gaussian distribution function of the i-th fuzzy set after h optimizations of the dust concentration deviation change Dc following the l-th fuzzy rule; The iterative optimization of the mean and variance of the membership functions of the dust concentration deviation parameter and the dust concentration deviation change parameter based on the optimization parameters includes: The mean and variance of the membership functions of the dust concentration deviation parameter and the dust concentration deviation change parameter are iteratively calculated using the following set of formulas: ； ...Formula 8 ； ...Formula 9 ； ...Formula 10 ； ...Formula 11 ； ...Formula 12 In formulas 8-12, , Let Ec and V represent the center and width of the Gaussian distribution function of the i-th fuzzy set after h+1 optimizations, respectively, for the dust concentration deviation value Ec following the l-th fuzzy rule. , Let represent the center and width of the Gaussian distribution function of the i-th fuzzy set after h+1 optimizations of the dust concentration deviation change Dc following the l-th fuzzy rule.

2. The control method for the dust suppression spray system of the scraper conveyor equipment according to claim 1, characterized in that, Step 3 specifically includes: The difference between the actual dust concentration data and the safe dust concentration data is calculated to obtain the dust concentration deviation value; Calculate the difference between the dust concentration deviation at time t+1 and the dust concentration deviation at time t to obtain the change in dust concentration deviation at time t.

3. The control method for the dust suppression spray system of the scraper conveyor equipment according to claim 1, characterized in that, Following step 5, the following is further included: S501: Obtain the current dust concentration value collected by the dust concentration sensor; S502: Determine whether the current dust concentration value is greater than the preset dust concentration threshold; if so, execute the preset alarm operation.

Images