Optimization Control Method for the Production Process of Fermented Rice Buns Based on Artificial Intelligence

Abstract

The present invention discloses an optimized control method for the production process of fermented rice steamed buns based on artificial intelligence, specifically relating to the technical field of artificial intelligence. The specific steps include installing sensors during the production process of fermented rice steamed buns to collect production characteristics and environmental optimization information, and transmitting them to a database for storage and management. Using historical data to train a machine learning model, analyzing the impact of data on the fermentation effect, establishing a mathematical model to predict the fermentation effect, and prompting production personnel. According to the monitoring data and prediction results, dynamically adjust the raw material ratio, introduce a closed-loop control system, and continuously optimize the production state. Deploy a computer vision system to detect the production effect in real time, and feedback the results to the production system, and further optimize production control by combining model analysis, which can effectively avoid waste of raw materials caused by production abnormal failures, reduce production costs, and effectively evaluate production efficiency in the case of gas transfer or leakage in the fermented rice container.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology. More specifically, the present invention is an optimization control method for the production process of fermented rice steamed buns based on artificial intelligence. Background Art

[0002] Fermented rice steamed buns are a traditional Chinese fermented pasta, mainly made of flour and fermented rice. Mix raw materials such as flour, fermented rice, and sugar, add an appropriate amount of water and knead into a smooth dough for fermentation. After shaping and cutting the fermented dough, perform secondary fermentation. The microorganisms in the fermented rice provide yeast. After fermentation is completed, steam the dough to make the dough retain the flavor of the fermented rice and make fermented pasta.

[0003] In the production process of fermented rice steamed buns, due to the adjustment of the production scheduling cycle and the change of the raw material state, the fermented rice used to provide yeast will change its activity with the change of the storage time and the feeding batch. Each time the storage device for storing fermented rice opens the material port for feeding, some air will be introduced. The oxygen in the air reacts with the fermented rice in advance, resulting in a change in the fermentation activity of the fermented rice, which in turn affects the forming effect of the fermentation after kneading and the secondary fermentation, resulting in inconsistent forming of fermented rice steamed buns in different production batches, uneven fermentation effect, and unbalanced output.

[0004] To solve the above defects, a technical solution is proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide an optimization control method for the production process of fermented rice steamed buns based on artificial intelligence to solve the deficiencies in the background art.

[0006] To achieve the above purpose, the present invention provides the following technical solution: An optimization control method for the production process of fermented rice steamed buns based on artificial intelligence, the specific steps include:

[0007] S1: Install sensors in the production link of fermented rice steamed buns to collect production feature information and environmental optimization information, and transmit the production feature information and environmental optimization information to the database for data storage and management;

[0008] S2: Use historical data to train a machine learning model, analyze the influence of different data on the fermentation effect, establish a mathematical model of the production process, input the data into the trained model for analysis, predict the fermentation effect of fermented rice steamed buns, and prompt the production personnel according to the prediction results;

[0009] S3: Dynamically adjust the proportion of raw materials according to the monitoring data and the model prediction results, introduce a closed-loop control system, and continuously adjust and optimize the production state according to the real-time feedback during the fermentation process;

[0010] S4: Deploy a computer vision system to detect the production effect of fermented rice buns in real time, feedback the production effect to the production system, and further optimize production control in combination with the model analysis results.

[0011] Preferably, the logic for establishing a mathematical model of the production process based on production characteristic information and environmental optimization information is as follows:

[0012] The production characteristic information includes a temperature-humidity balance coefficient and a visual inspection coefficient. The environmental optimization information is the transfer sensitivity. The calibrated temperature-humidity balance coefficient is Th, the visual inspection coefficient is Fv, and the transfer sensitivity is Ts. A regression index Lr is established, and the expression is In the formula, α, β, and γ are the weight coefficients of the temperature-humidity balance coefficient, the visual inspection coefficient, and the transfer sensitivity respectively, and α, β, and γ are all greater than 0.

[0013] Preferably, the calculation method of the temperature-humidity balance coefficient is as follows:

[0014] The expression of the temperature-humidity balance coefficient is Th = Ds * |Ta - Tb| * |Ha - Hb|. In the formula, Ds is a coefficient related to the volume of the fermentation chamber, and Ds > 0. Ta is the actual fermentation temperature, Tb is the standard fermentation temperature under the standard formula, Ha is the actual fermentation humidity, and Hb is the standard fermentation humidity under the standard formula.

[0015] Preferably, the calculation method of the visual inspection coefficient is as follows:

[0016] The expression of the visual inspection coefficient is In the formula, Cr is a coefficient related to the conveying speed of the fermented rice bun production line, and Cr > 0. Fs is the F-score value obtained by the computer vision system using machine learning algorithms to detect the quality of fermented rice buns. The calculation expression of the F-score value is Where Pr is the precision of the machine learning model, and Re is the recall rate of the machine learning model.

[0017] Preferably, the steps for obtaining the F-score value of the computer vision system using machine learning algorithms to detect the quality of fermented rice buns are as follows:

[0018] Collect the predicted labels and true labels in the test dataset according to the test of the machine learning prediction model;

[0019] Establish a confusion matrix based on the comparison of the predicted labels and the true labels. The number of positive classes correctly predicted by the model is the true positive, the number of positive classes mispredicted by the model is the false positive, the number of negative classes correctly predicted by the model is the true negative, and the number of negative classes mispredicted by the model is the false negative;

[0020] Calculate the precision Pr according to the true positive and the false positive. The expression is The recall rate Re is calculated based on true positives and false negatives, and the expression is

[0021] The F-score value is calculated based on the precision Pr and the recall rate Re.

[0022] Preferably, the calculation method of the transfer sensitivity is as follows:

[0023] The expression of the transfer sensitivity is Ts = Ac * ln(Pv), where Ac is the alcohol content of the fermented rice raw material, and Pv is the gas transfer volume of the fermented rice container filled with fermented rice according to the standard formula. The calculation method of Pv is Pv = |Pa - Pb|, where Pa is the gas volume in the fermented rice container before filling the fermented rice according to the standard formula, and Pb is the gas volume in the fermented rice container after filling the fermented rice according to the standard formula. The gas volume in the fermented rice container is obtained through a gas sensor.

[0024] Preferably, the logic for analysis and prediction based on the regression index is as follows:

[0025] A preset regression index threshold Gr is set, and the calculated regression index is compared with the regression index threshold. If the regression index Lr is greater than or equal to the regression index threshold Gr, the production consistency of the fermented rice steamed buns is better, and the production control is more refined;

[0026] If the regression index Lr is less than the regression index threshold Gr, the production consistency of the fermented rice steamed buns is worse, and the production control is more rough.

[0027] Preferably, the logic for giving a prompt based on the analysis and prediction result of the logistic regression index is as follows:

[0028] When the regression index Lr is greater than or equal to the regression index threshold Gr, the feedback signal of the production control process of the fermented rice steamed buns is marked as a healthy signal, and according to the healthy signal, it is prompted that the production status of the production personnel is stable, and the fermentation expected difference is within the standard formula;

[0029] When the regression index Lr is less than the regression index threshold Gr, the feedback signal of the production control process of the fermented rice steamed buns is marked as a risk signal, and according to the risk signal, it is prompted that there is a risk of imbalance in the production status of the production personnel, and there is a risk of out-of-control in the degree of fermentation effect difference.

[0030] In the above technical solution, the technical effects and advantages provided by the present invention:

[0031] This application can optimize production control by focusing on two aspects: feeding and inspection during the production process of fermented rice steamed buns. It endows the traditional production line with an intelligent core using artificial intelligence technology, optimizes production process control by establishing a model based on historical data, predicts production effects using artificial intelligence algorithms, and conducts comparisons according to the inspection method of computer vision algorithms. This can effectively avoid waste of raw materials caused by production anomalies and faults, reduce production costs, effectively evaluate production efficiency in the case of gas transfer or leakage in the fermented rice container, and greatly reduce the work pressure of production employees using an automated warning prompt logic. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings.

[0033] Figure 1 It is a flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0035] Embodiment 1

[0036] Please refer to Figure 1 As shown, the present invention is an optimization control method for the production process of fermented rice steamed buns based on artificial intelligence. The specific steps include:

[0037] S1: Install sensors in the production process of fermented rice steamed buns to collect production characteristic information and environmental optimization information, and transmit the production characteristic information and environmental optimization information to the database for data storage and management;

[0038] S2: Use historical data to train a machine learning model, analyze the influence of different data on the fermentation effect, establish a mathematical model of the production process, input the data into the trained model for analysis, predict the fermentation effect of the fermented rice steamed buns, and prompt the production personnel according to the prediction results;

[0039] S3: Dynamically adjust the proportion of raw materials according to the monitoring data and the model prediction results, introduce a closed-loop control system, and continuously adjust and optimize the production state according to the real-time feedback during the fermentation process;

[0040] S4: Deploy a computer vision system to detect the production effect of fermented rice buns in real time, feedback the production effect to the production system, and further optimize production control in combination with the model analysis results.

[0041] Install sensors in the production process of fermented rice buns. The sensors include various sensors such as temperature sensors, humidity sensors, gas sensors, and mass flow sensors. Sensor data is collected through a collection module PLC or an industrial control computer, and through wired methods such as industrial Ethernet or RS485 to ensure the stability and reliability of data transmission, or use wireless transmission technology to transmit data to the central control system, which can reduce wiring complexity. Wireless transmission technologies include Wi-Fi, Zigbee, etc.;

[0042] The process of transmitting the collected data to the database for data storage and management is as follows:

[0043] Store the collected data in the central database to provide basic data for historical analysis and model training. Clean and preprocess the collected data to remove outliers and noise to ensure data quality. Use data analysis software or platforms to analyze real-time data and discover potential problems and trends. Data analysis software or platforms include Python, R, Matlab, etc.,

[0044] The data storage method can be local storage or cloud storage. Using a local database for data storage meets the scenarios with high requirements for data security. Local databases include SQL Server, MySQL, etc. Using a cloud database to store data facilitates large-scale data management and remote access. Cloud databases include AWS RDS, Azure SQL Database, etc.;

[0045] The methods of data management include:

[0046] Data cleaning and preprocessing: Clean the collected data, remove outliers and noise, and perform data standardization and normalization processing to ensure data quality;

[0047] Data tagging: Tag each batch of production data, including production date, time, raw material batch, process parameters, etc., for subsequent analysis and model training.

[0048] Use historical data to train a machine learning model and analyze the impact of different data on the fermentation effect. The steps to establish a mathematical model of the fermentation process include:

[0049] Data preparation:

[0050] Divide the collected dataset into a training set, a validation set, and a test set. Usually, the ratio is 70% for the training set, 20% for the validation set, and 10% for the test set. Extract and select features from the data to construct features that are helpful for model training, such as time series features of fermentation temperature and humidity, pH value of fermented glutinous rice wine, etc.;

[0051] Select appropriate machine learning algorithms:

[0052] Select those for predicting continuous variables, such as the impact of fermentation time and temperature on fermentation effect. Commonly used algorithms include linear regression, ridge regression, Lasso regression, etc. Select those for classification problems, such as predicting whether the fermentation effect of a certain batch meets the standard. Commonly used algorithms include decision trees, random forests, support vector machines, etc. Select time series analysis: for processing time series data and predicting future trends. Commonly used algorithms include ARIMA models, long short-term memory networks, etc.;

[0053] Model training and validation:

[0054] Use the training set to train the selected machine learning algorithms, adjust the model parameters, and minimize the loss function. Use the validation set to evaluate the model performance, and select the optimal model parameters through cross-validation methods to prevent overfitting;

[0055] Model evaluation and optimization:

[0056] Evaluation metrics include mean squared error, root mean squared error, accuracy, precision, recall, etc. to evaluate the model performance. Model optimization is to optimize the model by adjusting hyperparameters, adding features, adopting ensemble learning, etc. to improve the prediction accuracy and generalization ability of the model; Ensemble learning includes methods such as Bagging and Boosting:

[0057] Model deployment:

[0058] The online model can deploy the trained model to the production environment, integrate it into the production control system, and achieve real-time prediction and optimal control. Continuous learning is to use the continuous accumulation of monitoring data to update and retrain the model regularly to ensure that the model always maintains the best performance.

[0059] In step S3, input the data into the trained model for analysis, predict the fermentation effect of fermented glutinous rice buns, and adjust the production parameters according to the prediction results, including:

[0060] According to the monitoring data and model prediction results, dynamically adjust the proportion of raw materials, introduce a closed-loop control system, and continuously adjust and optimize the production status according to the real-time feedback during the fermentation process. The closed-loop control system consists of a closed-loop control architecture and monitoring feedback. The closed-loop control architecture feeds back the key parameters monitored by sensors to the central control system. The control algorithm of the architecture uses algorithms such as PID control algorithm or model predictive control algorithm to dynamically adjust the raw material proportion and fermentation parameters. The monitoring feedback includes the setting of the control interface and the completion of automatic feedback regulation. The monitoring interface is a visual interface set in the central control room, which displays the status and change trends of each key parameter in real time, facilitating the monitoring by operators. The automatic feedback regulation can automatically adjust the raw material proportion and fermentation parameters according to the real-time feedback to ensure the stability of the production process.

[0061] In step S4, the method for deploying a computer vision system to detect the production effect of fermented rice steamed buns in real time is as follows:

[0062] S4.1: Deploy a computer vision system, select cameras and sensors, including high-resolution cameras for capturing the detailed features of steamed buns, such as appearance, size, and color, and 3D sensors for obtaining the three-dimensional shape and volume information of steamed buns. Determine the installation positions of the cameras and sensors, and install the cameras and sensors at key links of the production line, such as after the steamed bun is formed, before steaming, after steaming, and before packaging, etc.;

[0063] S4.2: Image acquisition and processing, real-time image acquisition, including continuous shooting and image transmission. The camera continuously shoots images of steamed buns to ensure that each steamed bun can be detected. Image transmission is to transmit the images to the processing unit through a high-speed data transmission interface, and the high-speed data transmission interface includes USB 3.0, GigE, etc.;

[0064] S4.3: Image preprocessing includes noise removal and edge detection. Use filtering techniques to remove noise in the images and improve the image quality. Apply edge detection algorithms to extract the contours of steamed buns, such as the typical Canny edge detection;

[0065] S4.4: Feature extraction methods include size measurement: calculate the size of steamed buns, such as diameter, height, etc. through image analysis algorithms, color analysis: use color space conversion to analyze the color of steamed buns to judge the steaming degree, and shape analysis: analyze the shape of steamed buns through morphological processing to detect whether there are deformations or defects;

[0066] S4.5 Defect detection inspects the imaging quality of fermented rice steamed buns, including appearance defects: detect whether there are cracks, bubbles or other defects on the surface. Size deviation: detect whether the size of the steamed buns is within the preset range. Color deviation: detect whether the color of the steamed buns is uniform and whether there is over-steaming or under-steaming phenomenon.

[0067] Feed the production effects back to the production system. Combining the results of model analysis, further optimize the production control logic, including quality inspection result feedback and model analysis optimization. Quality inspection result feedback includes data recording and storage and abnormal alarm. The inspection results of each steamed bun are recorded and stored in the database in real time through real-time recording. The stored data can be used for subsequent analysis and optimization;

[0068] Model analysis optimization includes data analysis, optimization suggestions, and automatic control. Analyze the inspection data through statistical analysis tools to find common quality problems and their occurrence frequencies. Use machine learning algorithms to identify patterns that may cause quality problems during the production process. Typical machine learning algorithms such as clustering analysis;

[0069] Based on the analysis results, the system automatically generates process parameter adjustment suggestions, such as adjusting fermentation time, temperature, humidity, etc. Adjust the formula ratio according to the system suggestions, such as adjusting the dosage of fermented glutinous rice or flour, to improve the fermentation effect;

[0070] The intelligent feedback system transmits the optimization suggestions to the production control system in real time, automatically adjusts the production parameters, and through the closed-loop control system, realizes real-time monitoring and automatic optimization of the production process to ensure production consistency.

[0071] Example 2

[0072] In step S2, input the data into the trained model for analysis to predict the fermentation effect of fermented glutinous rice steamed buns. Take the regression algorithm as an example to build a model and analyze the data;

[0073] Collect the production characteristic information and environmental optimization information during the production process of fermented glutinous rice steamed buns through sensors. The production characteristic information includes the temperature and humidity balance coefficient and the visual inspection coefficient. The environmental optimization information is the transfer sensitivity. Calibrate the temperature and humidity balance coefficient as Th, the visual inspection coefficient as Fv, and the transfer sensitivity as Ts. Establish the regression index Lr, and the expression is , where α, β, and γ are the weight coefficients of the temperature and humidity balance coefficient, the visual inspection coefficient, and the transfer sensitivity respectively, and α, β, and γ are all greater than 0;

[0074] The expression of the temperature and humidity balance coefficient is Th = Ds * |Ta - Tb| * |Ha - Hb|, where Ds is a coefficient related to the volume of the fermentation chamber and Ds is greater than 0, Ta is the actual fermentation temperature, Tb is the standard fermentation temperature under the standard formula, Ha is the actual fermentation humidity, and Hb is the standard fermentation humidity under the standard formula;

[0075] The expression of the visual inspection coefficient is Where Cr is a coefficient related to the conveying speed of the fermented rice bun production line, and Cr > 0, Fs is the F-score value obtained by the computer vision system using machine learning algorithms to detect the quality of fermented rice buns. The calculation expression of the F-score value is where Pr is the precision of the machine learning model and Re is the recall rate of the machine learning model;

[0076] The steps to obtain the F-score value obtained by the computer vision system using machine learning algorithms to detect the quality of fermented rice buns are as follows:

[0077] Collect the predicted labels and true labels in the test dataset according to the test of the machine learning prediction model;

[0078] Establish a confusion matrix based on the comparison of the predicted labels and the true labels. The number of positive classes correctly predicted by the model is the true positive, the number of positive classes mispredicted by the model is the false positive, the number of negative classes correctly predicted by the model is the true negative, and the number of negative classes mispredicted by the model is the false negative;

[0079] Calculate the precision Pr based on the true positive and the false positive. The expression is Calculate the recall rate Re based on the true positive and the false negative. The expression is

[0080] Calculate the F-score value based on the calculated precision Pr and recall rate Re;

[0081] The expression of the transfer sensitivity is Ts = Ac * ln(Pv). In the formula, Ac is the alcohol content of the fermented rice raw material, and Pv is the gas transfer volume of the fermented rice container filled with fermented rice according to the standard formula. The calculation method of Pv is Pv = |Pa - Pb|. In the formula, Pa is the gas volume in the fermented rice container before filling the fermented rice according to the standard formula, and Pb is the gas volume in the fermented rice container after filling the fermented rice according to the standard formula. The gas volume in the fermented rice container is obtained by a gas sensor;

[0082] Preset the regression index threshold Gr, and compare the calculated regression index with the regression index threshold. If the regression index Lr is greater than or equal to the regression index threshold Gr, the production consistency of the fermented rice buns is better and the production control is more refined;

[0083] If the regression index Lr is less than the regression index threshold Gr, the production consistency of the fermented rice buns is worse and the production control is more rough;

[0084] When the regression index Lr is greater than or equal to the regression index threshold Gr, mark the feedback signal of the fermented rice bun production control process as a healthy signal; when the regression index Lr is less than the regression index threshold Gr, mark the feedback signal of the fermented rice bun production control process as a risk signal;

[0085] According to the health signal prompt, the production status of the production personnel is stable, and the fermentation expectation difference is within the standard formula;

[0086] According to the risk signal prompt, there is a risk of imbalance in the production status of the production personnel, and there is a danger of out-of-control in the degree of fermentation effect difference.

[0087] This application can optimize production control in two directions of feeding and inspection in the production process of fermented rice steamed buns, endow the traditional production line with an intelligent core with artificial intelligence technology, optimize production process control by establishing a model based on historical data, predict production effects using artificial intelligence algorithms, and compare according to the inspection method of computer vision algorithms. It can effectively avoid waste of raw materials caused by abnormal production failures, reduce production costs, effectively evaluate production efficiency in the case of gas transfer or leakage in the fermented rice container, and greatly reduce the work pressure of production employees using an automated early warning prompt logic.

[0088] The above formulas are all dimensionless and take their numerical values for calculation. The formula is a formula obtained by collecting a large amount of data for software simulation to approximate the real situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0089] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired or wireless (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0090] It should be understood that in various embodiments of the present application, the sequence numbers of the above processes do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0091] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0092] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the system described above can refer to the corresponding process in the foregoing method embodiments, and will not be described herein again.

[0093] If the described function is implemented in the form of a software functional unit and sold or used as an independent commodity, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software commodity. This computer software commodity is stored in a storage medium, including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0094] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all of them should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An optimization control method for the production process of fermented rice steamed buns based on artificial intelligence, characterized in that, The specific steps include: S1: Install sensors in the production process of fermented rice steamed buns to collect production characteristic information and environmental optimization information, and transmit the production characteristic information and environmental optimization information to the database for data storage and management; S2: Use historical data to train a machine learning model, analyze the impact of different data on the fermentation effect, establish a mathematical model of the production process, input the data into the trained model for analysis, predict the fermentation effect of fermented rice steamed buns, and prompt the production personnel according to the prediction results; S3: Dynamically adjust the proportion of raw materials according to the monitoring data and model prediction results, introduce a closed-loop control system, and continuously adjust and optimize the production status according to the real-time feedback during the fermentation process; S4: Deploy a computer vision system to detect the production effect of fermented rice steamed buns in real time, feedback the production effect to the production system, and further optimize the production control in combination with the model analysis results; The logic for establishing a mathematical model of the production process based on production characteristic information and environmental optimization information is: The production characteristic information includes the temperature-humidity balance coefficient and the visual inspection coefficient. The environmental optimization information is the transfer sensitivity. The calibrated temperature-humidity balance coefficient is Th, the visual inspection coefficient is Fv, and the transfer sensitivity is Ts. A regression index Lr is established, and the expression is In the formula, α, β, and γ are the weight coefficients of the temperature-humidity balance coefficient, the visual inspection coefficient, and the transfer sensitivity respectively, and α, β, and γ are all greater than 0; The calculation method of the temperature-humidity balance coefficient is: The expression of the temperature-humidity balance coefficient is Th = Ds * |Ta - Tb| * |Ha - Hb|, where Ds is a coefficient related to the volume of the fermentation box and Ds > 0, Ta is the actual fermentation temperature, Tb is the standard fermentation temperature under the standard formula, Ha is the actual fermentation humidity, and Hb is the standard fermentation humidity under the standard formula; The calculation method of the visual inspection coefficient is: The expression of the visual inspection coefficient is In the formula, Cr is the coefficient related to the conveying speed of the fermented rice bun production line, and Cr >

0. Fs is the F-score value obtained by the computer vision system for quality inspection of fermented rice buns using machine learning algorithms. The calculation expression of the F-score value is where Pr is the precision of the machine learning model, and Re is the recall rate of the machine learning model; The steps for obtaining the F-score value of the quality inspection of fermented rice steamed buns by applying machine learning algorithms to the computer vision system are: Collect the predicted labels and true labels in the test dataset according to the test of the machine learning prediction model; Establish a confusion matrix based on the comparison of the predicted labels and true labels. The number of positive classes correctly predicted by the model is the true positive, the number of positive classes wrongly predicted by the model is the false positive, the number of negative classes correctly predicted by the model is the true negative, and the number of negative classes wrongly predicted by the model is the false negative; Calculate the precision Pr based on true positives and false positives, and the expression is Calculate the recall Re based on true positives and false negatives, and the expression is Calculate the F-score value according to the precision Pr and recall Re; The calculation method of the transfer sensitivity is: The expression of the transfer sensitivity is Ts = Ac * ln(Pv), where Ac is the alcohol content of the fermented rice raw material, Pv is the gas transfer volume of the fermented rice container filled with fermented rice according to the standard formula, and the calculation method of Pv is Pv = |Pa - Pb|, where Pa is the gas volume in the fermented rice container before filling the fermented rice according to the standard formula, Pb is the gas volume in the fermented rice container after filling the fermented rice according to the standard formula, and the gas volume in the fermented rice container is obtained through a gas sensor; The logic for analysis and prediction according to the regression index is: Preset a regression index threshold Gr, compare the calculated regression index with the regression index threshold. If the regression index Lr is greater than or equal to the regression index threshold Gr, the production consistency of the fermented rice steamed buns is better and the production control is more refined; If the regression index Lr is less than the regression index threshold Gr, the production consistency of the fermented rice steamed buns is worse and the production control is more rough; The logic for prompting according to the analysis and prediction results of the logistic regression index is: When the regression index Lr is greater than or equal to the regression index threshold Gr, the feedback signal of the production control process of fermented rice buns is marked as a healthy signal, indicating to the production personnel that the production state is stable according to the healthy signal, and the expected fermentation difference is within the standard formula; When the regression index Lr is less than the regression index threshold Gr, the feedback signal of the production control process of fermented rice buns is marked as a risk signal, indicating to the production personnel that there is a risk of imbalance in the production state according to the risk signal, and there is a danger of out-of-control in the degree of fermentation effect difference.

Images