CNOs-based coal drop port flashboard anti-freezing heating system and device

Abstract

The invention relates to the technical field of anti-freezing heating devices, in particular to a CNOs-based anti-freezing heating system and device.The CNOs-based anti-freezing heating device comprises a heating device and a control box, and the heating device is composed of a heating plate made of a carbon nano onion material, a heat preservation layer and a waterproof layer; wherein the heat preservation layer is arranged on the back face of the heating plate, the waterproof layer is arranged on the back face of the heat preservation layer, and an intelligent temperature control controller and a temperature optimization controller are arranged in the control box. According to the anti-freezing heating system and device for the coal falling port flashboard based on the CNOs, through accurate temperature sensor layout, dynamic temperature difference monitoring and an intelligent control system, temperature adjustment of the coal falling port flashboard of a coal bunker can be effectively achieved, the icing problem is avoided, and the heating device is based on temperature difference information, collected in real time, of different areas; and the heating temperature is automatically adjusted, and the coal loading process is smoothly carried out.

Description

Technical Field

[0001] The present invention relates to the technical field of antifreeze heating devices, and in particular to a CNOs-based coal drop port gate antifreeze heating system and device. Background Art

[0002] The loading silo of the coal mine is directly affected by the low temperature weather. The surface of the coal drop port and the gate is prone to ice. After ice forms, the movement of the gate will be restricted, and the coal cannot fall smoothly, resulting in partial blockage of the loading port. Even if there is enough coal in the coal bunker, the equipment jamming caused by ice will cause delays or even stagnation in the loading process, which will affect the normal loading and transportation of coal.

[0003] In order to prevent the gate from freezing when in use, a heating device is generally provided to heat the existing gate. However, the traditional antifreeze heating method (hot air heating and electric heating) lacks intelligent temperature regulation and automatic optimization during heating, which on the one hand causes energy waste, and on the other hand may cause local overheating, leading to spontaneous combustion of coal or decomposition of coal powder. Summary of the invention

[0004] In order to solve the problems existing in the prior art, the present invention provides a CNOs-based coal drop port gate anti-freezing heating system and device.

[0005] The present invention adopts the following technical scheme: a CNOs-based coal drop gate antifreeze heating system is applied to a CNOs-based coal drop gate antifreeze heating device, the CNOs-based coal drop gate antifreeze heating device comprises a heating device and a control box, the heating device is composed of a heating plate made of carbon nano onion material, a thermal insulation layer and a waterproof layer, and the control box is provided with an intelligent temperature control controller and a temperature optimization controller; the CNOs-based coal drop gate antifreeze heating system comprises:

[0006] The intelligent temperature control controller comprises:

[0007] A data collection module collects historical heating training parameters of the heating device, the historical heating training parameters including an environmental state coefficient, a gate temperature, and a heating plate heating temperature;

[0008] Model training module, based on historical heating training parameters, trains a machine learning model for predicting the heating temperature of the heating plate, collects real-time environmental state coefficients and gate temperature, predicts the heating temperature of the heating plate based on the trained machine learning model, and controls the operation of the heating plate based on the predicted heating temperature of the heating plate;

[0009] The temperature optimization controller comprises:

[0010] The area division module takes the center of the heating plate as the center of the circle and draws a circle with a preset radius R to divide the gate plate into N heating areas;

[0011] The data acquisition module sets a temperature sensor in each heating area to collect the temperature value of each heating area and establishes a temperature set M. ;

[0012] The temperature optimization module obtains the heating stability coefficient of the gate based on the temperature value of each heating area, compares and analyzes the heating stability coefficient of the gate with the preset stability coefficient threshold, and generates a temperature adjustment instruction.

[0013] As a further description of the above technical solution: the parameters affecting the environmental state coefficient include external environment temperature, external environment humidity and gate ice thickness;

[0014] The method for obtaining the environmental state coefficient is: multiplying the external environment temperature, the external environment humidity and the gate ice thickness based on the piecewise function relationship to obtain the environmental state coefficient.

[0015] As a further description of the above technical solution: the method for obtaining the gate ice thickness includes:

[0016] Install the laser distance sensor at a fixed position, pointing it toward the gate surface;

[0017] The laser beam is controlled to penetrate the ice layer and reach the gate surface. The laser ranging sensor receives the reflected signal and calculates the time difference between the laser reaching the ice layer and the gate surface to obtain the thickness of the ice layer.

[0018] As a further description of the above technical solution: the training method of the machine learning model for predicting the heating temperature of the heating plate includes:

[0019] Convert the collected historical heating training parameters into a corresponding set of feature vectors;

[0020] Each group of feature vectors is used as the input of the machine learning model, and the machine learning model takes the heating temperature of the heating plate corresponding to each group of environmental state coefficients and gate temperature as the output, and takes the heating temperature of the heating plate actually corresponding to each group of environmental state coefficients and gate temperature as the prediction target, and takes minimizing the loss function value of the machine learning model as the training target; when the loss function value of the machine learning model is less than or equal to the preset target loss value, the training is stopped.

[0021] As a further description of the above technical solution: the parameters affecting the heating stability coefficient of the gate include the temperature uniformity coefficient and the temperature standard deviation;

[0022] The method for obtaining the temperature uniformity coefficient includes:

[0023] Get the maximum temperature difference of the heating area;

[0024] Get the average temperature difference of the heating area;

[0025] The temperature uniformity coefficient is calculated based on the maximum temperature difference of the heated area and the average temperature difference of the heated area.

[0026] As a further description of the above technical solution: the method for obtaining the heating stability coefficient is: performing a weighted sum operation on the temperature uniformity coefficient and the temperature standard deviation to obtain the heating stability coefficient.

[0027] As a further description of the above technical solution: the temperature adjustment instruction includes a first temperature adjustment instruction, a second temperature adjustment instruction and a third temperature adjustment instruction, and the first temperature adjustment instruction, the second temperature adjustment instruction and the third temperature adjustment instruction are all for lowering the heating temperature of the heating plate, and the temperature values ​​for lowering the heating temperature of the heating plate increase sequentially.

[0028] As a further description of the above technical solution: the method of comparing and analyzing the heating stability coefficient of the gate plate with a preset stability coefficient threshold to generate a temperature adjustment instruction includes:

[0029] Preset stability factor threshold JR 1 , JR 2 and JR 3 ; and JR 1 <JR 2 <JR 3 ;

[0030] when ≤JR 1 When , no temperature adjustment instruction is generated;

[0031] When JR 1 < ≤JR 2 When , a first temperature adjustment instruction is generated;

[0032] When JR 2 < ≤JR 3 When , a second temperature adjustment instruction is generated;

[0033] when >JR 3 When the temperature reaches 0.05°C, a third temperature adjustment instruction is generated.

[0034] As a further description of the above technical solution: the CNOs-based coal drop gate antifreeze heating system also includes an abnormal feedback repair module, and the abnormal feedback repair module includes:

[0035] A data acquisition module, which acquires the temperature standard deviation of the heating area;

[0036] The data analysis module presets a temperature standard deviation threshold, and when the obtained temperature standard deviation is greater than or equal to the preset temperature standard deviation threshold, obtains the heating area with the highest current temperature, and marks the heating area as a heating abnormality area;

[0037] The remote alarm module obtains the heating area of ​​the heating plate corresponding to the abnormal heating area, records it as the abnormal heating area, and sends the location and alarm information of the abnormal heating area to the mobile terminal, wherein the mobile terminal includes a terminal PC and a mobile phone.

[0038] A CNOs-based coal drop gate anti-freezing heating device, wherein the thermal insulation layer is arranged on the back of the heating plate, the waterproof layer is arranged on the back of the thermal insulation layer, a cable electrically connected to the heating plate is also arranged in the control box, and an overload protection air switch and a manual switch are installed on the cable.

[0039] Beneficial effects:

[0040] The CNOs-based coal drop gate antifreeze heating system and device provided by the present invention collects historical heating training parameters of the heating device, the historical heating training parameters include the environmental state coefficient, the gate temperature and the heating temperature of the heating plate, trains a machine learning model for predicting the heating temperature of the heating plate, collects the real-time environmental state coefficient and the gate temperature, predicts the heating temperature of the heating plate based on the trained machine learning model, and controls the operation of the heating plate based on the predicted heating temperature of the heating plate, that is, it realizes real-time dynamic adjustment of the heating temperature of the heating plate according to the environmental state coefficient and the gate temperature, prevents the temperature from being too high, and avoids spontaneous combustion of coal or decomposition of coal powder;

[0041] The present invention divides the gate plate into N heating areas by drawing a circle with a preset radius R with the center of the heating plate as the center, and by arranging a temperature sensor in each heating area to collect the temperature value of each heating area. Based on the temperature value of each heating area, the heating stability coefficient of the gate plate is obtained, and the heating stability coefficient of the gate plate is compared and analyzed with a preset stability coefficient threshold value to generate a temperature adjustment instruction. Therefore, through precise temperature sensor layout, dynamic temperature difference monitoring and intelligent control system, the temperature adjustment of the gate plate at the coal drop port of the coal bunker can be effectively achieved to avoid the problem of icing. The heating device automatically adjusts the heating temperature (the heating temperature is adjusted by adjusting the heating power) based on the temperature difference information of different areas collected in real time, so as to ensure the smooth progress of the coal loading process and save energy, while improving the reliability and safety of the use of the heating plate. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The present invention will be further explained below in conjunction with the accompanying drawings and embodiments:

[0043] Figure 1 A schematic diagram of the structure of a CNOs-based coal drop gate antifreeze heating device provided in an embodiment of the present invention;

[0044] Figure 2 A module connection diagram of an intelligent temperature control controller provided in an embodiment of the present invention;

[0045] Figure 3 A flow chart of a method for obtaining a temperature uniformity coefficient provided by an embodiment of the present invention;

[0046] Figure 4 A module connection diagram of a temperature optimization controller provided by an embodiment of the present invention;

[0047] Figure 5 A schematic diagram of the structure of an abnormal feedback repair module provided in an embodiment of the present invention.

[0048] Figure numerals: 1. Heating device; 2. Heating plate; 3. Insulation layer; 4. Waterproof layer; 5. Control box; 6. Intelligent temperature control controller; 7. Temperature optimization controller; 8. Manual switch; 9. Overload protection air switch; 11. Cable. DETAILED DESCRIPTION

[0049] In order to make the technical means, creative features, objectives and effects of the present invention easy to understand, the present invention is further described below with reference to specific diagrams. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0050] Example 1

[0051] See also Figure 1 , the embodiment of the invention provides a technical solution: a CNOs-based coal drop gate antifreeze heating device, comprising a heating device 1 and a control box 5;

[0052] Among them, CNOs is a spherical structure composed of multiple layers of carbon atoms, similar to the multi-layered appearance of an onion, hence the name carbon nano-onion material. CNOs is a type of carbon nanomaterial with a unique structure and significant physical and chemical properties, and therefore has potential application value in multiple fields.

[0053] The heating device 1 is composed of a heating plate 2 made of carbon nano-onion material, a heat preservation layer 3 and a waterproof layer 4, wherein the heat preservation layer 3 is arranged on the back of the heating plate 2, and the waterproof layer 4 is arranged on the back of the heat preservation layer 3;

[0054] The control box 5 is provided with an intelligent temperature control controller 6 and a temperature optimization controller 7; the control box 5 is also provided with a cable 11 electrically connected to the heating plate 2, and the cable 11 is installed with an overload protection air switch 9 and a manual switch 8.

[0055] Specifically, when the CNOs-based coal outlet gate antifreeze heating device is in use, the heating device 1 is fixed to the outside of the coal outlet gate of the loading station by a firm metal rope and fits tightly. The cable 11 is arranged in a standardized manner and connected to the control box 5. The control box 5 is installed on the wall of the loading channel. The manual switch 8 is convenient for personnel to operate. The AC220V power supply (power 800W) is connected to the control box 5.

[0056] Specifically, carbon nano-onion is a new type of zero-dimensional carbon nanomaterial with a unique multi-layer quasi-spherical or polyhedral shell structure. Its characteristics are:

[0057] Efficient heat conversion performance: Carbon nano onion has excellent heat conversion performance, which means that during the heating process, it can efficiently convert electrical energy or other forms of energy into heat energy. This efficient energy conversion gives carbon nano onion significant advantages in heating applications, such as faster heating speed, higher energy utilization efficiency, etc.

[0058] Stable heating performance: The carbon nano-onion has a stable structure and excellent heat resistance and chemical stability. This allows it to maintain good heating performance in high temperature environments and is not prone to structural damage or performance degradation. Therefore, the carbon nano-onion material has great potential in applications that require long-term high-temperature heating.

[0059] Microwave absorption properties: Carbon nano onions can efficiently absorb microwave energy, so they have faster heating speed and more uniform heating effect in microwave heating applications.

[0060] In this embodiment, by using carbon nano-onion heating materials, the anti-freezing effect of the gate is improved, the normal loading and transportation of coal is ensured, energy consumption is reduced, operating costs are reduced, operating procedures are simplified, and work efficiency is improved.

[0061] Example 2

[0062] See also Figure 1 and Figure 2 Based on the above embodiments, this embodiment further discloses a CNOs-based coal drop gate antifreeze heating system, which is applied to a CNOs-based coal drop gate antifreeze heating device;

[0063] Among them, the intelligent temperature control controller 6 includes:

[0064] A data collection module collects historical heating training parameters of the heating device 1, the historical heating training parameters including the environmental state coefficient, the gate temperature and the heating temperature of the heating plate 2;

[0065] It should be noted that the gate temperature is the average value of the temperatures collected by multiple temperature sensors installed on the gate.

[0066] The parameters affecting the environmental state coefficient include external environment temperature, external environment humidity and gate ice thickness;

[0067] The external environment temperature and the external environment humidity can be directly collected and obtained through temperature and humidity sensors.

[0068] The method for obtaining the gate ice thickness comprises:

[0069] Install the laser distance sensor at a fixed position, pointing it toward the gate surface;

[0070] The laser beam is controlled to penetrate the ice layer and reach the gate surface. The laser ranging sensor receives the reflected signal and calculates the time difference between the laser reaching the ice layer and the gate surface to obtain the thickness of the ice layer.

[0071] Specifically, the lower the external environment temperature, the higher the heating temperature of the heating plate 2, and vice versa. Because when the temperature is extremely low (such as -20°C or lower), the device can quickly heat to about 80°C at high power, and then switch to constant temperature mode to maintain the temperature. When the temperature is relatively mild, the heating temperature can be lowered to 40°C to 60°C, effectively preventing energy waste and reducing potential impacts on coal; secondly, the higher the external environment humidity, the higher the heating temperature of the heating plate 2, and vice versa. The higher the ice thickness of the gate plate, the higher the heating temperature of the heating plate 2, and vice versa.

[0072] The method for obtaining the environmental state coefficient is: multiplying the external environment temperature, the external environment humidity and the gate ice thickness based on the piecewise function relationship to obtain the environmental state coefficient.

[0073] Preferably, the calculation formula of the environmental state coefficient is:

[0074] ;

[0075] In the formula, Environmental status coefficient, is the external environment temperature, is the external environment humidity, is the gate ice thickness, is the maximum value of the external environment humidity, is the maximum ice thickness of the gate, is the gate ice thickness threshold, is the weight coefficient, is a piecewise function, when The value is 1 when , otherwise it is 0.

[0076] It should be noted that the size of the weight coefficient is a specific value obtained by quantifying each data to facilitate subsequent comparison. The size of the weight coefficient is set by those skilled in the art.

[0077] The maximum value of the external environment humidity and the maximum value of the gate plate ice thickness are determined by technical personnel in this field according to specific application requirements.

[0078] The model training module trains a machine learning model for predicting the heating temperature of the heating plate 2 based on historical heating training parameters, collects real-time environmental state coefficients and gate temperature, predicts the heating temperature of the heating plate 2 based on the trained machine learning model, and controls the operation of the heating plate 2 based on the predicted heating temperature of the heating plate 2;

[0079] The training method of the machine learning model for predicting the heating temperature of the heating plate 2 includes:

[0080] Convert the collected historical heating training parameters into a corresponding set of feature vectors;

[0081] Each group of feature vectors is used as the input of the machine learning model, and the machine learning model takes the heating temperature of the heating plate 2 corresponding to each group of environmental state coefficients and gate temperature as the output, and takes the heating temperature of the heating plate 2 actually corresponding to each group of environmental state coefficients and gate temperature as the prediction target, and takes minimizing the loss function value of the machine learning model as the training target; when the loss function value of the machine learning model is less than or equal to the preset target loss value, the training is stopped.

[0082] The machine learning model may be one of support vector machine regression, random forest regression or neural network regression models.

[0083] The loss function value of the machine learning model is the mean square error. The mean square error is one of the commonly used loss functions. The model is trained with minimization as the goal, so that the machine learning model can better fit the data, thereby improving the performance and accuracy of the model.

[0084] In the loss function is the loss function value of the machine learning model, is the feature vector group number; is the number of eigenvector groups; For the The heating temperature of the heating plate 2 corresponding to the group eigenvector, For the The heating temperature of the heating plate 2 corresponding to the group feature vector in real time.

[0085] Other model parameters, target loss values, optimization algorithms, training set, test set, validation set ratios, and loss function optimization of the machine learning model are all achieved through actual engineering and obtained through continuous experimental tuning.

[0086] In this embodiment, by collecting historical heating training parameters of the heating device 1, the historical heating training parameters include the environmental state coefficient, the gate temperature and the heating temperature of the heating plate 2, training a machine learning model for predicting the heating temperature of the heating plate 2, collecting real-time environmental state coefficient and gate temperature, predicting the heating temperature of the heating plate 2 based on the trained machine learning model, and controlling the operation of the heating plate 2 based on the predicted heating temperature of the heating plate 2, thereby realizing real-time dynamic adjustment of the heating temperature of the heating plate 2 according to the environmental state coefficient and the gate temperature, preventing the temperature from being too high, and avoiding spontaneous combustion of coal or decomposition of coal powder.

[0087] Example 3

[0088] See also Figure 1-Figure 4 , based on the above embodiment, this embodiment further discloses the structure of the temperature optimization controller 7;

[0089] The temperature optimization controller 7 comprises:

[0090] The area division module takes the center of the heating plate 2 as the center of the circle and draws a circle with a preset radius R to divide the gate into N heating areas; it should be noted that the first heating area is the circular area with a radius of R, the second heating area is the circular area with a radius of 2R minus the circular area with a radius of R, and so on, to obtain each heating area.

[0091] The data acquisition module sets a temperature sensor in each heating area to collect the temperature value of each heating area and establishes a temperature set M. ;

[0092] The temperature optimization module obtains the heating stability coefficient of the gate based on the temperature value of each heating area, compares and analyzes the heating stability coefficient of the gate with the preset stability coefficient threshold, and generates a temperature adjustment instruction.

[0093] The parameters affecting the heating stability coefficient of the gate include temperature uniformity coefficient and temperature standard deviation;

[0094] The method for obtaining the temperature uniformity coefficient includes:

[0095] The maximum temperature difference of the heating area is obtained. The calculation formula of the maximum temperature difference of the heating area is:

[0096] ;

[0097] In the formula, ∈M, ∈M, where is the maximum value in the temperature set M, is the minimum value in the temperature set M, is the maximum temperature difference in the heating area;

[0098] The average temperature difference of the heating area is obtained. The calculation formula of the average temperature difference of the heating area is:

[0099] ;

[0100] In the formula, is the average temperature difference in the heating area, is the absolute value of the temperature difference between two adjacent heating areas; is the temperature value of the i-th heating area;

[0101] The temperature uniformity coefficient is calculated based on the maximum temperature difference of the heating area and the average temperature difference of the heating area. The calculation formula of the temperature uniformity coefficient is:

[0102] ;

[0103] In the formula, is the temperature uniformity coefficient.

[0104] It should be noted that the temperature uniformity coefficient is an indicator to measure the temperature change and temperature difference in different areas of the gate during the heating process, reflecting the stability and temperature uniformity of the heating process. The calculation and analysis of this coefficient can help evaluate whether the heating system can efficiently and evenly heat the gate to avoid local overheating or overcooling.

[0105] The calculation formula of the temperature standard deviation is: ;

[0106] In the formula, is the temperature standard deviation, is the average temperature of all heating zones.

[0107] It should be noted that the temperature standard deviation measures the degree of dispersion of the temperature distribution of the N heating areas. The larger the standard deviation, the more uneven the temperature distribution, and vice versa.

[0108] The method for obtaining the heating stability coefficient is: performing a weighted sum operation on the temperature uniformity coefficient and the temperature standard deviation to obtain the heating stability coefficient.

[0109] Preferably, the heating stability coefficient of the gate plate is generated as follows:

[0110] ;

[0111] In the formula, is the heating stability coefficient of the gate, and is the weight coefficient, and and Greater than 0.

[0112] The temperature adjustment instructions include a first temperature adjustment instruction, a second temperature adjustment instruction and a third temperature adjustment instruction, and the first temperature adjustment instruction, the second temperature adjustment instruction and the third temperature adjustment instruction are all for reducing the heating temperature of the heating plate 2, and the temperature values ​​for reducing the heating temperature of the heating plate 2 increase sequentially.

[0113] The method of comparing and analyzing the heating stability coefficient of the gate plate with a preset stability coefficient threshold and generating a temperature adjustment instruction includes:

[0114] Preset stability factor threshold JR 1 , JR 2 and JR 3 ; and JR 1 <JR 2 <JR 3 ;

[0115] when ≤JR 1 When , no temperature adjustment instruction is generated;

[0116] When JR 1 < ≤JR 2 When , a first temperature adjustment instruction is generated;

[0117] When JR 2 < ≤JR 3 When , a second temperature adjustment instruction is generated;

[0118] when >JR 3 When the temperature reaches 0.05°C, a third temperature adjustment instruction is generated.

[0119] In this embodiment, the gate plate is divided into N heating areas by drawing a circle with a preset radius R with the center of the heating plate 2 as the center. A temperature sensor is set in each heating area to collect the temperature value of each heating area. Based on the temperature value of each heating area, the heating stability coefficient of the gate plate is obtained, and the heating stability coefficient of the gate plate is compared and analyzed with the preset stability coefficient threshold to generate a temperature adjustment instruction. Therefore, through precise temperature sensor layout, dynamic temperature difference monitoring and intelligent control system, the temperature adjustment of the gate plate at the coal drop port of the coal bunker can be effectively achieved to avoid icing problems. The heating device 1 automatically adjusts the heating temperature (the heating temperature is adjusted by adjusting the heating power) based on the real-time collected temperature difference information of different areas, thereby ensuring the smooth progress of the coal loading process and saving energy, while improving the reliability and safety of the use of the heating plate 2.

[0120] Example 4

[0121] See also Figure 1-Figure 5Based on the above embodiment, this embodiment further discloses an abnormal feedback repair module, and the abnormal feedback repair module includes:

[0122] A data acquisition module, which acquires the temperature standard deviation of the heating area (the method for acquiring the temperature standard deviation has been described in Example 3);

[0123] The data analysis module presets a temperature standard deviation threshold, and when the obtained temperature standard deviation is greater than or equal to the preset temperature standard deviation threshold, obtains the heating area with the highest current temperature, and marks the heating area as a heating abnormality area;

[0124] The remote alarm module obtains the heating area of ​​the heating plate 2 corresponding to the abnormal heating area, records it as the abnormal heating area, and sends the location and alarm information of the abnormal heating area to the mobile terminal, wherein the mobile terminal includes a terminal PC and a mobile phone.

[0125] In this embodiment, the temperature standard deviation of the heating area is obtained. The larger the temperature standard deviation, the more uneven the temperature distribution in the heating area. Then, based on the preset temperature standard deviation threshold, it is determined whether an abnormal heating area occurs. When an abnormal heating area occurs, the heating area of ​​the corresponding heating plate 2 is determined and fed back to the heating system, so that timely maintenance can be carried out to avoid safety hazards.

[0126] The basic principles, main features and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and the description in the specification are only to illustrate the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A CNOs-based coal drop gate antifreeze heating system, applied to a CNOs-based coal drop gate antifreeze heating device, the CNOs-based coal drop gate antifreeze heating device comprising a heating device (1) and a control box (5), the heating device (1) comprising a heating plate (2) made of carbon nano-onion material, a heat-insulating layer (3) and a waterproof layer (4), the control box (5) being provided with an intelligent temperature control controller (6) and a temperature optimization controller (7), characterized in that: The intelligent temperature control controller (6) comprises: A data collection module for collecting historical heating training parameters of the heating device (1), the historical heating training parameters including an environmental state coefficient and a gate temperature and a heating temperature of the heating plate (2); A model training module, based on historical heating training parameters, trains a machine learning model for predicting the heating temperature of the heating plate (2), collects real-time environmental state coefficients and gate temperature, predicts the heating temperature of the heating plate (2) based on the trained machine learning model, and controls the operation of the heating plate (2) based on the predicted heating temperature of the heating plate (2); The temperature optimization controller (7) comprises: An area division module, taking the center of the heating plate (2) as the center of the circle and drawing a circle with a preset radius R, to divide the gate plate into N heating areas; The data acquisition module sets a temperature sensor in each heating area to collect the temperature value of each heating area and establishes a temperature set M. ; The temperature optimization module obtains the heating stability coefficient of the gate based on the temperature value of each heating area, compares and analyzes the heating stability coefficient of the gate with the preset stability coefficient threshold, and generates a temperature adjustment instruction.

2. The CNOs-based coal drop gate antifreeze heating system according to claim 1 is characterized in that: The parameters affecting the environmental state coefficient include external environment temperature, external environment humidity and gate ice thickness; The method for obtaining the environmental state coefficient is: multiplying the external environment temperature, the external environment humidity and the gate ice thickness based on the piecewise function relationship to obtain the environmental state coefficient.

3. The CNOs-based coal drop gate antifreeze heating system according to claim 2 is characterized in that: The method for obtaining the gate plate ice thickness comprises: Install the laser distance sensor at a fixed position, pointing it toward the gate surface; The laser beam is controlled to penetrate the ice layer and reach the gate surface. The laser ranging sensor receives the reflected signal and calculates the time difference between the laser reaching the ice layer and the gate surface to obtain the thickness of the ice layer.

4. The CNOs-based coal drop gate antifreeze heating system according to claim 1 is characterized in that: The training method of the machine learning model for predicting the heating temperature of the heating plate (2) comprises: Convert the collected historical heating training parameters into a corresponding set of feature vectors; Each set of feature vectors is used as the input of the machine learning model. The machine learning model uses the heating temperature of the heating plate (2) corresponding to each set of environmental state coefficients and gate temperature as the output, uses the heating temperature of the heating plate (2) actually corresponding to each set of environmental state coefficients and gate temperature as the prediction target, and uses minimizing the loss function value of the machine learning model as the training target; when the loss function value of the machine learning model is less than or equal to a preset target loss value, the training is stopped.

5. The CNOs-based coal drop gate antifreeze heating system according to claim 1, characterized in that: The parameters affecting the heating stability coefficient of the gate include temperature uniformity coefficient and temperature standard deviation; The method for obtaining the temperature uniformity coefficient includes: Get the maximum temperature difference of the heating area; Get the average temperature difference of the heating area; The temperature uniformity coefficient is calculated based on the maximum temperature difference of the heated area and the average temperature difference of the heated area.

6. The CNOs-based coal drop gate antifreeze heating system according to claim 5 is characterized in that: The method for obtaining the heating stability coefficient is: performing a weighted sum operation on the temperature uniformity coefficient and the temperature standard deviation to obtain the heating stability coefficient.

7. The CNOs-based coal drop gate antifreeze heating system according to claim 6 is characterized in that: The temperature adjustment instruction comprises a first temperature adjustment instruction, a second temperature adjustment instruction and a third temperature adjustment instruction, and the first temperature adjustment instruction, the second temperature adjustment instruction and the third temperature adjustment instruction are all for reducing the heating temperature of the heating plate (2), and the temperature values ​​for reducing the heating temperature of the heating plate (2) increase in sequence.

8. The CNOs-based coal drop gate antifreeze heating system according to claim 7, characterized in that: The method of comparing and analyzing the heating stability coefficient of the gate plate with a preset stability coefficient threshold to generate a temperature adjustment instruction includes: Preset stability coefficient thresholds JR1, JR2 and JR3; and JR1<JR2<JR3; when When ≤JR1, no temperature adjustment instruction is generated; When JR1< When ≤JR2, the first temperature adjustment instruction is generated; When JR2< When ≤JR3, a second temperature adjustment instruction is generated; when >JR3, a third temperature adjustment command is generated.

9. The CNOs-based coal drop gate antifreeze heating system according to claim 7, characterized in that: It also includes an abnormal feedback repair module, which includes: A data acquisition module, which acquires the temperature standard deviation of the heating area; The data analysis module presets a temperature standard deviation threshold, and when the obtained temperature standard deviation is greater than or equal to the preset temperature standard deviation threshold, obtains the heating area with the highest current temperature, and marks the heating area as a heating abnormality area; The remote alarm module obtains the heating area of ​​the heating plate (2) corresponding to the abnormal heating area, records it as the abnormal heating area, and sends the location and alarm information of the abnormal heating area to the mobile terminal, wherein the mobile terminal includes a terminal PC and a mobile phone.

10. A CNOs-based coal drop gate antifreeze heating device, implemented based on the CNOs-based coal drop gate antifreeze heating system according to any one of claims 1 to 9, characterized in that: The thermal insulation layer (3) is arranged on the back of the heating plate (2), the waterproof layer (4) is arranged on the back of the thermal insulation layer (3), and a cable (11) electrically connected to the heating plate (2) is also arranged in the control box (5), and an overload protection air switch (9) and a manual switch (8) are installed on the cable (11).

Images