Food baking processing program control system and method

Abstract

The invention discloses a food baking processing program control system and method, and relates to the technical field of food processing intelligent control, and the method comprises the steps: collecting the dielectric characteristics of a material, capturing the change dynamic state of a dielectric loss angle tangent value, and recognizing the phase change stage of the material in real time through a time domain dielectric spectrum analysis method; constructing a dual-channel heat conduction model, and dynamically identifying the regional temperature gradient of the baking equipment according to the phase change stage of the material; and based on the regional temperature gradient of the baking equipment, through a multi-parameter coupling control algorithm, calculating the microwave power adjusting quantity and the wind speed ratio adjusting quantity of the baking equipment, and generating a composite control instruction set. According to the method, the phase change stage of the material is recognized in real time through a time domain dielectric spectrum analysis method, the relevance between relaxation time distribution and a phase change characteristic spectrum is accurately analyzed through inverse Laplace transformation and a dynamic time warping algorithm, and dynamic capture of key phase change nodes such as glass transition and starch gelatinization is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control of food processing, and particularly to a food baking processing program control system and method. Background Art

[0002] In the field of food baking processing, conventional control methods mainly rely on a closed-loop regulation system based on temperature feedback and preset process parameters. Existing technologies usually use a thermocouple array to monitor the surface temperature distribution of materials, and combine a PID controller to dynamically adjust the microwave power output and the fan speed to achieve temperature field uniformity control. Some systems obtain the tangent value of the dielectric loss angle through frequency-domain dielectric spectroscopy analysis to characterize the moisture content of materials and the activity intensity of polar molecules, and then assist in judging the baking stage. Such methods generate control instructions by establishing a linear mapping relationship among the temperature gradient, microwave power, and wind speed, and using a multivariable regression model, and have achieved certain applications in the stability control of the baking process. In addition, the off-line detection data of texture analyzers and colorimeters are often used for posterior correction of process parameters to optimize the consistency of product quality.

[0003] However, there is room for optimization in the dynamic characteristic analysis and heat conduction modeling in the phase change stage. Although conventional frequency-domain dielectric spectroscopy analysis can obtain the frequency response characteristics of the tangent value of the dielectric loss angle, it does not establish a dynamic correlation between the time-domain relaxation current signal and the phase change characteristics, resulting in limited recognition accuracy of key phase change nodes such as glass transition and starch gelatinization. On the other hand, a single heat conduction model is difficult to simultaneously characterize the coupling effect of slow heat relaxation (dominated by molecular chain movement) and fast heat transfer (dominated by moisture migration), resulting in a deviation between the predicted value of the temperature gradient and the actual phase change dynamics process. Such a deviation is particularly significant in the starch gelatinization stage. Due to the high moisture migration rate, it is difficult for the traditional PID control algorithm to achieve coordinated adaptive adjustment of microwave power and wind speed, easily causing local overheating or under-baking phenomena. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a food baking processing program control method to solve the problems of insufficient recognition accuracy in the phase change stage and inaccurate coordinated regulation of microwave-wind speed leading to temperature field instability.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides a method for controlling a food baking process, which includes collecting the dielectric properties of the material and capturing the dynamic changes in the tangent value of the dielectric loss angle, and simultaneously using time-domain dielectric spectroscopy to identify the phase change stage of the material in real time; constructing a two-channel heat conduction model, and dynamically identifying the regional temperature gradient of the baking equipment according to the phase change stage of the material; based on the regional temperature gradient of the baking equipment, calculating the microwave power adjustment amount and the wind speed ratio adjustment amount of the baking equipment through a multi-parameter coupling control algorithm, and generating a composite control instruction set; obtaining the change range of the material color difference and texture data, dynamically generating pulse cooling and gradient heating compensation instructions through a fuzzy PID compensator, and dynamically correcting the composite control instruction set.

[0007] As a preferred embodiment of the method for controlling a food baking process according to the present invention, wherein: the capturing of the dynamic changes in the tangent value of the dielectric loss angle means obtaining the tangent value of the dielectric loss angle through frequency-domain dielectric spectroscopy according to the dielectric constant and loss factor, and using TTS for dynamic tracking analysis to obtain the dynamic change curve of the tangent value of the dielectric loss angle.

[0008] As a preferred embodiment of the method for controlling a food baking process according to the present invention, wherein: the step of using time-domain dielectric spectroscopy to identify the phase change stage of the material in real time is as follows, Based on the dynamic change curve of the tangent value of the dielectric loss angle, using the sliding window difference method to extract the phase change characteristics of the material, and generating a phase change characteristic spectrum through the dynamic time warping algorithm; Performing an inverse Laplace transform on the time-domain dielectric relaxation current signal of the material to generate a relaxation time distribution aligned with the time of the phase change characteristic spectrum; Using time-domain dielectric spectroscopy to calculate the minimum cumulative difference between the relaxation time distribution and the phase change characteristic spectrum; Defining a low deviation threshold and a high deviation threshold, and comparing them with the minimum cumulative difference between the relaxation time distribution and the phase change characteristic spectrum to identify the glass transition stage, starch gelatinization stage, and setting and ripening stage of the material.

[0009] As a preferred embodiment of the method for controlling a food baking process according to the present invention, wherein: the step of constructing a two-channel heat conduction model and dynamically identifying the regional temperature gradient of the baking equipment according to the phase change stage of the material is as follows, The two-channel heat conduction model includes a slow heat relaxation channel and a fast heat transfer channel; The slow heat relaxation channel uses time-domain dielectric relaxation spectroscopy to identify the molecular chain movement retardation characteristics; Calibrating the relaxation activation energy and thermal history temperature characteristics of the material through differential scanning calorimetry, and using Prony series fitting to construct a slow heat relaxation time spectrum; By means of the finite element discretization method, the spatial grid solution of the slow thermal relaxation time spectrum is carried out to predict the regional temperature gradient of the baking equipment; For the fast heat transfer channel, TGA-FTIR is used to measure the moisture diffusion rate and the change rate of thermal conductivity during the baking process, and a quantitative relationship between moisture migration and heat conduction is established by fitting through the Arrhenius equation. At the same time, the finite volume method is used to predict the regional temperature gradient of the baking equipment; The slow thermal relaxation channel and the fast heat transfer channel of the dual-channel heat conduction model are used to process the materials at different phase change stages respectively.

[0010] As a preferred scheme of the food baking process control method described in the present invention, wherein: the generation of the composite control instruction set means that based on the regional temperature gradient of the baking equipment, the microwave power adjustment amount and the air velocity ratio adjustment amount are calculated through a multi-parameter coupling control algorithm, and the composite control instruction set is generated through a linear interpolation mapping method.

[0011] As a preferred scheme of the food baking process control method described in the present invention, wherein: to obtain the change range of the material color difference and texture data, and dynamically generate pulse cooling and gradient heating compensation instructions through a fuzzy PID compensator, the steps are as follows Based on the real-time material color difference and texture data, the sliding window statistical method is used to identify the change range of the material color difference and texture data; The fuzzy clustering algorithm is used to divide the change range of the material color difference and texture data into multiple fuzzy subsets, and the IF-THEN control rules of each fuzzy subset are established; Based on the material color difference and texture data, through the IF-THEN control rules of each fuzzy subset, the pulse cooling intensity instruction and the gradient heating compensation instruction are generated.

[0012] As a preferred scheme of the food baking process control method described in the present invention, wherein: the dynamic correction of the composite control instruction set means that through a fuzzy PID compensator, the pulse cooling intensity instruction and the gradient heating compensation instruction are superimposed and corrected with the composite control instruction set, and the corrected composite control instruction set is used to carry out real-time control of the baking process.

[0013] Second aspect, the present invention provides a food baking processing program control system, including a phase change recognition module, a temperature gradient recognition module, an instruction generation module, and an instruction correction module; the phase change recognition module is used to collect the dielectric properties of the material and capture the change dynamics of the tangent value of the dielectric loss angle, and at the same time use the time-domain dielectric spectroscopy method to identify the material phase change stage in real time; the temperature gradient recognition module is used to construct a dual-channel heat conduction model and dynamically identify the regional temperature gradient of the baking equipment according to the material phase change stage; the instruction generation module is used to calculate the microwave power adjustment amount and the air velocity ratio adjustment amount of the baking equipment through a multi-parameter coupling control algorithm based on the regional temperature gradient of the baking equipment, and generate a composite control instruction set; the instruction correction module is used to obtain the change range of the material color difference and texture data, dynamically generate pulse cooling and gradient heating compensation instructions through a fuzzy PID compensator, and dynamically correct the composite control instruction set.

[0014] Third aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program is executed by the processor, any step of the food baking processing program control method described in the first aspect of the present invention is implemented.

[0015] Fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by the processor, any step of the food baking processing program control method described in the first aspect of the present invention is implemented.

[0016] The beneficial effects of the present invention are as follows: By using the time-domain dielectric spectroscopy method to identify the material phase change stage in real time, and using the inverse Laplace transform and the dynamic time warping algorithm to accurately analyze the correlation between the relaxation time distribution and the phase change characteristic spectrum, the dynamic capture of key phase change nodes such as glass transition and starch gelatinization is realized. By constructing a dual-channel heat conduction model, based on the Prony series fitting of the molecular chain motion characteristics and the TGA-FTIR determination of the moisture migration law respectively, a coupling calculation framework of slow heat relaxation and fast heat transfer is established, and the accurate matching of the phase change stage and the temperature gradient prediction is completed. Description of the Drawings

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of the food baking processing program control method.

[0019] Figure 2It is a schematic diagram of a food baking processing program control system.

[0020] Figure 3 It is a flow chart for identifying the material phase change stage.

[0021] Figure 4 It is a flow chart of a dual-channel heat conduction model. Specific implementation manners

[0022] To make the above objects, features and advantages of the present invention more obvious and understandable, the specific implementation manners of the present invention will be described in detail below with reference to the accompanying drawings of the specification.

[0023] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0024] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure or characteristic that can be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude each other with other embodiments.

[0025] Refer to Figures 1 to 4 , which is an embodiment of the present invention. This embodiment provides a food baking processing program control method, including the following steps: S1. Collect the dielectric properties of the material and capture the dynamic change of the tangent value of the dielectric loss angle. At the same time, use the time-domain dielectric spectroscopy method to identify the material phase change stage in real time.

[0026] The dielectric properties of the material refer to the dielectric constant and the loss factor, which are collected by a broadband dielectric sensor; According to the dielectric constant and the loss factor, obtain the tangent value of the dielectric loss angle through the frequency-domain dielectric spectroscopy method, and use TTS for dynamic tracking analysis to obtain the dynamic change curve of the tangent value of the dielectric loss angle; Furthermore, the frequency-domain dielectric spectroscopy method scans the dielectric response of the material in a logarithmic step manner within the frequency range of 10 Hz to 1 MHz. A precision LCR tester is used in conjunction with the three-electrode measurement method to synchronously collect the dielectric constant and loss factor. Through complex number operations, the ratio of the dielectric constant to the loss factor is converted into the tangent value of the dielectric loss angle. The time-temperature superposition principle (TTS) sets isothermal measurement points in the temperature range of 25 °C to 150 °C. The horizontal shift factor and vertical scaling factor are calculated for the frequency-domain dielectric spectroscopy obtained at each temperature point. The frequency-domain data of each temperature segment is mapped to the reference temperature using the WLF equation to construct a master curve covering 12 orders of magnitude of frequency. The Hann window weighted moving average algorithm is used to process the master curve data, and the tangent value of the dielectric loss angle in the characteristic frequency band is extracted at a step of 0.5 octave. The dynamic change curve of the tangent value of the dielectric loss angle with a time resolution of 10 ms is generated by adaptive piecewise cubic Hermite interpolation. Based on the dynamic change curve of the tangent value of the dielectric loss angle, the sliding window difference method is used to extract the phase transition characteristics of the material, and the phase transition characteristic spectrum is generated through the dynamic time warping algorithm. Furthermore, the dynamic change curve of the tangent value of the dielectric loss angle slides along the time axis through a rectangular window with a fixed time width. The first-order difference operation is performed on the numerical values of adjacent data points within the window to calculate the local slope change amount and the density of extreme points. The section where the slope mutation rate in the dynamic change curve of the tangent value of the dielectric loss angle exceeds the mutation threshold (value range: 0.5 - 3.0) is captured as the candidate region for phase transition characteristics. The dynamic time warping algorithm non-linearly aligns the slope change sequence in the candidate region with the standard phase transition template sequence, eliminates the time dimension scaling difference by constructing a dynamic bending path and a cumulative difference matrix, and integrates the slope mutation rate, characteristic peak intensity, and platform duration extracted from multiple windows into a set of time-aligned phase transition characteristic vectors to form a phase transition characteristic spectrum representing the glass transition and starch gelatinization processes of the material.

[0027] The phase transition characteristics of the material include the slope mutation rate, characteristic peak intensity, and platform duration (the time period during which the tangent value of the dielectric loss angle maintains stable fluctuations) in the dynamic change of the tangent value of the dielectric loss angle.

[0028] The time-domain dielectric relaxation current signal of the material is synchronously collected through a current probe and a high-voltage pulse generator. Furthermore, in the process of collecting the time-domain dielectric relaxation current signal, a square-wave excitation with a nanosecond rising edge is applied by a high-voltage pulse generator and connected to a three-electrode test fixture through a coaxial cable. The material is placed as a dielectric between the electrodes. The current probe adopts a broadband Rogowski coil structure and surrounds the high-voltage circuit wire to capture the polarization current decay waveform in real time. The synchronous trigger mechanism ensures that the leading edge of the excitation pulse is strictly aligned with the acquisition clock of the oscilloscope. The signal conditioning circuit performs logarithmic amplification and baseline drift compensation on the micro-current signal, and finally obtains a complete time-domain dielectric relaxation current decay curve in an equally spaced sampling manner and stores it as a time-current amplitude sequence.

[0029] Perform an inverse Laplace transform on the time-domain dielectric relaxation current signal of the material to generate a relaxation time distribution aligned with the phase transition characteristic spectrum in time. Furthermore, in the inverse Laplace transform process, the time decay curve of the time-domain dielectric relaxation current signal is used as the input, and a complex frequency domain integral equation is established to characterize the relaxation process. The ill-conditioned integral equation is solved by the regularized least squares method, and high-frequency noise interference is suppressed by truncated singular value decomposition. The transform kernel function selects an exponential decay basis function group, and the grid refinement algorithm is used to optimize the distribution density of the basis functions. The time axis of the relaxation time distribution is aligned with the time marking points of the phase transition characteristic spectrum by linear interpolation to form a relaxation time distribution with a strictly matched time dimension.

[0030] Adopt the time-domain dielectric spectroscopy method to calculate the minimum cumulative difference between the relaxation time distribution and the phase transition characteristic spectrum. The expression is: ; Where represents the minimum cumulative difference between the relaxation time distribution and the phase transition characteristic spectrum. is a set of paths connecting the data points of the two signal sequences composed of a series of discrete coordinate points. is the amplitude of the relaxation time distribution at the sampling time . represents the th sampling time of the time-domain dielectric relaxation current signal. is the amplitude of the phase transition characteristic spectrum at the sampling time . is the index of the sampling time of the time-domain dielectric relaxation current signal. is the index of the sampling time of the phase transition characteristic spectrum.

[0031] Furthermore, when the time-domain dielectric spectroscopy method calculates the minimum cumulative difference between the relaxation time distribution and the phase transition characteristic spectrum, the dynamic time warping algorithm first constructs a two-dimensional grid coordinate system between the amplitude sequences of the relaxation time distribution and the phase transition characteristic spectrum and traverses all possible path sets Connection method of discrete coordinate points; for each candidate path, calculate the amplitude of the relaxation time distribution corresponding to each coordinate point on the path and the amplitude of the phase transition characteristic spectrum The square of the difference is accumulated to form the total path difference value; the dynamic programming method is used to iteratively update the cumulative difference matrix from the starting point to the ending point, and the minimum cumulative difference value of each grid point is retained; finally, through the backtracking path set The path with the smallest cumulative difference in the set, extract the sum of the squares of the differences of all coordinate points on the path, and take the square root to obtain the minimum cumulative difference between the relaxation time distribution and the phase transition characteristic spectrum .

[0032] Based on the time-domain dielectric relaxation current signal of historical materials, define the low deviation threshold D1 and the high deviation threshold D2; It should be noted that based on the time-domain dielectric relaxation current signal of historical materials, by statistically analyzing the distribution range of the minimum cumulative difference D between the relaxation time distribution and the phase transition characteristic spectrum corresponding to the materials in the glass transition stage, starch gelatinization stage, and final shaping and ripening stage, the upper limit of the distribution of the minimum cumulative difference in the glass transition stage is taken as the low deviation threshold D1, and the boundary value of the distribution of the minimum cumulative difference in the starch gelatinization stage and the final shaping and ripening stage is taken as the high deviation threshold D2; the value range of the low deviation threshold D1 is 0.5 - 1.5, and the value range of the high deviation threshold D2 is 1.5 - 3.0.

[0033] When ≤ D1, it is considered that the material is in the glass transition stage; for example, when the minimum cumulative difference = 0.8 ( ≤ D1 = 1.0), the material is in the glass transition stage, and at this time, the tangent value of the dielectric loss angle shows a slow upward trend; When D1 < ≤ D2, it is considered that the material is in the starch gelatinization stage; for example, when the minimum cumulative difference = 1.8 (D1 = 1.0 < ≤ D2 = 2.5), the material is in the starch gelatinization stage, and at this time, the tangent value of the dielectric loss angle climbs rapidly; When > D2, it is considered that the material is in the final shaping and ripening stage.

[0034] When the minimum cumulative difference = 3.2 ( > D2 = 2.5), the material is in the final shaping and ripening stage, and at this time, the tangent value of the dielectric loss angle tends to be stable.

[0035] S2. Construct a dual-channel heat conduction model and identify the regional temperature gradient of the baking equipment according to the dynamics of the material phase change stage; The dual-channel heat conduction model includes a slow heat relaxation channel and a fast heat transfer channel; The slow heat relaxation channel is as follows: Based on the dielectric loss tangent value, time-domain dielectric relaxation spectroscopy analysis is used to identify the characteristics of molecular chain motion retardation; Furthermore, the process of time-domain dielectric relaxation spectroscopy analysis for identifying the characteristics of molecular chain motion retardation is as follows: The broadband dielectric spectrometer collects the time-domain decay curve of the dielectric loss tangent value, applies a step voltage excitation and records the time-domain response of the polarization current; The analysis process focuses on the non-linear decay characteristics of the dielectric loss tangent value with time, uses the multi-exponential fitting method to separate the relaxation peaks on different time scales, and calculates the ratio of the full width at half maximum of the main relaxation peak to the peak position time constant; By evaluating the integral area ratio of the relaxation peak tailing effect, the weight of the long-time relaxation component in the total relaxation energy is quantified; When analyzing the degree of hindrance of molecular chain conformation change, the asymmetric characteristics of the relaxation time distribution are examined; The final identification result shows the characteristics of molecular chain motion retardation, and the specific characteristics include dynamic parameters such as the broadening of the full width at half maximum of the main relaxation peak and the increase in the span of the main peak time constant distribution. Based on the characteristics of chain motion retardation, the relaxation activation energy and thermal history temperature characteristics of the material are calibrated by differential scanning calorimetry, and the Prony series fitting is used to construct the slow heat relaxation time spectrum; Furthermore, differential scanning calorimetry measures the curve of the heat flow of the material changing with temperature at a constant heating rate, determines the glass transition temperature through the starting point of the endothermic peak, and calculates the relaxation activation energy by integrating the area of the endothermic peak; The calibration of the thermal history temperature characteristics is based on a multi-step annealing experiment, records the enthalpy relaxation recovery curve at different temperature holding stages, and analyzes the relationship between the recovery rate constant and temperature; The relaxation time constant sequence of the time-domain dielectric relaxation spectroscopy analysis is used as the initial parameter, and the attenuation curve of the slow heat relaxation process is approximated in the form of a linear combination of exponential terms, and the amplitude coefficient and time constant of each exponential term are optimized by the least squares method; Finally, the slow heat relaxation time spectrum is formed.

[0036] Through the finite element discretization method, the spatial grid solution of the slow heat relaxation time spectrum is carried out to predict the regional temperature gradient of the baking equipment, and the expression is as follows: ; Among them, is the regional temperature gradient of the baking equipment, is the effective working volume in the baking equipment, is the slow heat relaxation intensity coefficient, is the current baking duration, is the spatial curvature of the temperature distribution in the baking equipment, is the a time scale, is the total number of time scales of molecular chain motion, is the index of the time scale of molecular chain motion, is the thermal history correction coefficient of the th time scale, is the molar gas constant, is the current real-time temperature of the material, is the thermal history temperature characteristic; Furthermore, the finite element discretization method first discretizes the effective working volume of the baking equipment into tetrahedral or hexahedral mesh elements, and assigns the time scale of molecular chain motion in the slow thermal relaxation time spectrum, the slow thermal relaxation strength coefficient, the thermal history correction coefficient, and the real-time temperature at each unit node; based on the current baking duration and the thermal history temperature characteristic , calculate the instantaneous value of the exponential decay term in each unit, and simultaneously solve the spatial curvature of the temperature distribution by the central difference method; multiply the summation result of the exponential decay terms of each unit by the spatial curvature , and perform numerical integration within the unit volume using the Gaussian integration method; after accumulating the integration contributions of all mesh units, obtain the regional temperature gradient of the baking equipment, and this gradient value reflects the coupling effect of the slow thermal relaxation effect and the spatial variation of the temperature field.

[0037] It should be noted that the slow thermal relaxation strength coefficient : 1.0×10² to 5.0×10³, the thermal history correction coefficient : 0.1 to 5.0, the time scale of molecular chain motion : 1.0 second to 1.0×10³ seconds, the molar gas constant : fixed value 8.314 J / (mol·K).

[0038] The fast heat transfer channels are as follows: Adopt TGA-FTIR to measure the moisture diffusion rate and the change rate of thermal conductivity during the baking process, and establish a quantitative relationship between moisture migration and heat conduction by fitting through the Arrhenius equation; Furthermore, the specific methods for synchronously collecting the moisture diffusion rate and the change rate of thermal conductivity during baking by TGA-FTIR are as follows: the moisture diffusion rate is obtained through the first derivative of the mass loss curve, and the change rate of thermal conductivity is determined by comparing the slopes of the heat flux response curves of the material at different temperatures; during the fitting process of the Arrhenius equation, the measured moisture diffusion rate and the corresponding temperature are taken the natural logarithm and then linearly regressed. The slope reflects the activation energy of moisture migration, and the intercept represents the pre-exponential factor; when establishing the quantitative relationship between moisture migration and heat conduction, the activation energy of moisture migration obtained from the Arrhenius equation and the change rate of thermal conductivity are subjected to multiple linear regression to obtain the proportional coefficient and coupling constant between the moisture diffusion rate and the change rate of thermal conductivity, and finally a quantitative relationship describing the change of heat conduction driven by moisture migration during baking is formed.

[0039] Based on the quantitative relationship between moisture migration and heat conduction, the finite volume method (FVM) is used to predict the regional temperature gradient of the baking equipment, and the expression is: Among them, is the total number of heat transfer channels dominated by moisture migration, is the index variable of the heat transfer channels dominated by moisture migration, is the th mass transfer and heat transfer coupling coefficient of the heat transfer channel (the value range is 0.01 - 1.0), is the temperature-dependent moisture diffusion rate measured by TGA-FTIR in the th heat transfer channel at the current real-time temperature of the material, is the th moisture migration characteristic time scale of the heat transfer channel, is the th apparent enthalpy change of moisture migration of the heat transfer channel; Furthermore, the finite volume method divides the effective working volume of the baking equipment into control volume units, and assigns the temperature-dependent moisture diffusion rate measured by TGA-FTIR, the mass transfer and heat transfer coupling coefficient , the moisture migration characteristic time scale and the apparent enthalpy change of moisture migration at the central node of each unit; based on the current baking duration and the real-time temperature , the instantaneous value of the exponential decay term in each unit is calculated, and at the same time the second-order central difference scheme is used to solve the spatial curvature of the temperature distribution; the sum of the exponential decay terms of all heat transfer channels in each control volume unit is combined with the spatial curvature Multiply and perform a flux integral on the cell surface using the Gauss divergence theorem; after accumulating the integration results of all control volume cells, obtain the regional temperature gradient of the baking equipment. This gradient value reflects the dynamic coupling effect between the moisture migration process and the heat conduction effect.

[0040] It should be noted that the apparent enthalpy change of moisture migration in the th heat transfer channel refers to the energy required for moisture to separate from the material during the starch gelatinization stage and the setting and ripening stage, which is obtained by scanning the heating rate of the TGA weight loss curve, and the value range is 0–120 kJ / mol (for the starch gelatinization stage =1, it takes 40–80 kJ / mol, and for the setting and ripening stage =2, it takes 80–120 kJ / mol).

[0041] When the material is in the glass transition stage, predict the regional temperature gradient of the baking equipment through the slow heat relaxation channel; When the material is in the starch gelatinization stage and the setting and ripening stage, predict the regional temperature gradient of the material in the baking equipment through the fast heat transfer channel; Furthermore, S3. Based on the regional temperature gradient of the baking equipment, calculate the microwave power adjustment amount and the air velocity ratio adjustment amount of the baking equipment through the multi-parameter coupling control algorithm, and generate a composite control instruction set; Calculate the microwave power adjustment amount and the air velocity ratio adjustment amount based on the regional temperature gradient of the baking equipment through the multi-parameter coupling control algorithm; The expression for the microwave power adjustment amount is: ; where is the microwave power adjustment amount at time , is the initial microwave power, is the weight coefficient of the regional temperature gradient amplitude for the microwave power adjustment amount (the value range is 0.1 - 0.5), is the weight coefficient of the regional temperature gradient change rate (the value range is 0.05 - 0.3), is the regional temperature gradient at time ; Furthermore, the multi-parameter coupling control algorithm first obtains the regional temperature gradient at time , calculates the regional temperature gradient amplitude and its change rate with time ; the weight coefficient The weight coefficient (value range: 0.1 - 0.5) for the change rate of the regional temperature gradient and the weight coefficient (value range: 0.05 - 0.3) are respectively multiplied by the corresponding gradient amplitude and change rate, and then added to the initial microwave power to obtain the microwave power adjustment amount at time .

[0042] The expression for the wind speed ratio adjustment amount is as follows: ; where is the wind speed ratio adjustment amount at time , is the reference wind speed ratio coefficient, is the weight coefficient of the regional temperature gradient amplitude for the wind speed ratio adjustment amount (value range: 0.05 - 0.25), is the lag adjustment weight coefficient of the regional temperature gradient cumulative effect on the wind speed ratio (value range: 0.01 - 0.1).

[0043] Furthermore, the multi - parameter coupling control algorithm first collects the regional temperature gradient at time in real - time, and calculates the regional temperature gradient amplitude ; uses the trapezoidal numerical integration method to perform cumulative integration on the regional temperature gradient amplitude within the time interval from 0 to to obtain ; multiplies the weight coefficient of the regional temperature gradient amplitude for the wind speed ratio adjustment amount (value range: 0.05 - 0.25) by the regional temperature gradient amplitude, and multiplies the lag adjustment weight coefficient of the regional temperature gradient cumulative effect on the wind speed ratio (value range: 0.01 - 0.1) by the cumulative integration value; performs a linear combination on the two weighted results and the reference wind speed ratio coefficient to output the wind speed ratio adjustment amount at time .

[0044] Based on the microwave power adjustment amount and the wind speed ratio adjustment amount, a composite control instruction set is generated through the linear interpolation mapping method; Furthermore, first normalize the microwave power adjustment amount and the wind speed ratio adjustment amount to the same control parameter interval, and locate the coordinate position of the current adjustment amount combination in the two - dimensional parameter space based on the historical optimal combination database of the baking equipment control parameters; use the bilinear interpolation algorithm to calculate the execution parameter combinations corresponding to the adjacent four optimal control points, and perform weighted fusion according to the distance weight to generate a composite control instruction set including the microwave generator output power curve and the fan speed curve.

[0045] S4. Obtain the variation ranges of the material color difference and texture data, dynamically generate pulse cooling and gradient heating compensation instructions through a fuzzy PID compensator, and dynamically correct the composite control instruction set.

[0046] The texture data refers to the hardness, elasticity, adhesiveness, and chewiness of the material measured by a texture analyzer. The material color difference refers to the CIE Lab color space difference value between the material color and the standard color plate. Based on the real-time material color difference and texture data, adopt a sliding window statistical method to identify the variation ranges of the material color difference and texture data. Furthermore, the sliding window statistical method traverses the real-time material color difference and texture data sequences with a fixed time window length, calculates statistics such as the mean, standard deviation of the material color difference, and the kurtosis and skewness of the texture data within each window; by comparing the differences in statistics between adjacent windows, identify the fluctuation range of the ΔE value of the color difference in the Lab color space and the coefficient of variation range of the texture data (such as hardness, elastic modulus); dynamically adjust the window length to capture the parameter drift characteristics at different time scales, and finally output the variation ranges of the material color difference and texture data. For example, when it is detected that the standard deviation increase rate of the material color difference ΔE value exceeds 30% within three consecutive windows, it is determined that the surface browning rate is abnormal. At this time, the output color difference variation range is ΔE = 2.5 - 4.0, and the coefficient of variation range of the texture hardness is adjusted to 0.15 - 0.25.

[0047] Adopt a fuzzy clustering algorithm to divide the variation ranges of the material color difference and texture data into multiple fuzzy subsets, and establish IF-THEN control rules for each fuzzy subset. Furthermore, the fuzzy clustering algorithm first inputs the joint distribution data of the color difference and texture data (hardness, adhesiveness) into the fuzzy C-means clustering process, optimizes the membership matrix and the position of the clustering center through iterative calculation, and divides the data space into several fuzzy subsets; each fuzzy subset uses a Gaussian membership function to accurately describe the belonging degree of the color difference-texture data. For example, the color difference = in the range of 3.0 - 5.0 and the hardness in the range of 50 - 70N constitute a typical fuzzy subset; based on the centroid characteristics and boundary conditions of each fuzzy subset, construct a complete IF-THEN control rule base, such as "if the color difference = belongs to the 3.0 - 5.0 fuzzy subset and the hardness belongs to the 50 - 70N fuzzy subset, then output the cooling intensity adjustment coefficient 0.5".

[0048] Based on the material color difference and texture data, generate pulse cooling intensity instructions and gradient heating compensation instructions through the IF-THEN control rules of each fuzzy subset. Further, after the real-time material color difference and texture data are input into the fuzzy subsets divided by the fuzzy clustering algorithm, the membership degree weights of each subset are calculated; according to the logical condition matching degree of the corresponding subset in the IF-THEN control rule, the weighted average method is used to fuse the output quantities of multiple rules; when the material color difference ΔE value belongs to the high deviation fuzzy subset, a pulse cooling intensity instruction is triggered, and this instruction maps the color difference deviation degree to a step increment of the duty ratio of the cooling fan; when the texture parameters (hardness, elastic modulus) belong to the non-ideal state fuzzy subset, a gradient heating compensation instruction is generated, and this instruction calculates the progressive compensation amount of the microwave power according to the texture deviation amount; after defuzzification by the maximum-minimum inference method, the pulse cooling intensity instruction and the gradient heating compensation instruction that can directly control the actuator are finally output.

[0049] Through the fuzzy PID compensator, the pulse cooling intensity instruction and the gradient heating compensation instruction are superimposed and corrected with the composite control instruction set, and the corrected composite control instruction set is used to perform real-time control on the baking process.

[0050] Further, the fuzzy PID compensator receives the pulse cooling intensity instruction and the gradient heating compensation instruction, and superimposes them with the microwave power adjustment amount and the wind speed ratio adjustment amount in the composite control instruction set; the proportional-integral-differential parameters are dynamically adjusted according to the real-time errors of the color difference and texture data. For example, when the color difference ΔE error is large, the weight of the proportional term is increased, and when there is an accumulated deviation in the texture parameters, the role of the integral term is enhanced; the corrected composite control instruction set synchronously adjusts the output power of the microwave generator and the rotational speed of the fan through the actuator to achieve the coordinated control of the baking process temperature and the material state.

[0051] This embodiment also provides a food baking processing program control system, including: a phase change recognition module, a temperature gradient recognition module, an instruction generation module, and an instruction correction module; the phase change recognition module is used to collect the dielectric properties of the material and capture the change dynamics of the tangent value of the dielectric loss angle, and at the same time use the time-domain dielectric spectroscopy analysis method to identify the material phase change stage in real time; the temperature gradient recognition module is used to construct a two-channel heat conduction model and dynamically identify the regional temperature gradient of the baking equipment according to the material phase change stage; the instruction generation module is used to calculate the microwave power adjustment amount and the wind speed ratio adjustment amount of the baking equipment through a multi-parameter coupling control algorithm based on the regional temperature gradient of the baking equipment, and generate a composite control instruction set; the instruction correction module is used to obtain the change range of the material color difference and texture data, and through the fuzzy PID compensator This embodiment also provides a computer device applicable to the case of the food baking processing program control method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the food baking processing program control method proposed in the above embodiment.

[0052] The computer device may be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be implemented through WIFI, carrier networks, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, trackball, or touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0053] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the food baking process control method proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, abbreviated as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, abbreviated as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, abbreviated as EPROM), programmable read-only memory (Programmable Red-Only Memory, abbreviated as PROM), read-only memory (Read-Only Memory, abbreviated as ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0054] In summary, the present invention: uses time-domain dielectric spectroscopy analysis to identify the material phase transition stage in real time, adopts inverse Laplace transform and dynamic time warping algorithm to accurately analyze the correlation between the relaxation time distribution and the phase transition characteristic spectrum, and realizes the dynamic capture of key phase transition nodes such as glass transition and starch gelatinization. By constructing a two-channel heat conduction model, respectively based on Prony series to fit the molecular chain motion characteristics and TGA-FTIR to measure the moisture migration law, and establishing a coupled calculation framework for slow thermal relaxation and fast heat transfer, the accurate matching of the phase transition stage and temperature gradient prediction is completed.

[0055] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A method for controlling a food baking process, characterized in that: Including, Collecting the dielectric properties of the material and capturing the dynamic changes in the tangent value of the dielectric loss angle, and simultaneously using time-domain dielectric spectroscopy analysis to identify the phase change stage of the material in real time; Constructing a two-channel heat conduction model and dynamically identifying the regional temperature gradient of the baking equipment according to the phase change stage of the material; Based on the regional temperature gradient of the baking equipment, calculating the microwave power adjustment amount and the airspeed ratio adjustment amount of the baking equipment through a multi-parameter coupling control algorithm, and generating a composite control instruction set; Obtaining the change range of the material color difference and texture data, dynamically generating pulse cooling and gradient heating compensation instructions through a fuzzy PID compensator, and dynamically correcting the composite control instruction set.

2. The food baking processing program control method according to claim 1, characterized in that: The capturing the dynamic changes in the tangent value of the dielectric loss angle refers to obtaining the tangent value of the dielectric loss angle through frequency-domain dielectric spectroscopy analysis according to the dielectric constant and loss factor, and using TTS for dynamic tracking analysis to obtain the dynamic change curve of the tangent value of the dielectric loss angle.

3. The food baking process control method according to claim 2, characterized in that: The using time-domain dielectric spectroscopy analysis to identify the phase change stage of the material in real time has the following steps Based on the dynamic change curve of the tangent value of the dielectric loss angle, using the sliding window difference method to extract the phase change characteristics of the material, and generating a phase change characteristic spectrum through the dynamic time warping algorithm; Performing an inverse Laplace transform on the time-domain dielectric relaxation current signal of the material to generate a relaxation time distribution aligned with the time of the phase change characteristic spectrum; Using time-domain dielectric spectroscopy analysis to calculate the minimum cumulative difference between the relaxation time distribution and the phase change characteristic spectrum; Defining a low deviation threshold and a high deviation threshold, and comparing them with the minimum cumulative difference between the relaxation time distribution and the phase change characteristic spectrum to identify the glass transition stage, starch gelatinization stage, and final setting and ripening stage of the material.

4. The food baking process control method according to claim 1, characterized in that: The constructing a two-channel heat conduction model and dynamically identifying the regional temperature gradient of the baking equipment according to the phase change stage of the material has the following steps The two-channel heat conduction model includes a slow heat relaxation channel and a fast heat transfer channel; The slow heat relaxation channel uses time-domain dielectric relaxation spectroscopy analysis to identify the hysteresis characteristics of molecular chain movement; Calibrating the relaxation activation energy and thermal history temperature characteristics of the material through differential scanning calorimetry, and using Prony series fitting to construct a slow heat relaxation time spectrum; Through the finite element discretization method, spatially grid-solving the slow heat relaxation time spectrum to predict the regional temperature gradient of the baking equipment; The fast heat transfer channel uses TGA-FTIR to measure the moisture diffusion rate and the change rate of thermal conductivity during the baking process, and establishes a quantitative relationship between moisture migration and heat conduction through Arrhenius equation fitting, and simultaneously uses the finite volume method to predict the regional temperature gradient of the baking equipment; Processing the materials in different phase change stages through the slow heat relaxation channel and the fast heat transfer channel of the two-channel heat conduction model.

5. The food baking processing program control method according to claim 1, characterized in that: The generating a composite control instruction set refers to calculating the microwave power adjustment amount and the airspeed ratio adjustment amount based on the regional temperature gradient of the baking equipment through a multi-parameter coupling control algorithm, and generating a composite control instruction set through the linear interpolation mapping method.

6. The food baking processing program control method according to claim 1, wherein: The obtaining the change range of the material color difference and texture data, and dynamically generating pulse cooling and gradient heating compensation instructions through a fuzzy PID compensator has the following steps Based on the real-time material color difference and texture data, the sliding window statistical method is used to identify the change range of the material color difference and texture data; Using the fuzzy clustering algorithm, the change range of the material color difference and texture data is divided into multiple fuzzy subsets, and the IF-THEN control rules for each fuzzy subset are established; Based on the material color difference and texture data, through the IF-THEN control rules of each fuzzy subset, the pulse cooling intensity instruction and the gradient heating compensation instruction are generated.

7. The food baking processing program control method according to claim 6, wherein: The dynamic correction of the composite control instruction set refers to using the fuzzy PID compensator to superimpose and correct the pulse cooling intensity instruction and the gradient heating compensation instruction with the composite control instruction set, and using the corrected composite control instruction set to perform real-time control on the baking process.

8. A food baking processing program control system, based on the food baking processing program control method according to any one of claims 1 to 7, characterized in that: It includes a phase change identification module, a temperature gradient identification module, an instruction generation module, and an instruction correction module; The phase change identification module is used to collect the dielectric properties of the material and capture the change dynamics of the tangent value of the dielectric loss angle, and at the same time use the time-domain dielectric spectroscopy analysis method to identify the material phase change stage in real time; The temperature gradient identification module is used to construct a two-channel heat conduction model and dynamically identify the regional temperature gradient of the baking equipment according to the material phase change stage; The instruction generation module is used to calculate the microwave power adjustment amount and the air volume ratio adjustment amount of the baking equipment through the multi-parameter coupling control algorithm based on the regional temperature gradient of the baking equipment, and generate a composite control instruction set; The instruction correction module is used to obtain the change range of the material color difference and texture data, dynamically generate the pulse cooling and gradient heating compensation instructions through the fuzzy PID compensator, and perform dynamic correction on the composite control instruction set.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the food baking process control method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the food baking process control method according to any one of claims 1 to 7.

Images