Coke cake temperature detection method and system, equipment and storage medium

Abstract

The invention provides a coke cake temperature detection method and system, equipment and a storage medium, and belongs to the technical field of coking production process detection.The method comprises the steps that infrared image data of a coke cake is obtained, and first temperature data is obtained through calculation according to the infrared image data; constructing a heat transfer model according to the material thermophysical parameters of the coke cake, the first temperature data and the furnace temperature data of the coke oven, and calculating second temperature data of the coke cake based on the heat transfer model; and performing weighted fusion on the first temperature data and the second temperature data to obtain target temperature data. According to the coke cake temperature detection method and system, the equipment and the storage medium provided by the invention, the accuracy of acquiring the coke cake temperature information is improved.

Description

Technical Field

[0001] The present application belongs to the field of coking production process detection technology, and more specifically, relates to a coke cake temperature detection method and system, equipment, and storage medium. Background Art

[0002] In modern coking production, coke cake temperature is a key indicator of coke quality and production efficiency. Traditional coke cake temperature measurement methods have many limitations. For example, contact temperature measurement can interfere with the coking process and easily damage the temperature measurement equipment. Infrared temperature measurement only measures the surface temperature of the coke cake, failing to reflect the actual temperature inside the coke cake. Therefore, this method cannot accurately reflect the coke cake temperature.

[0003] As the coking industry's requirements for product quality and production stability continue to increase, there is an urgent need for a detection method that can accurately obtain coke cake temperature information. Summary of the Invention

[0004] The purpose of this application is to provide a coke cake temperature detection method and system, equipment, and storage medium to improve the accuracy of obtaining coke cake temperature information.

[0005] A first aspect of an embodiment of the present application provides a coke cake temperature detection method, comprising: Acquire infrared image data of the coke cake, and calculate first temperature data based on the infrared image data; constructing a heat transfer model according to the material thermophysical property parameters of the coke cake, the first temperature data, and the furnace temperature data of the coke oven, and calculating the second temperature data of the coke cake based on the heat transfer model; The first temperature data and the second temperature data are weightedly fused to obtain target temperature data.

[0006] A second aspect of an embodiment of the present application provides a coke cake temperature detection system, comprising: an infrared module, configured to obtain infrared image data of the coke cake and calculate first temperature data based on the infrared image data; a heat transfer module, configured to construct a heat transfer model according to the material thermophysical properties of the coke cake, the first temperature data, and the temperature data of the coke oven, and calculate the second temperature data of the coke cake based on the heat transfer model; The target module is used to perform weighted fusion on the first temperature data and the second temperature data to obtain target temperature data.

[0007] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned coke cake temperature detection method when executing the computer program.

[0008] According to a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned coke cake temperature detection method are implemented.

[0009] The beneficial effects of the coke cake temperature detection method, system, equipment, and storage medium provided in the embodiments of the present application are: the present application calculates the first temperature data by obtaining the infrared image data of the coke cake, and constructs a heat transfer model based on the thermal physical properties and boundary conditions of the coke cake material to obtain the second temperature data. The surface temperature and internal temperature of the coke cake can be processed to obtain accurate data that can reflect the coke cake temperature, thereby improving the accuracy of coke cake temperature detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0011] Figure 1 A schematic flow chart of a coke cake temperature detection method according to an embodiment of the present application; Figure 2 This is a structural block diagram of a coke cake temperature detection system provided in one embodiment of the present application; Figure 3 A schematic block diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0013] In order to make the purpose, technical solutions and advantages of this application clearer, specific embodiments will be described below with reference to the accompanying drawings.

[0014] Please refer to Figure 1 , Figure 1 This is a flow chart of a coke cake temperature detection method provided in one embodiment of the present application, the method comprising: S101: Acquire infrared image data of the coke cake, and calculate first temperature data based on the infrared image data.

[0015] In this embodiment, an infrared thermal imager is used to capture infrared image data of the coke cake. The operating wavelength of the infrared thermal imager covers the primary infrared wavelength range emitted by the coke cake surface, enabling accurate capture of infrared radiation information from the coke cake surface. To protect the infrared thermal imager from the harsh environment of the coke oven, such as high temperatures and dust, the camera is equipped with a dedicated high-temperature and dust-proof protective cover.

[0016] The infrared thermal imager captures an infrared image of the focus cake at a set sampling frequency. Before calculating the first temperature data based on the infrared image data, this embodiment also performs a preprocessing operation on the captured infrared image data. The preprocessing operation includes: using a filtering algorithm (such as a median filter or a Gaussian filter) to remove salt and pepper noise and Gaussian noise in the image; and performing image enhancement processing on the denoised infrared image data to obtain enhanced infrared image data.

[0017] In this embodiment, the principle of calculating the first temperature data based on the infrared image data includes: Based on Planck's law, a quantitative relationship between infrared radiation intensity and temperature is established; For the collected infrared image, the gray value of each pixel corresponds to the infrared radiation intensity of that point. According to known calibration parameters of the infrared thermal imager (including emissivity, atmospheric transmittance, etc.), the pixel grayscale value is converted into an actual temperature value to obtain a first temperature data distribution on the coke cake surface.

[0018] This embodiment can also make corresponding corrections based on the impact of environmental factors (such as ambient temperature, ambient humidity, etc.) on infrared radiation to improve the accuracy of temperature calculation.

[0019] S102: constructing a heat transfer model according to the material thermophysical property parameters of the coke cake, the first temperature data and the oven temperature data of the coke oven, and calculating the second temperature data of the coke cake based on the heat transfer model.

[0020] In this embodiment, the coke cake material thermophysical parameters include thermal conductivity, specific heat capacity, and density. These material thermophysical parameters vary with factors such as the coke cake's composition and temperature. To accurately determine these material thermophysical parameters, experimental measurements can be performed on coke cake samples of varying composition at different temperatures. Furthermore, a database of coke cake thermophysical parameters varying with temperature and composition is established based on relevant literature and industrial experience.

[0021] In this embodiment, the finite element method or the finite difference method is used to construct a heat transfer model of the coke cake. The coke cake is regarded as a three-dimensional heat transfer body, and a grid is divided according to its shape and size. The accuracy of the grid needs to be set according to the calculation accuracy requirements. The heat transfer modes in the heat transfer model include: heat conduction inside the coke cake, heat convection between the coke cake and the coke oven wall, and heat radiation. Among them, for heat conduction, the heat conduction equation is established according to Fourier's law; for heat convection, the Newton cooling formula is used to calculate the convective heat exchange between the coke cake surface and the gas in the furnace; for heat radiation, the radiation heat exchange between the coke cake surface and the surrounding objects is calculated according to the Stefan-Boltzmann law; this embodiment combines the heat transfer modes of these three heat transfer models when constructing the heat transfer model.

[0022] In this embodiment, temperature sensors installed at various locations within the coke oven (e.g., the roof, walls, and floor) collect real-time coke oven temperature data. This embodiment performs spatial interpolation on this collected temperature data to determine the temperature distribution within the entire coke oven. This temperature distribution serves as the external ambient temperature boundary condition for the heat transfer model, simulating the effects of the high temperature environment within the coke oven on the heat transfer of the coke cake. This embodiment utilizes numerical calculation methods to solve the constructed heat transfer model and calculate the second temperature data within the coke cake.

[0023] S103: Perform weighted fusion on the first temperature data and the second temperature data to obtain target temperature data.

[0024] In this embodiment, a method based on error analysis and adaptive adjustment can be used to perform weighted fusion of the first temperature data and the second temperature data to obtain target temperature data. This embodiment analyzes the error between the first temperature data and the second temperature data under different operating conditions through historical data and actual measurement data. For example, indicators such as the mean square error and mean absolute error between the two temperature data and the actual true temperature can be calculated. Then, based on the error analysis results, a functional relationship between the weight and the operating condition parameters is established. For example, in the early stage of coking of the coke cake, the infrared image reflects the surface temperature of the coke cake, while the heat transfer model's prediction of the internal temperature is relatively inaccurate. At this time, the weight of the first temperature data can be increased; when the coke cake is close to maturity, the heat transfer model can more accurately obtain the internal temperature of the coke cake, and the weight of the second temperature data can be increased accordingly. In addition, a machine learning algorithm can be used to automatically learn the weight distribution under different operating conditions by training on a large amount of historical data.

[0025] In this embodiment, for each location on the coke cake surface, the first temperature data at that location is multiplied by its corresponding weight, and the second temperature data is multiplied by its corresponding weight. The two weighted temperature data are then added together to obtain the target temperature data for that location. This weighted approach combines the real-time performance and surface temperature accuracy of infrared temperature measurement with the advantages of internal temperature prediction using heat transfer models, resulting in more accurate coke cake temperature data.

[0026] This embodiment can also verify the fused target temperature data by comparing it with other independent temperature measurement methods (such as invasive temperature measurement performed under safe conditions) to evaluate the accuracy and reliability of the target temperature data; based on the verification results, the weights of the weighted fusion are adjusted to improve detection accuracy and stability.

[0027] From the above, it can be concluded that the present application calculates the first temperature data by obtaining the infrared image data of the coke cake, and constructs a heat transfer model based on the thermal physical properties and boundary conditions of the coke cake material to obtain the second temperature data. The surface temperature and internal temperature of the coke cake can be processed to obtain accurate data that can reflect the coke cake temperature, thereby improving the accuracy of coke cake temperature detection.

[0028] In one embodiment of the present application, calculating the first temperature data based on the infrared image data includes: Performing noise reduction processing on the infrared image data to obtain target infrared image data; Convert target infrared image data into radiation intensity data; The first temperature data is calculated based on the radiation intensity data and Blanck's law.

[0029] In this embodiment, during the process of acquiring infrared image data of the coke cake, noise is generated from many aspects. On the one hand, the electronic components of the infrared thermal imager itself generate thermal noise during operation. On the other hand, the complex environment inside the coke oven is also an important source of noise, such as the flow of high-temperature gas and the scattering of dust, which lead to blurring, speckling and other noise in the image.

[0030] In order to effectively remove these noises, this embodiment adopts multiple noise reduction algorithms. Among them, for Gaussian noise, a Gaussian filtering algorithm is adopted; by performing weighted averaging on the pixel values of each pixel point in the image and its neighborhood, the image is smoothed and the impact of noise is reduced; the weights are distributed according to the Gaussian function, and the closer the pixel is to the center pixel, the greater the weight; for salt and pepper noise, a median filter is adopted; the pixel values in the neighborhood of each pixel point are sorted, and then the value of the pixel point is replaced by the median value to remove isolated bright spots or dark spots; in order to further improve the noise reduction effect, this embodiment can also adopt an adaptive filtering algorithm to automatically adjust the filtering parameters according to the local features of the image. For example, in the edge area of the image, the smoothness of the filter is reduced to retain the detailed information of the image.

[0031] This embodiment can also evaluate the noise reduction effect after completing the noise reduction process; using objective indicators such as peak signal-to-noise ratio and structural similarity index; the peak signal-to-noise ratio reflects the degree of error between the original image and the noise-reduced image, and the higher the value, the better the noise reduction effect; the structural similarity index represents the similarity between the two images in terms of brightness, contrast and structure, and the closer it is to 1, the more visually similar the noise-reduced image is to the original image, and more image information is retained; at the same time, subjective visual evaluation can also be combined, and professionals can observe the noise-reduced image to determine whether the expected noise reduction effect has been achieved and whether the key features of the burnt cake surface have been retained.

[0032] The output of the infrared thermal imager used in this embodiment is a grayscale image related to infrared radiation. However, to convert this into radiation intensity data, the thermal imager must first be calibrated. The calibration process includes determining the thermal imager's response function, which is the quantitative relationship between grayscale value and radiation intensity. After calibration, the radiation intensity corresponding to each pixel in the target infrared image can be calculated based on its grayscale value and the calibrated response function. Because the infrared radiation from the coke surface may be affected by atmospheric absorption and scattering, the calculated radiation intensity also needs to be atmospherically corrected. Atmospheric correction can be performed using the atmospheric transmission model (Moderate Resolution Transmittance, MODTRAN) by inputting local atmospheric parameters and observation geometry information into the atmospheric transmission model to calculate the atmospheric attenuation coefficient of radiation, thereby correcting the radiation intensity and obtaining more accurate actual radiation intensity data from the coke surface.

[0033] This example uses Planck's law, which describes the relationship between the spectral radiant emittance of a blackbody and wavelength at different temperatures. In practical applications, since the coke cake is not an ideal blackbody, the actual radiant intensity must be calculated based on its emissivity. Given the radiant intensity data and Planck's law, the corresponding temperature can be calculated numerically. However, Planck's law is a nonlinear equation, making it difficult to directly solve for the temperature. Instead, an iterative method or a lookup table can be used.

[0034] In one embodiment of the present application, performing noise reduction processing on infrared image data to obtain target infrared image data includes: determining a first Gaussian kernel based on the resolution of the infrared image data; Determine the target standard deviation based on the noise intensity and noise suppression coefficient of the infrared image data; Adjust the first Gaussian kernel based on the target standard deviation to obtain the target Gaussian kernel; The infrared image data is denoised based on the target Gaussian kernel to obtain the target infrared image data.

[0035] In this embodiment, high-resolution infrared image data can capture more details, such as the distribution of tiny temperature differences on the surface of the coke cake; while low-resolution infrared image data is relatively blurred and has less detailed information; images of different resolutions have different requirements for the size of the Gaussian kernel when performing noise reduction processing.

[0036] Therefore, the higher the resolution, the richer the details in the image. To avoid excessive blurring of these details during the noise reduction process, a smaller Gaussian kernel should be selected. Conversely, low-resolution images, which have fewer details, can be more effectively denoised using a larger Gaussian kernel. This embodiment can also determine the first Gaussian kernel by establishing an empirical formula for the relationship between resolution and Gaussian kernel size.

[0037] In this embodiment, the target standard deviation can be calculated based on the noise intensity and the noise suppression coefficient. Noise intensity is a measure of the severity of noise in an infrared image. The noise intensity can be assessed by calculating the local variance of the image. Specifically, the image is divided into several small regions, the variance of the pixel values within each region is calculated, and the average of these variances is taken as the estimated noise intensity of the image. The noise suppression coefficient is a user-adjustable parameter that reflects the user's desired degree of noise removal. A larger value for this coefficient indicates a greater desire to remove noise, but this may also result in a greater loss of image detail. Conversely, a smaller value for this coefficient preserves more image detail, but the noise removal effect may be poorer. For images with high noise content and low detail requirements, a larger noise suppression coefficient can be selected. For images with low noise content and a high degree of detail that needs to be preserved, a smaller noise suppression coefficient can be selected.

[0038] In this embodiment, infrared image data is denoised by convolving a target Gaussian kernel with the image. Convolution is a linear operation that involves sliding the Gaussian kernel point by point across the image. At each position, the kernel's elements are multiplied by the image pixel values at the corresponding position, and these products are then summed to obtain a new pixel value. In this embodiment, when performing the convolution operation on the infrared image data, the infrared image's boundaries are also addressed to reduce distortion at these boundaries. This is because at these boundaries, the Gaussian kernel would extend beyond the image's bounds. Therefore, after the convolution operation and boundary processing, the resulting image is the denoised target infrared image data.

[0039] Through the above steps, this embodiment can adjust the Gaussian kernel according to the resolution, noise intensity and user needs of the infrared image data to achieve more effective noise reduction processing on the infrared image data.

[0040] In one embodiment of the present application, performing weighted fusion on the first temperature data and the second temperature data to obtain the target temperature includes: In response to the first temperature data being greater than a first temperature threshold, adjusting the first weight reference value based on the first weight adjustment step length to obtain a first weight; and adjusting the second weight reference value based on the first weight adjustment step length to obtain a second weight; Performing weighted calculation based on the first weight, the second weight, the first temperature data, and the second temperature data to obtain target temperature data; The first weight is a weight corresponding to the first temperature data, the second weight is a weight corresponding to the second temperature data, and the adjustment directions of the first weight reference value and the second weight reference value are different; In response to the first temperature data being less than or equal to a first temperature threshold, performing a weighted calculation based on a first weight reference value, a second weight reference value, the first temperature data, and the second temperature data to obtain target temperature data; The first weight reference value is a weight corresponding to the first temperature data, and the second weight reference value is a weight corresponding to the second temperature data.

[0041] In this embodiment, the setting of the first temperature threshold is based on experience and needs to be combined with the process requirements and actual experience of coke cake production. For example, in different coking stages of coke cake, its normal temperature range is different. If the coke cake temperature is generally low in the early stage of coking, the first temperature threshold set at this time may be relatively low; and near the end of coking, the coke cake temperature will rise, and the first temperature threshold should also be increased accordingly. By analyzing a large amount of historical production data, the temperature distribution in different stages can be statistically calculated, and then a reasonable first temperature threshold can be determined according to the process requirements. For example, after analysis, it was found that in a certain specific coking stage, the normal temperature of the coke cake is mostly between 800-1000℃, then the first temperature threshold can be set to 1000℃.

[0042] In this embodiment, the initial settings of the first and second weight reference values must be determined before weighted fusion begins. These two initial values must also be set based on actual conditions. If the first temperature data obtained from infrared image measurement is generally accurate and reliable, the first weight reference value can be set relatively large. Conversely, if the second temperature data calculated from the heat transfer model is more accurate, the second weight reference value can be set larger.

[0043] In this embodiment, the first weight adjustment step determines the amplitude of the weight adjustment; the size of the first weight adjustment step needs to ensure the adjustment effect while avoiding over-adjustment. This embodiment can dynamically adjust the step size according to the size of the temperature deviation; for example, when the difference between the first temperature data and the first temperature threshold is small, a smaller step size, such as 0.05, is used; when the difference is large, a larger step size, such as 0.1, is used. When the first temperature data is greater than the first temperature threshold, it means that the first temperature data may be abnormal and its weight in weighted fusion needs to be reduced. At this time, the first weight reference value is adjusted based on the first weight adjustment step to obtain the first weight. At the same time, since the adjustment directions of the first weight reference value and the second weight reference value are different, it is necessary to adjust the second weight reference value based on the first weight adjustment step to obtain the second weight.

[0044] This embodiment can also dynamically monitor the weight adjustment process; record the weight and target temperature data after each adjustment in real time, and compare them with the actual process requirements and other reference data; if it is found that the adjusted target temperature data still does not meet expectations, further analysis of the cause is required, and the first temperature threshold or the first weight adjustment step may need to be readjusted. If the first temperature data is continuously greater than the first temperature threshold, or the target temperature data still fluctuates greatly after the weight adjustment, it may indicate an abnormality. At this time, it is necessary to check the infrared image measurement equipment and the heat transfer model to check whether there is equipment failure or inaccurate model parameters. For example, check whether the infrared thermal imager is interfered with, whether the material thermal properties parameters in the heat transfer model need to be updated, etc.

[0045] In this embodiment, the calculation formula of the first weight is:

[0046] in, is the first weight reference value, To adjust the slope (the rate at which the weight changes with temperature), is the first temperature threshold, is the first temperature data, is the first weight.

[0047] In this embodiment, the formula for weighted fusion of the first temperature data and the second temperature data is:

[0048] in, is the target temperature data, is the weight of the first temperature data, i.e., the first weight; is the temperature gradient inside and outside the coke cake (the difference between the value calculated by the heat transfer model and the infrared surface value); is the gradient correction gain coefficient; is the temperature threshold attenuation coefficient; is the first temperature data, is the second temperature data; is the first temperature threshold.

[0049] In one embodiment of the present application, weighted fusion of the first temperature data and the second temperature data to obtain target temperature data includes: obtaining ultrasonic wave propagation data inside the coke cake, and calculating third temperature data based on the ultrasonic wave propagation data and a sound velocity-temperature mapping model; Performing weighted fusion on the second temperature data and the third temperature data to obtain fourth temperature data; The first temperature data and the fourth temperature data are weightedly fused to obtain target temperature data.

[0050] In this embodiment, an ultrasonic detection system is provided to obtain ultrasonic propagation data within the coke cake. The ultrasonic detection system includes an ultrasonic transmitting transducer, a receiving transducer, a signal generator, and a data acquisition device. The signal generator emits an ultrasonic signal, which propagates through the coke cake and is received by the receiving transducer. The data acquisition device records the propagation time from transmission to reception of the ultrasonic signal and other characteristic parameters of the signal. The ultrasonic transmitting and receiving transducers are installed in appropriate positions on the coke oven to ensure that the ultrasonic wave can effectively transmit into and out of the coke cake. For example, a high-temperature coupling agent can be used to fix the transducers to the coke oven wall so that they are in close contact with the coke cake. The signal generator is used to generate an ultrasonic signal of a specific frequency and intensity and transmit it into the coke cake. The data acquisition device is used to record the ultrasonic signal received by the receiving transducer, including information such as the propagation time and amplitude of the signal. The data acquisition device is used to collect ultrasonic data at a set acquisition frequency. The acquisition frequency can be determined based on the speed of coke cake temperature changes. For example, during the rapid heating phase of the coke cake, the acquisition frequency can be set to once per minute. During relatively stable temperature phases, the acquisition frequency can be reduced to once every five minutes.

[0051] In this embodiment, the sound speed-temperature mapping model describes the relationship between the ultrasonic propagation velocity and temperature inside the coke cake; establishing the sound speed-temperature mapping model can measure the ultrasonic propagation velocity of coke cake samples at different temperatures in a laboratory environment; the coke cake samples are heated to different temperature points by a heating device, and then the ultrasonic propagation velocity at each temperature point is measured using an ultrasonic detection system to analyze and fit the experimental data to obtain the sound speed-temperature mapping model; wherein, the sound speed-temperature mapping model can be a linear model v=aT+b, where T is temperature, and a and b are coefficients obtained by fitting the experimental data; or it can be a more complex nonlinear model, such as a polynomial model.

[0052] Based on the collected ultrasonic propagation data, the propagation speed of the ultrasonic wave inside the coke cake is calculated; the known propagation distance of the ultrasonic wave in the coke cake (this distance can be determined based on the installation position of the transducer) and the propagation time are substituted into the sound speed-temperature mapping model according to the sound speed to solve the corresponding temperature value, which is the third temperature data.

[0053] In this embodiment, the second temperature data is calculated based on a heat transfer model, which can be subject to error. The third temperature data is obtained through ultrasonic testing, which directly reflects information about the coke cake's interior. However, ultrasonic propagation can be affected by the uneven structure of the coke cake. Therefore, this embodiment performs a weighted fusion calculation on the second and third temperature data based on the determined weights to obtain the fourth temperature data, which is a more accurate measure of the coke cake's internal temperature. This embodiment determines the weights of the second and third temperature data by statistically analyzing historical data to determine their deviations from the actual temperature. Alternatively, an adaptive method can be used to adjust the weights of the second and third temperature data based on current operating conditions and data quality.

[0054] In this embodiment, for the weighted fusion of the first temperature data and the fourth temperature data, it is also necessary to determine appropriate weights. The first temperature data is obtained by calculating the infrared image and mainly reflects the temperature of the coke cake surface. The fourth temperature data integrates the information of the heat transfer model and ultrasonic detection, and focuses more on the temperature inside the coke cake. The weights can be determined according to the production stage of the coke cake and actual needs. In the early stage of coke cake production, the surface temperature varies greatly, and the first temperature data is more important. The weight of the first temperature data can be set higher, for example, to 0.6; the weight of the fourth temperature data can be set lower, for example, to 0.4. When the coke cake is close to maturity, the internal temperature is more critical. The weight of the fourth temperature data can be set higher, for example, to 0.6; the weight of the first temperature data can be set lower, for example, to 0.4. This embodiment introduces ultrasonic detection data and performs multiple weighted fusions to obtain coke cake temperature information more comprehensively and accurately, providing a more reliable basis for coke oven production control and quality assurance.

[0055] In one embodiment of the present application, the coke cake temperature detection method further includes: inputting the operating condition data of the coke cake into a temperature prediction model to obtain temperature range data; Determine the temperature anomaly result of the coke cake based on the temperature range data and the target temperature data; The temperature prediction model is trained based on historical operating data and the corresponding actual coke cake temperature data.

[0056] In this embodiment, the temperature prediction model is constructed using a large amount of historical operating condition data and corresponding actual coke cake temperature data; the operating condition data includes various operating parameters of the coke oven, such as the heating system (such as heating time, heating intensity), coal loading, coal blending ratio, furnace pressure, ventilation volume, etc.; the corresponding actual coke cake temperature data is obtained through a variety of reliable measurement methods (such as infrared temperature measurement, thermocouple measurement, etc.).

[0057] Before inputting the coke cake operating condition data into the temperature prediction model, this embodiment requires preprocessing the collected data. This includes data cleaning to remove missing and outliers. For example, if the coal loading data at a certain moment shows an obviously unreasonable value, this data point can be removed or filled in using interpolation. The data must also be normalized to bring data of different ranges and magnitudes onto the same scale. This can speed up model training and improve model stability.

[0058] The temperature prediction model of this embodiment can select a suitable machine learning or deep learning model, such as a neural network (such as a multi-layer perceptron, a long short-term memory network, etc.), support vector regression, random forest regression, etc.

[0059] In this embodiment, sensors such as pressure sensors, flow sensors, temperature sensors, etc. can be installed at various key positions of the coke oven to collect working condition data such as heating system, coal loading, furnace pressure, ventilation volume, etc. in real time.

[0060] Input the real-time working condition data into the trained temperature prediction model. Due to various uncertainties in actual production, the model output is not a fixed temperature value, but a temperature range data. The temperature range can be determined by the probability distribution output of the model or based on a certain confidence interval. For example, the temperature range output by the model is [T min ,T max ], indicating that under a certain confidence level, the actual temperature of the coke cake will most likely fall within this range.

[0061] In this embodiment, if the target temperature data is less than the lower limit of the temperature interval or greater than the upper limit, the coke cake temperature is determined to be abnormal. Specifically, when the target temperature data is less than the lower limit of the temperature interval, the coke cake temperature is too low; when the target temperature data is greater than the lower limit of the temperature interval, the coke cake temperature is too high. Determining a coke cake temperature abnormality requires prompt action. If the temperature is too low, the heating system can be checked for proper operation, and the heating intensity or heating time can be increased. If the temperature is too high, the ventilation system can be checked for proper operation, and ventilation volume can be increased to reduce the temperature. Temperature anomaly events are also recorded, including the time of occurrence, the type of anomaly (temperature too high or too low), and the operating data at the time, for subsequent analysis and empirical research to further optimize the temperature prediction model and production process.

[0062] This embodiment uses the temperature prediction model and target temperature data to promptly detect abnormal coke cake temperature, thereby ensuring stable coke oven production and coke quality.

[0063] In one embodiment of the present application, the temperature anomaly result includes a temperature anomaly level; Determine the abnormal temperature results of the coke cake based on the temperature range data and the target temperature data, including: Calculate the deviation between the target temperature data and the boundary value of the temperature interval data; Determine the temperature anomaly level of the coke cake based on the deviation value and anomaly level table.

[0064] In this embodiment, the known temperature interval data is [T min ,T max ], the target temperature data is T; the calculation of the deviation value D needs to be calculated based on the temperature range data: When T ≥ T min And T≤T max When , it means that the target temperature data is within the normal temperature range, and the deviation value D=0.

[0065] When T <T min When the deviation ,The deviation value indicates the degree to which the target temperature is lower than the lower limit of the normal temperature range; When T>T max When the deviation ,The deviation value indicates the degree to which the target temperature is higher than the upper limit of the normal temperature range.

[0066] In this embodiment, developing the abnormality level table requires comprehensive consideration of multiple factors. First, the sensitivity of the coke cake production process to temperature. Different coke cake production processes have varying tolerances for temperature fluctuations. For example, certain high-precision coke cake production processes have extremely stringent temperature requirements, and even small temperature deviations can significantly impact product quality. Meanwhile, some common processes may have a relatively high tolerance for temperature fluctuations. Second, the potential impact of temperature deviations on subsequent production processes and product quality must be considered. Temperature anomalies can cause changes in the physical and chemical properties of the coke cake, affecting indicators such as the strength and wear resistance of the coke, and may also have a knock-on effect on subsequent coking and ironmaking processes.

[0067] Based on the above considerations, this embodiment divides temperature anomalies into different levels, see Table 1. For example, mild anomaly, moderate anomaly, and severe anomaly. More detailed divisions can also be made based on actual needs.

[0068] Table 1 Temperature abnormality level table

[0069] The specific values of D1 and D2 are determined through extensive experimentation and data analysis based on actual production conditions. For example, statistical analysis of historical production data reveals how varying degrees of temperature deviation affect product quality, helping to determine the appropriate dividing line.

[0070] This embodiment can more accurately determine the temperature anomaly level of the coke cake based on the target temperature data and the temperature interval data, and take effective treatment measures to ensure the quality and stability of coke cake production.

[0071] Corresponding to the coke cake temperature detection method of the above embodiment, Figure 2 This is a structural block diagram of a coke cake temperature detection system provided in one embodiment of the present application. For ease of explanation, only the parts related to the embodiment of the present application are shown. Figure 2 The coke cake temperature detection system 20 includes: an infrared module 21, a heat transfer module 22 and a target module 23.

[0072] The infrared module 21 is used to obtain infrared image data of the coke cake and calculate the first temperature data based on the infrared image data; a heat transfer module 22 for constructing a heat transfer model according to the material thermophysical properties of the coke cake, the first temperature data, and the temperature data of the coke oven, and calculating the second temperature data of the coke cake based on the heat transfer model; The target module 23 is used to perform weighted fusion on the first temperature data and the second temperature data to obtain target temperature data.

[0073] In one embodiment of the present application, the infrared module 21 is specifically used to: Performing noise reduction processing on the infrared image data to obtain target infrared image data; Convert target infrared image data into radiation intensity data; The first temperature data is calculated based on the radiation intensity data and Blanck's law.

[0074] In one embodiment of the present application, the infrared module 21 is specifically used to: determining a first Gaussian kernel based on the resolution of the infrared image data; Determine the target standard deviation based on the noise intensity and noise suppression coefficient of the infrared image data; Adjust the first Gaussian kernel based on the target standard deviation to obtain the target Gaussian kernel; The infrared image data is denoised based on the target Gaussian kernel to obtain the target infrared image data.

[0075] In one embodiment of the present application, the target module 23 is specifically configured to: In response to the first temperature data being greater than a first temperature threshold, adjusting the first weight reference value based on the first weight adjustment step length to obtain a first weight; and adjusting the second weight reference value based on the first weight adjustment step length to obtain a second weight; Performing weighted calculation based on the first weight, the second weight, the first temperature data, and the second temperature data to obtain target temperature data; The first weight is a weight corresponding to the first temperature data, the second weight is a weight corresponding to the second temperature data, and the adjustment directions of the first weight reference value and the second weight reference value are different; In response to the first temperature data being less than or equal to the first temperature threshold, a weighted calculation is performed based on the first weight reference value, the second weight reference value, the first temperature data, and the second temperature data to obtain the target temperature data, where the first weight reference value is the weight corresponding to the first temperature data, and the second weight reference value is the weight corresponding to the second temperature data.

[0076] In one embodiment of the present application, the target module 23 is further specifically configured to: Acquiring ultrasonic propagation data inside the coke cake, and calculating third temperature data based on the ultrasonic propagation data and a sound velocity-temperature mapping model; Performing weighted fusion on the second temperature data and the third temperature data to obtain fourth temperature data; The first temperature data and the fourth temperature data are weightedly fused to obtain target temperature data.

[0077] In one embodiment of the present application, the target module 23 is further specifically configured to: Input the working condition data of the coke cake into the temperature prediction model to obtain the temperature range data; Determine the temperature anomaly result of the coke cake based on the temperature range data and the target temperature data; The temperature prediction model is trained based on historical operating data and the corresponding actual coke cake temperature data.

[0078] In one embodiment of the present application, the target module 23 is further specifically configured to: the temperature anomaly result includes a temperature anomaly level; Calculate the deviation between the target temperature data and the boundary value of the temperature interval data; Determine the temperature anomaly level of the coke cake based on the deviation value and anomaly level table.

[0079] See also Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided in one embodiment of the present application. Figure 3 The electronic device 300 in the embodiment shown 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 memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules in the above-mentioned device embodiments, such as Figure 2 The functions of the infrared module 21, the heat transfer module 22 and the target module 23 are shown.

[0080] It should be understood that in the embodiment of the present application, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), 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, etc.

[0081] The input device 302 may include a touchpad, a fingerprint collection sensor (for collecting user fingerprint information and fingerprint direction information), a microphone, etc. The output device 303 may include a display (LCD, etc.), a speaker, etc.

[0082] The memory 304 may include a read-only memory and a random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store device type information.

[0083] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present application can execute the implementation methods described in the first and second embodiments of the coke cake temperature detection method provided in the embodiments of the present application, and can also execute the implementation methods of the electronic device described in the embodiments of the present application, which will not be repeated here.

[0084] In another embodiment of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, all or part of the process of the method in the above embodiment is implemented. The computer program can also be used to instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above method embodiments are implemented. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium.

[0085] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the aforementioned 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, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the computer-readable storage medium can include both an internal storage unit of the electronic device and an external storage 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 is about to be output.

[0086] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0087] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0088] In the several 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 device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or can be an electrical, mechanical or other form of connection.

[0089] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0090] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0091] The above are only specific embodiments of the present application, but the scope of protection of the present 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 such modifications or substitutions should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A coke cake temperature detection method, characterized in that: include: Acquire infrared image data of the coke cake, and calculate first temperature data based on the infrared image data; constructing a heat transfer model according to the material thermophysical property parameters of the coke cake, the first temperature data, and the furnace temperature data of the coke oven, and calculating the second temperature data of the coke cake based on the heat transfer model; The first temperature data and the second temperature data are weightedly fused to obtain target temperature data.

2. The coke cake temperature detection method according to claim 1, wherein: Calculating first temperature data according to the infrared image data includes: performing noise reduction processing on the infrared image data to obtain target infrared image data; Converting the target infrared image data into radiation intensity data; First temperature data is obtained by calculation according to the radiation intensity data and Bronck's law.

3. The coke cake temperature detection method according to claim 2, wherein: The performing noise reduction processing on the infrared image data to obtain target infrared image data includes: determining a first Gaussian kernel based on a resolution of the infrared image data; determining a target standard deviation based on the noise intensity and noise suppression coefficient of the infrared image data; Adjusting the first Gaussian kernel based on the target standard deviation to obtain a target Gaussian kernel; The infrared image data is subjected to denoising processing based on the target Gaussian kernel to obtain the target infrared image data.

4. The coke cake temperature detection method according to claim 1, wherein: The weighted fusion of the first temperature data and the second temperature data to obtain the target temperature includes: In response to the first temperature data being greater than a first temperature threshold, adjusting a first weight reference value based on a first weight adjustment step length to obtain a first weight; and adjusting a second weight reference value based on the first weight adjustment step length to obtain a second weight; Performing weighted calculation based on the first weight, the second weight, the first temperature data, and the second temperature data to obtain target temperature data; The first weight is a weight corresponding to the first temperature data, the second weight is a weight corresponding to the second temperature data, and the adjustment directions of the first weight reference value and the second weight reference value are different; In response to the first temperature data being less than or equal to a first temperature threshold, performing weighted calculation based on a first weight reference value, a second weight reference value, the first temperature data, and the second temperature data to obtain target temperature data; The first weight reference value is a weight corresponding to the first temperature data, and the second weight reference value is a weight corresponding to the second temperature data.

5. The coke cake temperature detection method according to claim 1, wherein: The weighted fusion of the first temperature data and the second temperature data to obtain target temperature data includes: Acquiring ultrasonic propagation data inside the coke cake, and calculating third temperature data based on the ultrasonic propagation data and a sound velocity-temperature mapping model; performing weighted fusion on the second temperature data and the third temperature data to obtain fourth temperature data; The first temperature data and the fourth temperature data are weightedly fused to obtain target temperature data.

6. The coke cake temperature detection method according to claim 1, wherein: Also includes: Inputting the working condition data of the coke cake into a temperature prediction model to obtain temperature range data; The temperature prediction model is trained based on historical operating data and corresponding actual coke cake temperature data; The temperature abnormality result of the coke cake is determined according to the temperature interval data and the target temperature data.

7. The coke cake temperature detection method according to claim 6, wherein: Temperature anomaly results include temperature anomaly level; The determining of the abnormal temperature result of the coke cake according to the temperature interval data and the target temperature data includes: Calculating a deviation value between the target temperature data and a boundary value of the temperature interval data; The temperature abnormality level of the coke cake is determined according to the deviation value and the abnormality level table.

8. A coke cake temperature detection system, characterized in that: include: an infrared module, configured to obtain infrared image data of the coke cake and calculate first temperature data based on the infrared image data; a heat transfer module, configured to construct a heat transfer model according to the material thermophysical properties of the coke cake, the first temperature data, and the temperature data of the coke oven, and calculate the second temperature data of the coke cake based on the heat transfer model; The target module is used to perform weighted fusion on the first temperature data and the second temperature data to obtain target temperature data.

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, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images