Temperature measurement control method and system of coke oven straight movement temperature measurement robot

Abstract

The invention provides a temperature measurement control method and system for a coke oven straight-movement temperature measurement robot, and belongs to the technical field of coke oven temperature control. The method comprises the following steps: acquiring the real temperature of a flame path according to the coke oven straight-movement temperature measurement robot; constructing a temperature correlation model of the flame path and the carbonization chamber according to the real temperature of the flame path and the historical temperature of the carbonization chamber; and determining a mapping relation between the three-dimensional temperature field of the carbonization chamber and the center temperature of the coke cake according to the temperature correlation model, and controlling the coking degree of the center of the coke cake according to the mapping relation. According to the temperature measurement control method and system for the coke oven straight-movement temperature measurement robot, the temperature value of the center of the coke cake can be determined according to the flame path temperature detected by the coke oven straight-movement temperature measurement robot, the temperature of the center of the coke cake is controlled to be within the coking range, local over-coking or under-coking of the coke cake is avoided, and excessive consumption of fuel is reduced.

Description

Technical Field

[0001] This application belongs to the field of coke oven temperature control technology, and more specifically, it relates to a temperature measurement control method and system for a coke oven straight-line temperature measuring robot. Background Technology

[0002] In traditional coke oven production, the flue temperature is the main basis for controlling the coke oven temperature. However, there is a lag and non-linear relationship in the temperature transfer between the flue, the carbonization chamber, and the center of the coke cake. Traditional methods often rely on experience to adjust the flue temperature, but it is difficult to accurately reflect the actual coking state of the coke cake by relying solely on the flue temperature, which can easily lead to local over-coking or under-coking of the coke cake. In traditional methods, in order to avoid under-coking of the coke cake, a conservative heating strategy (higher flue temperature) is often adopted, which leads to increased fuel consumption. Summary of the Invention

[0003] The purpose of this application is to provide a method and system for temperature control of a coke oven straight-line temperature measuring robot, which determines the temperature value of the coke cake center by detecting the fire channel temperature through the coke oven straight-line temperature measuring robot, controls the temperature of the coke cake center to be within the coking range, avoids local over-coking or under-coking of the coke cake, and reduces excessive fuel consumption.

[0004] A first aspect of this application provides a temperature control method for a coke oven linear temperature measuring robot, comprising: The actual temperature of the fire channel is obtained from the coke oven straight-line temperature measuring robot; A temperature correlation model between the fire channel and the carbonization chamber is constructed based on the actual temperature of the fire channel and the historical temperature of the carbonization chamber. The mapping relationship between the three-dimensional temperature field of the carbonization chamber and the temperature at the center of the coke cake is determined by the temperature correlation model, and the degree of coking at the center of the coke cake is controlled according to the mapping relationship.

[0005] A second aspect of this application provides a temperature measurement and control system for a coke oven linear temperature measurement robot, comprising: The flue temperature acquisition module is used to obtain the actual temperature of the flue based on the coke oven straight-line temperature measuring robot; The model building module is used to build a temperature correlation model between the fire channel and the carbonization chamber based on the actual temperature of the fire channel and the historical temperature of the carbonization chamber. The coking degree control module is used to determine the mapping relationship between the three-dimensional temperature field of the carbonization chamber and the temperature at the center of the coke cake based on the temperature correlation model, and to control the coking degree at the center of the coke cake based on the mapping relationship.

[0006] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above-described coke oven straight-line temperature measurement robot temperature measurement control method.

[0007] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described coke oven straight-line temperature measurement robot temperature control method.

[0008] The beneficial effects of the coke oven straight-line temperature measurement robot temperature control method and system provided in this application embodiment are as follows: This application embodiment obtains the real temperature of each point in the fire channel by the straight-line temperature measurement robot, controls the temperature of the carbonization chamber by adjusting the temperature of the fire channel, accurately regulates the carbonization process, ensures uniform temperature in each area of ​​the carbonization chamber, and avoids the phenomenon of coking or over-coking of coke; furthermore, based on the mapping relationship between the three-dimensional temperature field of the carbonization chamber and the temperature of the coke cake center, the fire channel temperature can be adjusted to achieve precise control of the degree of coking in the center of the coke cake, ensuring coke quality, improving production efficiency, and avoiding resource waste in the coking process of the coke cake. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 A schematic flowchart illustrating the temperature control method for a coke oven linear temperature measuring robot provided in an embodiment of this application; Figure 2 This is a structural block diagram of a coke oven straight-line temperature measurement robot temperature measurement control system provided in an embodiment of this application; Figure 3 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0011] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0012] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0013] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a temperature control method for a coke oven linear temperature measuring robot according to an embodiment of this application. The method may include: S101: Obtain the actual temperature of the fire channel based on the coke oven straight-line temperature measuring robot.

[0014] In this embodiment, the fire channels are located on both sides of the carbonization chamber and arranged longitudinally. As a key channel for heating the coke oven, the temperature of the fire channels directly affects the coking process in the carbonization chamber. The coal charging car can travel along the track on the top of the coke oven, enabling it to cover the entire fire channel. The coke oven straight-line temperature measurement robot, based on a positioning device and combined with an infrared thermometer, collects the temperature of the fire channels.

[0015] In this embodiment, a coke oven straight-line temperature measurement robot is installed on a coal charging car. Infrared temperature probes are installed in the outer space of the front end on both sides of the coal charging car. The core components of the coke oven straight-line temperature measurement robot include an industrial camera, a lidar, and an encoder. The industrial camera is a high-definition industrial camera with a resolution of 1920×1080. The high-definition industrial camera is used to locate the temperature measurement point in the fire channel, and the lidar is used to measure the distance between the infrared temperature probe and the fire channel. After the coal charging car completes the coal charging operation, it travels along the top track of the oven to the coke oven position corresponding to the fire channel to be measured (e.g., the fire channels on both sides of the No. 3 carbonization chamber). Using the scale markings on the top of the coke oven, the coal charging car is parked directly above the fire channel. The high-definition industrial camera determines the fire channel opening, and then determines the current fire channel number.

[0016] Temperature data is continuously collected a first preset number of times using an external temperature probe at preset intervals. Outliers are removed, and the average temperature value is obtained, which is used as the original temperature value. A temperature correction value is determined based on a preset standard distance, the distance between the infrared temperature probe and the fire channel, and the original temperature value. for Where T is the original temperature value, s1 is the preset standard distance, and s2 is the distance between the infrared temperature probe and the fire channel. The temperature correction value is taken as the actual temperature of the fire channel.

[0017] This embodiment obtains the true temperature of the fire channel by measuring and correcting the fire channel temperature through non-contact measurement, thus avoiding damage to the equipment from high temperatures.

[0018] S102: Construct a temperature correlation model between the fire channel and the carbonization chamber based on the actual temperature of the fire channel and the historical temperature of the carbonization chamber.

[0019] In this embodiment, the actual temperature of the fire channel is matched with the historical temperature of the carbonization chamber according to the time dimension to ensure that the temperature of the fire channel on both sides of the same carbonization chamber at the same time forms a data pair with the temperature of the carbonization chamber.

[0020] The Pearson correlation coefficient between the flue temperature and the carbonization chamber temperature was determined based on the data. The correlation characteristics between these two temperatures were then determined based on the correlation coefficient and a preset threshold, which could be 0.8. If the correlation coefficient was greater than the preset threshold, a correlation was considered to exist between the two temperatures; otherwise, no correlation was considered. Data pairs exhibiting correlation characteristics were used as input data for the temperature correlation model. The input data was divided into training and testing sets according to a preset ratio, such as 7:3. Mean squared error was used as the loss function in both training and testing of the temperature correlation model. The parameters of the temperature correlation model were optimized using gradient descent until the preset number of iterations or the mean squared error of the testing set stabilized at approximately 8℃², indicating good generalization ability of the temperature correlation model.

[0021] S103: Determine the mapping relationship between the three-dimensional temperature field of the carbonization chamber and the temperature at the center of the coke cake based on the temperature correlation model, and control the degree of coking at the center of the coke cake based on the mapping relationship.

[0022] In this embodiment, based on the temperature correlation model between the fire channel and the carbonization chamber, temperature data at different spatial locations within the carbonization chamber are acquired to determine the three-dimensional temperature field of the carbonization chamber. Features related to the coke cake center temperature are extracted from each feature point within the three-dimensional temperature field of the carbonization chamber. These features may include the average temperature and dimensional variance within a 0.5-meter radius around the coke cake center, the temperature gradient at the coke cake center along different directions within the carbonization chamber, the temperature of the furnace wall closest to the coke cake center, and the fire channel temperature. Coking time may also be included. Based on a pre-trained mapping model between the three-dimensional temperature field of the carbonization chamber and the coke cake center temperature, the mapping relationship between the three-dimensional temperature field of the carbonization chamber and the coke cake center temperature is determined.

[0023] The relationship between the coke cake center temperature and the degree of coking is determined based on the quality requirements of the coke. If the coke cake center temperature is lower than a first temperature, it is considered under-coked; if the coke cake center temperature is higher than the first temperature but lower than a second temperature, it is considered mature; if the coke cake center temperature is higher than the second temperature, it is considered over-coked. The first temperature can be 950℃, and the second temperature can be 1000℃. The three-dimensional temperature field of the carbonization chamber is determined based on the actual temperature of the flue. This three-dimensional temperature field data is then input into a mapping model to obtain the predicted temperature value at the coke cake center. The degree of coking is then determined based on the relationship between the coke cake center temperature and the degree of coking.

[0024] As can be seen from the above, this embodiment corrects the original temperature of the fire channel by using the coke oven straight-line robot and infrared temperature probe to obtain the true temperature of the fire channel, thus enabling precise control of the fire channel temperature. Based on the temperature correlation model, the internal temperature gradient of the carbonization chamber can be derived from the fire channel temperature, ensuring uniform temperature in all areas of the carbonization chamber and avoiding coking or over-coking of the coke. Based on the carbonization chamber temperature and the thermophysical parameters of the coke cake, a dynamic mapping relationship from the carbonization chamber to the center of the coke cake is obtained, enabling accurate prediction of the temperature at the center of the coke cake and improving coke quality.

[0025] In one embodiment of this application, the mapping relationship between the three-dimensional temperature field of the carbonization chamber and the temperature at the center of the coke cake is determined according to a temperature correlation model, and the degree of coking at the center of the coke cake is controlled according to the mapping relationship, including: The temperature of the grid points in the carbonization chamber is determined based on the temperature correlation model, and the three-dimensional temperature field of the carbonization chamber is determined based on the temperature of the grid points using the inverse distance weighting method. Based on the three-dimensional temperature field of the carbonization chamber, at least one feature point uniformly distributed in the carbonization chamber is selected, and the temperature of the coke cake center and the corresponding temperature field data of each feature point in the three-dimensional temperature field of the carbonization chamber at different coking stages are obtained. A sample library is established, and the mapping relationship between the three-dimensional temperature field of the carbonization chamber and the temperature of the coke cake center is determined based on the sample library and the backpropagation neural network. Based on the mapping relationship, the predicted temperature value of the center of the cake is determined, and a temperature change trend curve is generated. The degree of coking at the center of the coke cake is controlled based on the temperature change trend curve and the target temperature range at the center of the coke cake.

[0026] In this embodiment, the temperature values ​​of each grid point in the carbonization chamber are determined according to a temperature correlation model, wherein each grid point is uniformly distributed in the carbonization chamber space according to a preset density. Based on the temperature values ​​of each grid point, the difference is calculated using an inverse distance weighting method to determine the distance between each grid point and the feature point to be determined. The weight of each grid point is determined according to the distance, thereby determining the temperature at any location in the carbonization chamber space and determining the three-dimensional temperature field of the carbonization chamber.

[0027] At least one uniformly distributed feature point is selected from the three-dimensional temperature field of the carbonization chamber. At different coking stages, the coke cake center temperature corresponding to the uniformly distributed feature point, as well as the temperature field data corresponding to the feature point location, are collected. A sample library is established by organizing the coke cake center temperature and the corresponding temperature field data for each feature point. This sample library includes sufficient coking stages and feature point information to ensure data comprehensiveness. A backpropagation neural network is trained based on the data in the sample library. Using the three-dimensional temperature field data of the carbonization chamber as input and the coke cake center temperature as output, the neural network is trained iteratively multiple times to accurately fit the relationship between the two, thus determining the mapping relationship between the three-dimensional temperature field of the carbonization chamber and the coke cake center temperature. The data from the three-dimensional temperature field of the carbonization chamber is input into the determined mapping relationship to obtain the predicted temperature value of the coke cake center. Multiple temperature prediction values ​​are organized in chronological order to determine the temperature change trend curve. The temperature change trend curve is compared with the preset temperature range of the coke cake center. When the temperature prediction value deviates from the target range, relevant parameters of the carbonization chamber (such as heating temperature and heating time) are adjusted to keep the coke cake center temperature within the preset temperature range, thereby controlling the degree of coking. Specifically, if the predicted temperature at the center of the coke cake is lower than the first temperature, it is determined that the coke cake is under-coked, and the gas flow rate in the carbonization chamber is increased to raise the combustion temperature and enhance the heating of the carbonization chamber; if the predicted temperature at the center of the coke cake is higher than the first temperature but lower than the second temperature, it is determined that the coke cake is mature; if the predicted temperature at the center of the coke cake is higher than the second temperature, it is determined that the coke cake is over-coked, and the gas flow rate is reduced to lower the combustion temperature, the heating of the carbonization chamber is reduced, the coking time is shortened, the amount of combustion air is reduced, and the combustion efficiency is reduced.

[0028] For example, five uniformly distributed feature points are selected in the three-dimensional temperature field of the carbonization chamber. During the coking process, data is collected at each feature point every hour. This data includes the temperature of each feature point, the temperature difference between each feature point and its adjacent grid points, and the heat transfer rate of each feature point. The temperature of the coke cake center is obtained using a high-precision thermocouple at the center of the coke cake. For instance, after 6 hours of coking, the temperatures of the five feature points are 420℃, 430℃, 410℃, 395℃, and 400℃, respectively, at which point the corresponding coke cake center temperature is 380℃. After 15 hours of coking, the temperatures of the five feature points rise to 750℃, 760℃, 740℃, 720℃, and 735℃, respectively, and the coke cake center temperature reaches 690℃. After accumulating data over multiple coking cycles, a total of 200 sets of valid data were collected (5 feature points × 20 coking times × 2 parallel experiments). A sample library was established based on this valid data. The input parameters are the temperature, temperature difference, and heat conduction rate of the 5 feature points, totaling 15 parameters. The output parameter is the temperature at the center of the coke cake. The mapping relationship between the three-dimensional temperature field of the carbonization chamber and the temperature at the center of the coke cake was determined based on this sample library and a backpropagation neural network. Based on the mapping relationship between the three-dimensional temperature field of the carbonization chamber and the temperature at the center of the coke cake, the predicted temperature value at the center of the coke cake during the coking process was determined, thus determining the temperature change trend curve. In the initial stage of coking (0-5 hours), the temperature rises slowly, from room temperature (25℃) to about 300℃; in the middle stage of coking (5-20 hours), the temperature rise rate accelerates, gradually rising from 300℃ to about 900℃; in the later stage of coking (20-28 hours), the temperature rise rate slows down, finally reaching 980℃ at 28 hours. The target temperature range for the center of the coke cake is set to 950-1000℃. Based on the temperature change trend curve, the coking process at the center of the coke cake is controlled to ensure that the temperature at the center of the coke cake is always within the target temperature range.

[0029] In one embodiment of this application, before determining the three-dimensional temperature field of the carbonization chamber based on the temperature of the grid points using the inverse distance weighting method, the method further includes: A spatial rectangular coordinate system is constructed based on the three-dimensional physical boundary parameters of the carbonization chamber to determine the coordinates of each feature point; Based on the temperature correlation model, determine the coordinates of each feature point and record the temperature value corresponding to each feature point; A three-dimensional mesh is divided according to a preset precision to form a set of mesh points; The three-dimensional temperature field of the carbonization chamber was determined using the inverse distance weighting method, including: Determine the straight-line distance between the coordinates of each grid point and each feature point; The weight of each grid point is determined based on the straight-line distance between the coordinates of each grid point and each feature point. The temperature value of each grid point is determined based on its weight. The three-dimensional temperature field of the carbonization chamber is determined based on the temperature value of each grid point.

[0030] In this embodiment, using the physical boundary of the carbonization chamber as a reference, the point at the bottom left end of the carbonization chamber is selected as the origin. A spatial rectangular coordinate system is constructed along the length, width, and height directions, where the length direction is the X-axis, the width direction is the Y-axis, and the height direction is the Z-axis. In this spatial rectangular coordinate system, feature points are selected according to a uniform distribution principle, and the coordinates (x, y, z) of each feature point are determined. i y i , z i Each feature point is input into the temperature correlation model to determine the corresponding temperature value of each feature point under the current operating conditions; according to the preset accuracy requirements, the carbonization chamber space is meshed in a spatial rectangular coordinate system to determine the coordinates (x, y, y) of all grid points. j y j , z j The preset precision requirement for the grid is (△x, △y, △z). For a given grid point, calculate its spatial distance to all feature points. The spatial distance between the grid point and each feature point is... The influence weight of temperature at each feature point is assigned according to the inverse distance weighting method, and the weight is... ,in, , p The temperature value of a grid point is determined by a weighted sum of the temperatures of all feature points, where the sum is the distance power. ,in, n The total number of feature points. Let be the temperature of the i-th feature point. Correlate the coordinates of all grid points with their corresponding temperature values ​​to determine the three-dimensional temperature field of the carbonization chamber.

[0031] For example, a carbonization chamber is 12 meters long, 0.6 meters wide, and 5 meters high. The origin of the spatial rectangular coordinate system is (0, 0, 0) with the vertex at the bottom left end of the carbonization chamber as the origin. The X-axis extends along the length direction, 0≤x≤12, the Y-axis extends along the width direction, 0≤y≤0.6, and the Z-axis extends along the height direction, 0≤z≤5.

[0032] The coordinates of the five selected feature points are A(3, 0.15, 1.25), B(9, 0.15, 1.25), C(3, 0.45, 3.75), D(9, 0.45, 3.75), and E(6, 0.3, 2.5). The temperatures of the five feature points are 750℃, 760℃, 740℃, 720℃, and 735℃, respectively. The preset accuracy requirements for mesh generation are Δx = 1, Δy = 0.1, and Δz = 0.5. The total number of mesh points after generation is 13 × 7 × 11 = 1001.

[0033] This example uses grid point F (6, 0.3, 2) as an example. The spatial distance and corresponding weight between grid point F and each feature point are calculated, thus determining the total weight to be 4.374. Based on the temperature of each feature point, its corresponding weight, and the total weight, the temperature of the grid point is determined to be approximately 736℃. The temperature value of each grid point is determined based on the coordinates of the 1001 grid points and each feature point, thereby determining the three-dimensional temperature field of the carbonization chamber.

[0034] In one embodiment of this application, controlling the degree of coking at the center of the coke cake based on a temperature change trend curve and a target temperature range at the center of the coke cake includes: The temperature change trend curve is updated according to a preset time interval to determine the temperature value at the center of the cake and the rate of temperature change. If the temperature at the center of the coke cake is within the first target temperature range and the rate of temperature change is less than or equal to the first rate of change, then the dynamic working condition of the temperature at the center of the coke cake is determined to be a stable state. If the temperature at the center of the coke cake is within the second target temperature range, or the rate of temperature change is greater than the second rate of change, then the dynamic condition of the temperature at the center of the coke cake is determined to be a fluctuating state. If the temperature at the center of the coke cake is within the third target temperature range, or the rate of temperature change is greater than the second rate of change, then the dynamic operating condition of the coke cake center temperature is determined to be abnormal. The degree of coking at the center of the coke cake is controlled based on the dynamic operating conditions of the coke cake center temperature.

[0035] In this embodiment, based on the latest predicted temperature value at the center of the burnt cake, the temperature change trend curve is updated according to a preset time interval (e.g., 1 hour), and the current temperature value T1 and the rate of temperature change are determined. v The rate of temperature change is ,in, T 2 represents the temperature at the previous moment. The time interval is defined as follows: In this embodiment, the first target temperature range is the ideal range for coke cake maturation, with a temperature of 950-1000℃; the second target temperature range is the range where the coke cake is nearing maturity but fluctuates, with a temperature of 900-950℃ or 1000-1050℃; the third target temperature range is the range where the coke cake is abnormal (under-coated or over-coated), with a temperature below 900℃ or above 1050℃. The first rate of change set in this embodiment... v 1 represents the maximum permissible rate in a steady state, for example... v 1≤5℃ / h, second rate of change v 2 represents the trigger rate for fluctuations or abnormal states, for example... v2 > 10℃ / h. The dynamic operating condition is determined based on the temperature value at the center of the coke cake and the rate of temperature change, and the degree of coking at the center of the coke cake is controlled accordingly. If the current operating condition is stable, the current parameters are maintained to preserve the coking rhythm; if the current operating condition is fluctuating, the parameters are fine-tuned (e.g., slightly increasing or decreasing the gas flow rate) to suppress fluctuations; if the current operating condition is abnormal, the parameters are urgently adjusted (e.g., significantly increasing or decreasing the gas flow rate, advancing or delaying coking) to correct deviations.

[0036] This embodiment can respond promptly to abnormal conditions at the center of the coke cake, adjust the gas flow rate accordingly to reduce production risks, accurately control coking quality and improve product stability, and optimize energy consumption by adjusting the gas flow rate according to the temperature at the center of the coke cake, thereby achieving energy saving and consumption reduction.

[0037] For example, after 22 hours of coking, the temperature at the center of the coke cake is 945℃, within the second target temperature range. The previous temperature was 938℃, and the rate of change is 7℃ / h, which is less than the second rate of change. At this point, the operating condition at the center of the coke cake is fluctuating, and the gas flow rate can be slightly increased to enhance the heating intensity. After 24 hours of coking, the temperature at the center of the coke cake is 1010℃, within the second target temperature range. The previous temperature was 990℃, and the rate of change is 20℃ / h, which is greater than the second rate of change. At this point, the operating condition at the center of the coke cake is also fluctuating, and the gas flow rate can be slightly reduced to decrease the heating intensity and suppress the temperature rise.

[0038] In one embodiment of this application, a temperature correlation model between the fire channel and the carbonization chamber is constructed based on the actual temperature of the fire channel and the historical temperature of the carbonization chamber, including: Obtain historical temperature data of the carbonization chamber and match the actual temperature of the fire channel with the historical temperature data of the carbonization chamber according to the time dimension; Based on the matched temperature data of the fire channel and the carbonization chamber, correlation analysis was used to screen the fire channel temperature features related to the carbonization chamber temperature, and a temperature correlation model between the fire channel and the carbonization chamber was constructed.

[0039] In this embodiment, historical temperature data of the carbonization chamber is collected, including the temperature of the coke cake center and the temperature of the carbonization chamber furnace wall at different coking stages. Corresponding timestamps are recorded to ensure the continuity of the data time series between the actual temperature of the fire channel and the historical temperature of the carbonization chamber. The fire channel temperature data and the carbonization chamber temperature data are aligned by time (matching temperature data from the same minute or hour) to form a time series dataset of fire channel temperature and carbonization chamber temperature. Based on the matched dataset, correlation analysis is used to calculate the correlation coefficient between the temperature characteristics of each fire channel and the carbonization chamber temperature, with a preset threshold of 0.8. If the correlation coefficient is greater than or equal to the preset threshold, it is determined that there is a correlation between the fire channel temperature and the carbonization chamber temperature; if the correlation coefficient is less than the preset threshold, it is determined that there is no correlation between the fire channel temperature and the carbonization chamber temperature. Data pairs with correlated characteristics are used as input data for the temperature correlation model. The input data is divided into a training set and a test set according to a preset ratio, which can be 7:3. The temperature correlation model is optimized through training to ensure that the prediction error of the temperature correlation model for the carbonization chamber temperature is less than or equal to 5℃.

[0040] In one embodiment of this application, based on the matched temperature data of the fire channel and the carbonization chamber, a correlation analysis method is used to screen the fire channel temperature features related to the carbonization chamber temperature, and a temperature correlation model between the fire channel and the carbonization chamber is constructed, including: The dataset was determined based on the matched temperature data of the fire channel and carbonization chamber. Based on the time sequence, the dataset is divided into a training set and a validation set according to a preset ratio. An initial temperature correlation model is trained based on the training set and tested using the validation set. If the deviation between the temperature of the carbonization chamber predicted by the initial temperature correlation model and the actual temperature is within a preset range, then the initial temperature correlation model is determined as the temperature correlation model.

[0041] In this embodiment, a structured dataset is constructed based on the time-matched temperature data of the fire channels and carbonization chambers. The input features are the temperature parameters of each fire channel, and the output label is the carbonization chamber temperature at the corresponding time. In this embodiment, the preset ratio is 7:3; the dataset is divided into a training set and a validation set in a 7:3 ratio according to time sequence. Multiple linear regression, random forest, or long short-term memory neural network can be selected as the initial temperature correlation model. The training set is used to fit the parameters and learn the mapping relationship between the fire channel temperature and the carbonization chamber temperature. The validation set is used to thoroughly analyze the initial temperature correlation model and determine the temperature deviation between the predicted and actual temperatures. If the temperature deviation is within a preset range (e.g., mean absolute error ≤ 5℃), the initial temperature correlation model is used as the final temperature correlation model. If the temperature deviation exceeds the range, the model structure needs to be adjusted (e.g., increasing feature dimensions, changing the algorithm) or features need to be re-selected, and training and validation repeated until the target is met.

[0042] Corresponding to the temperature control method of the coke oven straight-line temperature measuring robot in the above embodiment, Figure 2 This is a structural block diagram of a coke oven linear temperature measurement robot temperature control system provided in one embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 2 The temperature control system 20 of the coke oven straight-line temperature measurement robot includes: a fire channel temperature acquisition module 21, a model construction module 22, and a coking degree control module 23.

[0043] Among them, the fire channel temperature acquisition module 21 is used to acquire the actual temperature of the fire channel based on the coke oven straight-line temperature measurement robot; Model building module 22 is used to build a temperature correlation model between the fire channel and the carbonization chamber based on the actual temperature of the fire channel and the historical temperature of the carbonization chamber. The coking degree control module 23 is used to determine the mapping relationship between the three-dimensional temperature field of the carbonization chamber and the temperature at the center of the coke cake according to the temperature correlation model, and to control the coking degree at the center of the coke cake according to the mapping relationship.

[0044] In one embodiment of this application, the coking degree control module 23 is specifically used to determine the temperature of the grid points in the carbonization chamber according to the temperature correlation model, and to determine the three-dimensional temperature field of the carbonization chamber based on the temperature of the grid points according to the inverse distance weighting method. Based on the three-dimensional temperature field of the carbonization chamber, at least one feature point uniformly distributed in the carbonization chamber is selected, and the temperature of the coke cake center and the corresponding temperature field data of each feature point in the three-dimensional temperature field of the carbonization chamber at different coking stages are obtained. A sample library is established, and the mapping relationship between the three-dimensional temperature field of the carbonization chamber and the temperature of the coke cake center is determined based on the sample library and the backpropagation neural network. Based on the mapping relationship, the predicted temperature value of the center of the cake is determined, and a temperature change trend curve is generated. The degree of coking at the center of the coke cake is controlled based on the temperature change trend curve and the target temperature range at the center of the coke cake.

[0045] In one embodiment of this application, before determining the three-dimensional temperature field of the carbonization chamber based on the temperature of the grid points using the inverse distance weighting method, the coke oven linear temperature measurement robot temperature control system 20 further includes a grid point determination module. The grid point determination module is used to construct a spatial rectangular coordinate system based on the three-dimensional physical boundary parameters of the carbonization chamber and determine the coordinates of each feature point. Based on the temperature correlation model, determine the coordinates of each feature point and record the temperature value corresponding to each feature point; A three-dimensional mesh is divided according to a preset precision to form a set of mesh points.

[0046] In one embodiment of this application, the coking degree control module 23 is further configured to determine the temperature value of each grid point based on the inverse distance weighting method and the temperature value of each grid point; The three-dimensional temperature field of the carbonization chamber is determined based on the temperature value of each grid point.

[0047] In one embodiment of this application, the coking degree control module 23 is further configured to determine the straight-line distance between the coordinates of each grid point and each feature point; The weight of each grid point is determined based on the straight-line distance between the coordinates of each grid point and each feature point. The temperature value of each grid point is determined based on its weight.

[0048] In one embodiment of this application, the coking degree control module 23 is further configured to update the temperature change trend curve according to a preset time interval, and determine the temperature value and temperature change rate at the center of the coke cake. If the temperature at the center of the coke cake is within the first target temperature range and the rate of temperature change is less than or equal to the first rate of change, then the dynamic working condition of the temperature at the center of the coke cake is determined to be a stable state. If the temperature at the center of the coke cake is within the second target temperature range, or the rate of temperature change is greater than the second rate of change, then the dynamic condition of the temperature at the center of the coke cake is determined to be a fluctuating state. If the temperature at the center of the coke cake is within the third target temperature range, or the rate of temperature change is greater than the second rate of change, then the dynamic operating condition of the temperature at the center of the coke cake is determined to be an abnormal state. The degree of coking at the center of the coke cake is controlled based on the dynamic operating conditions of the coke cake center temperature.

[0049] In one embodiment of this application, the model building module 22 is further used to obtain historical temperature data of the carbonization chamber and match the actual temperature of the fire channel with the historical temperature data of the carbonization chamber according to the time dimension. Based on the matched temperature data of the fire channel and the carbonization chamber, correlation analysis was used to screen the fire channel temperature features related to the carbonization chamber temperature, and a temperature correlation model between the fire channel and the carbonization chamber was constructed.

[0050] In one embodiment of this application, the model building module 22 is further used to determine the dataset based on the matched fire channel and carbonization chamber temperature data; Based on the time sequence, the dataset is divided into a training set and a validation set according to a preset ratio. An initial temperature correlation model is trained based on the training set and tested using the validation set. If the deviation between the temperature of the carbonization chamber predicted by the initial temperature correlation model and the actual temperature is within a preset range, then the initial temperature correlation model is determined as the temperature correlation model.

[0051] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of the modules in the aforementioned system embodiments, for example... Figure 2 The functions of the fire channel temperature acquisition module 21, model construction module 22, and coking degree control module 23 are shown.

[0052] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0053] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0054] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store information on the actual temperature of the flue, the mapping relationship between the three-dimensional temperature field of the carbonization chamber and the center temperature of the coke cake.

[0055] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation method described in the temperature control method of the coke oven straight-line temperature measuring robot provided in the embodiments of this application, or they can execute the implementation method of the electronic device described in the embodiments of this application, which will not be repeated here.

[0056] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to implement these processes. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or system capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0057] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., provided on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0058] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0059] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0060] In the embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules, units, or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or modules, or it may be an electrical, mechanical, or other form of connection.

[0061] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules / units. Some or all of the modules can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0062] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The integrated modules / units described above can be implemented in hardware or in the form of software functional modules / units.

[0063] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A temperature measurement control method for a coke oven linear temperature measurement robot, characterized in that, include: The actual temperature of the fire channel is obtained from the coke oven straight-line temperature measuring robot; A temperature correlation model between the fire channel and the carbonization chamber is constructed based on the actual temperature of the fire channel and the historical temperature of the carbonization chamber. The mapping relationship between the three-dimensional temperature field of the carbonization chamber and the temperature at the center of the coke cake is determined based on the temperature correlation model, and the degree of coking at the center of the coke cake is controlled based on the mapping relationship.

2. The temperature measurement and control method of the coke oven straight-line temperature measurement robot as described in claim 1, characterized in that, The step of determining the mapping relationship between the three-dimensional temperature field of the carbonization chamber and the temperature at the center of the coke cake based on the temperature correlation model, and controlling the degree of coking at the center of the coke cake based on the mapping relationship, includes: The temperature of the grid points in the carbonization chamber is determined based on the temperature correlation model, and the three-dimensional temperature field of the carbonization chamber is determined based on the temperature of the grid points using the inverse distance weighting method. Based on the three-dimensional temperature field of the carbonization chamber, at least one feature point uniformly distributed within the carbonization chamber is selected. The temperature of the coke cake center and the corresponding temperature field data of each feature point in the three-dimensional temperature field of the carbonization chamber at different coking stages are obtained. A sample library is established. Based on the sample library and the backpropagation neural network, the mapping relationship between the three-dimensional temperature field of the carbonization chamber and the temperature of the coke cake center is determined. Based on the mapping relationship, the predicted temperature value of the center of the cake is determined, and a temperature change trend curve is generated. The degree of coking at the center of the coke cake is controlled based on the temperature change trend curve and the target temperature range at the center of the coke cake.

3. The temperature measurement and control method of the coke oven straight-line temperature measuring robot as described in claim 2, characterized in that, Before determining the three-dimensional temperature field of the carbonization chamber based on the temperature of the grid points using the inverse distance weighting method, the method further includes: A spatial rectangular coordinate system is constructed based on the three-dimensional physical boundary parameters of the carbonization chamber to determine the coordinates of each feature point; Based on the temperature correlation model, determine the coordinates of each feature point and record the temperature value corresponding to each feature point; A three-dimensional mesh is divided according to a preset precision to form a set of mesh points; The determination of the three-dimensional temperature field of the carbonization chamber based on the inverse distance weighting method includes: Based on the inverse distance weighting method, the temperature value of each grid point is determined according to the temperature value of each grid point; The three-dimensional temperature field of the carbonization chamber is determined based on the temperature value of each grid point.

4. The temperature measurement and control method of the coke oven straight-line temperature measurement robot as described in claim 3, characterized in that, The method based on inverse distance weighting, which determines the temperature value of each grid point according to the temperature value of each grid point, includes: Determine the straight-line distance between the coordinates of each grid point and each feature point; The weight of each grid point is determined based on the straight-line distance between the coordinates of each grid point and each feature point. The temperature value of each grid point is determined based on its weight.

5. The temperature measurement and control method for the coke oven straight-line temperature measuring robot as described in claim 2, characterized in that, The step of controlling the degree of coking at the center of the coke cake based on the temperature change trend curve and the target temperature range at the center of the coke cake includes: The temperature change trend curve is updated according to a preset time interval to determine the temperature value at the center of the cake and the rate of temperature change. If the temperature value at the center of the coke cake is within the first target temperature range, and the rate of temperature change is less than or equal to the first rate of change, then the dynamic working condition of the temperature at the center of the coke cake is determined to be a stable state. If the temperature value at the center of the coke cake is within the second target temperature range, or if the rate of temperature change is greater than the second rate of change, then the dynamic working condition of the temperature at the center of the coke cake is determined to be a fluctuating state. If the temperature value at the center of the coke cake is within the third target temperature range, or if the rate of temperature change is greater than the second rate of change, then the dynamic operating condition of the temperature at the center of the coke cake is determined to be an abnormal state. The degree of coking at the center of the coke cake is controlled based on the dynamic operating conditions of the coke cake center temperature.

6. The temperature measurement and control method for the coke oven straight-line temperature measuring robot as described in claim 1, characterized in that, The step of constructing a temperature correlation model between the fire channel and the carbonization chamber based on the actual temperature of the fire channel and the historical temperature of the carbonization chamber includes: Obtain historical temperature data of the carbonization chamber, and match the actual temperature of the fire channel with the historical temperature data of the carbonization chamber according to the time dimension; Based on the matched temperature data of the fire channel and the carbonization chamber, correlation analysis was used to screen the fire channel temperature features related to the carbonization chamber temperature, and a temperature correlation model between the fire channel and the carbonization chamber was constructed.

7. The temperature measurement and control method for a coke oven straight-line temperature measuring robot as described in claim 6, characterized in that, Based on the matched flue and carbonization chamber temperature data, correlation analysis is used to screen flue temperature features related to the carbonization chamber temperature, and a temperature correlation model between the flue and the carbonization chamber is constructed, including: The dataset is determined based on the matched temperature data of the fire channel and carbonization chamber. Based on the time sequence, the dataset is divided into a training set and a validation set according to a preset ratio. An initial temperature correlation model is trained based on the training set and tested using the validation set. If the deviation between the temperature of the carbonization chamber predicted by the initial temperature correlation model and the actual temperature is within a preset range, then the initial temperature correlation model is determined as the temperature correlation model.

8. A temperature measurement and control system for a coke oven linear temperature measurement robot, characterized in that, include: The flue temperature acquisition module is used to obtain the actual temperature of the flue based on the coke oven straight-line temperature measuring robot; The model building module is used to build a temperature correlation model between the fire channel and the carbonization chamber based on the actual temperature of the fire channel and the historical temperature of the carbonization chamber. The coking degree control module is used to determine the mapping relationship between the three-dimensional temperature field of the carbonization chamber and the temperature at the center of the coke cake according to the temperature correlation model, and to control the coking degree at the center of the coke cake according to the mapping relationship.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images