Blast furnace thermocouple detection correction method and system, computer device and medium

Abstract

The present application provides a kind of blast furnace thermocouple detection correction method and system, computer equipment and medium, by stage mechanism modeling, data multidimensional reliability evaluation, three technical schemes based on mechanism dynamic compensation, the problem existing in temperature detection during the use period of blast furnace hearth can be solved.This application can judge the situation of hardware damage and data error that may occur in the thermocouple during the service life of blast furnace, can screen out potential abnormal thermocouple, improve the reliability of blast furnace body safety supervision system, reduce labor cost and improve processing efficiency.The present application detects and corrects abnormal temperature measuring thermocouple online through three-dimensional conjugate heat transfer model of hearth, carries out quantitative evaluation, and improves the quality of temperature data.The present application uses model prediction results to supplement missing thermocouple data, ensures the continuity and integrity of temperature data, provides more accurate data support for hearth state evaluation, fault diagnosis and predictive maintenance, and ensures the safe and stable operation of blast furnace.

Description

Technical Field

[0001] This invention relates to the field of blast furnace ironmaking technology, and in particular to a method and system for detecting and correcting blast furnace thermocouples, as well as computer equipment and media. Background Technology

[0002] As the core equipment in steel production, the long-term stability of the blast furnace hearth directly determines the overall service life of the furnace. Severe erosion and burn-through in the hearth can directly lead to the end of a furnace's service life, causing huge losses. However, the hearth is in a closed state for extended periods and is submerged in high-temperature molten iron, making it impossible to directly assess internal erosion. Currently, assessments of blast furnace conditions primarily rely on temperature data collected by numerous thermocouples embedded in the furnace for heat transfer analysis, combined with Fourier's law to evaluate refractory material thickness.

[0003] In actual production, due to drastic temperature changes within the furnace and the accompanying complex physical and chemical processes, thermocouple temperature measurement data exhibits abnormal fluctuations. As the furnace ages, the probability of thermocouple failure increases. In the later stages of furnace service, thermocouple damage is quite common, resulting in a lack of blast furnace condition monitoring data. This makes it impossible to accurately assess hearth erosion, posing a potential safety hazard. Furthermore, there is currently a lack of reliability evaluation rules for thermocouple-collected data.

[0004] Due to the large number of thermocouples, the complexity of their failures, and the numerous factors involved, manual anomaly detection is labor-intensive and technically demanding. Furthermore, while existing technologies offer methods for thermocouple anomaly detection, they require high data quality and a large sample size, necessitating pre-selection of the thermocouples to be detected. This presents limitations when dealing with complex operating conditions and drastic changes in blast furnace production load. Since the erosion profile within the furnace continuously changes throughout the production cycle, thermocouple temperature data does not correspond one-to-one with furnace conditions, historical data patterns are limited, and corrections for identified abnormal thermocouple data are not possible. Summary of the Invention

[0005] This invention provides a method and system for detecting and correcting thermocouples in blast furnaces, as well as computer equipment and media, to solve the technical problems existing in the prior art.

[0006] The present invention provides a method for correcting the detection of thermocouples in a blast furnace, comprising the following steps: The thermocouple temperature data stored in advance or in real time is used as thermocouple temperature data samples, and the thermocouple temperature data samples are divided into training set and test set; A three-dimensional conjugate heat transfer model of the blast furnace hearth is established based on the parameters of the blast furnace hearth for thermocouple detection. The parameters of the blast furnace hearth include: the actual structure of the blast furnace hearth, the actual dimensions of the blast furnace hearth, the actual material composition of the blast furnace hearth, and the operating conditions of the blast furnace hearth. The training set is used to perform simulation calculations on the three-dimensional conjugate heat transfer model of the furnace hearth, and the test set is used to verify the three-dimensional conjugate heat transfer model of the furnace hearth after the simulation calculations are completed. The presence of anomalies in the target thermocouple is confirmed by using a validated three-dimensional conjugate heat transfer model of the furnace hearth. When anomalies are found in the target thermocouple, the simulation results of the validated three-dimensional conjugate heat transfer model of the furnace hearth are used to correct the target thermocouple and supplement the temperature data of the failed thermocouple. The target thermocouple includes abnormal thermocouples selected based on pre-determined thermocouple reliability evaluation rules.

[0007] Optionally, the process of dividing the thermocouple temperature data samples into a training set and a test set includes: The thermocouple temperature data samples are stratified according to thermocouple characteristics; wherein, the thermocouple characteristics include the height of the thermocouple in the blast furnace hearth, the insertion depth of the thermocouple in the blast furnace hearth, and the angle of the thermocouple in the blast furnace hearth. Calculate the proportion of thermocouple temperature data samples in each layer to the total thermocouple temperature data, and determine the number of training samples and test samples to be extracted in each layer based on the proportion. Thermocouple temperature data is extracted from the thermocouple temperature data sample according to the number of training samples to be extracted in each layer, and the training set is formed based on the thermocouple temperature data extracted from all layers; and the test set is formed based on the number of test samples to be extracted in each layer.

[0008] Optionally, the process of establishing a three-dimensional conjugate heat transfer model of the blast furnace hearth for thermocouple detection based on the hearth parameters includes: A three-dimensional geometric model is established based on the actual structure and dimensions of the blast furnace hearth components; wherein, the blast furnace hearth components include: furnace shell, cooling wall, ramming material layer, carbon brick, ceramic cup, molten iron layer and slag skin; Based on the actual material composition of the blast furnace hearth components, the composition of the molten iron in the blast furnace hearth, and the composition of the slag-iron mixture in the blast furnace hearth, the material property parameters of the three-dimensional geometric model are defined; wherein, the material property parameters include: effective thermal conductivity at different operating temperatures, density at different operating temperatures, dynamic viscosity at different operating temperatures, and specific heat capacity at different operating temperatures; The physical field control equations of the three-dimensional geometric model are set according to the momentum transfer, mass transfer and heat transfer processes of the blast furnace hearth in actual production; wherein, the physical field control equations include momentum conservation equation, continuity equation and energy conservation equation; The boundaries of the three-dimensional geometric model are set according to the operating conditions of the blast furnace hearth. The boundaries include: flow inlet boundary, pressure outlet boundary, temperature boundary, and erosion boundary. The three-dimensional geometric model is meshed and scaled, and combined with the material property parameters, the physical field control equations and the boundary, a three-dimensional geometric model that does not fluctuate with the number or quality of meshes is output as the three-dimensional conjugate heat transfer model of the furnace hearth.

[0009] Optionally, the process of using the training set to perform simulation calculations on the three-dimensional conjugate heat transfer model of the furnace hearth, and using the test set to verify the three-dimensional conjugate heat transfer model of the furnace hearth after the simulation calculations are completed, includes: Thermocouple data in the training set is used as a correction condition to calculate the relative error of the three-dimensional conjugate heat transfer model of the furnace hearth. When the relative error is greater than a preset threshold, the erosion node is controlled to move inward or outward. The erosion node is used to control the erosion boundary. Based on the erosion node movement results, the three-dimensional conjugate heat transfer model of the furnace hearth is simulated again, and the simulation is repeated multiple times until the simulation results meet the preset iteration exit conditions; and the erosion boundary is updated based on the most severely eroded location point in the erosion node movement results, and the erosion boundary is used as the initial boundary for the next simulation calculation of the three-dimensional conjugate heat transfer model of the furnace hearth. The thermocouple data in the test set is input into the three-dimensional conjugate heat transfer model of the furnace after the simulation calculation is completed. The predicted temperature of each thermocouple in the test set is output by the three-dimensional conjugate heat transfer model of the furnace after the simulation calculation, and the error is calculated with the actual collected temperature at the corresponding collection time in the test set. If the error between the predicted temperature and the actual collected temperature meets the preset error condition, then the three-dimensional conjugate heat transfer model of the furnace hearth is determined to have passed the verification. If the error between the predicted temperature and the actual collected temperature does not meet the preset error condition, the three-dimensional conjugate heat transfer model of the furnace hearth will be reconstructed.

[0010] Optionally, the process of screening abnormal thermocouples based on predetermined thermocouple reliability evaluation rules includes: If the thermocouple temperature data is non-positive, the corresponding thermocouple will be marked as an abnormal thermocouple. And / or, if the temperature change of a thermocouple causes the local entropy generation rate to be negative, then a physical logic anomaly is determined to have occurred, and the corresponding thermocouple is marked as an abnormal thermocouple; And / or, if the temperature of a thermocouple changes between two adjacent acquisition times and the temperature difference is greater than or equal to a preset temperature value, the corresponding thermocouple will be marked as an abnormal thermocouple. And / or, calculate the local heat flux tensor through the temperature gradient between adjacent thermocouple groups, and use the local heat flux tensor to determine whether the corresponding thermocouple is abnormal; And / or, if the temperature data of the thermocouple at the hot end of the refractory material at the bottom of the blast furnace is less than or equal to the temperature data of the thermocouple at the cold end of the refractory material at the bottom of the blast furnace, the two thermocouples are marked as abnormal thermocouples. And / or, if the temperature data of the thermocouple inside the blast furnace hearth is less than or equal to the temperature data of the thermocouple outside the blast furnace hearth when two thermocouples are set in pairs, then the two corresponding thermocouples are marked as abnormal thermocouples. And / or, if the thermocouple data processed by the sliding window remains constant within a preset time period, the corresponding thermocouple will be marked as an abnormal thermocouple.

[0011] Optionally, the process of correcting the target thermocouple includes: if the thermocouple fails or no thermocouple temperature data is collected, the three-dimensional conjugate heat transfer model of the furnace hearth is used to predict the temperature data of the corresponding failure point, and the predicted temperature data is used as supplementary thermocouple temperature data of the corresponding failure point.

[0012] Optionally, the method further includes: calculating the residual thickness of the blast furnace hearth refractory based on the corrected thermocouple temperature data, and assessing the degree of erosion of the blast furnace hearth and the remaining service life of the blast furnace hearth based on the calculation results of the residual thickness of the blast furnace hearth refractory; and / or, establishing files based on the location of the thermocouples, and storing the collected thermocouple temperature data according to the filing results.

[0013] The present invention also provides a blast furnace thermocouple detection and correction system, the system comprising: Data acquisition module: used to acquire and store thermocouple temperature data at preset positions in the blast furnace hearth; The sample classification module is used to take the stored thermocouple temperature data as thermocouple temperature data samples and divide the thermocouple temperature data samples into training set and test set; The mechanism modeling module is used to establish a three-dimensional conjugate heat transfer model of the blast furnace hearth for thermocouple detection based on the parameters of the blast furnace hearth. The parameters of the blast furnace hearth include: the actual structure of the blast furnace hearth, the actual dimensions of the blast furnace hearth, the actual material composition of the blast furnace hearth, and the operating conditions of the blast furnace hearth. The model training module is used to perform simulation calculations on the three-dimensional conjugate heat transfer model of the furnace hearth using the training set, and to verify the three-dimensional conjugate heat transfer model of the furnace hearth after the simulation calculations are completed using the test set. An anomaly detection module is used to confirm whether the target thermocouple is abnormal based on the verified three-dimensional conjugate heat transfer model of the furnace hearth; wherein, the target thermocouple includes abnormal thermocouples screened based on pre-determined thermocouple reliability evaluation rules; The data correction module is used to correct the target thermocouple by using the simulation results of the verified three-dimensional conjugate heat transfer model of the furnace hearth when the target thermocouple is abnormal; and to supplement the temperature data of the failed thermocouple.

[0014] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the blast furnace thermocouple detection and correction method described in any one of the above.

[0015] The beneficial effects of this invention are as follows: This invention proposes a method and system for detecting and correcting thermocouples in a blast furnace, along with computer equipment and media. Through a three-pronged technical approach—phased mechanism modeling, multi-dimensional data reliability assessment, and mechanism-based dynamic compensation—it addresses the challenges of insufficient early-stage model validation, poor mid-stage anomaly detection accuracy, and difficulty in compensating for missing data in the later stages of blast furnace hearth temperature monitoring, compared to traditional single-threshold detection. Furthermore, this invention assesses potential hardware damage and data acquisition errors in thermocouples during the blast furnace's service life, effectively identifying potentially abnormal thermocouples and improving the reliability of the blast furnace's safety monitoring system. It also reduces labor costs and increases processing efficiency. In addition, this invention uses a three-dimensional conjugate heat transfer model of the hearth to detect and correct abnormal temperature-measuring thermocouples online, conducting quantitative assessments to improve temperature data quality. For cases of complete thermocouple failure, model prediction results are used to supplement missing thermocouple data, ensuring the continuity and integrity of temperature data. This provides more accurate data support for hearth condition assessment, fault diagnosis, and predictive maintenance, ensuring the safe and stable operation of the blast furnace. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0017] In the attached diagram: Figure 1 This is a flowchart illustrating a blast furnace thermocouple detection and correction method provided in one embodiment of the present invention. Figure 2 This is a flowchart illustrating a blast furnace thermocouple detection and correction method provided in another embodiment of the present invention. Figure 3 This is a flowchart illustrating a blast furnace thermocouple detection and correction method according to another embodiment of the present invention. Figure 4This is a schematic diagram of a process for dividing thermocouple temperature data samples into a training set and a test set, according to an embodiment of the present invention. Figure 5 This is a schematic diagram of the process for establishing a three-dimensional conjugate heat transfer model of a blast furnace hearth according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the hardware structure of a blast furnace thermocouple detection and correction system provided in one embodiment of the present invention; Figure 7 This is a schematic diagram of the hardware structure of a computer device suitable for implementing one or more embodiments of the present invention. Detailed Implementation

[0018] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0019] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0020] Figure 1 A schematic flowchart of a blast furnace thermocouple detection correction method is shown. Specifically, in an exemplary embodiment, as... Figure 1 As shown, this embodiment provides a method for correcting blast furnace thermocouple detection, including the following steps: S11, use the pre-stored or real-time thermocouple temperature data as thermocouple temperature data samples, and divide the thermocouple temperature data samples into training set and test set.

[0021] In some examples, the process of dividing thermocouple temperature data samples into training and testing sets includes: stratifying the thermocouple temperature data samples according to thermocouple characteristics, including the height of the thermocouple in the blast furnace hearth, the insertion depth of the thermocouple in the blast furnace hearth, and the angle of the thermocouple in the blast furnace hearth; calculating the proportion of thermocouple temperature data samples in each layer to the total thermocouple temperature data, and determining the number of training samples and test samples to be extracted in each layer based on the proportion; extracting the corresponding thermocouple temperature data from the thermocouple temperature data samples according to the number of training samples to be extracted in each layer, and forming a training set based on the thermocouple temperature data extracted from all layers; and extracting the corresponding thermocouple temperature data from the thermocouple temperature data samples according to the number of test samples to be extracted in each layer, and forming a test set based on the thermocouple temperature data extracted from all layers.

[0022] S12. Based on the parameters of the blast furnace hearth, a three-dimensional conjugate heat transfer model of the hearth is established for thermocouple detection. The parameters of the blast furnace hearth include: the actual structure of the blast furnace hearth, the actual dimensions of the blast furnace hearth, the actual material composition of the blast furnace hearth, and the operating conditions of the blast furnace hearth.

[0023] In some examples, the process of establishing a three-dimensional conjugate heat transfer model of the blast furnace hearth for thermocouple detection based on the hearth parameters includes: A three-dimensional geometric model is established based on the actual structure and dimensions of the blast furnace hearth components; the blast furnace hearth components include: furnace shell, cooling wall, ramming material layer, carbon brick, ceramic cup, molten iron layer and slag skin.

[0024] Based on the actual material composition of the blast furnace hearth components, the composition of the molten iron and the slag-iron mixture in the blast furnace hearth, the material property parameters of the three-dimensional geometric model are defined. Among them, the material property parameters include: effective thermal conductivity at different operating temperatures, density at different operating temperatures, dynamic viscosity at different operating temperatures, and specific heat capacity at different operating temperatures.

[0025] The physical field control equations of a three-dimensional geometric model are set up based on the momentum transfer, mass transfer and heat transfer processes in the actual production of the blast furnace hearth; among them, the physical field control equations include the momentum conservation equation, the continuity equation and the energy conservation equation.

[0026] The boundaries of the three-dimensional geometric model are set according to the operating conditions of the blast furnace hearth. The boundaries include: flow inlet boundary, pressure outlet boundary, temperature boundary, and erosion boundary.

[0027] The three-dimensional geometric model is meshed and scaled, and combined with material property parameters, physical field control equations and boundaries, a three-dimensional geometric model that does not fluctuate with the number or quality of meshes is output as the three-dimensional conjugate heat transfer model of the furnace hearth.

[0028] S13. The training set is used to perform simulation calculations on the three-dimensional conjugate heat transfer model of the furnace hearth, and the test set is used to verify the three-dimensional conjugate heat transfer model of the furnace hearth after the simulation calculations are completed.

[0029] In some examples, the process of simulating a three-dimensional conjugate heat transfer model of the furnace hearth using a training set and validating the simulated model using a test set includes: Thermocouple data from the training set are used as correction conditions to calculate the relative error of the three-dimensional conjugate heat transfer model of the furnace hearth. When the relative error is greater than a preset threshold, the erosion nodes are controlled to move inward or outward. The erosion nodes are used to control the erosion boundary.

[0030] The three-dimensional conjugate heat transfer model of the furnace hearth is simulated based on the erosion node movement results, and multiple iterations are performed during the simulation until the simulation results after multiple iterations meet the preset iteration exit conditions. Furthermore, the erosion boundary is constructed based on the most severely eroded location in the erosion node movement results, and the erosion boundary is used as the initial boundary for the next iteration calculation of the three-dimensional conjugate heat transfer model of the furnace hearth.

[0031] The thermocouple data in the test set is input into the three-dimensional conjugate heat transfer model of the furnace hearth after the simulation calculation is completed. The predicted temperature at the corresponding position of each thermocouple in the test set is output by the three-dimensional conjugate heat transfer model of the furnace hearth after the simulation calculation, and the error is calculated with the actual collected temperature at the corresponding collection time in the test set.

[0032] If the error between the predicted temperature and the actual collected temperature meets the preset error condition, the three-dimensional conjugate heat transfer model of the furnace hearth is verified; if the error between the predicted temperature and the actual collected temperature does not meet the preset error condition, the three-dimensional conjugate heat transfer model of the furnace hearth is reconstructed.

[0033] S14, confirm whether the target thermocouple is abnormal by verifying the three-dimensional conjugate heat transfer model of the furnace hearth, and when the target thermocouple is abnormal, correct the target thermocouple by the simulation results of the verified three-dimensional conjugate heat transfer model of the furnace hearth, and supplement the temperature data of the failed thermocouple; wherein, the target thermocouple includes abnormal thermocouples screened based on the pre-determined thermocouple reliability evaluation rules.

[0034] In some examples, the failed thermocouples are thermocouples that are unable to collect or output temperature data due to hardware or communication line burnout during the blast furnace's service life.

[0035] In some examples, the process of screening abnormal thermocouples based on predetermined thermocouple reliability evaluation rules includes: if the thermocouple temperature data is non-positive, the corresponding thermocouple is marked as an abnormal thermocouple. And / or, if a temperature change in a thermocouple results in a negative local entropy generation rate, a physical logic anomaly is determined, and the corresponding thermocouple is marked as an abnormal thermocouple. And / or, if the temperature of a thermocouple changes between two adjacent acquisition times, and the temperature difference is greater than or equal to a preset temperature value, the corresponding thermocouple is marked as an abnormal thermocouple. And / or, the local heat flux tensor is calculated using the temperature gradient between adjacent thermocouple groups, and the local heat flux tensor is used to determine whether the corresponding thermocouple is abnormal. And / or, if the temperature data of two paired thermocouples at the hot end of the refractory material at the bottom of the blast furnace is less than or equal to the temperature data of the thermocouple at the cold end of the refractory material at the bottom of the blast furnace, both corresponding thermocouples are marked as abnormal thermocouples. And / or, if the temperature data of the thermocouple inside the blast furnace hearth is less than or equal to the temperature data of the thermocouple outside the blast furnace hearth in a pair of thermocouples, then the corresponding two thermocouples will be marked as abnormal thermocouples. And / or, if a thermocouple processed through a sliding window remains constant within a preset time period, then the corresponding thermocouple will be marked as abnormal thermocouple. The preset time period can be selected or set according to actual conditions; for example, the preset time period can be one day, one week, one month, etc.

[0036] In some examples, the process of correcting the target thermocouple includes: if the thermocouple fails or no thermocouple temperature data is collected, the temperature data of the corresponding failure point is predicted using a three-dimensional conjugate heat transfer model of the furnace hearth, and the predicted temperature data is used as a supplement to the thermocouple temperature data of the corresponding failure point.

[0037] In an exemplary embodiment of the present invention, the blast furnace thermocouple detection correction method may further include: calculating the residual thickness of the blast furnace hearth refractory material based on the corrected thermocouple temperature data, and evaluating the degree of erosion of the blast furnace hearth and the remaining service life of the blast furnace hearth based on the calculation result of the residual thickness of the blast furnace hearth refractory material. And / or, establishing records based on the location of the thermocouples, and storing the collected thermocouple temperature data according to the record-keeping results, thereby allowing the stored thermocouple temperature data to be used as thermocouple temperature data samples.

[0038] In an exemplary embodiment of the present invention, such as Figure 2 As shown, this embodiment provides a method for correcting blast furnace thermocouple detection, including the following steps: S21. Label and file the thermocouples according to their specific locations in the blast furnace, and collect and store thermocouple temperature data. S22, sample the stored thermocouple temperature data, and divide the sampled thermocouple temperature data into training set and test set; S23. Based on the actual structure and dimensions, material composition and operating conditions of the blast furnace hearth, a three-dimensional conjugate heat transfer model of the hearth is established. S24, Simulation calculations are performed on the constructed three-dimensional conjugate heat transfer model of the furnace hearth based on the thermocouple temperature data in the training set; and the rationality verification of the three-dimensional conjugate heat transfer model of the furnace hearth is carried out based on the thermocouple temperature data in the test set. S25. Based on the thermocouple reliability evaluation rules, assess the temperature data collected by thermocouples during blast furnace operation and select suspected abnormal thermocouples. S26. The three-dimensional conjugate heat transfer model of the furnace hearth is used to verify whether the suspected thermocouple temperature data is indeed abnormal. The abnormal value correction and missing value supplementation are carried out in combination with the prediction results of the three-dimensional conjugate heat transfer model of the furnace hearth.

[0039] In some embodiments, if the above-described blast furnace thermocouple detection and correction method is implemented based on a three-dimensional conjugate heat transfer model of the hearth, the process of blast furnace thermocouple anomaly detection and correction based on the three-dimensional conjugate heat transfer model of the hearth is as follows: Figure 3 As shown in the figure. The three-dimensional conjugate heat transfer model of the furnace hearth is continuously updated and adjusted based on the actual temperature data of the blast furnace thermocouples. Based on the current operating conditions and erosion situation, it outputs the temperature prediction results of each temperature measurement point and compares them to carry out thermocouple anomaly detection and correction.

[0040] In some embodiments, the blast furnace thermocouples in step S21 cover the blast furnace hearth sidewall and bottom area. The blast furnace thermocouples in step S21 simultaneously consider the preset positions of the thermocouples during the blast furnace design process and the actual placement positions of each thermocouple during blast furnace construction. Assembly errors during the construction process can be introduced to ensure the consistency between the thermocouple's three-dimensional spatial coordinates and the actual temperature measurement points. In some examples, there are multiple preset positions, such as those located in the blast furnace hearth area and the blast furnace bottom area, involving different elevations, insertion depths, and circumferential angles. Thermocouple temperature data is obtained by collecting data from thermocouples placed at the preset positions.

[0041] In some embodiments, such as Figure 4 As shown, step S22 may further include the following steps: S221, Layering: The blast furnace thermocouple temperature data samples are divided into several complementary layers or groups with similar characteristics according to the characteristics of the thermocouple height, insertion depth, angle, etc. S222, Proportional Allocation: Calculate the proportion of the number of samples in each layer to the total number of thermocouples; S223, Determine the sample size: Determine the number of samples to be drawn from each layer based on the proportion; S224, Sampling: Samples are drawn proportionally from each layer, and the samples drawn from each layer are aggregated to form a sample set.

[0042] In some examples, the sampling method can be a stratified proportional sampling method, in which the training set is used to train the three-dimensional conjugate heat transfer model of the furnace hearth, while the test set is completely isolated from the training set and is only used to evaluate the generalization performance and rationality of the three-dimensional conjugate heat transfer model of the furnace hearth after the training is completed.

[0043] In some examples, the training set used to train the three-dimensional conjugate heat transfer model of the furnace hearth accounts for 90% of the total thermocouple samples, while the test set used to verify the prediction results of the three-dimensional conjugate heat transfer model of the furnace hearth accounts for 10% of the total thermocouple samples.

[0044] In some examples, when classifying thermocouple temperature data, a stratified sampling method can be used to select the training set, and the remaining thermocouple samples are automatically assigned to the test set.

[0045] In some embodiments, such as Figure 5 As shown, step S23 may also include the following steps: S231: Establish a three-dimensional geometric model based on the actual geometric dimensions of the blast furnace hearth components; among which, the blast furnace hearth components include the furnace shell, cooling wall, ramming material layer, carbon brick, ceramic cup, molten iron layer and slag skin; S232: Based on the specific material composition of each component of the blast furnace hearth and the specific composition of the molten iron and slag-iron mixture in the furnace, define the physical property parameters of each component and mixture in the three-dimensional geometric model; among which, the physical property parameters specifically include the effective thermal conductivity, density, dynamic viscosity, and specific heat capacity at different operating temperatures. S233: Set the corresponding physical field control equations for each computational domain of the three-dimensional geometric model; in some examples, the corresponding momentum conservation equation, continuity equation, and energy conservation equation can be set as the physical field control equations according to the momentum transfer, mass transfer, and heat transfer processes that occur in the actual production of the blast furnace hearth. For example, the finite volume method can be used to solve the three-dimensional mathematical model, and its heat transfer control equation is: In the formula, r, θ, z In spatial cylindrical coordinates, k r ( T )for r Temperature in the direction is T Thermal conductivity at that time k θ ( T )for θ Temperature in the direction is T Thermal conductivity at that time k z ( T )for z Temperature in the direction is T The thermal conductivity at that time.

[0046] S234: Set the corresponding boundaries and initial values ​​of the model according to the actual operation process. Among them, the boundaries include the flow inlet boundary, pressure outlet boundary, temperature boundary, and erosion boundary.

[0047] In some examples, the three-dimensional conjugate heat transfer model of the blast furnace hearth can be input with the actual operating conditions of the blast furnace hearth; the top of the three-dimensional geometric model is set as the ambient heat transfer boundary, and the ambient temperature is set as the temperature of the upper part of the furnace body; the inner wall of the three-dimensional geometric model is set as a constant temperature boundary and is always fixed at the position of the refractory inner profile; the bottom of the three-dimensional geometric model is set as a convective heat transfer boundary; the side wall of the three-dimensional geometric model is set as a variable temperature boundary, and the three-dimensional geometric model is estimated by interpolation according to the heat transfer law based on the side wall thermocouples; the output of the three-dimensional geometric model is the temperature field information such as the temperature at the corresponding position of each temperature measurement point and the 1150℃ isotherm. S235: Mesh the 3D geometric model and set the solver and convergence conditions for the 3D geometric model accordingly; S236: Conduct mesh independence analysis, perform local mesh scaling on sensitive areas of the 3D geometric model, compare the changes in output results, determine the appropriate number of meshes for the 3D conjugate heat transfer model of the furnace hearth, and establish the 3D conjugate heat transfer model of the furnace hearth.

[0048] In some examples, during the construction of the three-dimensional conjugate heat transfer model of the furnace hearth, considering that the hearth is constructed from refractory materials with different properties, a multi-layer temperature field calculation model can be established, encompassing molten iron, ceramic cups, various refractory materials, and ramming mix, covering the latent heat of solidification. Given that the thermal conductivity of materials has a significant impact on the erosion calculation results, a semi-empirical formula between the thermal conductivity of refractory materials and temperature can be established using Lagrange interpolation, and harmonic averaging can be applied to the interfaces between different materials.

[0049] In some examples, the thermal conductivity of the molten iron zone can be determined based on the temperature of the grid nodes: when the temperature of the grid nodes in the molten iron zone is greater than 1450℃, it is calculated as molten iron; when the temperature of the computational domain is between 1150℃ and 1450℃, it is assumed that molten iron erosion has occurred and a slag-iron layer has formed; when the temperature of the computational domain is less than 1150℃, the solution is set according to the thermal conductivity of refractory materials.

[0050] In some embodiments, step S24 may further include: conducting simulation calculations based on the thermocouple temperature data of the training set and adjusting the erosion boundary settings of the three-dimensional conjugate heat transfer model of the furnace hearth; and conducting model rationality verification based on the thermocouple temperature data of the test set. Specifically, the method for constructing the three-dimensional conjugate heat transfer model of the furnace hearth based on the training and test sets establishes an effective three-dimensional conjugate heat transfer model of the blast furnace hearth to characterize its thermal properties and erosion state during the early and middle stages of blast furnace operation and the normal operation phase of each thermocouple.

[0051] In some examples, the three-dimensional conjugate heat transfer model of the furnace hearth uses the measured temperature data of each thermocouple in the training set as correction conditions to solve the heat transfer "forward problem". Specifically, the temperature field distribution information at the corresponding time moment is obtained, and the relative error is calculated. When the relative error is higher than the set threshold, the erosion nodes are controlled to move inward or outward. After all erosion nodes have completed one movement, a new 1150°C line position is obtained. This process can be understood as solving the heat transfer "inverse problem". Then, the "forward problem" calculation is performed again, and the iteration is repeated multiple times until the iteration exit condition is met, and the 1150°C line position is updated. At the same time, each point on the 1150°C line will also be compared with each point on the historical erosion boundary to determine the degree of erosion. The point with the most severe erosion is combined to form the latest erosion boundary. The furnace hearth 1150°C line, erosion boundary, isotherms, and other information are updated and output on a rolling basis, and the latest erosion boundary is used as the initial boundary for the next iteration calculation of the model.

[0052] In some examples, the three-dimensional conjugate heat transfer model of the furnace hearth is validated for its rationality based on the measured temperature data of each thermocouple in the test set. The three-dimensional conjugate heat transfer model of the furnace hearth outputs the temperature information at the corresponding positions of each thermocouple in the test set, and performs error calculations with the temperature data collected at the corresponding time of the thermocouples in the test set. When the error requirement is met, the constructed three-dimensional conjugate heat transfer model of the furnace hearth is considered to be able to effectively predict the temperature distribution of the furnace hearth at the corresponding time; when the error requirement is not met, the three-dimensional conjugate heat transfer model of the furnace hearth is reconstructed based on the temperature data of the training set.

[0053] In some examples, during the early stages of blast furnace operation, when the thermocouples inside the furnace have just been put into operation and have not been subjected to significant thermal stress or erosion damage, each thermocouple is functioning normally. Conducting debugging and model verification of the three-dimensional conjugate heat transfer model of the blast furnace hearth during this stage can effectively ensure the relevance and accuracy of the temperature prediction results of the three-dimensional conjugate heat transfer model of the hearth, laying the model foundation for subsequent thermocouple anomaly detection and data correction.

[0054] In some embodiments, the specific process of step S25 may further include: the thermocouple reliability evaluation adopts an adaptive sliding window technique, and the window length is dynamically adjusted according to the blast furnace smelting cycle, such as the iron tapping interval and the shutdown time, to avoid misjudgment of data stability caused by a fixed window. The temperature signal is decomposed into a trend term (low frequency) and a noise term (high frequency) through wavelet decomposition, and thresholds are set for each to effectively distinguish between real operating condition fluctuations and sensor noise.

[0055] Thermocouple reliability evaluation rules can be as follows: (1) The thermocouple temperature data used for furnace hearth condition assessment must be positive and conform to the physical logic relationship with the temperature of the nearest temperature measurement point on the adjacent cross section; otherwise, it is marked as a suspected abnormal thermocouple. Furthermore, an entropy generation rate criterion based on non-equilibrium thermodynamics is set. If a temperature change at a certain point results in a negative local entropy generation rate, it is judged as a physical logic abnormality. The specific calculation formula is as follows: In the formula S For system entropy, For the local entropy generation rate, ▽ T The temperature gradient vector. q For heat flux density, V To control the volume.

[0056] (2) The temperature data collected at each thermocouple sampling time before and after the sampling time follow the historical change pattern, without significant jumps or abrupt changes; otherwise, it is marked as a suspected abnormal thermocouple. Preferably, the temperature measurement data at the same location before and after the sampling time |T t -T t-1 If the temperature is ≥15℃, the thermocouple temperature measurement data needs to be verified using a three-dimensional conjugate heat transfer model of the furnace hearth. t Let T be the temperature measurement data at the t-th sampling time. t-1 This represents the temperature measurement data at sampling time t-1. Furthermore, a consistency evaluation criterion for the three-dimensional heat flux vector field is established. The local heat flux tensor is calculated based on the temperature gradient between adjacent thermocouple groups to evaluate whether there are any anomalies in the thermocouples. The tensor expression for the furnace hearth heat flux vector is as follows: In the formula q For heat flux density, λ Thermal conductivity, T For temperature, x This is the distance between thermocouples.

[0057] (3) For thermocouples arranged in pairs, the temperature data collected at the hot end of the refractory material at the bottom of the blast furnace must be greater than the temperature data at the cold end, and the temperature data collected by the thermocouples inside the hearth must be greater than the temperature data outside the hearth; otherwise, they shall be marked as suspected abnormal thermocouples.

[0058] (4) For thermocouples whose temperature measurement data remains unchanged for a long period of time after processing with the adaptive sliding window technique, they are marked as suspected abnormal thermocouples. The preset time period can be selected or set according to actual conditions, and will not be elaborated here.

[0059] In some embodiments, step S26 may further include: using a three-dimensional conjugate heat transfer model of the furnace hearth to perform simulation calculations under the corresponding furnace condition—actual temperature boundary and erosion state—latest erosion boundary, comparing and evaluating whether the suspected thermocouple temperature data is indeed abnormal, and performing corresponding data correction based on the model prediction results; for thermocouple failure and inability to collect temperature data due to drastic temperature changes and complex physicochemical processes in the later stages of furnace service, using the three-dimensional conjugate heat transfer model of the furnace hearth to predict the temperature information of the corresponding failure point as supplementary data for the thermocouple at that point. Further, based on the corrected thermocouple information, calculating the residual thickness of the furnace hearth refractory material, assessing the degree of furnace hearth erosion and remaining furnace service life, and carrying out targeted operational adjustments.

[0060] In summary, this invention proposes a method for detecting and correcting thermocouples in blast furnaces. Through a three-pronged approach—phased mechanism modeling, multi-dimensional data reliability assessment, and mechanism-based dynamic compensation—this method addresses the challenges of insufficient early-stage model validation, poor mid-stage anomaly detection accuracy, and difficulty in compensating for missing data in the later stages of blast furnace hearth temperature monitoring, compared to traditional single-threshold detection. Furthermore, this method assesses potential hardware damage and data acquisition errors in thermocouples during the blast furnace's service life, effectively identifying potentially abnormal thermocouples and improving the reliability of the blast furnace's safety monitoring system. It also reduces labor costs and increases processing efficiency. In addition, this method uses a three-dimensional conjugate heat transfer model of the hearth to detect and correct abnormal temperature-measuring thermocouples online, conducting quantitative assessments to improve temperature data quality. For cases of complete thermocouple failure, model prediction results are used to supplement missing thermocouple data, ensuring the continuity and integrity of temperature data. This provides more accurate data support for hearth condition assessment, fault diagnosis, and predictive maintenance, ensuring the safe and stable operation of the blast furnace.

[0061] In an exemplary embodiment of the present invention, such as Figure 6 As shown, a blast furnace thermocouple detection and correction system is provided, comprising: The data acquisition module is used to collect and store thermocouple temperature data at preset locations in the blast furnace hearth. These preset locations can be multiple, such as the blast furnace hearth area or the blast furnace bottom area, and may involve positions with different elevations, insertion depths, and circumferential angles. Thermocouple temperature data is obtained through thermocouples positioned at the preset locations. The sample classification module is used to treat the stored thermocouple temperature data as thermocouple temperature data samples and to divide the thermocouple temperature data samples into training set and test set. The mechanism modeling module is used to establish a three-dimensional conjugate heat transfer model of the blast furnace hearth for thermocouple detection based on the parameters of the blast furnace hearth. The parameters of the blast furnace hearth include: the actual structure of the blast furnace hearth, the actual dimensions of the blast furnace hearth, the actual material composition of the blast furnace hearth, and the operating conditions of the blast furnace hearth. The model training module is used to perform simulation calculations on the three-dimensional conjugate heat transfer model of the furnace hearth using the training set, and to verify the three-dimensional conjugate heat transfer model of the furnace hearth after the simulation calculations are completed using the test set. An anomaly detection module is used to confirm whether there are any anomalies in the target thermocouples based on the verified three-dimensional conjugate heat transfer model of the furnace hearth; wherein, the target thermocouples include abnormal thermocouples screened out based on pre-determined thermocouple reliability evaluation rules; The data correction module is used to correct the target thermocouple by using the verified three-dimensional conjugate heat transfer model of the furnace hearth when the target thermocouple is abnormal; and to supplement the temperature data of the failed thermocouple.

[0062] It is understood that the blast furnace thermocouple detection and correction system provided in the above embodiments and the blast furnace thermocouple detection and correction method provided in the above embodiments belong to the same concept. The specific operation of the blast furnace thermocouple detection and correction method has been described in detail in the above method embodiments and will not be repeated here. In practical applications, the blast furnace thermocouple detection and correction system provided in the above embodiments can be assigned to different functional modules as needed. That is, the internal structure of the blast furnace thermocouple detection and correction system can be divided into different functional modules, and then all or part of the functions of the corresponding functional modules can be implemented through the blast furnace thermocouple detection and correction method described in the above embodiments. No specific limitations are imposed here.

[0063] In summary, this invention proposes a blast furnace thermocouple detection and correction system. Through a three-pronged approach—phased mechanism modeling, multi-dimensional data reliability assessment, and mechanism-based dynamic compensation—this system addresses the challenges of insufficient early-stage model validation, poor mid-stage anomaly detection accuracy, and difficulty in compensating for missing data in the later stages of blast furnace hearth temperature monitoring, compared to traditional single-threshold detection. Furthermore, this method assesses potential hardware damage and data acquisition errors in thermocouples during the blast furnace's service life, effectively identifying potentially abnormal thermocouples and improving the reliability of the blast furnace's safety monitoring system. It also reduces labor costs and increases processing efficiency. In addition, this method uses a three-dimensional conjugate heat transfer model of the hearth to detect and correct abnormal temperature-measuring thermocouples online, conducting quantitative assessments to improve temperature data quality. For cases of complete thermocouple failure, model prediction results are used to supplement missing thermocouple data, ensuring the continuity and integrity of temperature data. This provides more accurate data support for hearth condition assessment, fault diagnosis, and predictive maintenance, ensuring the safe and stable operation of the blast furnace.

[0064] In another exemplary embodiment of the present invention, a computer device is also provided, which may include a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to cause the computer device to perform... Figure 1 or Figure 2 The steps of the blast furnace thermocouple detection and correction method. Figure 7 A schematic diagram of the structure of a computer device 1000 is shown. (See attached diagram.) Figure 7 As shown, the computer device 1000 includes: a processor 1010, a memory 1020, a power supply 1030, a display unit 1040, and an input unit 1060.

[0065] The processor 1010 is the control center of the computer device 1000. It connects various components via various interfaces and lines, and executes various functions of the computer device 1000 by running or executing computer programs / instructions stored in the memory 1020, thereby performing overall monitoring of the computer device 1000. In this embodiment of the invention, when the processor 1010 calls the computer program stored in the memory 1020, it executes, for example... Figure 1 or Figure 2 The steps of the blast furnace thermocouple detection and correction method are described above. Optionally, the processor 1010 may include one or more processing units; preferably, the processor 1010 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. In some embodiments, the processor and memory can be implemented on a single chip; in some embodiments, they can also be implemented separately on independent chips.

[0066] The memory 1020 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, various applications, etc.; the data storage area may store instruction data created based on the use of the computer device 1000, etc. In addition, the memory 1020 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0067] The computer device 1000 also includes a power supply 1030 (such as a battery) that supplies power to various components. The power supply can be logically connected to the processor 1010 through a power management system, thereby enabling the management of charging, discharging, and power consumption.

[0068] The display unit 1040 can be used to display information input by the user or information provided to the user, as well as various menus of the computer device 1000. In this embodiment of the invention, it is mainly used to display the display interfaces of various applications in the computer device 1000, as well as text, images, and other objects displayed on the display interfaces. The display unit 1040 may include a display panel 1050. The display panel 1050 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0069] The input unit 1060 can be used to receive information such as numbers or characters input by the user. The input unit 1060 may include a touch panel 1070 and other input devices 1080. The touch panel 1070, also known as a touch screen, can collect touch operations on or near the user (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel 1070).

[0070] Specifically, the touch panel 1070 can detect user touch operations and the signals generated by these operations, convert them into touch point coordinates, send them to the processor 1010, and receive and execute commands from the processor 1010. Furthermore, the touch panel 1070 can be implemented using various types of sensors, including resistive, capacitive, infrared, and surface acoustic wave sensors. Other input devices 1080 can include, but are not limited to, one or more of the following: physical keyboard, function keys (such as volume control buttons, power buttons, etc.), trackball, mouse, joystick, etc.

[0071] Of course, the touch panel 1070 can cover the display panel 1050. When the touch panel 1070 detects a touch operation on or near it, it transmits the information to the processor 1010 to determine the type of touch event. Subsequently, the processor 1010 provides corresponding visual output on the display panel 1050 based on the type of touch event. Although in Figure 7 In this embodiment, the touch panel 1070 and the display panel 1050 are two separate components to realize the input and output functions of the computer device 1000. However, in some embodiments, the touch panel 1070 and the display panel 1050 can be integrated to realize the input and output functions of the computer device 1000.

[0072] The computer device 1000 may also include one or more sensors, such as pressure sensors, gravity acceleration sensors, proximity sensors, etc. Of course, depending on the specific application requirements, the computer device 1000 may also include other components such as cameras.

[0073] This invention also provides a computer-readable storage medium storing a computer program / instructions, which, when executed by a processor, enable the aforementioned device to perform the functions described in this invention. Figure 1 or Figure 2 The steps of the aforementioned blast furnace thermocouple detection and correction method.

[0074] It will be understood by those skilled in the art that Figure 7This is merely an example of a computer device and does not constitute a limitation on the device. The device may include more or fewer components than illustrated, or a combination of certain components, or different components. For ease of description, the above parts are divided into modules (or units) according to their functions and described separately. Of course, in implementing this invention, the functions of each module (or unit) can be implemented in one or more software or hardware components.

[0075] Those skilled in the art will understand that the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The present invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention, and it should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be applied to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing device, produce implementations of the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0076] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method for detecting and correcting thermocouples in a blast furnace, characterized in that, The method includes: The thermocouple temperature data stored in advance or in real time is used as thermocouple temperature data samples, and the thermocouple temperature data samples are divided into training set and test set; A three-dimensional conjugate heat transfer model of the blast furnace hearth is established based on the parameters of the blast furnace hearth for thermocouple detection. The parameters of the blast furnace hearth include: the actual structure of the blast furnace hearth, the actual dimensions of the blast furnace hearth, the actual material composition of the blast furnace hearth, and the operating conditions of the blast furnace hearth. The training set is used to perform simulation calculations on the three-dimensional conjugate heat transfer model of the furnace hearth, and the test set is used to verify the three-dimensional conjugate heat transfer model of the furnace hearth after the simulation calculations are completed. The presence of anomalies in the target thermocouple is confirmed by using a validated three-dimensional conjugate heat transfer model of the furnace hearth. When anomalies are found in the target thermocouple, the simulation results of the validated three-dimensional conjugate heat transfer model of the furnace hearth are used to correct the target thermocouple and supplement the temperature data of the failed thermocouple. The target thermocouple includes abnormal thermocouples selected based on pre-determined thermocouple reliability evaluation rules.

2. The blast furnace thermocouple detection and correction method according to claim 1, characterized in that, The process of dividing the thermocouple temperature data samples into training and testing sets includes: The thermocouple temperature data samples are stratified according to thermocouple characteristics; wherein, the thermocouple characteristics include the height of the thermocouple in the blast furnace hearth, the insertion depth of the thermocouple in the blast furnace hearth, and the angle of the thermocouple in the blast furnace hearth. Calculate the proportion of thermocouple temperature data samples in each layer to the total thermocouple temperature data, and determine the number of training samples and test samples to be extracted in each layer based on the proportion. Thermocouple temperature data is extracted from the thermocouple temperature data sample according to the number of training samples to be extracted in each layer, and the training set is formed based on the thermocouple temperature data extracted from all layers; and the test set is formed based on the number of test samples to be extracted in each layer.

3. The blast furnace thermocouple detection and correction method according to claim 1 or 2, characterized in that, The process of establishing a three-dimensional conjugate heat transfer model of the blast furnace hearth for thermocouple detection based on the hearth parameters includes: A three-dimensional geometric model is established based on the actual structure and dimensions of the blast furnace hearth components; wherein, the blast furnace hearth components include: furnace shell, cooling wall, ramming material layer, carbon brick, ceramic cup, molten iron layer and slag skin; Based on the actual material composition of the blast furnace hearth components, the composition of the molten iron in the blast furnace hearth, and the composition of the slag-iron mixture in the blast furnace hearth, the material property parameters of the three-dimensional geometric model are defined; wherein, the material property parameters include: effective thermal conductivity at different operating temperatures, density at different operating temperatures, dynamic viscosity at different operating temperatures, and specific heat capacity at different operating temperatures; The physical field control equations of the three-dimensional geometric model are set according to the momentum transfer, mass transfer and heat transfer processes of the blast furnace hearth in actual production; wherein, the physical field control equations include momentum conservation equation, continuity equation and energy conservation equation; The boundaries of the three-dimensional geometric model are set according to the operating conditions of the blast furnace hearth. The boundaries include: flow inlet boundary, pressure outlet boundary, temperature boundary, and erosion boundary. The three-dimensional geometric model is meshed and scaled, and combined with the material property parameters, the physical field control equations and the boundary, a three-dimensional geometric model that does not fluctuate with the number or quality of meshes is output as the three-dimensional conjugate heat transfer model of the furnace hearth.

4. The blast furnace thermocouple detection and correction method according to claim 3, characterized in that, The process of simulating the three-dimensional conjugate heat transfer model of the furnace hearth using the training set and verifying the simulated three-dimensional conjugate heat transfer model of the furnace hearth using the test set includes: Thermocouple data in the training set is used as a correction condition to calculate the relative error of the three-dimensional conjugate heat transfer model of the furnace hearth. When the relative error is greater than a preset threshold, the erosion node is controlled to move inward or outward. The erosion node is used to control the erosion boundary. Based on the erosion node movement results, the three-dimensional conjugate heat transfer model of the furnace hearth is simulated again, and the simulation is repeated multiple times until the simulation results meet the preset iteration exit conditions; and the erosion boundary is updated based on the most severely eroded location point in the erosion node movement results, and the erosion boundary is used as the initial boundary for the next simulation calculation of the three-dimensional conjugate heat transfer model of the furnace hearth. The thermocouple data in the test set is input into the three-dimensional conjugate heat transfer model of the furnace after the simulation calculation is completed. The predicted temperature of each thermocouple in the test set is output by the three-dimensional conjugate heat transfer model of the furnace after the simulation calculation, and the error is calculated with the actual collected temperature at the corresponding collection time in the test set. If the error between the predicted temperature and the actual collected temperature meets the preset error condition, then the three-dimensional conjugate heat transfer model of the furnace hearth is determined to have passed the verification. If the error between the predicted temperature and the actual collected temperature does not meet the preset error condition, the three-dimensional conjugate heat transfer model of the furnace hearth will be reconstructed.

5. The blast furnace thermocouple detection and correction method according to claim 1 or 4, characterized in that, The process of screening abnormal thermocouples based on predetermined thermocouple reliability evaluation rules includes: If the thermocouple temperature data is non-positive, the corresponding thermocouple will be marked as an abnormal thermocouple. And / or, if the temperature change of a thermocouple causes the local entropy generation rate to be negative, then a physical logic anomaly is determined to have occurred, and the corresponding thermocouple is marked as an abnormal thermocouple; And / or, if the temperature of a thermocouple changes between two adjacent acquisition times and the temperature difference is greater than or equal to a preset temperature value, the corresponding thermocouple will be marked as an abnormal thermocouple. And / or, calculate the local heat flux tensor through the temperature gradient between adjacent thermocouple groups, and use the local heat flux tensor to determine whether the corresponding thermocouple is abnormal; And / or, if the temperature data of the thermocouple at the hot end of the refractory material at the bottom of the blast furnace is less than or equal to the temperature data of the thermocouple at the cold end of the refractory material at the bottom of the blast furnace, the two thermocouples are marked as abnormal thermocouples. And / or, if the temperature data of the thermocouple inside the blast furnace hearth is less than or equal to the temperature data of the thermocouple outside the blast furnace hearth when two thermocouples are set in pairs, then the two corresponding thermocouples are marked as abnormal thermocouples. And / or, if the thermocouple data processed by the sliding window remains constant within a preset time period, the corresponding thermocouple will be marked as an abnormal thermocouple.

6. The blast furnace thermocouple detection and correction method according to claim 1, characterized in that, The process of correcting the target thermocouple includes: If the thermocouple fails or no thermocouple temperature data is collected, the three-dimensional conjugate heat transfer model of the furnace cylinder is used to predict the temperature data of the corresponding failure point, and the predicted temperature data is used as a supplement to the thermocouple temperature data of the corresponding failure point.

7. The blast furnace thermocouple detection and correction method according to claim 1 or 6, characterized in that, The method further includes: The residual thickness of the blast furnace hearth refractory is calculated based on the corrected thermocouple temperature data, and the degree of erosion of the blast furnace hearth and the remaining service life of the blast furnace hearth are evaluated based on the calculation results. And / or, create a record based on the location of the thermocouples, and store the collected thermocouple temperature data according to the record creation results.

8. A blast furnace thermocouple detection and correction system, characterized in that, The system includes: Data acquisition module: used to acquire and store thermocouple temperature data at preset positions in the blast furnace hearth; The sample classification module is used to take the stored thermocouple temperature data as thermocouple temperature data samples and divide the thermocouple temperature data samples into training set and test set; The mechanism modeling module is used to establish a three-dimensional conjugate heat transfer model of the blast furnace hearth for thermocouple detection based on the parameters of the blast furnace hearth. The parameters of the blast furnace hearth include: the actual structure of the blast furnace hearth, the actual dimensions of the blast furnace hearth, the actual material composition of the blast furnace hearth, and the operating conditions of the blast furnace hearth. The model training module is used to perform simulation calculations on the three-dimensional conjugate heat transfer model of the furnace hearth using the training set, and to verify the three-dimensional conjugate heat transfer model of the furnace hearth after the simulation calculations are completed using the test set. An anomaly detection module is used to confirm whether the target thermocouple is abnormal based on the verified three-dimensional conjugate heat transfer model of the furnace hearth; wherein, the target thermocouple includes abnormal thermocouples screened based on pre-determined thermocouple reliability evaluation rules; The data correction module is used to correct the target thermocouple by using the simulation results of the verified three-dimensional conjugate heat transfer model of the furnace hearth when the target thermocouple is abnormal; and to supplement the temperature data of the failed thermocouple.

9. A computer device, characterized in that, The device includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the blast furnace thermocouple detection and correction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the steps of the blast furnace thermocouple detection and correction method according to any one of claims 1 to 7.

Images