High-temperature heating furnace temperature measurement system based on temperature emissivity inversion algorithm

Abstract

The invention relates to a high-temperature heating furnace temperature measurement system based on a temperature emissivity inversion algorithm, and belongs to the technical field of metallurgical industry temperature measurement. The system comprises a spectrum detection system, a master control upper computer and a temperature adjusting system, the spectrum detection system is used for acquiring a plurality of wavelengths and corresponding gray values of a melt in the heating furnace; the temperature adjusting system is used for adjusting the temperature of the heating furnace; the master control upper computer is used for receiving the wavelengths and the corresponding gray values obtained by the spectrum detection system to obtain the spectral radiation brightness corresponding to the wavelengths; obtaining the temperature of the melt in the heating furnace by using a free energy minimization temperature emissivity inversion method based on each wavelength and the corresponding spectral radiance; and the temperature adjusting system is controlled to adjust the temperature of the heating furnace based on the temperature of the melt in the heating furnace. Real-time and accurate temperature measurement of melts with different emissivity is realized, the production cost is reduced, and the temperature measurement precision is high.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature measurement in the metallurgical industry, and particularly to a temperature measurement system for a high-temperature heating furnace based on a temperature emissivity inversion algorithm. Background Art

[0002] High-temperature sintering furnaces are widely used in the sintering of powder metallurgy products, metal injection molding products, stainless steel substrates, cemented carbides, ceramic materials, magnetic materials, neodymium iron boron and other materials. They are usually classified into low-temperature sintering furnaces and high-temperature sintering furnaces according to the sintering temperature. The low-temperature sintering furnace refers to those below 1300 degrees, and the high-temperature sintering furnace is above 1300 degrees, with the highest sintering temperature reaching 2400 degrees. The high-temperature sintering technology has the properties of no oxidation, no decarburization, and degreasing, with good degassing effect. The products have the advantages of good surface quality, small deformation, excellent performance, and long service life.

[0003] The working principle of the high-temperature sintering furnace is to place the pre-formed products in the furnace, pressurize the furnace through a heating pressure device, and start heating after reaching the preset pressure value. There are two heating methods: resistance heating and induction heating. During the heating process, it is necessary to measure the temperature inside the furnace through a temperature measuring element, feedback it to the temperature controller, and then control the output power of the heating power supply through the temperature controller to achieve reasonable temperature control.

[0004] When measuring the temperature of the existing heating furnace, manual operation often uses a platinum-rhodium thermocouple for multiple temperature measurements. However, in actual smelting production, the thermocouple can usually accurately measure the temperature only two or three times in one production cycle. The reason is that the thermocouple will be immediately damaged by high temperature in an instant after measuring the temperature. Therefore, the traditional manual temperature measurement method not only has a relatively high temperature measurement cost, poor stability, too few temperature measurement points, and the temperature representativeness of the measurement points is not good to a certain extent, but also has a low hit rate at the end of the measurement, consumes a large amount of various raw materials, and has poor quality. Summary of the Invention

[0005] In view of the above analysis, the embodiments of the present invention aim to provide a temperature measurement system for a high-temperature heating furnace based on a temperature emissivity inversion algorithm to solve the problems of low accuracy and waste of raw materials in the existing contact-type heating furnace temperature measurement.

[0006] The object of the present invention is mainly achieved through the following technical solutions:

[0007] The present invention provides a molten metal temperature detection system in a heating furnace based on a temperature emissivity inversion method, including: a spectral detection system, a main control upper computer, and a temperature regulation system; wherein,

[0008] The spectral detection system is used to obtain multiple wavelengths and corresponding gray values of the molten metal in the heating furnace;

[0009] The temperature regulation system is used to regulate the temperature of the heating furnace;

[0010] The main control host computer is used to receive the wavelengths and corresponding gray values obtained by the spectral detection system to obtain the spectral radiance corresponding to each of the wavelengths; use the temperature emissivity inversion method of minimizing free energy based on each of the wavelengths and its corresponding spectral radiance to obtain the temperature of the melt in the heating furnace; and control the temperature regulation system to regulate the temperature of the heating furnace based on the temperature of the melt in the heating furnace.

[0011] Further, the main control host computer includes a data reception and processing module, a temperature emissivity separation and inversion module, and a temperature control module;

[0012] The data reception and processing module receives the wavelengths and corresponding gray values obtained by the spectral detection system, and uses the pre-calibrated gray value - spectral radiance data to obtain the spectral radiance corresponding to each of the wavelengths;

[0013] The temperature emissivity inversion module receives each of the wavelengths and the corresponding spectral radiance and uses the temperature emissivity inversion method of minimizing free energy to obtain the temperature of the melt in the heating furnace;

[0014] The temperature control module outputs a temperature regulation power using a fuzzy PID temperature control method based on the temperature of the melt in the heating furnace and a preset temperature.

[0015] Further, the temperature control module of the main control host computer outputs a temperature regulation power using the fuzzy PID temperature control method, including: comparing the temperature of the melt in the heating furnace with a preset temperature to obtain a temperature deviation;

[0016] Using the temperature deviation and the differential of the temperature deviation as input parameters of a fuzzy PID controller to obtain the control parameters of the PID controller according to fuzzy rules;

[0017] The PID controller outputs a temperature regulation power based on the control parameters.

[0018] Further, the temperature regulation system receives the temperature regulation power sent by the main control host computer and controls the melt heating element of the heating furnace to heat or cool the melt in the heating furnace.

[0019] Further, receiving each of the wavelengths and the corresponding spectral radiance and using a temperature - emissivity separation inversion method to obtain the spectral emissivity of the melt in the heating furnace includes:

[0020] Based on the spectral radiance of each wavelength, using Planck's blackbody radiation formula to obtain the blackbody temperature of each wavelength of an ideal blackbody;

[0021] Based on the spectral radiance corresponding to each wavelength and the blackbody temperature corresponding to each wavelength, the EM optimization strategy is used to obtain the temperature of the melt in the heating furnace after inversion and the spectral emissivity corresponding to each wavelength.

[0022] Further, in one iteration process of the EM optimization strategy:

[0023] Obtain the initial temperature of this iteration and the initial spectral emissivity corresponding to each wavelength;

[0024] In the maximization step of the EM optimization strategy: Based on the initial spectral emissivity of each wavelength, the free energy minimization method is used as the maximum likelihood function of the EM optimization strategy to calculate the optimal temperature as the hidden parameter of the EM optimization strategy;

[0025] In the expectation step of the EM optimization strategy: Based on the optimal temperature, obtain the spectral emissivity of each wavelength at this temperature as the spectral emissivity expectation value corresponding to each wavelength;

[0026] The optimal temperature is used as the initial temperature of the next iteration, and the spectral emissivity expectation value corresponding to each wavelength is used as the initial spectral emissivity of the next iteration;

[0027] When the spectral emissivity expectation values corresponding to each wavelength and the initial spectral emissivity of each wavelength satisfy the convergence condition, the obtained optimal temperature and the spectral emissivity of each wavelength are used as the temperature after inversion and the spectral emissivity corresponding to each wavelength, and the iteration ends.

[0028] Further, in the first iteration process, the initial temperature is the maximum temperature T among the blackbody temperatures of each wavelength max .

[0029] Further, in the first iteration process, the initial spectral emissivity of each wavelength is obtained based on the maximum temperature using Planck's blackbody radiation formula.

[0030] Further, the optimal temperature is calculated using the free energy minimization method based on the initial emissivity of each wavelength, where the formula of the free energy minimization method is:

[0031]

[0032]

[0033]

[0034] where, T opt is the optimal temperature; ΔA is the internal energy change; C V is the heat capacity of the material; is the initial spectral emissivity at wavelength λ i ; I obs (λ i ) is the spectral radiance corresponding to the wavelength λ i to be separated; I B (λ i , T opt ) is the spectral radiance of a perfect blackbody at wavelength λ i at temperature T opt .

[0035] Furthermore, the spectral emissivities at each wavelength at this temperature are obtained by using the following formula based on the optimal temperature as the expected values of the spectral emissivities corresponding to each wavelength:

[0036]

[0037] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0038] 1. The present invention uses a spectrometer to measure the wavelength and gray value of the melt in the heating furnace, and uses an emissivity-temperature separation inversion algorithm to achieve non-contact measurement of the temperature of the melt in the heating furnace, which can measure the temperature of the melt with different emissivities in real time and accurately, reduce production costs, and has high temperature measurement accuracy;

[0039] 2. The emissivity-temperature separation inversion algorithm used in the present invention can separately calculate the spectral emissivity and temperature of the melt in the heating furnace only by relying on the heat capacity function of the melt in the heating furnace, and this function is known for most materials, with simple calculation and high reliability;

[0040] 3. The present invention uses a fuzzy PID control method during temperature regulation, which makes the temperature control of the melt in the heating furnace have high precision and strong stability, and an ideal control curve can still appear through parameter optimization under the action of strong non-linear disturbances.

[0041] In the present invention, the above technical solutions can also be combined with each other to achieve more preferred combination schemes. Other features and advantages of the present invention will be described in the subsequent description, and some advantages can be made obvious from the description, or understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the content specifically pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings are only used for the purpose of showing specific embodiments, and are not considered as a limitation to the present invention. Throughout the drawings, the same reference signs represent the same components.

[0043] Figure 1Schematic structural diagram of a temperature measurement system for a high-temperature heating furnace based on a temperature-emissivity inversion algorithm in an embodiment of the present invention;

[0044] Figure 2 Schematic flow diagram of the EM optimization strategy in an embodiment of the present invention;

[0045] Figure 3 Schematic flow diagram of the spectral emissivity fitting and smoothing method in an embodiment of the present invention;

[0046] Figure 4 Schematic diagram of the self-controlled fuzzy PID control principle in an embodiment of the present invention. Detailed implementation manners

[0047] The following will specifically describe the preferred embodiments of the present invention with reference to the accompanying drawings. The accompanying drawings form a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, rather than to limit the scope of the present invention.

[0048] A specific embodiment of the present invention discloses a temperature measurement system for a high-temperature heating furnace based on a temperature-emissivity inversion algorithm. As Figure 1 shown, it includes: a spectral detection system, a main control host computer, and a temperature regulation system; wherein,

[0049] The spectral detection system is used to obtain multiple wavelengths and corresponding gray values of the melt in the heating furnace;

[0050] Specifically, the spectral detection system is a spectrometer arranged outside the heating furnace, which can obtain multiple wavelengths emitted by the melt in the heating furnace and their corresponding gray values;

[0051] The temperature regulation system is used to regulate the temperature of the heating furnace;

[0052] The main control host computer is used to receive the wavelengths and corresponding gray values obtained by the spectral detection system to obtain the spectral radiance corresponding to each wavelength; use the temperature-emissivity inversion method of minimum free energy based on each wavelength and its corresponding spectral radiance to obtain the temperature of the melt in the heating furnace; and control the temperature regulation system to regulate the temperature of the heating furnace based on the temperature of the melt in the heating furnace.

[0053] Furthermore, the main control host computer includes a data reception and processing module, a temperature-emissivity separation and inversion module, and a temperature control module;

[0054] The data reception and processing module receives the wavelengths and corresponding gray values obtained by the spectral detection system, and uses the pre-calibrated gray value-spectral radiance data to obtain the spectral radiance corresponding to each wavelength;

[0055] The temperature emissivity inversion module receives each of the wavelengths and the corresponding spectral radiance, and obtains the temperature of the melt in the heating furnace by using the temperature emissivity inversion method with minimized free energy.

[0056] The temperature control module outputs a temperature adjustment power based on the temperature of the melt in the heating furnace and a preset temperature by using a fuzzy PID temperature control method.

[0057] Specifically, the data receiving module receives each of the wavelengths and the corresponding gray values obtained by the spectral detection system, filters out the error data, and obtains each of the wavelengths and the corresponding spectral radiance by using the pre-calibrated gray-spectral radiance data.

[0058] It should be noted that the error data filtering is for the situation where the signal-to-noise ratio at both ends of the wavelength region obtained by the spectrometer used to acquire data is relatively low, and negative values will appear after the gray value subtracts the background, so it needs to be removed.

[0059] Further, in the temperature emissivity separation and inversion module, the method of obtaining the temperature of the melt in the heating furnace by using the temperature emissivity inversion method with minimized free energy includes:

[0060] Based on the spectral radiance of each wavelength, obtain the blackbody temperature of each wavelength of the ideal blackbody.

[0061] Based on the spectral radiance corresponding to each wavelength and the blackbody temperature corresponding to each wavelength, use the EM optimization strategy to obtain the temperature of the material after inversion and the spectral emissivity corresponding to each wavelength.

[0062] Specifically, according to the energy distribution law of the blackbody radiation spectrum given by Planck's quantum hypothesis, use the following formula to obtain the blackbody temperature corresponding to each wavelength of the ideal blackbody:

[0063]

[0064] Among them, is the wavelength λ i At temperature The spectral radiance of the ideal blackbody; C1 is the first radiation constant, with a value of 3.74×10 -16 (watts × meters 2 ); C2 is the second radiation constant, with a value of 1.4398×10 -2 (meters × Kelvin).

[0065] Further, based on the spectral radiance corresponding to each wavelength and the blackbody temperature corresponding to each wavelength, use the EM optimization strategy to obtain the temperature of the material after inversion and the spectral emissivity corresponding to each wavelength.

[0066] Specifically, the EM optimization strategy is an iterative optimization strategy. Each iteration in its calculation method is divided into two steps, one is the expectation step, i.e., the E step, and the other is the maximization step, i.e., the M step, which is to solve the parameter estimation problem in the case of missing data (including latent variables).

[0067] Furthermore, the basic idea of the EM optimization strategy is as follows: First, based on the given observed data, estimate the values of the model parameters (initialization); then, based on the parameter values estimated in the previous step, estimate the values of the missing data, and then re-estimate the parameter values according to the estimated missing data plus the previously observed data, and then iterate repeatedly until convergence, and the iteration ends.

[0068] In this embodiment, as Figure 2 shown, the EM optimization strategy includes the following steps in one iteration process:

[0069] In one iteration process:

[0070] Step S301: Obtain the initial temperature of this iteration and the initial spectral emissivity corresponding to each wavelength;

[0071] Specifically, in the first iteration process, the initial temperature is the maximum temperature T among the blackbody temperatures of each wavelength max .

[0072] In the first iteration process, the initial spectral emissivity of each wavelength is obtained using the following formula based on the maximum temperature:

[0073]

[0074]

[0075] where, is the initial spectral emissivity at wavelength λ i ; T max is the maximum temperature; I obs (λ i ) is the spectral radiance corresponding to the wavelength λ to be separated i ; I B (λ i , T max ) is the spectral radiance of an ideal blackbody at wavelength λ i at temperature T max ; e is the natural constant.

[0076] Step S302: In the maximization step of the EM optimization strategy: Calculate the optimal temperature as the hidden parameter of the EM optimization strategy using the free energy minimization method based on the initial spectral emissivity of each wavelength as the maximum likelihood function of the EM optimization strategy;

[0077] Specifically, when calculating the emissivity at a certain wavelength point based on measured data, it often implies that the data is under certain temperature conditions, and it also implies that the emissivities at other wavelength points can be calculated based on this temperature, that is, the obtained emissivity information is related to temperature.

[0078] In this embodiment, the emissivity-temperature separation algorithm based on the minimization of free energy refers to calculating the entropy using the spectral emissivity and calculating the internal energy using the material heat capacity, and obtaining the optimal temperature through the minimization of free energy.

[0079] In statistics, the KL divergence is generally used to measure the "distance" between two probability distribution functions, and can describe the relative distance between two distributions P i and Q i to a certain extent:

[0080]

[0081] Similarly, in thermodynamics, the KL divergence corresponds to the sum of the entropy changes of the system and the environment in these two different states:

[0082]

[0083] where ΔS is the change in entropy; ΔU env is the change in the internal energy of the environment; ΔS sys is the entropy of the system; ΔS env is the entropy of the environment; T0 is the temperature.

[0084] Specifically, according to the definition of Helmholtz free energy:

[0085] A = U - TS

[0086] Assume that the volume and energy of the system can be ignored relative to the environment, and the temperature change of the environment before and after the energy exchange with the system can be ignored. Then the total change in free energy of the system and the environment before and after the state change can be defined as:

[0087] ΔA = ΔU - TΔS = ΔU - TD KL (ε2||ε1)

[0088] where ΔU is the change in the internal energy of the system, which can be calculated using the heat capacity, and the formula is:

[0089] ΔU = C v (T - T0)

[0090] where C v is the heat capacity of the material, which is generally a function of temperature: C v(T) = f(T); Many scientists have accurately measured the heat capacity values of various substances at various temperatures using experimental methods and obtained empirical expressions representing the relationship between heat capacity and temperature.

[0091] Further, the optimal temperature T is calculated using the free energy minimization method as the maximum likelihood function in the maximization step of the EM optimization strategy. opt ;

[0092] Specifically, the formula for the free energy minimization method is:

[0093]

[0094]

[0095]

[0096] where T opt is the optimal temperature and serves as the hidden parameter of the EM optimization strategy; ΔA is the change in internal energy; C V is the heat capacity of the material; is the initial spectral emissivity at wavelength λ i ; I obs (λ i ) is the spectral radiance corresponding to the wavelength λ to be separated i ; I B (λ i , T opt ) is the spectral radiance of an ideal blackbody at wavelength λ i at temperature T opt .

[0097] Step S303, in the expectation step of the EM optimization strategy: Based on the optimal temperature, the spectral emissivity of each wavelength at this temperature is obtained as the expected value of the spectral emissivity corresponding to each wavelength;

[0098] Specifically, the following formula is used to calculate the spectral emissivity of each wavelength at the optimal temperature

[0099]

[0100] It should be noted that during the measurement process, due to reasons such as detector noise, wavelength calibration, and stray radiation interference, the measured data is always accompanied by a large amount of fluctuations. Therefore, the calculated spectral emissivity of the material is also accompanied by a large amount of fluctuations. Effective fitting and smoothing of the spectral emissivity of the material is also very crucial in this embodiment.

[0101] Therefore, in this embodiment, the spectral emissivity fitting and smoothing method is used to fit and smooth the spectral emissivity of each wavelength;

[0102] Further, as Figure 3 shown, the spectral emissivity fitting and smoothing method includes:

[0103] Step S3031: Obtain the single-wavelength radiation entropy of each wavelength based on the spectral emissivity corresponding to each wavelength;

[0104] Specifically, according to the probability characteristics of the emissivity and the Lebesgue measure, the entropy of the system at this wavelength can be measured by the following formula:

[0105]

[0106] where g(m) is the degeneracy of the state when exactly m particles radiate and de-excite, and its numerical value is indicating that there are g(m) microscopic states with the same energy.

[0107] Further, from the above formula, it can be deduced that:

[0108] H λ =-N[ε λ lnε λ +(1 - ε λ )ln(1 - ε λ )]

[0109] Therefore, the single-wavelength radiation entropy of a single particle at each wavelength is:

[0110]

[0111] where is the single-wavelength radiation entropy at wavelength λ i ; is the spectral emissivity corresponding to wavelength λ i ; in order to avoid the situation where the spectral emissivity is greater than or equal to 1 or less than or equal to 0 (in these cases the calculation result is a complex number), the modulus of the calculation result is taken to obtain

[0112] It can be seen from this that the entropy of the system is equal to the entropy of a single particle multiplied by the total number of particles N, and its magnitude is related to the emissivity of the material in different wavelength bands.

[0113] Step S3032: Use the high-order polynomial fitting method for the single-wavelength radiation entropy of each wavelength to obtain the smoothed wavelength radiation entropy;

[0114] Specifically, the high-order polynomial fitting method includes: for each wavelength, using a kernel function as a weight to perform local polynomial kernel regression to obtain a high-order polynomial as a regression function, and using the regression function to calculate the single-wavelength radiation entropy of each wavelength as the smoothed wavelength radiation entropy; wherein, the local polynomial kernel regression includes: selecting a preset number of wavelengths adjacent to this wavelength, and performing polynomial fitting based on the kernel function within this range.

[0115] It should be noted that the preset number is the number of data points participating in the calculation on both sides of the smoothing point, which controls how many adjacent data points are used in the calculation; the larger the preset number range, the smoother the result. Preferably, the preset number N is selected to be 10 - 50.

[0116] Furthermore, according to solid-state physics theory, the spectral emissivity reflects the micro-scale photoacoustic coupling characteristics of the material, which should exhibit certain short-range continuity, smoothness, and certain long-range correlation in hyperspectral data. The smoothness of the material spectral emissivity means that the derivative of the spectral emissivity is continuous when the wavelength changes. The short-range correlation and long-range correlation are the external manifestations of the material energy band structure. When the material is a mixture, the long-range correlation and short-range correlation weaken, but still maintain relatively high spectral continuity and smoothness.

[0117] Furthermore, the continuity and smoothness of the material spectral emissivity are due to the fact that the radiation entropy H at different wavelengths at the microscale λ has smooth and continuous characteristics.

[0118] Specifically, high-order polynomial fitting is a method commonly used in data analysis and machine learning, which can fit a set of data into a high-order polynomial model. This method can improve the fitting accuracy of the data to a certain extent.

[0119] The basic idea of high-order polynomial fitting is to find an optimal polynomial function to fit the given data set, so as to minimize the error between the fitting function and the original data set. To achieve this goal, we need to select a suitable polynomial function and solve the coefficients of the polynomial function by the least squares method.

[0120] Specifically, we can select an nth-degree polynomial function about the independent variable λ i to fit the data. In this embodiment, this polynomial function as the regression function can be expressed as:

[0121] H(λ i ) = a0 + a1λ i + a2λ i 2 + a3λ i 3 + … + a nλ i n

[0122] where λ i is the wavelength value of the i-th wavelength; a0, a1…a n are the coefficients of the polynomial function, and n is the order of the polynomial function. By the least squares method, we can solve for the optimal values of these coefficients, thus obtaining an optimal polynomial function to fit the data.

[0123] It should be noted that high-order polynomial fitting may cause overfitting problems in some cases. Overfitting refers to the situation where, when fitting the data, in order to achieve a better fitting effect, the original data set is overfitted, resulting in a poor prediction effect for new data. Therefore, when performing high-order polynomial fitting, it is necessary to select the order of the polynomial according to the specific situation and make appropriate adjustments and optimizations.

[0124] Specifically, the order of the polynomial is from 2 to 11, preferably an odd order.

[0125] In this embodiment, the order is preferably 5.

[0126] As can be seen from the above, as long as the polynomial coefficients of the radiation entropy at different wavelengths are obtained, the emissivity of the material can be fitted and smoothed. However, if a fixed polynomial is used, this fitting method has a strong long-range correlation, which does not conform to the actual material characteristics.

[0127] Therefore, in this embodiment, kernel regression is used to fit the entropy, so that while meeting the requirements of smoothness and continuity, the hard constraint of its long-range correlation is reduced.

[0128] Specifically, traditional linear regression can only fit a straight line. Kernel regression is a regression method based on non-linear mapping, which is a method that only uses multiple data points near the data point for regression. Essentially, it uses the kernel function as the weight function to establish a non-linear regression model.

[0129] Furthermore, according to the least squares method, local polynomial kernel regression is to solve the coefficients θ of the polynomial function to minimize the following objective function J(θ):

[0130] J(θ) = (Xθ - Y) T K(Xθ - Y)

[0131] where θ is the coefficient vector of the polynomial function; X is the Vandermonde matrix with respect to the wavelength; K is the diagonalized kernel function matrix; Y is the single-wavelength radiation entropy vector of each of the wavelengths.

[0132] Therefore, according to the coefficient calculation formula of the polynomial function can be obtained:

[0133]

[0134] Further, the Vandermonde matrix X regarding the wavelength is as follows:

[0135]

[0136] where λ is the smoothed wavelength; i is the sequence number of the i-th wavelength currently selected; and N is the preset quantity.

[0137] It should be noted that in the matrix, if i - N is less than 1, the calculation starts from 1; if i + N is greater than the total number of wavelengths within the wavelength range to be fitted, the calculation is only performed up to the last wavelength.

[0138] Further, the diagonalized kernel function matrix K is as follows:

[0139] K = diag(k(λ, λ i-N ), …, k(λ, λ i ), …, k(λ, λ i+N ))

[0140] where k(λ, λ i ) is the kernel function; λ is the smoothed wavelength; i is the sequence number of the i-th wavelength currently selected; and N is the preset quantity.

[0141] Specifically, the kernel function defines the similarity measurement method of the input data in the feature space. Commonly used kernel functions include Gaussian kernel function, polynomial kernel function, sigmoid kernel function, etc.

[0142] Preferably, a Gaussian kernel function regression model is selected in the present invention:

[0143]

[0144] where σ is the standard deviation.

[0145] Specifically, the Gaussian kernel function can be regarded as a weight negatively correlated with the distance from the center. When smoothing, adjusting the standard deviation is to adjust the influence degree of the surrounding wavelengths on the current wavelength. Increasing σ increases the influence degree of the distant wavelengths on the central wavelength, and the filtering result is smoother.

[0146] Further, the single-wavelength radiation entropy vector of the wavelength is as follows:

[0147]

[0148] where is the single-wavelength radiation entropy of the wavelength λ i ; i is the sequence number of the i-th wavelength currently selected; and N is the preset quantity.

[0149] So far, for the wavelength λ i after substituting it into the regression function H(λ), the calculated H(λ i ) is the entropy after smoothing for this wavelength

[0150] Step S3033: Obtain the fitted and smoothed spectral emissivity based on the smoothed wavelength radiation entropy.

[0151] Specifically, based on the smoothed wavelength radiation entropy, the following formula is used to obtain the fitted and smoothed spectral emissivity in the wavelength range to be fitted:

[0152]

[0153] where, is the spectral emissivity of the smoothed wavelength λ i , which is the expected value of the spectral emissivity of the wavelength λ i for this iteration; is the single-wavelength radiation entropy of the smoothed wavelength λ i .

[0154] Step S304: Use the optimal temperature as the initial temperature for the next iteration, and the expected values of the spectral emissivities corresponding to each wavelength as the initial spectral emissivities for the next iteration, and perform the next iteration;

[0155] Step S305: When the expected values of the spectral emissivities corresponding to each wavelength and the initial spectral emissivities of each wavelength satisfy the convergence condition, the obtained optimal temperature and the spectral emissivities of each wavelength are used as the temperature and the spectral emissivities corresponding to each wavelength after inversion, and the iteration ends.

[0156] Specifically, the method for judging the convergence condition is to calculate . When its value is less than a specific value, it is judged to satisfy the convergence condition.

[0157] It should be noted that the specific value can be adjusted according to the actual situation and accuracy requirements; in this embodiment, the specific value is taken as 1E-8.

[0158] Furthermore, in this embodiment, the Anderson acceleration algorithm is preferably used to accelerate the iteration process of the EM optimization strategy, which can greatly improve the convergence speed of the algorithm.

[0159] Furthermore, in the temperature control module, based on the temperature of the melt in the heating furnace and the preset temperature, the fuzzy PID temperature control method is used to output the temperature adjustment power, including:

[0160] Compare the temperature of the melt in the heating furnace with a preset temperature to obtain a temperature deviation; use the temperature deviation and the differential of the temperature deviation as input parameters of a fuzzy PID controller, obtain the control parameters of the PID controller according to fuzzy rules, and the PID controller outputs a temperature adjustment power based on the control parameters.

[0161] Specifically, the temperature control of the melt in the heating furnace is another key technology of the present invention; for a linear time-invariant system or a system with a determined mathematical model in an industrial production process, PID control has the advantages of simple structure, strong reliability, easy implementation, and can eliminate steady-state errors. However, in industrial applications, the temperature control system has characteristics such as large inertia and long delay time. When using traditional PID control, the dynamic and static characteristic indexes of the controlled object cannot meet the requirements in the application. By combining fuzzy control and PID, using the experience of experts to write fuzzy control rules to control the temperature control system, it can not only meet the requirements of the system dynamic performance indexes but also control the steady-state error of the system within the allowable range.

[0162] As Figure 4 shown, this embodiment adopts an adaptive fuzzy PID control, and the structure of a two-dimensional fuzzy controller is used. The temperature deviation e obtained by comparing the temperature of the melt in the heating furnace with a preset temperature and the differential of the temperature deviation, that is, the error change rate ec, are used as input variables; according to the changes of the two parameter variables, using the fuzzy control rule table, the three parameters K p 、K i and K d of the PID are modified and adjusted. After the fuzzification link, the approximate reasoning link, and the final defuzzification link, the obtained output quantities are respectively added to the PID controller to perform real-time online adjustment on the three parameters.

[0163] Specifically, the control parameter K p represents the proportional adjustment coefficient, which is used to accelerate the response speed of the system and improve the adjustment accuracy of the system; the control parameter K i represents the integral adjustment coefficient, which is used to eliminate the residual error; the control parameter K d represents the differential adjustment coefficient, which is used to improve the dynamic performance of the system.

[0164] Furthermore, in order to ensure that the control system under the fuzzy self-tuning PID control law is globally stable, then a deviation strategy for fuzzy adjustment of K p 、K i and K d should be used. That is, before control, the initial PID parameters K p0 、K i0 and K d0 are obtained.

[0165] During control, the dynamic values ΔK p 、ΔK i and ΔK d of the three parameters of the PID controller are continuously calculated according to the deviation value e and the deviation change rate ec; finally, the control parameters of the PID are calculated according to the following formula:

[0166] K p = K p0 + ΔK p

[0167] K i = K i0 + ΔK i

[0168] K d = K d0 + ΔK d

[0169] Specifically, when determining the dynamic values of the control parameters K p 、K i and K d according to the fuzzy rules, the deviation levels of the deviation value e and the deviation change rate ec include: large positive deviation, medium positive deviation, small positive deviation, zero deviation, small negative deviation, medium negative deviation and large negative deviation.

[0170] Furthermore, the temperature regulation system receives the temperature regulation power sent by the master upper computer, and controls the melt heating element of the heating furnace to heat or cool the melt in the heating furnace.

[0171] Preferably, the melt heating element uses a graphite heating element with high temperature resistance, small thermal expansion and strong thermal shock resistance.

[0172] In summary, a high-temperature heating furnace temperature measurement system based on a temperature emissivity inversion algorithm according to an embodiment of the present invention has the following beneficial effects:

[0173] 1. The present invention uses a spectrometer to measure the wavelength and gray value of the melt in the heating furnace, and the emissivity-temperature separation inversion algorithm used realizes non-contact measurement of the temperature of the melt in the heating furnace, and can accurately measure the temperature of materials with different emissivities, reducing costs;

[0174] 2. The emissivity-temperature separation inversion algorithm used in the present invention can separately calculate and obtain the spectral emissivity and temperature of the melt in the heating furnace only by relying on the heat capacity function of the melt in the heating furnace, and this function is known for most materials, with simple calculation and high reliability;

[0175] 3. The present invention uses the fuzzy PID control method during temperature regulation, resulting in high control precision and strong stability of the melt temperature in the heating furnace. Even under the action of strong nonlinear disturbances, an ideal control curve can still appear through parameter optimization.

[0176] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A high-temperature heating furnace temperature measurement system based on a temperature-emissivity inversion algorithm, characterized in that, Including: A spectral detection system, a main control host computer, and a temperature regulation system; among them, The spectral detection system is used to obtain multiple wavelengths and corresponding gray values of the melt in the heating furnace; The temperature regulation system is used to regulate the temperature of the heating furnace; The main control host computer is used to receive the wavelengths and corresponding gray values obtained by the spectral detection system to obtain the spectral radiance corresponding to each of the wavelengths; use the temperature emissivity inversion method with minimum free energy based on each of the wavelengths and its corresponding spectral radiance to obtain the temperature of the melt in the heating furnace; and control the temperature regulation system to regulate the temperature of the heating furnace based on the temperature of the melt in the heating furnace.

2. The system according to claim 1, wherein The main control host computer includes a data reception and processing module, a temperature emissivity separation and inversion module, and a temperature control module; The data reception and processing module receives the wavelengths and corresponding gray values obtained by the spectral detection system, and uses the pre-calibrated gray value - spectral radiance data to obtain the spectral radiance corresponding to each of the wavelengths; The temperature emissivity inversion module receives each of the wavelengths and the corresponding spectral radiance, and uses the temperature emissivity inversion method with minimum free energy to obtain the temperature of the melt in the heating furnace; The temperature control module outputs the temperature regulation power based on the temperature of the melt in the heating furnace and the pre-set temperature using the fuzzy PID temperature control method.

3. The system according to claim 2, wherein The temperature control module of the main control host computer outputs the temperature regulation power using the fuzzy PID temperature control method, including: comparing the temperature of the melt in the heating furnace with the pre-set temperature to obtain a temperature deviation; Taking the temperature deviation and the differential of the temperature deviation as the input parameters of the fuzzy PID controller, and obtaining the control parameters of the PID controller according to the fuzzy rules; The PID controller outputs the temperature regulation power based on the control parameters.

4. The system according to claim 3, wherein The temperature regulation system receives the temperature regulation power sent by the main control host computer, and controls the melt heating element of the heating furnace to heat or cool the melt in the heating furnace.

5. The system according to claim 2, characterized in that The receiving of each of the wavelengths and the corresponding spectral radiance and using the temperature-emissivity separation inversion method to obtain the spectral emissivity of the melt in the heating furnace includes: Based on the spectral radiance of each wavelength, using the Planck blackbody radiation formula to obtain the blackbody temperature of each wavelength of the ideal blackbody; Based on the spectral radiance corresponding to each wavelength and the blackbody temperature corresponding to each wavelength, using the EM optimization strategy to obtain the temperature of the melt in the heating furnace after inversion and the spectral emissivity corresponding to each wavelength.

6. The system according to claim 5, wherein The EM optimization strategy, in one iteration process: Obtaining the initial temperature of this iteration and the initial spectral emissivity corresponding to each wavelength; In the maximization step of the EM optimization strategy: using the free energy minimization method based on the initial spectral emissivity of each of the wavelengths as the maximum likelihood function of the EM optimization strategy to calculate the optimal temperature as the hidden parameter of the EM optimization strategy; In the expectation step of the EM optimization strategy: obtaining the spectral emissivity of each of the wavelengths at this temperature as the spectral emissivity expectation value corresponding to each wavelength; The optimal temperature is used as the initial temperature for the next iteration, and the expected values of the spectral emissivities corresponding to each of the wavelengths are used as the initial spectral emissivities for the next iteration; When the expected values of the spectral emissivities corresponding to each of the wavelengths and the initial spectral emissivities corresponding to each of the wavelengths satisfy the convergence condition, the obtained optimal temperature and the spectral emissivities corresponding to each of the wavelengths are used as the temperature and the spectral emissivities corresponding to each of the wavelengths after inversion, and the iteration is terminated.

7. The system according to claim 6, wherein During the first iteration, the initial temperature is the maximum temperature T among the blackbody temperatures of each of the wavelengths max .

8. The system according to any one of claims 6 or 7, characterized in that, In the first iteration process, the initial spectral emissivities of each wavelength are obtained using the Planck blackbody radiation formula based on the maximum temperature.

9. The system according to claim 6, wherein The optimal temperature is calculated using the free energy minimization method based on the initial emissivities of each of the wavelengths, where the formula for the free energy minimization method is: Among them, T opt is the optimal temperature; ΔA is the change in internal energy; C V is the heat capacity of the material; is the initial spectral emissivity at wavelength λ i ; I obs (λ i ) is the spectral radiance corresponding to the wavelength λ i to be separated; I B (λ i , T opt ) is the spectral radiance of an ideal blackbody at wavelength λ i at temperature T opt .

10. The system according to claim 7, wherein Based on the optimal temperature, the spectral emissivity at each of the wavelengths at this temperature is obtained using the following formula as the expected value of the spectral emissivity corresponding to each wavelength:

Images