Apparatus and control algorithm for optimizing heat field uniformity during macaron baking
By constructing a heat field uniformity optimization device and control algorithm, the problem of lag in heat field uniformity control during macaron baking was solved, achieving precise and real-time heat field uniformity optimization and improving the baking quality of macarons.
Patent Information
- Application Number
- CN202610386174.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-03-27
- Publication Date
- 2026-06-26
AI Technical Summary
In existing technologies, the heat field uniformity control during the macaron baking process uses a PID algorithm, which has a lag and cannot accurately control the heat field uniformity.
A device and control algorithm for optimizing the thermal field uniformity during macaron baking were developed, including data acquisition, thermal field uniformity evaluation, adaptive fuzzy neural network control model, thermal field prediction control model for baking equipment, and inter-layer thermal interference compensation model, to achieve temperature prediction control and real-time optimization.
It achieves precise control of the heat field uniformity during the macaron baking process, has forward-looking and real-time optimization capabilities, and improves baking quality.
Smart Images
Figure CN122284429A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of food processing technology, specifically relating to equipment and control algorithms for optimizing the uniformity of heat field during macaron baking. Background Technology
[0002] Macarons are a type of French dessert made primarily from meringue, almond flour, and powdered sugar. They are baked to create a crisp outer shell and a soft interior.
[0003] The quality of macarons is highly dependent on the uniform distribution of heat during the baking process.
[0004] Currently, the PID algorithm control strategy is generally used to control the uniformity of the heat distribution during the macaron baking process. This strategy is a temperature feedback control, which has a lag and cannot accurately control the uniformity of the heat distribution during the macaron baking process.
[0005] Therefore, we designed a device and control algorithm to optimize the heat field uniformity during the macaron baking process in order to solve the above problems. Summary of the Invention
[0006] To address the problems mentioned in the background section, this invention provides a device and control algorithm for optimizing the heat field uniformity during macaron baking. This device features precise control of the heat field uniformity during macaron baking while enabling real-time optimization.
[0007] To achieve the above objectives, the present invention provides the following technical solution: an algorithm for optimizing and controlling the heat field uniformity during the macaron baking process, comprising the following steps: 1. Construct a data acquisition device for macaron baking to collect data on the heat field distribution, humidity distribution, and surface condition of macarons inside the baking device; 2. Construct a thermal field uniformity evaluation index, and generate an evaluation of the thermal field uniformity inside the macaron baking equipment based on the collected thermal field distribution data and macaron surface state data; 3. Construct an adaptive fuzzy neural network control model to generate control parameters for the macaron baking equipment based on the initial parameters of the macarons, the collected thermal field distribution data, and the generated thermal field uniformity evaluation. IV. Construct a predictive control model for the thermal field of the baking equipment, predict the thermal field distribution of the macaron baking equipment based on the generated control parameters, and optimize the control parameters of the macaron baking equipment. 5. Construct an interlayer thermal interference compensation model, perform interlayer thermal interference compensation on the optimized control parameters, and generate the final control parameters; VI. Control the macaron baking equipment based on the generated final control parameters to optimize the uniformity of the heat field during the macaron baking process.
[0008] Furthermore, in step one, the macaron baking data acquisition device includes an infrared thermal imaging sensor array, a multi-channel thermocouple array, a humidity sensor array, and a sensor. Infrared thermal imaging sensor arrays acquire thermal field distribution data on the surface of the baked macaron layer; A multi-channel thermocouple array is used to collect temperature data at different locations on the baking layer. A humidity sensor array collects humidity data at different locations on the baking layer; A visual sensor captures the formation of the macaron skirt and the surface coloring status of the baked layer.
[0009] Furthermore, in step two, the expression for the thermal field uniformity evaluation index is as follows: In the formula: , and Indicates the weighting coefficient; The temperature standard deviation is calculated from the collected data on the thermal field distribution of the macaron surface and the temperature data at different locations. The maximum temperature difference is calculated from the collected data on the thermal field distribution of the macaron surface and the temperature data at different locations. Indicates the set temperature; This represents the color uniformity coefficient, calculated from the collected data on macaron skirt formation and surface coloring status.
[0010] Furthermore, in step three, the adaptive fuzzy neural network control model includes an input layer, a fuzzification layer, a rule layer, a defuzzification layer, and an output layer; The input layer receives the initial moisture content of the macaron batter, almond powder particle size distribution, thermal field uniformity evaluation value, temperature deviation, and deviation change rate. The initial moisture content of the macaron batter and almond powder particle size distribution are measured by the instrument, while the temperature deviation and deviation change rate are calculated from the collected thermal field distribution data of the macaron surface and the temperature data at different locations. The fuzzification layer constructs several fuzzy subsets, and calculates the membership value of each input data under several fuzzy subsets based on the Gaussian membership function; The rule layer constructs fuzzy control rules for each stage of macaron baking, and calculates the activation degree of each rule based on the minimum membership value of each input data. The defuzzing layer converts the activation degree of each rule and the corresponding fuzzy subset representative value into control rules based on the centroid method; The output layer generates control parameters based on control rules.
[0011] Furthermore, in step four, the expression for the thermal field prediction and control model of the baking equipment is: In the formula: Indicates time-domain prediction; Indicates the first Predicted temperature field values; Indicates the first Step temperature field target value; Indicates time-domain control; Indicates the first Step control increment; This represents the uniformity weighting coefficient; Indicates the first Evaluation index of thermal field uniformity; Indicates the first Power of each heating element; This indicates the maximum power of the heating element; Indicates the rate of temperature change; Indicates the uniformity of the thermal field; This represents the minimum value of the thermal field uniformity index; A rolling optimization strategy based on genetic algorithms is used to solve the above-mentioned constrained optimization control parameters.
[0012] Furthermore, in step five, the expression for the interlayer thermal interference compensation model is as follows: In the formula: Indicates the first Layered heat compensation; Indicates the inter-layer viewing angle coefficient; Indicates emissivity; This represents the Stefan-Boltzmann constant; Indicates the first Absolute temperature of the layer; Indicates the first Absolute temperature of the layer; Represents the distance and occlusion attenuation function; Indicates the first Layer and First Interlayer spacing; Indicates the angle of obstruction; Expressions for interlayer thermal interference compensation control parameters: In the formula: Indicates the first Layer adjustment control parameters; Indicates the first Layer control parameters; Indicates the proportional gain coefficient; Indicates the first Layered heat compensation; This represents the integral gain coefficient.
[0013] The device for optimizing the uniformity of the heat field during the macaron baking process includes a processor and a memory. The processor executes the steps of the method by calling programs or instructions stored in the memory.
[0014] Compared with the prior art, the beneficial effects of the present invention are: This invention constructs a thermal field uniformity evaluation index, an adaptive fuzzy neural network control model, a baking equipment thermal field prediction control model, and an interlayer thermal interference compensation model. It transforms temperature feedback control into temperature prediction control, which is forward-looking and can accurately control the thermal field uniformity during the macaron baking process while performing real-time optimization. Attached Figure Description
[0015] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation
[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0017] The algorithm for optimizing the uniformity of the thermal field during macaron baking includes the following steps: I. Constructing a data acquisition device for macaron baking; An array of infrared thermal imaging sensors is deployed at the top center of each baking layer in the macaron baking equipment. The macaron baking equipment deploys a multi-channel thermocouple array at the center and edge of each baking layer; The macaron baking equipment deploys an array of humidity sensors at equal intervals along the height of each baking layer; Visual sensors are deployed in front of each baking layer of the macaron baking equipment; II. Constructing evaluation indices for thermal field uniformity; Evaluation index of thermal field uniformity: In the formula: , and Indicates the weighting coefficient; Indicates the standard deviation of temperature; Indicates the maximum temperature difference; Indicates the set temperature; Indicates the color uniformity coefficient; Temperature standard deviation: In the formula: Indicates the first One temperature measurement; Indicates average temperature; Indicates the total number of measured temperatures; Maximum temperature difference: In the formula: This indicates the maximum temperature. Indicates the minimum temperature; Color uniformity coefficient: In the formula: This represents the average color of all pixels on the surface of a macaron. Indicates the standard deviation of the color channels; III. Constructing an adaptive fuzzy neural network control model; The adaptive fuzzy neural network control model includes an input layer, a fuzzification layer, a rule layer, a defuzzification layer, and an output layer. The input layer receives the initial moisture content of the macaron batter, almond powder particle size distribution, thermal field uniformity evaluation value, temperature deviation, and deviation change rate. The initial moisture content of the macaron batter was measured using a moisture analyzer; The particle size distribution of almond powder was measured using a laser particle size analyzer. Temperature deviation: In the formula: Indicates the target temperature; Indicates the actual temperature; Deviation change rate: In the formula: Indicates the first Periodic temperature deviation; Indicates the first Temperature deviation in the previous cycle; The fuzzification layer constructs several fuzzy subsets, and calculates the membership value of each input data under several fuzzy subsets based on the Gaussian membership function; Gaussian membership function: In the formula: Indicates the membership degree value; Indicates input data; Indicates the center of a fuzzy subset; Indicates the width of the membership function; The rule layer constructs fuzzy control rules for each stage of macaron baking, and calculates the activation degree of each rule based on the minimum membership value of each input data. The defuzzing layer converts the activation degree of each rule and the corresponding fuzzy subset representative value into control rules based on the centroid method; Center of gravity method: In the formula: Indicates the first The activation level of the rule; Indicates the first Each rule outputs a representative value for a fuzzy subset; The output layer generates control parameters based on control rules; IV. Constructing a predictive control model for the thermal field of baking equipment; Baking equipment thermal field prediction and control model: In the formula: Indicates time-domain prediction; Indicates the first Predicted temperature field values; Indicates the first Step temperature field target value; Indicates time-domain control; Indicates the first Step control increment; This represents the uniformity weighting coefficient; Indicates the first Evaluation index of thermal field uniformity; Indicates the first Power of each heating element; This indicates the maximum power of the heating element; Indicates the rate of temperature change; Indicates the uniformity of the thermal field; This represents the minimum value of the thermal field uniformity index; V. Construct an interlayer thermal interference compensation model; Interlayer thermal interference compensation model: In the formula: Indicates the first Layered heat compensation; Indicates the inter-layer viewing angle coefficient; Indicates emissivity; This represents the Stefan-Boltzmann constant; Indicates the first Absolute temperature of the layer; Indicates the first Absolute temperature of the layer; Represents the distance and occlusion attenuation function; Indicates the first Layer and First Interlayer spacing; Indicates the angle of obstruction; VI. During the macaron baking process, an infrared thermal imaging sensor array collects thermal field distribution data on the surface of the macarons in the baking layer, a multi-channel thermocouple array collects temperature data at different locations on the baking layer, a humidity sensor array collects humidity data at different locations on the baking layer, and a visual sensor collects data on the formation of the macaron skirts and the surface coloring state. The collected thermal field distribution data and macaron surface state data are used to generate a thermal field uniformity evaluation index for the internal thermal field of the macaron baking equipment. The initial parameters of the macarons, the collected thermal field distribution data, and the generated thermal field uniformity evaluation are used to generate control parameters for the macaron baking equipment based on an adaptive fuzzy neural network control model. The control parameters are used to solve constraints and predict the thermal field distribution of the macaron baking equipment based on the thermal field prediction control model of the baking equipment through a rolling optimization strategy of a genetic algorithm, and to optimize the control parameters of the macaron baking equipment. The optimized control parameters are then used to compensate for interlayer thermal interference based on an interlayer thermal interference compensation model to generate the final control parameters. The macaron baking equipment is controlled based on the generated final control parameters to optimize the thermal field uniformity during the macaron baking process. The rolling optimization strategy of the genetic algorithm refers to predicting a time domain backward and searching for the optimal control sequence again using the current latest state at fixed time steps, and only executing the first step of the control quantity of the sequence. This process is repeated at the next time step. Through the closed loop of "looking forward - finding the optimal solution - only taking one step", dynamic and robust optimal control of the thermal field is achieved. Genetic algorithms refer to the global search for the optimal control sequence in the feasible solution space by simulating the selection, crossover, and mutation processes of biological evolution. Expressions for interlayer thermal interference compensation control parameters: In the formula: Indicates the first Layer adjustment control parameters; Indicates the first Layer control parameters; Indicates the proportional gain coefficient; Indicates the first Layered heat compensation; This represents the integral gain coefficient.
[0018] The device for optimizing the uniformity of heat field during the macaron baking process includes a processor and a memory. The processor executes the steps of the method by calling programs or instructions stored in the memory.
[0019] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.
Claims
1. An algorithm for optimizing and controlling the uniformity of the thermal field during macaron baking, characterized in that, Includes the following steps:
1. Construct a data acquisition device for macaron baking to collect data on the heat field distribution, humidity distribution, and surface condition of macarons inside the baking device; 2. Construct a thermal field uniformity evaluation index, and generate an evaluation of the thermal field uniformity inside the macaron baking equipment based on the collected thermal field distribution data and macaron surface state data; 3. Construct an adaptive fuzzy neural network control model to generate control parameters for the macaron baking equipment based on the initial parameters of the macarons, the collected thermal field distribution data, and the generated thermal field uniformity evaluation. IV. Construct a predictive control model for the thermal field of the baking equipment, predict the thermal field distribution of the macaron baking equipment based on the generated control parameters, and optimize the control parameters of the macaron baking equipment.
5. Construct an interlayer thermal interference compensation model, perform interlayer thermal interference compensation on the optimized control parameters, and generate the final control parameters; VI. Control the macaron baking equipment based on the generated final control parameters to optimize the uniformity of the heat field during the macaron baking process.
2. The algorithm for optimizing and controlling the uniformity of the thermal field during the macaron baking process according to claim 1, characterized in that: In step one, the macaron baking data acquisition device includes an infrared thermal imaging sensor array, a multi-channel thermocouple array, a humidity sensor array, and a sensor. Infrared thermal imaging sensor arrays acquire thermal field distribution data on the surface of the baked macaron layer; A multi-channel thermocouple array is used to collect temperature data at different locations on the baking layer. A humidity sensor array collects humidity data at different locations on the baking layer; A visual sensor captures the formation of the macaron skirt and the surface coloring status of the baked layer.
3. The algorithm for optimizing and controlling the uniformity of the thermal field during the macaron baking process according to claim 2, characterized in that: In step two, the expression for the thermal field uniformity evaluation index is as follows: In the formula: , and Indicates the weighting coefficient; The temperature standard deviation is calculated from the collected data on the thermal field distribution of the macaron surface and the temperature data at different locations. The maximum temperature difference is calculated from the collected data on the thermal field distribution of the macaron surface and the temperature data at different locations. Indicates the set temperature; This represents the color uniformity coefficient, calculated from the collected data on macaron skirt formation and surface coloring status.
4. The algorithm for optimizing and controlling the uniformity of the thermal field during the macaron baking process according to claim 3, characterized in that: In step three, the adaptive fuzzy neural network control model includes an input layer, a fuzzification layer, a rule layer, a defuzzification layer, and an output layer; The input layer receives the initial moisture content of the macaron batter, almond powder particle size distribution, thermal field uniformity evaluation value, temperature deviation, and deviation change rate. The initial moisture content of the macaron batter and almond powder particle size distribution are measured by the instrument, while the temperature deviation and deviation change rate are calculated from the collected thermal field distribution data of the macaron surface and the temperature data at different locations. The fuzzification layer constructs several fuzzy subsets, and calculates the membership value of each input data under several fuzzy subsets based on the Gaussian membership function; The rule layer constructs fuzzy control rules for each stage of macaron baking, and calculates the activation degree of each rule based on the minimum membership value of each input data. The defuzzing layer converts the activation degree of each rule and the corresponding fuzzy subset representative value into control rules based on the centroid method; The output layer generates control parameters based on control rules.
5. The algorithm for optimizing and controlling the uniformity of the thermal field during the macaron baking process according to claim 4, characterized in that: In step four, the expression for the thermal field prediction and control model of the baking equipment is: In the formula: Indicates time-domain prediction; Indicates the first Predicted temperature field values; Indicates the first Step temperature field target value; Indicates time-domain control; Indicates the first Step control increment; This represents the uniformity weighting coefficient; Indicates the first Evaluation index of thermal field uniformity; Indicates the first Power of each heating element; This indicates the maximum power of the heating element; Indicates the rate of temperature change; Indicates the uniformity of the thermal field; This represents the minimum value of the thermal field uniformity index; A rolling optimization strategy based on genetic algorithms is used to solve the above-mentioned constrained optimization control parameters.
6. The algorithm for optimizing and controlling the uniformity of the thermal field during the macaron baking process according to claim 5, characterized in that: In step five, the expression for the interlayer thermal interference compensation model is as follows: In the formula: Indicates the first Layered heat compensation; Indicates the inter-layer viewing angle coefficient; Indicates emissivity; This represents the Stefan-Boltzmann constant; Indicates the first Absolute temperature of the layer; Indicates the first Absolute temperature of the layer; Represents the distance and occlusion attenuation function; Indicates the first Layer and First Interlayer spacing; Indicates the angle of obstruction; Expressions for interlayer thermal interference compensation control parameters: In the formula: Indicates the first Layer adjustment control parameters; Indicates the first Layer control parameters; Indicates the proportional gain coefficient; Indicates the first Layered heat compensation; This represents the integral gain coefficient.
7. Equipment for optimizing the heat field uniformity during macaron baking, characterized in that, include: A processor and a memory, wherein the processor performs the steps of the method as described in any one of claims 1 to 6 by invoking a program or instructions stored in the memory.