A temperature calibration model construction method and device, and a temperature control method and device

Abstract

The application provides a temperature calibration model construction method and device, a temperature control method and equipment, and relates to the technical field of high-temperature testing of metal materials. The method comprises periodically collecting a first thermal parameter, a first thermocouple temperature measurement value, an infrared temperature measurement value and a first material image when each preset metal material is heated; a first true temperature estimation value is obtained from the first thermal parameter and the first thermocouple temperature measurement value by using a preset heat conduction model, and a first heat conduction model is obtained by correcting the preset heat conduction model according to a first deviation; a second true temperature estimation value corresponding to a first material image in which a preset solid-liquid coexistence feature is first detected is determined; and the first heat conduction model is corrected according to a second deviation between each second true temperature estimation value and a reference melting point value to obtain a temperature calibration model. The application compensates for the thermocouple hysteresis effect based on the infrared temperature measurement value, improves the model precision by using the reference melting point value of the material itself, and ensures the accuracy and reliability of temperature estimation.

Description

Technical Field

[0001] This invention relates to the field of high-temperature testing technology for metallic materials, and more specifically, to a method, apparatus, temperature control method, and equipment for constructing a temperature calibration model. Background Technology

[0002] In fields such as in-situ observation under high-energy beam heating, the observed microstructure evolution processes, such as phase transitions, recrystallization, and dissolution of precipitated phases, can be correlated with precise temperature values ​​in real time. This can help researchers gain a deeper understanding of the intrinsic mechanisms of microstructural changes in materials under the action of high-energy beams, providing key evidence for material performance optimization and the development of new materials.

[0003] However, the response of commonly used temperature sensors (such as thermocouples) usually lags behind the actual temperature change of the material. When the sensor temperature reaches the set value, the actual temperature of the material has already far exceeded the set value, so the measured temperature data cannot truly reflect the real-time temperature state at the laser spot. Summary of the Invention

[0004] The problem addressed by this invention is how to achieve both accuracy and reliability in temperature measurement.

[0005] To address the above problems, this invention provides a method for constructing a temperature calibration model, comprising: The first thermal parameters, the first thermocouple temperature measurement value, the infrared temperature measurement value, and the first material image are periodically collected when heating each preset metal material. Using a preset heat conduction model, a first true temperature estimate is obtained based on the first thermal parameters and the first thermocouple temperature measurement value. The preset heat conduction model is then corrected based on the first deviation between the first true temperature estimate and the corresponding infrared temperature measurement value to obtain a first heat conduction model. The preset heat conduction model is used to describe the dynamic relationship between the thermal parameters, the thermocouple temperature measurement value, and the true temperature estimate. For each of the preset metallic materials, a second true temperature estimate corresponding to the first material image that first detects the preset solid-liquid phase coexistence characteristics is determined; wherein, the second true temperature estimate is obtained using the first heat conduction model based on the first thermal parameters corresponding to the first material image and the temperature measured by the first thermocouple. The first heat conduction model is corrected based on the second deviation between each of the second true temperature estimates and the corresponding pre-associated reference melting point value of the preset metal material to obtain the second heat conduction model, and a temperature calibration model is obtained based on the second heat conduction model.

[0006] Optionally, the thermal parameters include ambient temperature and laser power; the preset heat conduction model satisfies: C×dTtrue / dt=P heat -(T true -T env ) / R; T true =T tc +ΔT error ; Among them, T true T represents the estimated true temperature value; tc This indicates the temperature value measured by the thermocouple; T env P represents the ambient temperature; heat The laser power is represented by C; the equivalent specific heat capacity is represented by R; the equivalent thermal resistance is represented by ΔT. error This indicates the error term.

[0007] Optionally, the error term satisfies: ; Where, ΔT bias Indicates static systematic error; This represents the time constant.

[0008] Optionally, correcting the preset heat conduction model based on the first deviation between the first estimated true temperature value and the corresponding infrared thermometric value includes: Using the least squares method, with the goal of minimizing the sum of squares of each of the first deviations, the static system error, time constant, equivalent specific heat capacity, and equivalent thermal resistance in the preset heat conduction model are updated. And / or, the step of correcting the first heat conduction model based on the second deviation between each of the second true temperature estimates and the corresponding pre-associated reference melting point value of the preset metallic material includes: Using the least squares method, with the goal of minimizing the sum of squares of each of the second deviations, the static system error, time constant, equivalent specific heat capacity, and equivalent thermal resistance in the first heat conduction model are updated.

[0009] Optionally, obtaining the temperature calibration model based on the second heat conduction model includes: The system collects the second thermal parameters, the second thermocouple temperature value, and the second material image when heating the metal material to be tested, and obtains the reference metallographic temperature values ​​corresponding to the occurrence of each preset metallographic feature of the metal material to be tested. For each of the preset metallographic features, a third true temperature estimate corresponding to the first material image that detects the preset metallographic feature is determined; wherein, the third true temperature estimate is obtained using the second heat conduction model based on the second thermal parameters corresponding to the second material image and the temperature measured by the second thermocouple; The second heat conduction model is corrected based on the third deviation between each of the third true temperature estimates and the corresponding reference metallographic temperature values ​​to obtain the temperature calibration model.

[0010] Optionally, the step of correcting the second heat conduction model based on the third deviation between each of the third true temperature estimates and the corresponding reference metallographic temperature values ​​includes: Using the least squares method, with the goal of minimizing the sum of squares of each of the third deviations, the equivalent specific heat capacity and equivalent thermal resistance in the second heat conduction model are updated.

[0011] In this invention, the first thermal parameters, first thermocouple temperature readings, infrared temperature readings, and first material images are periodically collected when heating each preset metal material. This facilitates multi-dimensional verification and analysis of the temperature conditions during the heating process of the preset metal materials, providing a comprehensive data foundation for the construction of a temperature calibration model. Based on this, a preset heat conduction model is constructed to quantify the dynamic relationship between the thermal parameters, thermocouple temperature readings, and the estimated true temperature. This improves the reliability of the first true temperature estimate obtained using the preset heat conduction model based on the first thermal parameters and the first thermocouple temperature readings. Furthermore, since the infrared temperature measurement device uses non-contact measurement, it responds quickly to temperature changes, which is beneficial for reflecting the actual temperature of the preset metal material. Therefore, the first deviation between the first true temperature estimate and the corresponding infrared temperature reading in this invention reflects the deviation between the first true temperature estimate and the more real-time infrared temperature reading caused by the thermocouple hysteresis effect. Thus, the preset heat conduction model is corrected based on the first deviation to obtain the first heat conduction model, which helps compensate for the hysteresis effect of thermocouple temperature measurement caused by heat conduction delay. Furthermore, this invention utilizes a first heat conduction model to determine, based on first thermal parameters and first thermocouple temperature measurements, the second true temperature estimate corresponding to the first material image that detects the preset solid-liquid phase coexistence characteristic (i.e., the temperature estimate corresponding to the initial moment when the preset metal material melts), and obtains the pre-associated reference melting point value of the preset metal material. This is equivalent to using the inherent physical properties of the preset metal material combined with the identification of the preset solid-liquid phase coexistence characteristic to provide a more accurate actual temperature reference than the infrared temperature measurement value for the second true temperature estimate estimated by the first heat conduction model when the preset metal material melts. Thus, this invention corrects the first heat conduction model based on the second deviation between the second true temperature estimate and the corresponding reference melting point value, thereby further refining the preset heat conduction model, improving model accuracy, and ensuring that the final temperature calibration model guarantees the accuracy and reliability of temperature estimation.

[0012] The present invention also provides a temperature control method, comprising: Periodically collect the current thermal parameters, current thermocouple temperature readings, and current material images corresponding to the heating of the metal material under test; The current true temperature estimate is obtained using a temperature calibration model based on the current thermal parameters and the current thermocouple temperature measurement value, and the current true temperature estimate is correlated with the current material image; wherein, the temperature calibration model is constructed based on the temperature calibration model construction method according to any one of claims 1-6; The heating power is controlled based on the target deviation between the current estimated actual temperature and the preset target control temperature corresponding to the current cycle.

[0013] This invention periodically collects current thermal parameters, current thermocouple temperature readings, and current material images. The current thermal parameters and thermocouple temperature readings are then input into a temperature calibration model constructed using the previously described temperature calibration model construction method. This compensates for the thermocouple's hysteresis, yielding an accurate and reliable estimate of the current true temperature. This estimate is then correlated with the corresponding current material image, facilitating the observation of the phase transition behavior of the tested metallic material at different temperatures. Furthermore, this invention can obtain the preset target control temperature corresponding to the current period, determine the target deviation between the current true temperature estimate and the preset target control temperature, and perform feedback control of the heating power of the heating device based on the target deviation. This effectively improves the accuracy of temperature control and reduces temperature overshoot.

[0014] The present invention also provides a temperature calibration model construction apparatus, comprising: The information acquisition module is used to periodically acquire the first thermal parameters, the first thermocouple temperature measurement value, the infrared temperature measurement value, and the first material image when heating each preset metal material. The first correction module is used to obtain a corresponding first true temperature estimate based on the first thermal parameters and the first thermocouple temperature measurement value using a preset heat conduction model, and to correct the preset heat conduction model based on a first deviation between the first true temperature estimate and the corresponding infrared temperature measurement value to obtain a first heat conduction model; wherein, the preset heat conduction model is used to describe the dynamic relationship between the thermal parameters, the thermocouple temperature measurement value and the true temperature estimate. A temperature estimation module is used to determine, for each of the preset metal materials, a second true temperature estimate corresponding to the first material image that first detects the preset solid-liquid phase coexistence characteristics; wherein the second true temperature estimate is obtained using the first heat conduction model based on the first thermal parameters corresponding to the first material image and the temperature measured by the first thermocouple. The second correction module is used to correct the first heat conduction model based on the second deviation between each of the second true temperature estimates and the corresponding preset metal material’s pre-associated reference melting point value, to obtain a second heat conduction model, and to obtain a temperature calibration model based on the second heat conduction model.

[0015] The temperature calibration model construction device and the temperature calibration model construction method provided by this invention have essentially the same advantages over the prior art, and will not be repeated here.

[0016] The present invention also provides an electronic device, including a memory and a processor; The memory is used to store computer programs; The processor is used to implement the temperature calibration model construction method as described above, or to implement the temperature control method as described above, when executing the computer program.

[0017] The electronic device and the temperature calibration model construction method provided by this invention have essentially the same advantages over the prior art, and will not be elaborated further here.

[0018] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the temperature calibration model construction method as described above, or implements the temperature control method as described above.

[0019] The computer-readable storage medium provided by this invention has essentially the same advantages as the temperature calibration model construction method, or the temperature control method, compared to the prior art, and will not be elaborated further here. Attached Figure Description

[0020] Figure 1 This is a schematic flowchart of the temperature calibration model construction method according to an embodiment of the present invention; Figure 2 This is a schematic flowchart of the temperature control method according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the temperature control curve of the temperature control method according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the temperature calibration model construction device according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0021] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the accompanying drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0022] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0023] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optionally" means "optional embodiments". Definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc., mentioned in this invention are used only to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0024] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0025] like Figure 1 As shown in the figure, an embodiment of the present invention provides a method for constructing a temperature calibration model, which includes the following steps: S11: Periodically collect the first thermal parameters, the first thermocouple temperature measurement value, the infrared temperature measurement value, and the first material image when heating each preset metal material.

[0026] Specifically, in this embodiment, the "preset metal material" refers to a specific metal material selected beforehand for the experiment, such as aluminum alloys, titanium alloys, and steel materials, which have known reference melting points. The "first thermal parameter" in this embodiment refers to parameters related to heat transfer and heat conversion collected during the heating of the preset metal material, such as heating power and ambient temperature. These parameters describe the thermal state during the heating process. The "first thermocouple temperature measurement value" in this embodiment refers to the temperature value measured using a thermocouple when heating the preset metal material. Due to the contact-type temperature measurement, a hysteresis effect is unavoidable, but the temperature measurement performance is relatively stable and not prone to temperature drift. In this embodiment, the thermocouple probe is located on the upper surface of the preset metal material sample (i.e., the same surface heated by the high-energy beam, which can be fixed by welding) and adjacent to the observation area (i.e., the area covered by the first material image). During actual in-situ observation, the laser spot directly irradiates the surface of the sample observation area, depositing energy there and causing the temperature of the observation area to rise rapidly. The high temperature of the observation area diffuses the heat to the surroundings through the thermal conduction of the sample material itself, thereby transferring it to the thermocouple. In this embodiment, the infrared thermometry value refers to the temperature value of the surface of a preset metal material (such as the observation area) measured by an infrared thermometry device during the heating process. Infrared thermometry devices typically have a fast temperature response, but are prone to temperature drift. In this embodiment, the first material image refers to the material image acquired when the preset metal material is heated. This image can be acquired using a high-speed or high-frame-rate microscopic imaging device and is used to record the state changes of the sample in the observation area.

[0027] In one embodiment, when heating each preset metal material, the first thermal parameter, the first thermocouple temperature value, the infrared temperature value, and the first material image can be collected periodically (e.g., every 10ms). The information collected in the same period can be associated with the corresponding collection time to facilitate time alignment.

[0028] S12: Using a preset heat conduction model, based on the first thermal parameters and the first thermocouple temperature measurement value, obtain the corresponding first true temperature estimate value, and correct the preset heat conduction model based on the first deviation between the first true temperature estimate value and the corresponding infrared temperature measurement value to obtain the first heat conduction model; wherein, the preset heat conduction model is used to describe the dynamic relationship between the thermal parameters, the thermocouple temperature measurement value and the true temperature estimate value.

[0029] Specifically, the preset heat conduction model referred to in this embodiment can be a pre-defined mathematical model used to describe the dynamic relationship between thermal parameters, thermocouple temperature measurements, and the estimated true temperature. It can be constructed based on the basic principles of heat conduction. The first estimated true temperature in this embodiment refers to the estimated true temperature obtained by using the preset heat conduction model, combined with the first thermal parameters and the first thermocouple temperature measurement.

[0030] In one embodiment, heat is conducted from a high-temperature area to a low-temperature area at a rate that depends on the material's specific heat capacity, geometric dimensions, and other thermal parameters. Correspondingly, in the field of in-situ observation with high-energy beam heating, the heat conduction rate from laser energy to a pre-defined metallic sample, and from the sample to the thermocouple, is also influenced by thermal parameters. This embodiment can construct a dynamic relationship between thermal parameters, thermocouple temperature measurements, and estimated true temperatures based on heat conduction theory (e.g., the path of heat transfer from the laser energy deposition point to the pre-defined metallic sample follows Fourier's law of heat conduction and the principle of energy conservation; this process can be described by a one-dimensional or lumped-parameter form of unsteady-state heat conduction differential equation). After constructing the pre-defined heat conduction model, the corresponding first estimated true temperature can be obtained using the pre-defined heat conduction model based on the first thermal parameters and the first thermocouple temperature measurement. The first deviation between each first estimated true temperature and the corresponding infrared temperature measurement (based on time alignment matching) is then obtained. Based on this, the coefficients of the pre-defined heat conduction model can be adjusted according to the first deviation (e.g., using the least squares method or gradient descent method), thereby obtaining the first heat conduction model based on the corrected pre-defined heat conduction model.

[0031] S13: For each preset metal material, determine the second true temperature estimate corresponding to the first material image that first detects the preset solid-liquid phase coexistence characteristics; wherein, the second true temperature estimate is obtained using the first heat conduction model based on the first thermal parameters corresponding to the first material image and the temperature value measured by the first thermocouple.

[0032] Specifically, the preset solid-liquid coexistence characteristic referred to in this embodiment indicates that the metallic material exhibits the characteristic of simultaneously existing in solid and liquid states when it reaches its melting point. This is a key state transition point during the heating process of the metallic material and can be detected using a preset first image recognition model. The second true temperature estimate referred to in this embodiment represents an estimate of the current true temperature obtained using the first heat conduction model based on the first thermal parameters and the temperature measurement value of the first thermocouple.

[0033] In one embodiment, multiple historical images containing solid-liquid phase coexistence characteristics can be pre-acquired and labeled with feature tags to obtain a training set. Based on this, an initial image recognition model can be trained using the training set to obtain a first image recognition model. In practical use, for a preset metallic material (such as gold), the acquired images of each first material can be input into the first image recognition model according to their acquisition sequence. The acquisition time corresponding to the first material image that first recognizes the preset solid-liquid phase coexistence characteristics (i.e., the first material image that detects the preset solid-liquid phase coexistence characteristics) is obtained. The first thermal parameters and the first thermocouple temperature measurement value acquired at the acquisition time corresponding to the first material image are then input into the first heat conduction model to obtain the second true temperature estimate corresponding to the first material image that first detects the preset solid-liquid phase coexistence characteristics. Similarly, the second true temperature estimates corresponding to other preset metallic materials can be determined separately.

[0034] S14: Correct the first heat conduction model based on the second deviation between each second true temperature estimate and the corresponding preset reference melting point value of the metal material, obtain the second heat conduction model, and obtain the temperature calibration model based on the second heat conduction model.

[0035] Specifically, in this embodiment, a pre-associated reference melting point value for the metal material is preset. This is an inherent characteristic of the metal material and can be determined by consulting metal property parameter data. After obtaining each second true temperature estimate, a second deviation between the second true temperature estimate and the corresponding reference melting point value can be determined. Based on this second deviation, the first heat conduction model is corrected to obtain a second heat conduction model, and thus a temperature calibration model is obtained based on the second heat conduction model. For example, in this embodiment, the gradient descent method can be used. By calculating the gradient of the loss function with respect to the model parameters and updating the model parameters in the opposite direction of the gradient, the value of the loss function is gradually reduced. Therefore, after obtaining the second heat conduction model, it can be directly used as the temperature calibration model.

[0036] In this embodiment, the first thermal parameters, first thermocouple temperature measurement value, infrared temperature measurement value, and first material image are periodically collected when heating each preset metal material. This facilitates multi-dimensional verification and analysis of the temperature situation during the heating process of the preset metal materials, providing a comprehensive data foundation for the construction of the temperature calibration model. Based on this, by constructing a preset heat conduction model, it is beneficial to quantitatively express the dynamic relationship between the thermal parameters, thermocouple temperature measurement value, and the estimated true temperature value. This improves the reliability of the first true temperature estimate obtained using the preset heat conduction model based on the first thermal parameters and the first thermocouple temperature measurement value. Furthermore, since the infrared temperature measurement device uses non-contact temperature measurement, it responds quickly to temperature changes, which is beneficial for reflecting the actual temperature of the preset metal material. Therefore, in this embodiment, determining the first deviation between the first true temperature estimate and the corresponding infrared temperature measurement value can reflect the deviation between the first true temperature estimate and the more real-time infrared temperature measurement value caused by the thermocouple hysteresis effect. Thus, by correcting the preset heat conduction model based on the first deviation, the first heat conduction model is obtained, which is beneficial for compensating for the hysteresis effect of thermocouple temperature measurement caused by heat conduction delay. Furthermore, in this embodiment, the first heat conduction model determines the second true temperature estimate corresponding to the first material image that detects the preset solid-liquid phase coexistence characteristic (i.e., the temperature estimate corresponding to the initial moment when the preset metal material melts) based on the first thermal parameters and the temperature value measured by the first thermocouple, and obtains the reference melting point value pre-associated with the preset metal material. This is equivalent to using the inherent physical properties of the preset metal material combined with the identification of the preset solid-liquid phase coexistence characteristic to provide a more accurate actual temperature reference than the infrared temperature measurement value for the second true temperature estimate estimated by the first heat conduction model when the preset metal material melts. Thus, this embodiment corrects the first heat conduction model based on the second deviation between the second true temperature estimate and the corresponding reference melting point value, thereby achieving further correction of the preset heat conduction model, improving model accuracy, and ensuring that the final temperature calibration model can guarantee the accuracy and reliability of temperature estimation.

[0037] Optionally, the thermal parameters include ambient temperature and laser power; the preset heat conduction model satisfies: C×dT true / dt=P heat -(T true -T env ) / R; T true =T tc +ΔT error ; Among them, T true T represents the estimated true temperature. tc Indicates the temperature measured by the thermocouple; T env Indicates ambient temperature; P heatIndicates laser power; C represents equivalent specific heat capacity; R represents equivalent thermal resistance; ΔT error This indicates the error term.

[0038] Optionally, the error term satisfies: ; Where, ΔT bias Indicates static systematic error; This represents the time constant.

[0039] Specifically, the thermal parameters in this embodiment include ambient temperature and laser power. Ambient temperature refers to the temperature of the environment surrounding the preset metal material, which is a crucial factor influencing the heat conduction process between the sample and the thermocouple. Laser power refers to the current power of the laser used to heat the preset metal material, which determines the amount of heat input to the preset metal material per unit time. Equivalent specific heat capacity refers to the equivalent value of the specific heat capacity between the laser energy deposition point and the preset metal material, and between the preset metal material and the surrounding environment (including the thermocouple) during heat conduction in the heat conduction path. The initial value of the equivalent specific heat capacity in the preset heat conduction model can be selected from the specific heat capacity of the preset metal material. Equivalent thermal resistance refers to the equivalent value of the thermal resistance between the laser energy deposition point and the preset metal material, and between the preset metal material and the surrounding environment (including the thermocouple) during heat conduction in the heat conduction path, which affects the rate of heat transfer. Similarly, the initial value of the equivalent thermal resistance in this embodiment can be selected from the thermal resistance of the preset metal material.

[0040] In one embodiment, based on the theory of unsteady-state heat conduction, for a pre-defined metallic sample heated by a localized laser beam, the heat transfer path from the energy deposition point to the sample can be abstracted as a lumped-parameter thermal system. This system satisfies the law of conservation of energy, that is, the increase in thermal energy in the observation area per unit time equals the heating power minus the heat power lost to the environment. Therefore, according to the law of conservation of energy, the rate of increase in thermal energy within the control zone equals the input thermal power. By outputting thermal power, a heat conduction model between the energy deposition point and the preset metallic material can be constructed: C×dT true / dt=P heat -(T true -T env ) / R; Based on this, the estimated true temperature of the preset metallic material can be described as the sum of the current actual measurement value of the thermocouple (i.e., the thermocouple temperature reading) and the measurement error caused by the thermocouple hysteresis: T true =T tc +ΔT error ; Among them, T trueT represents the estimated true temperature. tc Indicates the temperature measured by the thermocouple; T env Indicates ambient temperature; P heat Indicates laser power; C represents equivalent specific heat capacity; R represents equivalent thermal resistance; ΔT error The error term is represented by the default heat conduction model, which can be used to describe the dynamic relationship between thermal parameters, thermocouple temperature measurements and actual temperature estimates.

[0041] Furthermore, in this embodiment, the error term caused by the thermocouple hysteresis can be decomposed into static system errors (such as poor contact, cold junction compensation errors, electromagnetic interference, etc.) and dynamic hysteresis errors (random noise is negligible). In this embodiment, assuming the thermocouple's dynamic response is a first-order inertial element, the error term can be obtained as follows: ; Where, ΔT bias Indicates static systematic error; This represents the time constant; the initial value of the time constant can be set to 1.

[0042] In this implementation, a thermal conduction relationship between the estimated true temperature and the energy deposition point is established by considering multiple thermal parameters such as ambient temperature and laser power, as well as the equivalent specific heat capacity and equivalent thermal resistance of the heat conduction path. Simultaneously, the estimated true temperature is described as the sum of the thermocouple's current actual temperature measurement and the measurement error term caused by the thermocouple's hysteresis, which helps compensate for the hysteresis of the thermocouple's temperature measurement. Based on this, the error term in this embodiment includes both static systematic errors that do not change over time and dynamic components related to the rate of change of the thermocouple's temperature measurement, comprehensively considering multiple error sources in the measurement process and comprehensively improving the reliability of the preset heat conduction model.

[0043] Optionally, the preset heat conduction model is corrected based on the first deviation between the first true temperature estimate and the corresponding infrared thermometry value, including: Using the least squares method, with the goal of minimizing the sum of squares of each first deviation, the static system error, time constant, equivalent specific heat capacity, and equivalent thermal resistance in the preset heat conduction model are updated. And / or, the first heat conduction model is corrected based on a second deviation between each second true temperature estimate and a corresponding preset reference melting point value associated with a preset metallic material, including: Using the least squares method, with the goal of minimizing the sum of squares of each second deviation, the static system error, time constant, equivalent specific heat capacity, and equivalent thermal resistance in the first heat conduction model are updated.

[0044] In one embodiment, after obtaining each first deviation (i.e., the deviation between the infrared temperature measurement value without significant delay and the first true temperature estimate predicted by the preset heat conduction model), the least squares method can be used, with the sum of squares of each first deviation as the objective function. By continuously adjusting the static systematic error, time constant, equivalent specific heat capacity, and equivalent thermal resistance in the preset heat conduction model, the objective function value is minimized, thereby correcting the preset heat conduction model and effectively reducing the deviation between the true temperature estimate and the actual measured value (i.e., the infrared temperature measurement value). This is beneficial for improving the model's estimation accuracy of the true temperature of the preset metallic material and compensating for the lag in thermocouple temperature measurement. Furthermore, after obtaining each second deviation (i.e., the deviation between the true melting point value and the second true temperature estimate predicted by the first heat conduction model), the least squares method can also be used, with the goal of minimizing the sum of squares of each second deviation, to update the static systematic error, time constant, equivalent specific heat capacity, and equivalent thermal resistance in the first heat conduction model, thereby achieving accurate correction of the first heat conduction model. Since the preset melting point of the metal material is more accurate and reliable in numerical terms than the infrared temperature measurement value, this embodiment uses the second deviation to correct the first heat conduction model, which is beneficial to further improve the model accuracy.

[0045] Optionally, a temperature calibration model is obtained based on the second heat conduction model, including: The system collects the second thermal parameters, the second thermocouple temperature value, and the second material image when heating the metal material to be tested, and obtains the reference metallographic temperature values ​​corresponding to the appearance of each preset metallographic feature of the metal material to be tested. For each preset metallographic feature, a third true temperature estimate corresponding to the first detected second material image of the preset metallographic feature is determined; wherein, the third true temperature estimate is obtained by using the second heat conduction model based on the second thermal parameters and the temperature measured by the second thermocouple corresponding to the second material image; The second heat conduction model is corrected based on the third deviation between each third true temperature estimate and the corresponding reference metallographic temperature value, thus obtaining the temperature calibration model.

[0046] Optionally, the second heat conduction model is corrected based on the third deviation between each third true temperature estimate and the corresponding reference metallographic temperature value, including: Using the least squares method, with the goal of minimizing the sum of squares of each third deviation, the equivalent specific heat capacity and equivalent thermal resistance in the second heat conduction model are updated.

[0047] Specifically, the metal material to be tested referred to in this embodiment refers to the material that actually needs to be observed in situ (such as high-nitrogen martensitic stainless steel). The second thermal parameter, the second thermocouple temperature value, and the second material image in this embodiment are essentially the same as the aforementioned first thermal parameter, the first thermocouple temperature value, and the first material image, and the acquisition method is also the same, so they will not be repeated here. The preset metallographic features referred to in this embodiment represent the microstructural features that the metal material to be tested will exhibit at a specific temperature during heating, such as specific grain morphologies (e.g., austenite nucleation, ferrite, martensite), phase transformation features, etc. These features are closely related to the temperature of the metal material, and reference metallographic temperature values ​​and reference images corresponding to each preset metallographic feature can be obtained in advance from relevant material property files. Based on this, the reference image can be used as input, and its corresponding preset metallographic features as labels to train the initial image recognition model, thereby obtaining the second image recognition model. In practical use, the acquired second material images can be input into the second image recognition model according to the shooting time sequence. When the preset metallographic features are recognized for the first time, the corresponding second thermal parameters and the second thermocouple temperature measurement value (such as based on time alignment matching) can be determined according to the acquisition time of the corresponding second material image (i.e. the first second material image that detects the preset metallographic features), and then input into the second heat conduction model to obtain the corresponding third true temperature estimate.

[0048] In one embodiment, after obtaining the third true temperature estimate corresponding to each preset metallographic feature, the third deviation between each third temperature estimate and the reference metallographic temperature value corresponding to the preset metallographic feature can be determined. Based on this, the least squares method can be used, with the sum of squares of each third deviation as the objective function. By adjusting the equivalent specific heat capacity and equivalent thermal resistance in the second heat conduction model, the objective function value is minimized, thereby correcting the second heat conduction model and obtaining the temperature calibration model. In this embodiment, the thermal properties of different samples are usually different, and the equivalent specific heat capacity and equivalent thermal resistance in the model also differ when heating different samples. After performing a first hysteresis correction on the model using infrared thermometry and a second accuracy correction using the reference melting point value of the metal material to be tested, this embodiment further fine-tunes the equivalent specific heat capacity and equivalent thermal resistance of the model based on the reference metallographic temperature value of the metal material to be tested, which is required for in-situ observation. This allows the final temperature calibration model to more accurately and reliably estimate the true temperature of the metal material to be tested based on thermocouple measurements, comprehensively improving the accuracy and reliability of the temperature calibration model.

[0049] like Figure 2 As shown in the figure, a temperature control method provided by an embodiment of the present invention includes the following steps: S21: Periodically collect the current thermal parameters, current thermocouple temperature readings, and current material image corresponding to the heating of the metal material under test; S22: Using a temperature calibration model, the current true temperature estimate is obtained based on the current thermal parameters and the current thermocouple temperature measurement value, and the current true temperature estimate is correlated with the current material image; wherein, the temperature calibration model is constructed based on the temperature calibration model construction method described above; S23: Control the heating power based on the target deviation between the current estimated actual temperature and the preset target control temperature corresponding to the current cycle.

[0050] Specifically, in this embodiment, the current thermal parameters, current thermocouple temperature values, and current material images can be collected according to a preset cycle (e.g., 10ms), which is essentially the same as the aforementioned first thermal parameters, first thermocouple temperature values, and first material images, and the acquisition method is also the same, so it will not be described again here.

[0051] In one embodiment, the heating rate of the metal material under test and the desired observation temperature point can be preset throughout the entire heating process, thereby obtaining the preset target control temperature for different heating cycles. In this embodiment, the heating cycle can be the same as the acquisition cycle (e.g., both are 10ms), thus matching the corresponding preset target control temperature for each cycle. When actually heating the metal material under test, after acquiring the current thermal parameters, current thermocouple temperature readings, and current material image for each cycle, the current thermal parameters and current thermocouple temperature readings can be input into the temperature calibration model constructed based on the temperature calibration model construction method described above, thereby compensating for the hysteresis of the thermocouple, obtaining an accurate and reliable estimate of the current true temperature, and associating it with the corresponding current material image, facilitating the observation of the phase transition behavior of the metal material under test at different temperatures. Furthermore, the preset target control temperature corresponding to the current cycle can be obtained, and the target deviation between the current true temperature estimate and the preset target control temperature can be determined. Based on this, this embodiment can use a PID controller to perform feedback control of the heating power of the heating device according to the target deviation, which can effectively improve the accuracy of temperature control and reduce temperature overshoot. For example, if the current estimated actual temperature is less than the preset target control temperature, the controller can increase the heating power; conversely, if the current estimated actual temperature is greater than the preset target control temperature, the controller can reduce the heating power to avoid overheating.

[0052] The temperature control curve diagram of the temperature control method in this embodiment is shown below. Figure 3 As shown, Figure 3 In the figure, T0 represents the preset target control temperature, TS1 represents the temperature control curve when using traditional PID control, and TS2 represents the corresponding temperature control curve when using the temperature control method in this embodiment. As can be seen from the figure, when using the temperature control method in this embodiment, the temperature overshoot is significantly lower than that of traditional PID control, effectively reducing the risk of temperature overshoot.

[0053] like Figure 4 As shown, an embodiment of the present invention provides a temperature calibration model construction device 400, comprising: The information acquisition module 410 is used to periodically acquire the first thermal parameters, the first thermocouple temperature measurement value, the infrared temperature measurement value, and the first material image when heating each preset metal material. The first correction module 420 is used to obtain a corresponding first true temperature estimate based on the first thermal parameters and the first thermocouple temperature measurement value using a preset heat conduction model, and to correct the preset heat conduction model based on the first deviation between the first true temperature estimate and the corresponding infrared temperature measurement value to obtain a first heat conduction model; wherein, the preset heat conduction model is used to describe the dynamic relationship between the thermal parameters, the thermocouple temperature measurement value and the true temperature estimate value. Temperature estimation module 430 is used to determine, for each of the preset metal materials, a second true temperature estimate corresponding to the first material image that first detects the preset solid-liquid phase coexistence characteristics; wherein the second true temperature estimate is obtained using the first heat conduction model based on the first thermal parameters corresponding to the first material image and the temperature measured by the first thermocouple. The second correction module 440 is used to correct the first heat conduction model based on the second deviation between each of the second true temperature estimates and the corresponding preset metal material’s pre-associated reference melting point value, to obtain a second heat conduction model, and to obtain a temperature calibration model based on the second heat conduction model.

[0054] The temperature calibration model construction device and the temperature calibration model construction method provided in this embodiment can produce basically the same technical effects, and will not be described in detail here.

[0055] like Figure 5 As shown, an electronic device 500 provided in this embodiment of the invention includes a memory 510 and a processor 520; the memory 510 is used to store a computer program; the processor 520 is used to implement the temperature calibration model construction method as described above, or the temperature control method as described above, when executing the computer program.

[0056] Alternatively, an electronic device 500 includes a memory 510 and a processor 520 coupled to the memory 510; the memory 510 is configured to store a computer program; and the processor 520 is configured to perform the following operations when the computer program is executed: The first thermal parameters, the first thermocouple temperature measurement value, the infrared temperature measurement value, and the first material image are periodically collected when heating each preset metal material. Using a preset heat conduction model, a first true temperature estimate is obtained based on the first thermal parameters and the first thermocouple temperature measurement value. The preset heat conduction model is then corrected based on the first deviation between the first true temperature estimate and the corresponding infrared temperature measurement value to obtain a first heat conduction model. The preset heat conduction model is used to describe the dynamic relationship between the thermal parameters, the thermocouple temperature measurement value, and the true temperature estimate. For each of the preset metallographic features, a third true temperature estimate corresponding to the first material image that detects the preset metallographic feature is determined; wherein, the third true temperature estimate is obtained using the second heat conduction model based on the second thermal parameters corresponding to the second material image and the temperature measured by the second thermocouple; The first heat conduction model is corrected based on the second deviation between each of the second true temperature estimates and the corresponding pre-associated reference melting point value of the preset metal material to obtain the second heat conduction model, and a temperature calibration model is obtained based on the second heat conduction model.

[0057] Alternatively, perform the following operation: Periodically collect the current thermal parameters, current thermocouple temperature readings, and current material images corresponding to the heating of the metal material under test; The current true temperature estimate is obtained using a temperature calibration model based on the current thermal parameters and the current thermocouple temperature measurement value, and the current true temperature estimate is correlated with the current material image; wherein, the temperature calibration model is constructed based on the temperature calibration model construction method described above; The heating power is controlled based on the target deviation between the current estimated actual temperature and the preset target control temperature corresponding to the current cycle.

[0058] The electronic device and temperature calibration model construction method provided in this embodiment, or the temperature control method, can produce basically the same technical effects, and will not be described in detail here.

[0059] This invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the temperature calibration model construction method or the temperature control method as described above.

[0060] Alternatively, a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the following operations: The first thermal parameters, the first thermocouple temperature measurement value, the infrared temperature measurement value, and the first material image are periodically collected when heating each preset metal material. Using a preset heat conduction model, a first true temperature estimate is obtained based on the first thermal parameters and the first thermocouple temperature measurement value. The preset heat conduction model is then corrected based on the first deviation between the first true temperature estimate and the corresponding infrared temperature measurement value to obtain a first heat conduction model. The preset heat conduction model is used to describe the dynamic relationship between the thermal parameters, the thermocouple temperature measurement value, and the true temperature estimate. For each of the preset metallic materials, a second true temperature estimate corresponding to the first material image that first detects the preset solid-liquid phase coexistence characteristics is determined; wherein, the second true temperature estimate is obtained using the first heat conduction model based on the first thermal parameters corresponding to the first material image and the temperature measured by the first thermocouple. The first heat conduction model is corrected based on the second deviation between each of the second true temperature estimates and the corresponding pre-associated reference melting point value of the preset metal material to obtain the second heat conduction model, and a temperature calibration model is obtained based on the second heat conduction model.

[0061] Alternatively, perform the following operation: Periodically collect the current thermal parameters, current thermocouple temperature readings, and current material images corresponding to the heating of the metal material under test; The current true temperature estimate is obtained using a temperature calibration model based on the current thermal parameters and the current thermocouple temperature measurement value, and the current true temperature estimate is correlated with the current material image; wherein, the temperature calibration model is constructed based on the temperature calibration model construction method described above; The heating power is controlled based on the target deviation between the current estimated actual temperature and the preset target control temperature corresponding to the current cycle.

[0062] The computer-readable storage medium and temperature calibration model construction method provided in this embodiment, or the temperature control method, can produce essentially the same technical effects, and will not be described in detail here.

[0063] Electronic device 500, which can serve as a server or client of the present invention, is described below as an example of a hardware device applicable to various aspects of the present invention. Electronic device 500 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 500 can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0064] Electronic device 500 includes a computing unit that can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) or a computer program loaded from a storage unit into random access memory (RAM). The RAM may also store various programs and data required for device operation. The computing unit, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0065] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc. In this application, 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 the embodiments of the present invention according to actual needs. Furthermore, the functional units in the various embodiments of the present invention 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 units can be implemented in hardware or as software functional units.

[0066] While the present invention has been disclosed above, its scope of protection is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, and all such changes and modifications will fall within the scope of protection of the present invention.

Claims

1. A method for constructing a temperature calibration model, characterized in that, include: The first thermal parameters, the first thermocouple temperature measurement value, the infrared temperature measurement value, and the first material image are periodically collected when heating each preset metal material. Using a preset heat conduction model, a first true temperature estimate is obtained based on the first thermal parameters and the first thermocouple temperature measurement value. The preset heat conduction model is then corrected based on the first deviation between the first true temperature estimate and the corresponding infrared temperature measurement value to obtain a first heat conduction model. The preset heat conduction model is used to describe the dynamic relationship between the thermal parameters, the thermocouple temperature measurement value, and the true temperature estimate. For each of the preset metallic materials, a second true temperature estimate corresponding to the first material image that first detects the preset solid-liquid phase coexistence characteristics is determined; wherein, the second true temperature estimate is obtained using the first heat conduction model based on the first thermal parameters corresponding to the first material image and the temperature measured by the first thermocouple. The first heat conduction model is corrected based on the second deviation between each of the second true temperature estimates and the corresponding pre-associated reference melting point value of the preset metal material to obtain the second heat conduction model, and a temperature calibration model is obtained based on the second heat conduction model.

2. The temperature calibration model construction method according to claim 1, characterized in that, The thermal parameters include ambient temperature and laser power; the preset heat conduction model satisfies: C×dT true / dt=P heat -(T true -T env ) / R; T true =T tc +ΔT error ; Among them, T true T represents the estimated true temperature value; tc This indicates the temperature value measured by the thermocouple; T env P represents the ambient temperature; heat The laser power is represented by C; the equivalent specific heat capacity is represented by R; the equivalent thermal resistance is represented by ΔT. error This indicates the error term.

3. The method for constructing a temperature calibration model according to claim 2, characterized in that, The error term satisfies: ； Where, ΔT bias Indicates static systematic error; This represents the time constant.

4. The temperature calibration model construction method according to claim 3, characterized in that, The step of correcting the preset heat conduction model based on the first deviation between the first estimated real temperature value and the corresponding infrared thermometric value includes: Using the least squares method, with the goal of minimizing the sum of squares of each of the first deviations, the static system error, time constant, equivalent specific heat capacity, and equivalent thermal resistance in the preset heat conduction model are updated. And / or, the step of correcting the first heat conduction model based on the second deviation between each of the second true temperature estimates and the corresponding pre-associated reference melting point value of the preset metallic material includes: Using the least squares method, with the goal of minimizing the sum of squares of each of the second deviations, the static system error, time constant, equivalent specific heat capacity, and equivalent thermal resistance in the first heat conduction model are updated.

5. The method for constructing a temperature calibration model according to claim 3, characterized in that, The temperature calibration model obtained based on the second heat conduction model includes: The system collects the second thermal parameters, the second thermocouple temperature value, and the second material image when heating the metal material to be tested, and obtains the reference metallographic temperature values ​​corresponding to the occurrence of each preset metallographic feature of the metal material to be tested. For each of the preset metallographic features, a third true temperature estimate corresponding to the first material image that detects the preset metallographic feature is determined; wherein, the third true temperature estimate is obtained using the second heat conduction model based on the second thermal parameters corresponding to the second material image and the temperature measured by the second thermocouple; The second heat conduction model is corrected based on the third deviation between each of the third true temperature estimates and the corresponding reference metallographic temperature values ​​to obtain the temperature calibration model.

6. The method for constructing a temperature calibration model according to claim 5, characterized in that, The step of correcting the second heat conduction model based on the third deviation between each of the third true temperature estimates and the corresponding reference metallographic temperature values ​​includes: Using the least squares method, with the goal of minimizing the sum of squares of each of the third deviations, the equivalent specific heat capacity and equivalent thermal resistance in the second heat conduction model are updated.

7. A temperature control method, characterized in that, include: Periodically collect the current thermal parameters, current thermocouple temperature readings, and current material images corresponding to the heating of the metal material under test; The current true temperature estimate is obtained using a temperature calibration model based on the current thermal parameters and the current thermocouple temperature measurement value, and the current true temperature estimate is correlated with the current material image; wherein, the temperature calibration model is constructed based on the temperature calibration model construction method according to any one of claims 1-6; The heating power is controlled based on the target deviation between the current estimated actual temperature and the preset target control temperature corresponding to the current cycle.

8. A temperature calibration model construction device, characterized in that, include: The information acquisition module is used to periodically acquire the first thermal parameters, the first thermocouple temperature measurement value, the infrared temperature measurement value, and the first material image when heating each preset metal material. The first correction module is used to obtain a corresponding first true temperature estimate based on the first thermal parameters and the first thermocouple temperature measurement value using a preset heat conduction model, and to correct the preset heat conduction model based on a first deviation between the first true temperature estimate and the corresponding infrared temperature measurement value to obtain a first heat conduction model; wherein, the preset heat conduction model is used to describe the dynamic relationship between the thermal parameters, the thermocouple temperature measurement value and the true temperature estimate. A temperature estimation module is used to determine, for each of the preset metal materials, a second true temperature estimate corresponding to the first material image that first detects the preset solid-liquid phase coexistence characteristics; wherein the second true temperature estimate is obtained using the first heat conduction model based on the first thermal parameters corresponding to the first material image and the temperature measured by the first thermocouple. The second correction module is used to correct the first heat conduction model based on the second deviation between each of the second true temperature estimates and the corresponding preset metal material’s pre-associated reference melting point value, to obtain a second heat conduction model, and to obtain a temperature calibration model based on the second heat conduction model.

9. An electronic device, characterized in that, Including memory and processor; The memory is used to store computer programs; The processor is configured to, when executing the computer program, implement the temperature calibration model construction method as described in any one of claims 1 to 6, or implement the temperature control method as described in claim 7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, implements the temperature calibration model construction method as described in any one of claims 1 to 6, or the temperature control method as described in claim 7.

Images