Temperature detection method, device and readable storage medium

Abstract

The application discloses a temperature detection method, device and readable storage medium, and relates to the technical field of roller surface temperature detection. The temperature detection method comprises the following steps: acquiring a spectral image of a roller when a rolling mill stops working and the roller is separated from the rolling mill; determining a plurality of detection positions on the roller and determining a first wavelength and a second wavelength corresponding to each detection position, wherein the first wavelength is smaller than the second wavelength; determining a first brightness value and a second brightness value of each detection position according to the spectral image, wherein the first brightness value is a brightness value corresponding to the first wavelength, and the second brightness value is a brightness value corresponding to the second wavelength; determining a first temperature value of each detection position according to the first wavelength, the second wavelength, the first brightness value and the second brightness value of each detection position; and performing error correction on the first temperature value of each detection position, so that the first temperature value of each detection position is updated to a second temperature value. The application improves the temperature detection accuracy of the roller.

Description

Technical Field

[0001] This application relates to the field of roll surface temperature detection technology, and in particular to a temperature detection method, apparatus and readable storage medium. Background Technology

[0002] Hot rolling rolls are the core components in strip and sheet rolling production. Their surface temperature distribution directly affects the roll's service life and roll change cycle, as well as the shape accuracy, surface quality, and mechanical properties of the rolled strip and sheet. During hot rolling, the rolls are subjected to the combined effects of various factors such as high-temperature rolling force, cyclic contact stress, and cooling water, resulting in a continuous dynamic evolution of their surface condition.

[0003] To ensure the stability of the rolling process and the quality of the strip, it is necessary to control the roll surface temperature within a suitable range. Simultaneously, it is crucial to accurately monitor the axial temperature distribution of the roll surface after rolling, thus providing effective support for efficient roll utilization. Excessive axial temperature difference along the roll surface can lead to uneven thermal expansion, altering the roll profile, affecting the contact stress distribution between the roll and the strip, and ultimately causing strip shape defects. Furthermore, excessively high local temperatures accelerate oxide film peeling and uneven wear, shortening roll service life. However, existing roll temperature detection methods suffer from technical problems such as poor detection accuracy. Summary of the Invention

[0004] This application provides a temperature detection method, apparatus, and readable storage medium to solve technical problems such as poor detection accuracy in the prior art.

[0005] A first aspect of this application provides a temperature detection method applied to the rolls of a rolling mill, the method comprising: Acquire spectral images of the rolls when the mill stops operating and the rolls separate on the mill. Multiple detection positions on the roll are determined, and a first wavelength and a second wavelength are determined for each detection position, wherein the first wavelength is shorter than the second wavelength; Based on the spectral image, determine the first brightness value and the second brightness value at each detection location. The first brightness value is the brightness value corresponding to the first wavelength, and the second brightness value is the brightness value corresponding to the second wavelength. The first temperature value for each detection location is determined based on the first wavelength, the second wavelength, the first brightness value, and the second brightness value for each detection location. Error correction is applied to the first temperature value at each detection location so that the first temperature value at each detection location is updated to the second temperature value.

[0006] The temperature detection method in this embodiment determines the first brightness value and the second brightness value at each detection position on the roll based on the spectral image of the roll. According to the first wavelength, the second wavelength, the first brightness value and the second brightness value at each detection position, the first temperature value at each detection position is determined. The method of determining the temperature by wavelength and brightness value can ensure the accuracy of the first temperature value. Then, the first temperature value at each detection position is corrected for error so that the first temperature value at each detection position is updated to the second temperature value, which further improves the accuracy of the second temperature value, thereby improving the accuracy of the roll temperature detection.

[0007] A second aspect of this application provides a temperature detection device applied to the rolls of a rolling mill, the device comprising: The acquisition unit is used to acquire spectral images of the rolls when the mill stops working and the rolls separate on the mill. The first processing unit is used to determine multiple detection positions on the roll and to determine a first wavelength and a second wavelength corresponding to each detection position, wherein the first wavelength is smaller than the second wavelength. The second processing unit is used to determine a first brightness value and a second brightness value for each detection position based on the spectral image. The first brightness value is the brightness value corresponding to the first wavelength, and the second brightness value is the brightness value corresponding to the second wavelength. The third processing unit is used to determine the first temperature value of each detection location based on the first wavelength, the second wavelength, the first brightness value, and the second brightness value of each detection location. The fourth processing unit is used to perform error correction on the first temperature value at each detection location so that the first temperature value at each detection location is updated to the second temperature value.

[0008] A third aspect of this application provides another temperature detection device, including a processor and a memory. The memory stores a computer program, which, when executed by the processor, implements the steps of the temperature detection method as described in any of the above embodiments. Therefore, this temperature detection device possesses all the beneficial effects of the temperature detection method in any of the above embodiments, and will not be elaborated further here.

[0009] A fourth aspect of this application provides a readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the temperature detection method as described in any of the above embodiments. Therefore, this readable storage medium possesses all the beneficial effects of the temperature detection method in any of the above embodiments, which will not be elaborated further here. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A flowchart of the temperature detection method provided in the embodiments of this application; Figure 2 A functional block diagram of the temperature detection device provided in the embodiments of this application; Figure 3 This is a structural block diagram of the temperature detection device provided in an embodiment of this application. Detailed Implementation

[0012] To better understand the technical solutions provided in the embodiments of this specification, the technical solutions of the embodiments of this specification will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0013] In this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, without necessarily requiring or implying any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. The term "two or more" includes two or more cases.

[0014] In some embodiments, Figure 1 A flowchart of the temperature detection method provided in the embodiments of this application is shown below. Figure 1 As shown, an embodiment of this application provides a temperature detection method, including: Step S101: When the rolling mill stops working and the rolls separate on the rolling mill, acquire the spectral image of the rolls; In this embodiment, a temperature detection method is proposed, which is applied to the rolls of a rolling mill. A rolling mill is equipment that realizes the metal rolling process; it generally refers to equipment that completes the entire process of rolled material production and is widely used in industries such as steel and non-ferrous metal processing. It applies pressure to metal through rolls, causing plastic deformation, thereby producing various metal materials such as plates, pipes, and profiles. The rolls of the rolling mill are the core working components that directly contact the metal material and apply pressure to cause plastic deformation; they can be considered the "cutting edge" of the rolling process.

[0015] For example, a rolling mill roll mainly consists of three parts: the roll body, which is the part that directly participates in the rolling process, and whose surface can be smooth or grooved, determining the shape of the finished product; the roll neck, which is the part where the bearing is installed, bearing the rolling force and transmitting power; and the shaft head, which connects to the transmission device and transmits the motor torque to the roll body.

[0016] After the rolling mill stops working, the rolls are removed from the rolling mill.

[0017] For example, after the mill has completed one cycle of rolling, the rolls are removed from the mill.

[0018] When the rolls separate on the rolling mill, a spectral image of the rolls is obtained. The spectral image is a visualization of the intensity distribution of light at different wavelengths after the light is spread out according to wavelength. The core representation is a curve with wavelength on the horizontal axis and light intensity on the vertical axis.

[0019] For example, a hyperspectral camera can be used to photograph the rolls of a mill to obtain a spectral image. A hyperspectral camera is an advanced imaging device that can simultaneously acquire a two-dimensional spatial image of a target object and continuous, narrow-band one-dimensional spectral information, forming a data cube that combines image and spectrum, enabling precise identification of material composition and visualization of its spatial distribution.

[0020] For example, hardware selection and installation: A multi-wavelength spectral camera covering the near-infrared band is selected and deployed at the inspection station after the rolls exit the mill, ensuring that the camera's field of view completely covers the entire axial length of the rolls, adapting to the length range of rolls rolling different specifications of strip steel, and the spatial resolution must meet the requirements for fine detection of axial temperature distribution. It is paired with an industrial computer and data storage equipment, with the industrial computer having a built-in data processing module for data processing and archiving.

[0021] For example, the core parameters are preset as follows: at least two wavelength combinations, including short-wave and long-wave combinations, are pre-stored in the data processing module to accommodate the significant changes in emissivity caused by oxide film wear on the roll surface. A radiation brightness adaptation range is set to match the detection capability of a conventional 12-bit radiation brightness camera, and a preset baseline exposure is established. Additional preset radiation brightness fluctuation and stability thresholds are used to distinguish between the usable and unusable areas. Simultaneously, the parameters required for the core formula of the dual-wavelength radiation thermometry method are preset: the first radiation constant radiance c1, the second radiation constant radiance c2, the emissivity baseline coefficient A0, and the wavelength correlation coefficient A1.

[0022] Step S102: Determine multiple detection positions on the roll and determine the first wavelength and second wavelength corresponding to each detection position; Multiple detection positions are marked on the roll, where the detection positions are monitoring points for real-time temperature detection.

[0023] For example, multiple detection positions can be evenly distributed along the axis of the roll.

[0024] Determine the first wavelength and the second wavelength corresponding to each detection position, wherein the first wavelength is shorter than the second wavelength, and the first wavelength and the second wavelength are preset detection wavelengths.

[0025] For example, there is an inverse relationship between wavelength and temperature; that is, the higher the temperature of an object, the shorter the peak wavelength of the electromagnetic waves it radiates; the lower the temperature, the longer the peak wavelength.

[0026] For example, the first wavelength corresponding to multiple detection locations can be the same wavelength.

[0027] For example, the er-th wavelength corresponding to multiple detection locations can be the same wavelength.

[0028] Step S103: Determine the first brightness value and the second brightness value for each detection location based on the spectral image; The brightness of each detection location is determined based on the spectral image to determine the first brightness value and the second brightness value corresponding to each detection location. The first brightness value is the brightness value corresponding to the first wavelength, and the second brightness value is the brightness value corresponding to the second wavelength.

[0029] For example, based on a first wavelength, brightness is extracted at each detection location in the spectral image to obtain a first brightness value.

[0030] For example, based on the second wavelength, brightness is extracted at each detection location in the spectral image to obtain a second brightness value.

[0031] Step S104: Determine the first temperature value for each detection location based on the first wavelength, the second wavelength, the first brightness value, and the second brightness value for each detection location; Data calculations are performed on the first wavelength, second wavelength, first brightness value, and second brightness value at each detection location to obtain the first temperature value at each detection location, where the first temperature value is the initial temperature value of the detection location.

[0032] For example, when there are 100 detection positions on the roll, data calculations can be performed on the first wavelength, second wavelength, first brightness value and second brightness value of each detection position to obtain 100 first temperature values.

[0033] Step S105: Correct the error of the first temperature value at each detection location so that the first temperature value at each detection location is updated to the second temperature value.

[0034] After determining the first temperature value at each detection location, it is necessary to perform error correction on the first temperature value at each detection location so that the first temperature value at each detection location is updated to a second temperature value, where the second temperature value is the accurate temperature value.

[0035] For example, after obtaining 100 first temperature values, error correction can be performed on the first temperature value at each detection location so that the 100 first temperature values ​​are updated to 100 second temperature values, thus ensuring the numerical accuracy of the second temperature values.

[0036] For example, after obtaining the second temperature value at each detection location, the temperature distribution of the roll can be determined based on multiple second temperature values, thereby providing effective data support for the efficient utilization of the roll and ensuring the stability of the rolling process and the quality of the strip.

[0037] The temperature detection method in this embodiment determines the first brightness value and the second brightness value at each detection position on the roll based on the spectral image of the roll. According to the first wavelength, the second wavelength, the first brightness value and the second brightness value at each detection position, the first temperature value at each detection position is determined. The method of determining the temperature by wavelength and brightness value can ensure the accuracy of the first temperature value. Then, the first temperature value at each detection position is corrected for error so that the first temperature value at each detection position is updated to the second temperature value, which further improves the accuracy of the second temperature value, thereby improving the accuracy of the roll temperature detection.

[0038] By way of example, the temperature detection method in this embodiment has the following beneficial effects: The inspection is efficient and convenient, requiring no additional adjustments to the roll transfer process. The entire inspection process is automated, without disrupting the original production rhythm, and is easy to operate.

[0039] The temperature measurement is accurate and reliable. Through dynamic wavelength selection and formula correction, it effectively offsets the influence of fluctuations in the surface emissivity of the rolls. At the same time, it supports the detection of rolls with different wear conditions and specifications, and supports roll maintenance decisions.

[0040] In some embodiments, this application provides a temperature detection method, which determines a first temperature value at each detection location based on a first wavelength, a second wavelength, a first brightness value, and a second brightness value at each detection location, including: Determine the first emissivity of the roll at a first wavelength, and determine the second emissivity of the roll at a second wavelength; In this embodiment, the first emissivity of the roll is determined based on a first wavelength, wherein the first emissivity is the emissivity of the roll at the first wavelength.

[0041] The second emissivity of the roll is determined based on the second wavelength, wherein the second emissivity is the emissivity of the roll at the second wavelength.

[0042] For example, emissivity is a physical quantity that measures the ability of an object's surface to release energy in the form of radiation. Its value is the ratio of the energy radiated per unit area of ​​the object at a specific temperature to the energy radiated by a blackbody at the same temperature, ranging from 0 to 1.

[0043] Data processing is performed on the first wavelength, second wavelength, first brightness value, second brightness value, first emissivity and second emissivity at each detection location to obtain the first temperature value at each detection location.

[0044] Based on a preset calculation formula, the first wavelength, second wavelength, first brightness value, second brightness value, first emissivity, and second emissivity of each detection location are processed to obtain the first temperature value of each detection location.

[0045] For example, the formula for calculating the first temperature value is as follows: ; Wherein, E1 is the first brightness value, E2 is the second brightness value, ε1 is the first emissivity, ε2 is the second emissivity, λ1 is the first wavelength, λ2 is the second wavelength, T is the first temperature value, and c2 is a preset coefficient.

[0046] In some embodiments, this application provides a temperature detection method that performs error correction on a first temperature value at each detection location to update the first temperature value at each detection location to a second temperature value, including: Obtain the first reference coefficient and the first wavelength correlation coefficient corresponding to the first wavelength; The updated first emissivity is determined based on the first reference coefficient and the first wavelength correlation coefficient; Obtain the second reference coefficient and the second wavelength correlation coefficient corresponding to the second wavelength; The updated second emissivity is determined based on the second reference coefficient and the second wavelength correlation coefficient; The first temperature value is updated to the second temperature value based on the updated first emissivity and the updated second emissivity.

[0047] In this embodiment, a first reference coefficient and a first wavelength correlation coefficient corresponding to a first wavelength are obtained, wherein the first reference coefficient is the reference coefficient corresponding to the first wavelength, and the first wavelength correlation coefficient is the wavelength correlation coefficient corresponding to the first wavelength.

[0048] For example, the first reference coefficient can be the emissivity reference coefficient corresponding to the first wavelength.

[0049] The updated first emissivity is determined based on the first reference coefficient and the first wavelength correlation coefficient.

[0050] For example, the updated first emissivity is calculated as follows: ε1=A0+(A1 / λ1), where ε1 is the updated first emissivity, A0 is the first reference coefficient, and A1 is the first wavelength correlation coefficient.

[0051] Obtain the second reference coefficient and the second wavelength correlation coefficient corresponding to the second wavelength, where the second reference coefficient is the reference coefficient corresponding to the second wavelength and the second wavelength correlation coefficient is the wavelength correlation coefficient corresponding to the second wavelength.

[0052] The updated second emissivity is determined based on the second reference coefficient and the second wavelength correlation coefficient.

[0053] For example, the updated second emissivity is calculated as follows: ε2=A0+(A1 / λ2), where ε2 is the updated second emissivity, A0 is the second reference coefficient, and A1 is the second wavelength correlation coefficient.

[0054] The first temperature value is updated to the second temperature value based on the updated first emissivity and the updated second emissivity.

[0055] For example, a more accurate second temperature value can be obtained by recalculating the first temperature value based on the updated first emissivity and the updated second emissivity.

[0056] In some embodiments of this application, a temperature detection method is provided to acquire a spectral image of a roll, including: Obtain the initial image of the roll; Boundary recognition is performed on the initial image to determine the head boundary of the roll; Based on the shaft head boundary, obtain the spectral image of the roll.

[0057] In this embodiment, an initial image of the roll is obtained, wherein the initial image is an initial spectral image of the roll.

[0058] Boundary recognition is performed on the initial image to determine the roll head boundary, where the roll head boundary is the boundary where the roll head is located.

[0059] For example, the edge recognition algorithm is used to determine the head boundary of the roll in the initial image.

[0060] Based on the shaft head boundary, obtain the spectral image of the roll.

[0061] In some embodiments, this application provides a temperature detection method for acquiring a spectral image of a roll based on the shaft end boundary, including: Determine the sampling area of ​​the roll based on the shaft head boundary; Spectral data is collected from the acquisition area to obtain a spectral image.

[0062] In this embodiment, the collection area of ​​the roll is determined based on the shaft head boundary, wherein the collection area is the effective area where the spectrum to be collected is required.

[0063] Spectral data is collected from the acquisition area to obtain a spectral image.

[0064] In some embodiments, this application provides a temperature detection method that performs error correction on a first temperature value at each detection location so that the first temperature value at each detection location is updated to a second temperature value. The method further includes: The second temperature value at each detection location is integrated to obtain a set of temperature values ​​for the roll. A temperature distribution map of the rolls is established based on the set of temperature values.

[0065] In this embodiment, the second temperature value at each detection location is integrated into a dataset to obtain a set of temperature values ​​for the roll, wherein the set of temperature values ​​is a dataset that includes all the second temperature values.

[0066] Based on the set of temperature values, a temperature distribution map of the roll is established, where the temperature distribution map is a map representing the temperature distribution of the roll.

[0067] For example, precise temperature data from all positions along the axial direction of the roll are sequentially integrated to form a continuous axial temperature distribution map, clearly presenting key information such as the temperature difference between the used area and the non-used area, and the local axial temperature difference.

[0068] In some embodiments of this application, a temperature detection method is provided. After establishing a temperature distribution map of the roll based on a set of temperature values, the method further includes: Based on the temperature distribution diagram, determine the rolling parameters of the rolls; When the rolls are reinstalled on the rolling mill, the rolls are controlled to perform the rolling process according to the rolling parameters.

[0069] In this embodiment, the rolling parameters of the roll are determined based on the temperature distribution spectrum, wherein the rolling parameters are preset operating parameters of the roll.

[0070] When the rolls are reinstalled on the rolling mill, the rolls are controlled to perform the rolling process according to the rolling parameters.

[0071] For example, a temperature detection method may include: Step 1: Hardware Deployment and Core Parameter Preset (1) Hardware selection and installation: A multi-wavelength spectral camera covering the near-infrared band is selected and deployed at the inspection station after the rolls come off the mill. The camera's field of view must completely cover the entire axial length of the rolls, and it must be compatible with the length range of rolls rolling different specifications of strip steel. The spatial resolution must meet the requirements for fine detection of axial temperature distribution. An industrial computer and data storage equipment are used in conjunction with the industrial computer. The industrial computer has a built-in data processing module for data processing and archiving.

[0072] (2) Core parameter presets: At least two wavelength combinations, including short-wave and long-wave combinations, are pre-stored in the data processing module to accommodate the significant changes in emissivity caused by oxide film wear on the roll surface. A radiation brightness adaptation range is set to match the detection capability of a conventional 12-bit radiation brightness camera, and a preset baseline exposure is established. Additional preset radiation brightness fluctuation thresholds and stability judgment thresholds are used to distinguish between the usage area and the non-use area. Simultaneously, the parameters required for the core formula of the dual-wavelength radiation thermometry method are preset: the first radiation constant radiation brightness c1, the second radiation constant radiation brightness c2, the emissivity baseline coefficient A0, and the wavelength correlation coefficient A1.

[0073] Step 2: Roll positioning and inspection area division (1) Axial positioning of rolls: The hyperspectral camera takes an initial picture of the rolls after the machine. The data processing module analyzes the axial distribution of radiance in the image, identifies the boundary of the roll ends, clarifies the effective detection range of the axial direction, and eliminates background interference in non-roll areas.

[0074] (2) Distinguishing between the used and unused areas: The data processing module continuously collects and analyzes the radiance data along the axial direction of the roll, and automatically determines the used and unused areas of the roll based on a preset threshold. The unused area of ​​the roll surface does not contact the strip steel, and the surface condition is relatively uniform. Its radiance is stable, so the area with fluctuation amplitude below the stability determination threshold is the unused area. The used area of ​​the roll contacts the strip steel, and there is non-uniform oxide film wear in the transverse direction of the roll body. The surface condition varies greatly, so the area with fluctuation amplitude exceeding the radiance fluctuation threshold is the used area. The critical position where the radiance changes from a stable state to a fluctuating state is the boundary between the used and unused areas.

[0075] (3) Refined division of the usage area: Based on the spatial resolution of the hyperspectral camera, the usage area of ​​the roll is uniformly divided into several small areas along the axial direction. The width of each small area is matched with the spatial resolution of the camera to ensure that the radiance data of each small area can be accurately captured by the camera, so as to realize refined temperature measurement of different wear positions in the usage area.

[0076] Step 3: Initial Imaging Calibration (1) Trial shooting and radiation brightness detection: The camera performs trial shooting on the entire axial range of the roll and extracts the radiation brightness values ​​corresponding to the longest and shortest wavelengths in each region.

[0077] (2) Dynamic adjustment of exposure amount: If the radiance of the longest wavelength is lower than the preset lower limit, this situation is likely to occur in the non-use area, and the exposure amount needs to be increased; if the radiance of the shortest wavelength is higher than the preset upper limit, this situation is likely to occur when the oxide film in the use area is thin, and the exposure amount needs to be reduced. Repeat the adjustment until the radiance values ​​of each region along the axis fall within the adaptation range, determine the final imaging parameters, and avoid radiance saturation or insufficiency.

[0078] Step 4: Continuous acquisition of multi-wavelength radiance (1) Axial full-range imaging: The hyperspectral camera continuously captures images of the roll in the axial full range at a set frame rate. A single image can acquire multi-wavelength radiance data at each position of the roll in the axial direction, forming a hyperspectral image dataset, which provides the original data source for short-wavelength radiance E1 and long-wavelength radiance E2.

[0079] (2) Data preprocessing: The data processing module performs background current calibration and reference exposure conversion on the collected raw radiance data, and converts them into radiance values ​​under standard conditions to eliminate the influence of ambient light and equipment errors and ensure data consistency.

[0080] Step 5: Region Adaptation and Dynamic Wavelength Selection (1) Emissivity status judgment: For each detection position along the axial direction of the roll, the emissivity status is judged in combination with the classification of its use area or non-use area and the magnitude of its radiation brightness. The wear degree of oxide film in the use area is different, and the emissivity fluctuates greatly, and the radiation brightness is relatively high; the emissivity in the non-use area is low, and the radiation brightness is low.

[0081] (2) Matching the optimal wavelength combination: In the high emissivity region, select the short-wave combination wavelength λ1 to avoid radiance saturation; in the low emissivity region, select the long-wave combination wavelength λ2 to compensate for insufficient radiance. Ensure that the two most suitable wavelengths (λ1, λ2) are used for temperature measurement at each position of the roll axis.

[0082] Step 6: Calculate the precise temperature using the two-color radiometric method. (1) Initial temperature calculation: The data processing module extracts the corresponding standard radiance value (E1 corresponds to short wave and E2 corresponds to long wave) for each selected wavelength (λ1 is short wave and λ2 is long wave) at each position along the axial direction of the roll, substitutes it into the two-color radiation temperature measurement formula, and calculates the initial temperature value at that position in combination with the preset radiation constant.

[0083] (2) Error correction optimization: The wavelength correlation coefficient (A0, A1) of the surface emissivity of the roll is introduced. This coefficient is preset based on the material characteristics of the hot-rolled roll to correct the initial temperature value, eliminate the systematic error caused by the change in emissivity due to oxide film wear, and obtain accurate temperature data for each position of the roll axial direction.

[0084] Step 7: Integration and Output of Axial Temperature Distribution of Rolls (1) Generate a continuous temperature distribution map: The data processing module integrates the accurate temperature data of all positions along the axial direction of the roll in sequence to form a continuous axial temperature distribution curve or a visual heat map, which clearly presents key information such as the temperature difference between the use area and the non-use area and the local axial temperature difference.

[0085] (2) Data storage and feedback: The temperature distribution data of the roll body, the division results of the used and unused areas, the wavelength selection record, and the parameters of the formula calculation process are stored synchronously in the database. At the same time, the data is output to the detection system terminal to provide data support for roll maintenance (such as roll cooling strategy adjustment, roll grinding amount setting, etc.).

[0086] Step 8: Dynamic Adaptation and Detection Process Iteration (1) Real-time parameter adjustment: If the radiation brightness of a certain area is found to be outside the adaptation range during the detection process, such as the local oxide film peeling off the roll causing a sudden change in emissivity, the system will automatically return to step 3 to recalibrate the exposure amount, and synchronously adjust the wavelength combination (λ1, λ2) of the area. After re-collecting the radiation brightness data (E1, E2), the temperature will be recalculated using the core temperature measurement formula and emissivity correction formula in step 6 to ensure the accuracy of temperature measurement.

[0087] (2) Multi-batch roll adaptation optimization: For rolls with different usage periods, the wear degree of oxide film on these rolls varies. Record the emissivity change law and the optimal wavelength combination (λ1, λ2) and exposure parameters. At the same time, based on the calculation results, optimize the coefficients (A0, A1) of the emissivity correction formula and update the preset parameter library of the data processing module so that the subsequent calculation is more suitable for the characteristics of rolls with different wear states, and improve the adaptation speed and accuracy of roll detection.

[0088] In some embodiments, Figure 2 This is a functional block diagram of the temperature detection device provided in the embodiments of this application, such as... Figure 2 As shown, an embodiment of this application provides a temperature detection device 200, including: The acquisition unit 202 is used to acquire a spectral image of the roll when the mill stops working and the rolls separate on the mill. The first processing unit 204 is used to determine multiple detection positions on the roll and to determine a first wavelength and a second wavelength corresponding to each detection position, wherein the first wavelength is smaller than the second wavelength. The second processing unit 206 is used to determine a first brightness value and a second brightness value for each detection position based on the spectral image, wherein the first brightness value is the brightness value corresponding to the first wavelength and the second brightness value is the brightness value corresponding to the second wavelength. The third processing unit 208 is used to determine the first temperature value of each detection location based on the first wavelength, the second wavelength, the first brightness value, and the second brightness value of each detection location. The fourth processing unit 210 is used to perform error correction on the first temperature value of each detection position so that the first temperature value of each detection position is updated to the second temperature value.

[0089] In some embodiments of this application, a temperature detection device 200 is provided, and the third processing unit 208 is further configured to: Determine the first emissivity of the roll at a first wavelength, and determine the second emissivity of the roll at a second wavelength; Data processing is performed on the first wavelength, second wavelength, first brightness value, second brightness value, first emissivity and second emissivity at each detection location to obtain the first temperature value at each detection location.

[0090] In some embodiments of this application, a temperature detection device 200 is provided, and the third processing unit 208 is further configured to: Obtain the first reference coefficient and the first wavelength correlation coefficient corresponding to the first wavelength; The updated first emissivity is determined based on the first reference coefficient and the first wavelength correlation coefficient; Obtain the second reference coefficient and the second wavelength correlation coefficient corresponding to the second wavelength; The updated second emissivity is determined based on the second reference coefficient and the second wavelength correlation coefficient; The first temperature value is updated to the second temperature value based on the updated first emissivity and the updated second emissivity.

[0091] In some embodiments of this application, a temperature detection device 200 is provided, and the acquisition unit 202 is further configured to: Obtain the initial image of the roll; Boundary recognition is performed on the initial image to determine the head boundary of the roll; Based on the shaft head boundary, obtain the spectral image of the roll.

[0092] In some embodiments of this application, a temperature detection device 200 is provided, and the acquisition unit 202 is further configured to: Determine the sampling area of ​​the roll based on the shaft head boundary; Spectral data is collected from the acquisition area to obtain a spectral image.

[0093] In some embodiments of this application, a temperature detection device 200 is provided, further comprising a fifth processing unit for: The second temperature value at each detection location is integrated to obtain a set of temperature values ​​for the roll. A temperature distribution map of the rolls is established based on the set of temperature values.

[0094] In some embodiments of this application, a temperature detection device 200 is provided, and the fifth processing unit is further configured to: Based on the temperature distribution diagram, determine the rolling parameters of the rolls; When the rolls are reinstalled on the rolling mill, the rolls are controlled to perform the rolling process according to the rolling parameters.

[0095] In some embodiments, Figure 3 This is a structural block diagram of the temperature detection device provided in the embodiments of this application, such as... Figure 3 As shown, a temperature detection device 300 is proposed. The temperature detection device 300 includes a processor 302 and a memory 304. The memory 304 stores a computer program, which, when executed by the processor 302, implements the steps of the temperature detection method as described in any of the above embodiments. Therefore, the temperature detection device 300 possesses all the beneficial effects of the temperature detection method in any of the above embodiments, which will not be elaborated further here.

[0096] In some embodiments, a readable storage medium is provided having a program stored thereon, which, when executed by a processor, implements the steps of the temperature detection method as described in any of the above embodiments, and thus has all the beneficial technical effects of the temperature detection method in any of the above embodiments.

[0097] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0098] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-readable program code.

[0099] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will 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 provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0100] These 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 function specified in one or more boxes.

[0101] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment 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.

[0102] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to perform a temperature detection method.

[0103] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0104] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0105] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0106] The units described as separate components may or may not be physically separate. 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 can be selected to achieve the purpose of this embodiment according to actual needs.

[0107] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0108] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0109] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

[0110] Although preferred embodiments have been described in this specification, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this specification.

[0111] Obviously, those skilled in the art can make various modifications and variations to this specification without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims and their equivalents, this specification is also intended to include such modifications and variations.

Claims

1. A temperature detection method, characterized in that, The method, applied to the rolls of a rolling mill, includes: When the mill stops operating and the rolls separate on the mill, a spectral image of the rolls is acquired; Multiple detection positions on the roll are determined, and a first wavelength and a second wavelength are determined for each detection position, wherein the first wavelength is smaller than the second wavelength; Based on the spectral image, a first brightness value and a second brightness value are determined for each detection position, wherein the first brightness value is the brightness value corresponding to the first wavelength and the second brightness value is the brightness value corresponding to the second wavelength. A first temperature value is determined for each detection location based on the first wavelength, the second wavelength, the first brightness value, and the second brightness value at each detection location; Error correction is performed on the first temperature value at each of the detection locations so that the first temperature value at each of the detection locations is updated to a second temperature value.

2. The method according to claim 1, characterized in that, The step of determining a first temperature value for each detection location based on the first wavelength, the second wavelength, the first brightness value, and the second brightness value for each detection location includes: Determine the first emissivity of the roll at the first wavelength, and determine the second emissivity of the roll at the second wavelength; Data processing is performed on the first wavelength, the second wavelength, the first brightness value, the second brightness value, the first emissivity, and the second emissivity at each detection location to obtain the first temperature value at each detection location.

3. The method according to claim 2, characterized in that, The step of correcting the error of the first temperature value at each detection location to update the first temperature value at each detection location to a second temperature value includes: Obtain the first reference coefficient and the first wavelength correlation coefficient corresponding to the first wavelength; The updated first emissivity is determined based on the first reference coefficient and the first wavelength correlation coefficient; Obtain the second reference coefficient and the second wavelength correlation coefficient corresponding to the second wavelength; The updated second emissivity is determined based on the second reference coefficient and the second wavelength correlation coefficient; The first temperature value is updated to the second temperature value based on the updated first emissivity and the updated second emissivity.

4. The method according to claim 1, characterized in that, The step of acquiring the spectral image of the roll includes: Obtain an initial image of the roll; Boundary recognition is performed on the initial image to determine the shaft head boundary of the roll; Based on the shaft head boundary, the spectral image of the roll is obtained.

5. The method according to claim 1, characterized in that, The step of acquiring the spectral image of the roll based on the shaft head boundary includes: The collection area of ​​the roll is determined based on the shaft head boundary; The spectral data of the acquisition area is acquired to obtain the spectral image.

6. The method according to any one of claims 1 to 5, characterized in that, After correcting the first temperature value at each detection location for errors, so that the first temperature value at each detection location is updated to a second temperature value, the method further includes: The second temperature value at each of the detection locations is integrated to obtain a set of temperature values ​​for the roll. Based on the set of temperature values, a temperature distribution map of the roll is established.

7. The method according to claim 6, characterized in that, After establishing the temperature distribution map of the roll based on the set of temperature values, the method further includes: Based on the temperature distribution spectrum, the rolling parameters of the roll are determined; When the rolls are reinstalled on the mill, the rolls are controlled to perform the rolling process according to the rolling parameters.

8. A temperature detection device, characterized in that, The device, used for rolling mill rolls, includes: The acquisition unit is used to acquire a spectral image of the roll when the mill stops working and the roll separates on the mill; A first processing unit is configured to determine multiple detection positions on the roll and determine a first wavelength and a second wavelength corresponding to each detection position, wherein the first wavelength is less than the second wavelength. The second processing unit is configured to determine a first brightness value and a second brightness value for each detection position based on the spectral image, wherein the first brightness value is the brightness value corresponding to the first wavelength and the second brightness value is the brightness value corresponding to the second wavelength. The third processing unit is used to determine a first temperature value for each detection location based on the first wavelength, the second wavelength, the first brightness value, and the second brightness value for each detection location. The fourth processing unit is used to perform error correction on the first temperature value at each of the detection locations, so that the first temperature value at each of the detection locations is updated to a second temperature value.

9. A temperature detection device, characterized in that, include: processor; A memory, which stores programs or instructions, wherein a processor, when executing the programs or instructions in the memory, implements the steps of the temperature detection method as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that, A program or instructions are stored on a readable storage medium, which, when executed by a processor, implement the steps of the temperature detection method as described in any one of claims 1 to 7.

Images