Method, computer equipment and system for detecting maturity of steamed water eggs

Abstract

The invention discloses a steamed water egg maturity detection method, computer equipment and a system, and relates to the technical field of food processing, computer simulation and machine learning. The method for detecting the maturity of the steamed water eggs comprises the following steps: collecting actually measured temperature data in a steaming process of the steamed water eggs in real time; establishing a geometric model, a coupling equation set and the thermophysical parameters to generate reference prediction data; building an analysis platform, training an initial detection model according to the reference prediction data, and extracting a target detection model from the initial detection model according to a training result; generating model prediction data according to the target detection model; verifying the target detection model according to the actually measured temperature data and model prediction data, and optimizing the target detection model according to a verification result; and analyzing the steaming maturing process of the steamed eggs according to the optimized target detection model. With the adoption of the method, the maturity of the steamed water eggs can be scientifically judged, the cooking efficiency is improved, and the taste quality is controlled.

Description

Technical Field

[0001] The present invention relates to the technical fields of food processing, computer simulation, and machine learning, and particularly to a method for detecting the maturity of steamed eggs, a computer device, and a system. Background Art

[0002] Steaming is a cooking method that uses water vapor as a heat transfer medium. During the steaming process, high-temperature water vapor exchanges heat with the surface of the relatively low-temperature food material. The water vapor transfers heat to the food material, causing the temperature of the food material to gradually increase, thereby achieving the cooking purpose of cooking the food material until it is cooked. The steaming process is a typical heating process, and the maturity of food is highly correlated with the thermal history of the food material.

[0003] The maturity of food is an important indicator for measuring food quality. Currently, for the research on the maturity of steamed foods, it is mainly determined by taking samples at regular intervals and then conducting sensory evaluation and texture analysis. However, sensory evaluation depends on personal subjectivity and is difficult to accurately and repeatedly quantify. Therefore, it is difficult to study the kinetics of food material maturity through traditional methods.

[0004] Therefore, it is urgently necessary to design a method for detecting the maturity of steamed eggs, a computer device, and a system to solve the above problems. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a method for detecting the maturity of steamed eggs, a computer device, and a system, which can scientifically determine the maturity of steamed eggs, improve cooking efficiency, and control the taste quality.

[0006] To solve the above technical problem, the present invention provides a method for detecting the maturity of steamed eggs, including: collecting real-time measured temperature data during the steaming process of the steamed eggs; establishing a geometric model, a coupled equation set, and thermophysical parameters to generate reference prediction data; building an analysis platform, training an initial detection model according to the reference prediction data, and extracting a target detection model from the initial detection model according to the training result; generating model prediction data according to the target detection model; verifying the target detection model according to the measured temperature data and the model prediction data, and optimizing the target detection model according to the verification result; analyzing the maturity process of the steamed eggs according to the optimized target detection model.

[0007] As an improvement to the above solution, the steps of establishing a geometric model, a coupled equation set, and thermophysical parameters to generate benchmark prediction data include: constructing a cavity model and an egg liquid model of the micro steam oven; constructing a coupled equation set, where the coupled equation set takes laminar flow with low Reynolds number, heat transfer between fluid and solid, and surface-to-surface radiation as physical fields to be analyzed, and constructs a multi-physical field coupling relationship by combining non-isothermal flow and surface-to-surface radiation heat transfer, and constructs a fluid flow and heat transfer control equation; constructing initial conditions and boundary conditions, where the initial conditions include the initial temperature and the initial pressure, and the boundary conditions include the surface emissivity of the inner wall of the micro steam oven, the thermal conductivity of the surface of the steamed egg, the thermal conductivity of steam on the surface of the steamed egg, the constant pressure heat capacity of the steamed egg, the density of the steamed egg, the thermal conductivity of the container for holding the steamed egg, the constant pressure heat capacity of the container for holding the steamed egg, and the boundary heat source; using free tetrahedral meshes to perform mesh division; setting the solution time step according to the process requirements and running the solution to generate the relationship between the temperature and time of the cavity of the micro steam oven and the steamed egg during the steaming process, and taking the relationship between the temperature and time as the benchmark prediction data.

[0008] As an improvement to the above solution, the coupled equation set includes the Navier-Stokes equation, the continuity equation, the thermal thin approximation equation, and the energy conservation equation.

[0009] As an improvement to the above solution, the analysis platform is built based on machine learning, and the analysis platform includes a platform front end, a platform back end, and platform scripts; the platform front end is developed based on the vue framework to implement functions such as module selection, file selection, execution of calculations, and acquisition of IOFile; the platform back end is developed based on php, and the corresponding platform scripts are called through the Thinkphp framework to execute calculations, and a user database and an execution information database are built using MySQL; the platform scripts are developed based on python, and the platform scripts are built through machine learning libraries of scikit-learn and pytorch.

[0010] As an improvement to the above solution, the initial detection model includes support vector machine regression, random forest regression, decision tree regression, K-nearest neighbor regression, AdaBoost regression, gradient boosting regression, and extremely randomized tree regression.

[0011] As an improvement to the above solution, the steps of validating the target detection model according to the measured temperature data and the model prediction data, and optimizing the target detection model according to the validation result include: fitting the model prediction data and the measured temperature data to calculate the coefficient of determination; determining whether the coefficient of determination is greater than a preset fitting limit value; if it is determined to be yes, then taking the target detection model as the optimized target detection model; if it is determined to be no, then retraining the target detection model.

[0012] As an improvement of the above solution, the steps of analyzing the steaming process of the steamed egg custard according to the optimized object detection model include: making predictions through the optimized object detection model to generate target prediction data; generating a temperature distribution cloud map according to the target prediction data; analyzing the central temperature at the central position of the steamed egg custard during the steaming process through the temperature distribution cloud map; and judging the maturity of the steamed egg custard based on the change of the central temperature.

[0013] As an improvement of the above solution, the object detection model is the model with the highest accuracy in the initial detection models.

[0014] The present invention also discloses a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.

[0015] The present invention also discloses a steamed egg custard maturity detection system, including an experimental device and the computer device as described above; the experimental device includes a micro steam oven, a multi-channel temperature inspection instrument, and a temperature sensor disposed in the micro steam oven; the micro steam oven is used for steaming the steamed egg custard; the temperature sensor is used for detecting the measured temperature data in the micro steam oven during the steaming process of the steamed egg custard; and the multi-channel temperature inspection instrument is used for storing the measured temperature data and sending the measured temperature data to the computer device.

[0016] The beneficial effects of implementing the present invention are as follows:

[0017] The steamed egg custard maturity detection method of the present invention trains the initial detection model through the reference prediction data to obtain the object detection model and its corresponding model prediction data, and then verifies the accuracy of the object detection model according to the measured temperature data and the model prediction data, so as to realize the scientific determination of the maturity of the steamed egg custard.

[0018] Furthermore, the steamed egg custard maturity detection method of the present invention calculates the coefficient of determination by fitting the model prediction data and the measured temperature data and presets a fitting limit value. By comparing the coefficient of determination with the fitting limit value, the accuracy of the object detection model can be judged, and the accuracy of the object detection model can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flowchart of the steamed egg custard maturity detection method of the present invention;

[0020] Figure 2 is a schematic diagram of the micro steam oven cavity model and the egg liquid model constructed in the steamed egg custard maturity detection method of the present invention;

[0021] Figure 3This is the three-dimensional image of the simulated heating process in the method for detecting the maturity of steamed egg custard of the present invention;

[0022] Figure 4 This is the curve graph of the predicted relationship between the temperature and time of the steamed egg custard in the method for detecting the maturity of steamed egg custard of the present invention;

[0023] Figure 5 This is the flowchart of the steps for validating the target detection model according to the measured temperature data and the model prediction data and optimizing the target detection model according to the validation result in the method for detecting the maturity of steamed egg custard of the present invention;

[0024] Figure 6 When the target detection model in the method for detecting the maturity of steamed egg custard of the present invention is a random forest, the model prediction data and the measured temperature data are fitted and the determination coefficient R 2 is schematically shown;

[0025] Figure 7 This is the structural schematic diagram of the system for detecting the maturity of steamed egg custard of the present invention;

[0026] Figure 8 This is the schematic diagram of the placement of the temperature sensor in the egg liquid in the method for detecting the maturity of steamed egg custard of the present invention. Detailed implementation mode

[0027] To make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. It is hereby declared that the orientation terms such as above, below, left, right, front, back, inside, outside, etc. that appear or will appear in the text of the present invention are only based on the accompanying drawings of the present invention, and they do not specifically limit the present invention.

[0028] As Figure 1 shown, the method for detecting the maturity of steamed egg custard of the present invention includes:

[0029] S101, Collecting the measured temperature data during the steaming process of the steamed egg custard in real time;

[0030] In practical applications, the measured temperature data during the steaming process of the steamed egg custard can be collected in real time by constructing the experimental device 1;

[0031] As Figure 7 shown, the experimental device 1 includes a micro steam oven 11, a multi-channel temperature inspection instrument 12 and a temperature sensor arranged in the micro steam oven 11; wherein, the micro steam oven 11 is used for steaming the steamed egg custard; the temperature sensor is used for detecting the measured temperature data in the micro steam oven 11 during the steaming process of the steamed egg custard; the multi-channel temperature inspection instrument 12 is used for storing the measured temperature data.

[0032] S102. Establish a geometric model, a coupled equation set, and thermophysical parameters to generate benchmark prediction data;

[0033] Correspondingly, the step of establishing a geometric model, a coupled equation set, and thermophysical parameters to generate benchmark prediction data includes:

[0034] (1) Construct a cavity model of a micro-steamer-roaster and an egg liquid model;

[0035] As Figure 2 shown, the egg liquid model is arranged inside the cavity model of the micro-steamer-roaster;

[0036] (2) Construct a coupled equation set;

[0037] The coupled equation set takes laminar flow with low Reynolds number, heat transfer between fluid and solid, and surface-to-surface radiation as the physical fields to be analyzed, and constructs a multi-physical field coupling relationship by combining non-isothermal flow and surface-to-surface radiation heat transfer, and constructs a control equation for fluid flow and heat transfer;

[0038] Furthermore, the coupled equation set includes the Navier-Stokes equation, the continuity equation, the thermal thin approximation equation, and the energy conservation equation. Specifically, as follows:

[0039] Navier-Stokes equation:

[0040]

[0041] Among them, u is the fluid velocity, p is the fluid pressure, ρ is the fluid density, μ is the dynamic viscosity of the fluid, I is the identity matrix, and g is the acceleration of gravity.

[0042] Continuity equation:

[0043]

[0044] Thermal thin approximation equation:

[0045]

[0046] Among them, k is the thermal conductivity, T is the temperature, is the gradient operator.

[0047] Energy conservation equation:

[0048]

[0049] Among them, u is the fluid velocity, p is the fluid pressure, ρ is the fluid density, Cp is the constant pressure heat capacity, T is the temperature, q is the heat, k is the thermal conductivity, Q is the external heat source, and Qs is the solid heating;

[0050] (3) Construct initial conditions and boundary conditions;

[0051] The initial conditions include the initial temperature and the initial pressure; wherein, the initial temperature is room temperature and the initial pressure is standard atmospheric pressure;

[0052] The boundary conditions include the surface emissivity of the inner wall of the micro steam oven, the thermal conductivity of the surface of the steamed egg custard, the thermal conductivity of the steam on the surface of the steamed egg custard, the constant-pressure heat capacity of the steamed egg custard, the density of the steamed egg custard, the thermal conductivity of the container for holding the steamed egg custard, the constant-pressure heat capacity of the container for holding the steamed egg custard, and the boundary heat source;

[0053] (4) Use a free tetrahedral mesh to divide the mesh;

[0054] (5) Set the solution time step according to the process requirements and run the solution to generate the relationship between the temperature and time of the cavity of the micro steam oven and the steamed egg custard during the steaming process, and use the relationship between the temperature and time as the benchmark prediction data.

[0055] Among them, the three-dimensional image for simulating the heating process refers to Figure 3 and the curve graph of the predicted relationship between the temperature and time of the steamed egg custard refers to Figure 4 ;

[0056] S103. Build an analysis platform, train the initial detection model according to the benchmark prediction data, and extract the target detection model from the initial detection model according to the training results;

[0057] Preferably, the analysis platform is built based on machine learning, and the analysis platform includes a platform front end, a platform back end, and a platform script;

[0058] The platform front end is developed based on the vue framework to implement functions such as module selection, file selection, execution calculation, and IOFile acquisition;

[0059] The platform back end is developed based on php, calls the corresponding platform script to execute calculations through the Thinkphp framework, and uses MySQL to build a user database and an execution information database;

[0060] The platform script is developed based on python, and the platform script is built through machine learning libraries of scikit-learn and pytorch.

[0061] The initial detection model includes support vector machine regression (SVR), random forest regression (RFR), decision tree regression (DTR), K-nearest neighbor regression (KNR), AdaBoost regression (ABR), gradient boosting regression (GBR), and extremely randomized tree regression (ETR).

[0062] The target detection model is the model with the highest accuracy among the initial detection models. That is, according to the characteristics of the reference prediction data, the target detection model needs to be selected from the initial detection models. For example, the Random Forest Regression (RFR) is selected. Its features are as follows: it provides feature importance evaluation, which helps to understand the data and the prediction results of the model. The Random Forest (RFR) has relatively few parameters and is not sensitive to the selection of parameters. Therefore, it is relatively easy to use and optimize in practical applications. The Random Forest (RFR) can handle large-scale data sets and can generate prediction results in a relatively short time. For data with non-linear relationships, the Random Forest (RFR) has strong fitting ability.

[0063] S104. Generate model prediction data according to the target detection model;

[0064] S105. Verify the target detection model according to the measured temperature data and the model prediction data, and optimize the target detection model according to the verification result;

[0065] As Figure 5 shown, the steps of verifying the target detection model according to the measured temperature data and the model prediction data, and optimizing the target detection model according to the verification result include:

[0066] (1) Fit the model prediction data with the measured temperature data to calculate the coefficient of determination R 2 ;

[0067] (2) Judge whether the coefficient of determination R 2 is greater than a preset fitting limit value;

[0068] (3) If the judgment is yes, then use the target detection model as the optimized target detection model;

[0069] (4) If the judgment is no, then retrain the target detection model.

[0070] It should be noted that the value of the coefficient of determination Rμ is between 0 and 1, where 1 indicates that the model perfectly fits the data, and 0 indicates that the model cannot explain any variation; that is, the closer the value of the coefficient of determination Rμ is to 1, the better the fitting effect of the model. The following are some general explanations for the value of the coefficient of determination R2:

[0071] (1) Rμ = 1: The model can fully explain the variability of the dependent variable, and the predicted value is exactly the same as the actual value without error.

[0072] (2) 0.8 < Rμ ≤ 1: The model can explain most of the variability of the dependent variable, and the fitting effect is very good;

[0073] (3) 0.6 < Rμ ≤ 0.8: The model can explain more than half of the variability of the dependent variable, and the fitting effect is good;

[0074] (4) 0.4 < Rμ ≤ 0.6: The model can explain a certain proportion of the variability of the dependent variable, and the fitting effect is average;

[0075] (5) 0.2 < Rμ ≤ 0.4: The model can only explain a small part of the variability of the dependent variable, and the fitting effect is poor;

[0076] (6) 0 < Rμ ≤ 0.2: The model can hardly explain the variability of the dependent variable, and the fitting effect is very poor;

[0077] (7) Rμ = 0: The model has no explanatory power. The model does not explain any variability of the dependent variable and shows no improvement compared to using the mean of the dependent variable as a prediction.

[0078] Therefore, the value of the fitting limit can be selected according to the actual application requirements. For example, the fitting limit = 0.8. By comparing the magnitude of the coefficient of determination R 2 with the fitting limit, the accuracy of the model's predicted data can be judged.

[0079] As Figure 6 shown, Figure 6 taking the selected object detection model, the random forest (RFR) as an example, the predicted data of the model is fitted with the measured temperature data and the coefficient of determination R 2 is calculated. Among them, the coefficient of determination R 2 = 0.99947 > the fitting limit = 0.8, and the corresponding object detection model can be used as the optimized object detection model.

[0080] S106. Analyze the steaming process of the steamed egg custard according to the optimized object detection model.

[0081] The steps of analyzing the steaming process of the steamed egg custard according to the optimized object detection model include:

[0082] (1) Make predictions through the optimized object detection model to generate target prediction data;

[0083] (2) Generate a temperature distribution cloud map according to the target prediction data;

[0084] (3) Analyze the central temperature at the center position of the steamed egg custard during the steaming process through the temperature distribution cloud map;

[0085] (4) Judge the ripeness of the steamed egg custard by the change of the central temperature.

[0086] In practical applications, the maturity temperature of steamed egg custard can be determined according to specific circumstances. Generally speaking, when the central temperature of the steamed egg custard reaches above 70°C, it can be considered that the steamed egg custard is mature; in the present invention, the steaming process is a steaming temperature of 100°C and a steaming time of 15 minutes.

[0087] Correspondingly, the present invention also discloses a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.

[0088] Meanwhile, as Figure 7 shown, the present invention also discloses a steamed egg custard maturity detection system, including an experimental device 1 and the above computer device 2;

[0089] The experimental device 1 includes a micro steam oven 11, a multi-channel temperature patrol instrument 12, and a temperature sensor disposed in the micro steam oven 11;

[0090] The micro steam oven 11 is used for steaming the steamed egg custard;

[0091] The temperature sensor is used to detect the measured temperature data in the micro steam oven 11 during the steaming process of the steamed egg custard; preferably, a thermocouple-temperature sensor is used to collect the temperature data and related information during the steaming process of the steamed egg custard. The placement schematic diagram of the temperature sensor in the egg liquid refers to Figure 8 the A part shown.

[0092] The multi-channel temperature patrol instrument 12 is used to store the measured temperature data and send the measured temperature data to the computer device 2.

[0093] To sum up, the steamed egg custard maturity detection method of the present invention trains the initial detection model through the benchmark prediction data to obtain the target detection model and its corresponding model prediction data, and then verifies the accuracy of the target detection model according to the measured temperature data and the model prediction data, so as to realize the scientific determination of the maturity of the steamed egg custard. The steamed egg custard maturity detection method of the present invention calculates the coefficient of determination and preset fitting limits by fitting the model prediction data and the measured temperature data, and judges the accuracy of the target detection model by comparing the coefficient of determination with the fitting limits, which can improve the accuracy of the target detection model.

[0094] The above is the preferred implementation manner of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements are also regarded as the protection scope of the present invention.

Claims

1. A method for detecting the maturity of steamed egg custard, characterized in that, Including: Real-time collecting the measured temperature data during the steaming process of steamed eggs with scallions; Establishing a geometric model, a coupled equation set and thermophysical parameters to generate benchmark prediction data; Building an analysis platform, training an initial detection model according to the benchmark prediction data, and extracting a target detection model from the initial detection model according to the training results; Generating model prediction data according to the target detection model; Verifying the target detection model according to the measured temperature data and the model prediction data, and optimizing the target detection model according to the verification results; Analyzing the ripening process of steamed eggs with scallions according to the optimized target detection model.

2. The method for detecting the maturity of steamed egg custard according to claim 1, wherein, The step of establishing a geometric model, a coupled equation set and thermophysical parameters to generate benchmark prediction data includes: Constructing a cavity model of a micro steam oven and an egg liquid model; Constructing a coupled equation set, which takes laminar flow with low Reynolds number, heat transfer between fluid and solid, and surface-to-surface radiation as the physical fields to be analyzed, and constructs a multi-physical field coupling relationship by combining non-isothermal flow and surface-to-surface radiation heat transfer, and constructs a fluid flow and heat transfer control equation; Constructing initial conditions and boundary conditions, where the initial conditions include the initial temperature and the initial pressure, and the boundary conditions include the surface emissivity of the inner wall of the micro steam oven, the thermal conductivity of the surface of the steamed eggs with scallions, the thermal conductivity of steam on the surface of the steamed eggs with scallions, the constant pressure heat capacity of the steamed eggs with scallions, the density of the steamed eggs with scallions, the thermal conductivity of the container for holding the steamed eggs with scallions, the constant pressure heat capacity of the container for holding the steamed eggs with scallions, and the boundary heat source; Performing mesh division using free tetrahedral meshes; Setting the solution time step according to the process requirements and running the solution to generate the relationship between the temperature and time of the cavity of the micro steam oven and the steamed eggs with scallions during the steaming process, and taking the relationship between the temperature and time as the benchmark prediction data.

3. The steamed egg maturity detection method according to claim 2, characterized in that, The coupled equation set includes the Navier-Stokes equation, the continuity equation, the thermal thin approximation equation and the energy conservation equation.

4. The method for detecting the maturity of steamed egg custard according to claim 1, wherein The analysis platform is built based on machine learning, and the analysis platform includes a platform front end, a platform back end and platform scripts; The platform front end is developed based on the vue framework to implement the functions of module selection, file selection, execution calculation and IOFile acquisition; The platform back end is developed based on php, calls the corresponding platform scripts to execute calculations through the Thinkphp framework, and uses MySQL to build a user database and an execution information database; The platform scripts are developed based on python, and the platform scripts are built through the machine learning libraries of scikit-learn and pytorch.

5. The method for detecting the maturity of steamed egg custard according to claim 1, wherein, The initial detection model includes support vector machine regression, random forest regression, decision tree regression, K-nearest neighbor regression, AdaBoost regression, gradient boosting regression and extremely randomized tree regression.

6. The method for detecting the maturity of steamed eggs according to claim 1, characterized in that, The step of verifying the target detection model according to the measured temperature data and the model prediction data, and optimizing the target detection model according to the verification results includes: Fitting the model prediction data with the measured temperature data to calculate the coefficient of determination; Judging whether the coefficient of determination is greater than a preset fitting limit value; If the judgment is yes, then taking the target detection model as the optimized target detection model; When the judgment is negative, the target detection model is retrained.

7. The method for detecting the maturity of steamed egg custard according to claim 1, characterized in that, The step of analyzing the steaming process of the steamed egg custard according to the optimized target detection model includes: Performing prediction through the optimized target detection model to generate target prediction data; Generating a temperature distribution cloud map according to the target prediction data; Analyzing the central temperature at the central position of the steamed egg custard during the steaming process through the temperature distribution cloud map; Judging the ripeness of the steamed egg custard by the change of the central temperature.

8. The method for detecting the maturity of steamed egg custard according to claim 1, characterized in that The target detection model is the model with the highest accuracy in the initial detection models.

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 method according to any one of claims 1 to 8.

10. A detection system for the maturity of steamed egg custard, characterized in that, It includes an experimental device and the computer device according to claim 9; The experimental device includes a micro steam oven, a multi-channel temperature inspection instrument, and a temperature sensor disposed in the micro steam oven; The micro steam oven is used for steaming the steamed egg custard; The temperature sensor is used for detecting the measured temperature data in the micro steam oven during the steaming process of the steamed egg custard; The multi-channel temperature inspection instrument is used for storing the measured temperature data and sending the measured temperature data to the computer device.

Images