Composite production line management method and system for food processing

Abstract

The present application provides a composite production line management method and system for food processing, which relates to the technical field of production management. The method includes: analyzing fermentation parameters to obtain multiple final fermentation parameters for fermentation; according to multiple fermentation specification information and multiple final fermentation information, analyzing the decoration placement parameters to obtain multiple decoration placement parameters; performing consistency analysis on production compounding, cutting, fermentation, and decoration placement to obtain compounding, cutting, fermentation, and decoration consistency parameters, and analyzing to obtain production line management parameters for discriminant management. Through the present application, the technical problem that due to the large number of bread production processes, it is difficult to analyze the consistency of bread production, resulting in the inability to perform targeted adjustment management on the bread production line and affecting the production efficiency and quality of bread can be solved. The technical goal of accurately adjusting the bread production line can be achieved, and the technical effect of improving the production efficiency and quality of bread can be achieved.

Description

Technical Field

[0001] This application relates to the technical field of production management, and particularly to a composite production line management method and system for food processing. Background Art

[0002] A bread composite production line is a bread production system integrating multiple functions. By integrating the equipment and systems of each of the above processes, the continuity and automation of the bread production process can be achieved, and it has multiple advantages such as high automation, high production efficiency, and stable product quality.

[0003] Currently, for the existing bread composite production management method, due to the large number of production processes, it is difficult to analyze the bread production consistency, resulting in the inability to perform targeted adjustment management on the bread production line, affecting the bread production efficiency and production quality. Summary of the Invention

[0004] The purpose of this application is to provide a composite production line management method and system for food processing, so as to solve the technical problems of the existing bread composite production management method that due to the large number of production processes, it is difficult to analyze the bread production consistency, resulting in the inability to perform targeted adjustment management on the bread production line, affecting the bread production efficiency and production quality.

[0005] In view of the above problems, this application provides a composite production line management method and system for food processing.

[0006] In a first aspect, this application provides a composite production line management method for food processing, which is implemented through a composite production line management system for food processing. Among them, the method includes: collecting multiple dough images of multiple doughs after segmentation and performing recognition to obtain multiple dough specification information and multiple preliminary fermentation information; according to the multiple dough specification information and multiple preliminary fermentation information, respectively performing fermentation parameter analysis on the final fermentation of the dough to obtain multiple final fermentation parameters and performing fermentation; after fermentation is completed, collecting multiple fermented dough images of multiple doughs and performing recognition to obtain multiple fermented specification information and multiple final fermentation information; according to the multiple fermented specification information and multiple final fermentation information, respectively performing decoration placement parameter analysis on the fermented dough to obtain multiple decoration placement parameters and performing decoration placement and baking; after baking is completed, collecting multiple baking images and performing production composite consistency analysis to obtain composite consistency parameters; respectively performing consistency analysis on cutting, fermentation, and decoration placement according to multiple dough images, multiple final fermentation parameters, and multiple decoration placement parameters to obtain cutting consistency parameters, fermentation consistency parameters, and decoration consistency parameters, and combining the composite consistency parameters, analyzing to obtain production line management parameters and performing discriminant management.

[0007] Second aspect, the present application also provides a composite production line management system for food processing, which is used to execute a composite production line management method for food processing as described in the first aspect. Among them, the system includes: a dough image recognition module, which is used to collect multiple dough images of multiple divided doughs, perform recognition, and obtain multiple dough specification information and multiple preliminary fermentation information; a fermentation parameter analysis module, which is used to perform fermentation parameter analysis on the final fermentation of the dough respectively according to the multiple dough specification information and multiple preliminary fermentation information, obtain multiple final fermentation parameters, and perform fermentation; a fermented dough image recognition module, which is used to collect multiple fermented dough images of multiple doughs after fermentation is completed, perform recognition, and obtain multiple fermentation specification information and multiple final fermentation information; a decoration placement parameter analysis module, which is used to perform decoration placement parameter analysis on the fermented dough respectively according to the multiple fermentation specification information and multiple final fermentation information, obtain multiple decoration placement parameters, and perform decoration placement and baking; a production composite consistency analysis module, which is used to collect multiple baking images after baking is completed, perform production composite consistency analysis, and obtain composite consistency parameters; a production line management parameter discrimination module, which is used to perform consistency analysis on cutting, fermentation, and decoration placement respectively according to multiple dough images, multiple final fermentation parameters, and multiple decoration placement parameters, obtain cutting consistency parameters, fermentation consistency parameters, and decoration consistency parameters, combine the composite consistency parameters, analyze and obtain production line management parameters, and perform discrimination management.

[0008] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0009] By collecting multiple dough images of multiple doughs after segmentation, identifying them, and obtaining multiple dough specification information and multiple preliminary fermentation information; according to the multiple dough specification information and multiple preliminary fermentation information, respectively analyzing the fermentation parameters of the final dough fermentation to obtain multiple final fermentation parameters, and performing fermentation; after fermentation is completed, collecting multiple fermented dough images of multiple doughs, identifying them, and obtaining multiple fermented specification information and multiple final fermentation information; according to the multiple fermented specification information and multiple final fermentation information, respectively analyzing the decoration placement parameters of the fermented dough to obtain multiple decoration placement parameters, and performing decoration placement and baking; after baking is completed, collecting multiple baking images, performing production composite consistency analysis, and obtaining composite consistency parameters; respectively performing consistency analysis of cutting, fermentation, and decoration placement based on multiple dough images, multiple final fermentation parameters, and multiple decoration placement parameters to obtain cutting consistency parameters, fermentation consistency parameters, and decoration consistency parameters, and combining the composite consistency parameters, analyzing to obtain production line management parameters, and performing discriminant management. That is to say, by identifying multiple dough images after segmentation, multiple dough specification information and multiple preliminary fermentation information are obtained; then, based on the multiple dough specification information and multiple preliminary fermentation information, optimization analysis of the dough fermentation parameters is performed to obtain multiple optimized final fermentation parameters for fermentation, which can improve the accuracy of the final fermentation parameter setting, thereby improving the dough fermentation quality; then, after fermentation is completed, multiple fermented dough images are identified to obtain multiple fermented specification information and multiple final fermentation information; further, based on the multiple fermented specification information and multiple final fermentation information, optimization analysis of the decoration placement parameters of the fermented dough is performed to obtain multiple optimized decoration placement parameters for decoration placement and baking, which can improve the consistency of the decoration distribution on the bread, thereby improving the appearance quality of the bread; and after baking is completed, production composite consistency analysis is performed based on multiple baking images to obtain composite consistency parameters; on the other hand, consistency analysis of cutting, fermentation, and decoration placement is performed based on multiple dough images, multiple final fermentation parameters, and multiple decoration placement parameters, and production line management parameters are obtained based on the cutting consistency parameters, fermentation consistency parameters, decoration consistency parameters, and composite consistency parameters, and when the production line management parameters do not meet the preset management parameter threshold, the bread composite production line is adjusted and optimized. It can improve the fineness and accuracy of the bread production consistency analysis, achieve the technical goal of accurately adjusting the bread production line, and achieve the technical effect of improving the bread production efficiency and production quality.

[0010] The above description is only an overview of the technical solution of the present application. In order to better understand the technical means of the present application, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically illustrates the specific embodiments of the present application. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary, and for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the provided drawings.

[0012] Figure 1 It is a schematic flow chart of a composite production line management method for food processing according to the present application;

[0013] Figure 2 It is a schematic flow chart of obtaining a plurality of dough specification information and a plurality of preliminary fermentation information in a composite production line management method for food processing according to the present application;

[0014] Figure 3 It is a schematic structural diagram of a composite production line management system for food processing according to the present application.

[0015] Description of the reference numerals:

[0016] Dough image recognition module 11, fermentation parameter analysis module 12, fermented dough image recognition module 13, decoration placement parameter analysis module 14, production composite consistency analysis module 15, production line management parameter discrimination module 16. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] By providing a composite production line management method and system for food processing, the present application solves the technical problem that in the existing bread composite production management method, due to the large number of production processes, it is difficult to analyze the production consistency of bread, resulting in the inability to perform targeted adjustment management on the bread production line, affecting the production efficiency and quality of bread. It can improve the fineness and accuracy of the bread production consistency analysis, achieve the technical goal of accurately adjusting the bread production line, and achieve the technical effect of improving the bread production efficiency and quality.

[0018] Next, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described herein. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application. Additionally, it should be noted that for the sake of description, only the parts related to the present application rather than all are shown in the accompanying drawings.

[0019] Embodiment 1

[0020] Please refer to the attached Figure 1 drawings. The present application provides a method for managing a composite production line for food processing. Among them, the method is applied to a management system for a composite production line for food processing. The method specifically includes the following steps:

[0021] Step 1: Collect multiple dough images of multiple doughs after segmentation, perform recognition, and obtain multiple dough specification information and multiple preliminary fermentation information;

[0022] Specifically, first, use an image sensing device to collect images of multiple doughs after segmentation. Dough segmentation refers to after the initial fermentation of the dough is completed, the dough is divided into multiple small doughs by a divider. Then, based on a convolutional neural network, a dough image recognizer is constructed to perform feature recognition on multiple dough images, and multiple dough specification information and multiple preliminary fermentation information are obtained. Among them, the dough specification information includes data such as the shape and size of the dough, and the preliminary fermentation information includes the preliminary fermentation degree of the dough, which can be analyzed through the number and size of the pores in the dough image. The number of pores, the size of the pores, and the preliminary fermentation degree of the dough are proportional, that is, the more pores on the dough and the larger the pore size, the better the preliminary fermentation degree of the dough is characterized.

[0023] Step 2: According to the multiple dough specification information and multiple preliminary fermentation information, respectively perform fermentation parameter analysis for the final fermentation of the dough, obtain multiple final fermentation parameters, and perform fermentation;

[0024] Specifically, based on the multiple dough specification information and multiple primary fermentation information, the fermentation parameter optimization for the final fermentation of the dough is carried out respectively. The final fermentation is a key step in the bread-making process. After the dough undergoes the primary fermentation, it is divided, shaped, and placed in a baking pan or other baking containers, and then the final fermentation is carried out. The purpose of the final fermentation is to allow the dough to expand again, increase the volume of the bread, and improve its taste and texture. During the final fermentation process, yeast will continue to consume the sugar in the dough, producing carbon dioxide and alcohol, thus causing the dough to expand and generating a unique aroma. The fermentation parameters include fermentation temperature, fermentation humidity, fermentation duration, and other fermentation control parameters. Based on the optimization results, multiple final fermentation parameters are obtained, and the fermentation control of the corresponding dough is performed according to the multiple final fermentation parameters.

[0025] By optimizing the final fermentation parameters of the dough based on the dough specification information and the primary fermentation information, and using the optimized final fermentation parameters to control the fermentation of the dough, the adaptability of the final fermentation parameters to the current state of the dough can be improved, making the setting of the final fermentation parameters more accurate, and thus improving the quality of dough fermentation.

[0026] Step 3: After the fermentation is completed, collect multiple fermented dough images of multiple doughs, perform identification, and obtain multiple fermentation specification information and multiple final fermentation information.

[0027] Specifically, after the dough fermentation is completed, multiple fermented dough images are collected through an image sensing device. Then, a fermented dough image recognizer is constructed based on a convolutional neural network. The fermented dough image recognizer includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. The input data of the input layer is the fermented dough image, and the output data is the fermentation specification information (fermentation shape, fermentation size, etc.) and the final fermentation information (volume expansion ratio, dough elasticity, dough softness). Then, a sample set of fermented dough images, a sample set of fermentation specification information, and a sample set of final fermentation information are collected to perform supervised training on the fermented dough image recognizer. The training process is as follows: First, the sample fermented dough images are used as the input and input into the input layer of the convolutional neural network. Then, the output layer of the model will output the predicted values of the fermentation specification information and the primary fermentation information. Further, the mean square error is used to evaluate the error between the predicted values of the model and the true values (sample fermentation specification information, sample final fermentation information). Then, the network weights are updated through the backpropagation algorithm, continuously reducing the error between the predicted values and the true values, and the model is continuously trained using the same method to obtain a fermented dough image recognizer that meets the expected convergence conditions.

[0028] Then, the multiple fermented dough images are subjected to feature recognition by the fermented dough image recognizer to obtain multiple fermentation specification information and multiple final fermentation information, where the fermentation specification information includes information such as the shape and size of the dough after final fermentation; the final fermentation information includes information such as the fermentation degree of the dough, the volume expansion ratio, the elasticity of the dough, and the softness of the dough.

[0029] Step Four: According to the multiple fermentation specification information and multiple final fermentation information, perform analysis on the decoration placement parameters of the fermented dough respectively, obtain multiple decoration placement parameters, and perform decoration placement and baking.

[0030] Specifically, according to the multiple fermentation specification information and multiple final fermentation information, optimize the decoration placement parameters of the fermented dough respectively. The decoration refers to the decorative food on the bread, such as sesame seeds, nuts, egg liquid, shredded meat floss, etc., which can be set according to the actual situation. The decoration placement parameters include the decoration placement area on the bread, the interval distance between decorations, etc. Among them, due to the different shapes, sizes and fermentation degrees of the fermented dough, the areas where the decorations are distributed after baking may also be different, affecting the consistency of the bread products. Therefore, optimize the decoration placement parameters according to the fermentation specification information and the final fermentation information to make the distribution of the decorations on the baked bread as consistent as possible, for example: place the decorations in the same position area on the bread; obtain multiple decoration placement parameters, and perform decoration placement on the fermented dough according to the multiple decoration placement parameters, and perform baking operations on the fermented dough after the decoration placement is completed.

[0031] By optimizing the decoration placement parameters of the fermented dough according to the fermentation specification information and the final fermentation information, the adaptability of the decoration placement parameters to the state of the fermented dough can be improved, making the decoration placement parameters more accurate, thereby improving the distribution consistency and appearance quality of the decorations on the baked bread.

[0032] Step Five: After baking is completed, collect multiple baking images, perform production composite consistency analysis, and obtain composite consistency parameters.

[0033] Specifically, after the bread baking operation is completed, use an image sensing device to collect images of the baked bread to obtain multiple baking images; then perform baking quality recognition according to the multiple baking images, and perform production composite consistency analysis according to the multiple baking quality recognition results, that is, calculate the overall uniformity and consistency of the baking quality of multiple breads to obtain composite consistency parameters to characterize the baking quality uniformity of the bread in the production line. The higher the baking quality uniformity, the larger the composite consistency parameter.

[0034] Step 6: Conduct consistency analyses of cutting, fermentation, and garnish placement respectively based on multiple dough images, multiple final fermentation parameters, and multiple garnish placement parameters to obtain cutting consistency parameters, fermentation consistency parameters, and garnish placement consistency parameters. Combine the composite consistency parameters to analyze and obtain production line management parameters for discriminative management.

[0035] Specifically, then conduct dough cutting consistency analysis based on multiple dough images, dough final fermentation consistency analysis based on multiple final fermentation parameters, and garnish placement consistency analysis based on multiple garnish placement parameters to obtain cutting consistency parameters, fermentation consistency parameters, and garnish placement consistency parameters. Among them, the cutting consistency parameter characterizes the overall uniformity of dough cutting, the fermentation consistency parameter characterizes the overall uniformity of dough final fermentation, and the garnish placement consistency parameter characterizes the overall uniformity of garnish placement on the bread. If the consistency is low, it indicates that each dough requires relatively different processing parameters during each production, or the consistency of the produced bread is low, affecting the production efficiency and quality of the bread. Then, conduct production line production consistency evaluation based on the cutting consistency parameter, fermentation consistency parameter, garnish placement consistency parameter, and composite consistency parameter to obtain production line management parameters; further determine whether the production line management parameters meet the preset management parameter threshold. If not, optimize and adjust the bread production line. For example, optimize the control parameters of the equipment in the bread production line, etc. Through the above method, the fineness and accuracy of bread production consistency analysis can be improved, the technical goal of accurately adjusting the bread production line can be achieved, and the technical effect of improving the bread production efficiency and quality can be achieved.

[0036] The described composite production line management method for food processing is applied to a composite production line management system for food processing, which can solve the technical problems of the existing bread composite production management method. Due to the large number of production processes, it is difficult to analyze the consistency of bread production, resulting in the inability to adjust and manage the bread production line specifically, affecting the production efficiency and quality of bread. First, collect multiple dough images of multiple doughs after segmentation, identify them, and obtain multiple dough specification information and multiple preliminary fermentation information; then, according to the multiple dough specification information and multiple preliminary fermentation information, analyze the fermentation parameters of the final fermentation of the dough respectively, obtain multiple final fermentation parameters, and carry out fermentation; next, after fermentation is completed, collect multiple fermented dough images of multiple doughs, identify them, and obtain multiple fermented specification information and multiple final fermentation information; then, according to the multiple fermented specification information and multiple final fermentation information, analyze the decoration placement parameters of the fermented dough respectively, obtain multiple decoration placement parameters, and carry out decoration placement and baking; in addition, after baking is completed, collect multiple baking images, carry out production composite consistency analysis, and obtain composite consistency parameters; finally, respectively carry out consistency analysis of cutting, fermentation, and decoration placement according to multiple dough images, multiple final fermentation parameters, and multiple decoration placement parameters, obtain cutting consistency parameters, fermentation consistency parameters, and decoration consistency parameters, combine the composite consistency parameters, analyze and obtain production line management parameters, and carry out discriminant management. It can improve the fineness and accuracy of bread production consistency analysis, achieve the technical goal of accurately adjusting the bread production line, and achieve the technical effect of improving the production efficiency and quality of bread.

[0037] Further, collect multiple dough images of multiple doughs after segmentation, identify them, and obtain multiple dough specification information and multiple preliminary fermentation information. As shown in the appendix Figure 2 This application's step one includes:

[0038] Collect multiple dough images of multiple doughs after segmentation;

[0039] According to the historical production data of the composite production line, obtain the sample dough image set;

[0040] Collect and identify the dough size specification information and preliminary fermentation information of the sample dough images, and obtain the sample dough specification information set and the sample preliminary fermentation information set. Among them, the preliminary fermentation information includes the degree of preliminary fermentation;

[0041] Use the sample dough image set, the sample dough specification information set, and the sample preliminary fermentation information set to construct a dough image recognizer, identify the multiple dough images, and obtain multiple dough specification information and multiple preliminary fermentation information.

[0042] Specifically, first, a plurality of doughs after segmentation are imaged by an image sensing device to obtain a plurality of dough images; on the other hand, historical production data of the composite production line is called, and a set of sample dough images is obtained based on the historical production data; then, information collection and identification are performed on the dough size specification information and the preliminary fermentation information of a plurality of sample dough images in the set of sample dough images to obtain a set of sample dough specification information and a set of sample preliminary fermentation information, where there is a mapping relationship between the sample dough images, the sample dough specification information, and the sample preliminary fermentation information. Among them, the preliminary fermentation information includes the degree of preliminary fermentation, and the degree of preliminary fermentation can be obtained by analyzing the number and size of pores in the dough image. The number of pores, the size of pores, and the degree of preliminary fermentation of the dough are directly proportional, that is, the more the number of pores on the dough and the larger the pore size, the better the degree of preliminary fermentation of the dough is characterized.

[0043] A dough image recognizer is constructed based on a convolutional neural network. The dough image recognizer is a convolutional neural network model that can be iteratively optimized in machine learning and is obtained through supervised training. The dough image recognizer includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. The input data of the input layer is a dough image, and the output data is dough specification information and preliminary fermentation information. Then, the set of sample dough images, the set of sample dough specification information, and the set of sample preliminary fermentation information are used as a training data set to perform supervised training on the dough image recognizer. The training method of the dough image recognizer is the same as the training method of the above-mentioned fermented dough image recognizer. Those skilled in the art can refer to the training process of the above-mentioned fermented dough image recognizer until a dough image recognizer that meets the preset accuracy constraint is obtained. Finally, the plurality of dough images are recognized by the dough image recognizer, and a plurality of dough specification information and a plurality of preliminary fermentation information are output. By constructing a dough image recognizer based on a convolutional neural network for dough feature analysis, the efficiency and accuracy of dough feature analysis can be improved, providing support for optimizing the final fermentation parameters in the next step.

[0044] Further, according to the plurality of dough specification information and the plurality of preliminary fermentation information, fermentation parameter analysis is respectively performed on the final fermentation of the dough to obtain a plurality of final fermentation parameters, and fermentation is carried out. Step two of this application includes:

[0045] Obtain standard fermentation specification information and standard final fermentation information;

[0046] Based on the standard fermentation specification information and the standard final fermentation information, a final fermentation optimization function is constructed as follows:

[0047]

[0048] Among them, FER is the fermentation fitness, w1 is the specification weight, w2 is the fermentation weight, D y is the standard fermentation specification information, F y is the standard final fermentation information, D f is the actual fermentation specification information after fermentation according to the final fermentation parameters, F f is the actual final fermentation information after fermentation according to the final fermentation parameters;

[0049] Optimize the fermentation parameters of the final fermentation of the dough according to the final fermentation optimization function to obtain the final fermentation parameters.

[0050] Specifically, first, obtain the standard fermentation specification information and the standard final fermentation information. The standard fermentation specification information refers to the expected fermentation specification requirements, including the standard fermentation shape, standard fermentation size (thickness, diameter, etc.), etc. The standard final fermentation information refers to the expected final state of the dough after fermentation, including indicators such as the volume expansion ratio, dough elasticity, and dough softness. Among them, the standard fermentation specification information and the standard final fermentation information can be set by those skilled in the art according to the actual bread production requirements.

[0051] Then, based on the standard fermentation specification information and the standard final fermentation information, construct a final fermentation optimization function, where the expression of the final fermentation optimization function is:

[0052] In the final fermentation optimization function, FER is the fermentation fitness, where the larger the fermentation fitness, the better the fermentation quality; w1 is the specification weight, representing the influence degree of fermentation specification information on fermentation quality; w2 is the fermentation weight, representing the influence degree of final fermentation information on fermentation quality. Among them, the sum of the specification weight and the fermentation weight is 1, and it can be set according to the influence degrees of fermentation specification information and final fermentation information on the overall fermentation quality. The greater the influence degree of a certain index, the greater the weight corresponding to the index, and the weights can be assigned according to the existing coefficient of variation method. For example, first calculate the mean values of all indexes (fermentation shape, fermentation size, etc.) in the fermentation specification information and the mean values of all indexes (volume expansion ratio, dough elasticity, etc.) in the final fermentation information; then calculate the standard deviations of each index in the fermentation specification information and the final fermentation information respectively; further calculate the coefficient of variation of the fermentation specification information based on the index mean value and index standard deviation of the fermentation specification information. The coefficient of variation is the ratio of the index standard deviation to the index mean value, and the coefficient of variation reflects the degree of data dispersion. The smaller the coefficient of variation, the more stable the index and the greater the influence on the fermentation fitness; calculate the coefficient of variation of the final fermentation information based on the index mean value and index standard deviation of the final fermentation information; then allocate the corresponding weights according to the coefficient of variation of the fermentation specification information and the coefficient of variation of the final fermentation information. The coefficient of variation and the weight are negatively correlated, that is, the greater the coefficient of variation, the smaller the weight, and the smaller the coefficient of variation, the greater the weight. For example, the ratio of the coefficient of variation of the fermentation specification information to the sum of the two coefficients of variation can be set as the fermentation weight of the final fermentation information, and the ratio of the coefficient of variation of the final fermentation information to the sum of the two coefficients of variation can be set as the fermentation weight of the fermentation specification information, so as to obtain the specification weight and the fermentation weight. D y is the standard fermentation specification information, F y is the standard final fermentation information, D f is the actual fermentation specification information after fermentation according to the final fermentation parameters, including the actual fermentation shape, actual fermentation size, etc.; F f is the actual final fermentation information after fermentation according to the final fermentation parameters, including the actual volume expansion ratio, actual dough elasticity, actual dough softness, etc. Further, based on the final fermentation optimization function, optimize the fermentation parameters of the dough final fermentation, and output the fermentation parameters with the largest fermentation fitness during the optimization process as the final fermentation parameters.

[0053] Furthermore, the present application further includes the following steps:

[0054] According to the historical production data of the dough final fermentation, obtain the sample dough specification information set and the sample preliminary fermentation information set, and obtain the sample final fermentation parameter set, the sample fermentation specification information set and the sample final fermentation information set, and construct a final fermentation predictor;

[0055] Randomly generate the first final fermentation parameters, and based on the final fermentation predictor, perform final fermentation prediction according to the first final fermentation parameters to obtain the first actual fermentation specification information and the first actual final fermentation information;

[0056] According to the final fermentation optimization function, combine the first actual fermentation specification information and the first actual final fermentation information, and calculate to obtain the first fermentation fitness;

[0057] Continue the optimization until convergence, and output the final fermentation parameters with the maximum fermentation fitness.

[0058] Specifically, the method for optimizing the fermentation parameters of the final dough fermentation according to the final fermentation optimization function to obtain the final fermentation parameters is as follows. First, call the historical production data of the final dough fermentation, and based on the historical production data, obtain the sample dough specification information set and the sample preliminary fermentation information set, and obtain the sample final fermentation parameter set, the sample fermentation specification information set and the sample final fermentation information set, where there is a mapping relationship between the sample dough specification information, the sample preliminary fermentation information, the sample final fermentation parameters, the sample fermentation specification information and the sample final fermentation information.

[0059] Construct a final fermentation predictor based on a BP neural network. The final fermentation predictor is a neural network model in a feedforward neural network that can be iteratively optimized and is obtained through supervised training using a training data set. The final fermentation predictor includes an input layer, multiple hidden layers, and an output layer. The input data of the input layer is dough specification information, preliminary fermentation information, and final fermentation parameters, and the output data of the output layer is fermentation specification information and final fermentation information. Then, use the sample dough specification information set, sample preliminary fermentation information set, sample final fermentation parameter set, sample fermentation specification information set, and sample final fermentation information set as the training data set to perform supervised training on the final fermentation predictor. First, divide the collected training data set into a training set, a validation set, and a test set. For example, 70% of the training set is used for model training, 15% of the validation set is used for validation during training to evaluate the performance of the model during training and prevent overfitting, and 15% of the test set is used for final evaluation of the generalization ability of the model. Then, use the training set to perform supervised training on the final fermentation predictor. First, input the input data (sample dough specification information, sample preliminary fermentation information, and sample final fermentation parameters) into the neural network. After calculation by the hidden layer, obtain the prediction results (fermentation specification information and final fermentation information) of the output layer. Then, calculate the error between the predicted value and the actual target value through a loss function. Further, through the gradient descent algorithm, use the gradient information of the error to perform backpropagation and update the weight parameters of the neural network. Finally, continuously iterate and optimize the model through multiple rounds of training to gradually converge the loss function and gradually improve the prediction accuracy of the model to obtain a final fermentation predictor that tends to a convergent state.

[0060] Then, use the validation set and the test set to perform performance verification and model testing on the final fermentation predictor respectively to obtain a final fermentation predictor with training completed.

[0061] Obtain the rated thresholds of fermentation parameters, including the temperature rated threshold, humidity rated threshold, etc. Then, randomly select any one parameter within the multiple parameter rated thresholds of the fermentation parameter rated threshold to form the first final fermentation parameter. Then, input the first final fermentation parameter into the final fermentation predictor for final fermentation prediction, and output the first actual fermentation specification information and the first actual final fermentation information. Further, according to the final fermentation optimization function, calculate the fermentation fitness of the first actual fermentation specification information and the first actual final fermentation information to obtain the first fermentation fitness.

[0062] Then, randomly select any one parameter again within multiple parameter rated thresholds of the fermentation parameter rated threshold to form a second final fermentation parameter, where the second final fermentation parameter is not exactly the same as the first final fermentation parameter, and calculate and obtain the second fermentation fitness of the second final fermentation parameter; then compare the first fermentation fitness and the second fermentation fitness. If the first fermentation fitness is greater than the second fermentation fitness, set the first final fermentation parameter as the current optimal fermentation parameter; conversely, if the first fermentation fitness is less than or equal to the second fermentation fitness, set the second final fermentation parameter as the current optimal fermentation parameter; continue iterative optimization until the preset number of optimization times is reached, and output the final fermentation parameter with the maximum fermentation fitness. The preset number of optimization times can be set according to the actual situation. By optimizing the final fermentation parameters of the dough based on the dough specification information and the preliminary fermentation information, and performing fermentation control on the dough with the optimized final fermentation parameters, the adaptability of the final fermentation parameters to the current state of the dough can be improved, making the setting of the final fermentation parameters more accurate, thereby improving the dough fermentation quality.

[0063] Further, according to the multiple fermentation specification information and multiple final fermentation information, analyze the ornament placement parameters of the fermented dough respectively. Step four of this application includes:

[0064] Obtain the standard ornament distribution information, where the standard ornament distribution information includes the standard distribution area of the ornament after baking.

[0065] Based on the standard ornament distribution information, construct an ornament placement optimization function as follows:

[0066]

[0067] where, ORN is the ornament fitness, Z y is the standard ornament distribution information, Z k is the actual ornament distribution information after being placed and baked according to the ornament placement parameters;

[0068] According to the ornament placement optimization function, perform optimization analysis on the ornament placement parameters of the fermented dough to obtain the multiple ornament placement parameters. During the optimization analysis of the ornament placement parameters, predict the ornament distribution information after baking based on the ornament placement parameters, fermentation specification information, final fermentation information, and baking parameters.

[0069] Specifically, first, obtain the standard ornament distribution information, where the standard ornament distribution information includes the standard distribution area of the ornament after baking, such as the standard distribution area of the ornament distribution area, which can be set by those skilled in the art according to the actual requirements of the bread product, such as extracting information through the bread product design drawing; then, based on the standard ornament distribution information, construct an ornament placement optimization function, and the expression of the ornament placement optimization function is: In the ornament placement optimization function, ORN is the decoration fitness, where the larger the decoration fitness, the better the decoration quality; Z y is the standard ornament distribution information, Z k is the actual ornament distribution information after placing and baking according to the ornament placement parameters, including the actual distribution area of the ornament distribution area, where the actual ornament distribution information can be obtained by using an image sensor to collect the baked bread image and extracting the ornament distribution area from the bread image.

[0070] Construct an ornament distribution prediction model based on the BP neural network, where the ornament distribution prediction model is a neural network model in machine learning that can be iteratively optimized, including an input layer, multiple hidden layers, and an output layer. The input data of the input layer is the ornament placement parameters, fermentation specification information, final fermentation information, and baking parameters, and the output data of the output layer is the ornament distribution prediction result; then, call the historical production data of dough baking to obtain a sample training data set. Among them, the sample training data includes sample ornament placement parameters, sample fermentation specification information, sample final fermentation information, sample baking parameters, and sample ornament distribution; then, use the sample ornament placement parameters, sample fermentation specification information, sample final fermentation information, and sample baking parameters as inputs, and use the sample ornament distribution as supervision, and use the sample training data set to supervise and train the ornament distribution prediction model, that is, the input data (sample ornament placement parameters, sample fermentation specification information, sample fermentation information, and sample baking parameters) is propagated forward through the neural network to obtain the predicted output (ornament distribution) of the model; then calculate the loss (error) between the model prediction value and the true value, and adjust the weights through the backpropagation algorithm; then perform iterative training, repeatedly perform forward propagation, error calculation, and backpropagation, and the model weights are continuously updated until the loss function converges to obtain the trained ornament distribution prediction model.

[0071] Next, according to the ornament placement optimization function, the ornament placement parameters of the fermented dough are optimized based on the ornament distribution prediction model, and the multiple ornament placement parameters are obtained based on the optimization result. The optimization method is the same as the optimization method for obtaining the final fermentation parameters described above, and will not be elaborated here. By optimizing the ornament placement parameters of the fermented dough according to the fermentation specification information and the final fermentation information, the adaptability of the ornament placement parameters to the state of the fermented dough can be improved, making the ornament placement parameters more accurate, thereby improving the distribution consistency and appearance quality of the ornaments on the baked bread.

[0072] Further, a plurality of baking images are collected for production composite consistency analysis to obtain composite consistency parameters. Step five of this application includes:

[0073] Collect a plurality of baking images after baking is completed;

[0074] Based on the historical data of bread production in the composite production line, obtain a set of sample baking images and a set of sample baking qualities, and construct a baking quality recognizer;

[0075] Based on the baking quality recognizer, identify the plurality of baking images to obtain a plurality of baking quality information;

[0076] Calculate and obtain the composite consistency parameters according to the plurality of baking quality information.

[0077] Specifically, a plurality of baked breads are imaged by an image sensing device to obtain a plurality of baking images; the historical data of bread production in the composite production line is called, and a set of sample baking images and a set of sample baking qualities are obtained based on the historical data. The sample baking images and the sample baking qualities correspond one by one, and the baking quality can be represented by a baking quality coefficient. The larger the quality coefficient, the better the baking quality. A baking quality recognizer is constructed based on a convolutional neural network. The baking quality recognizer includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. The input data of the input layer is a baking image, and the output data of the output layer is a baking quality coefficient; then, with the sample baking image as the input data and the sample baking quality as the supervision, the baking quality recognizer is supervised and trained using the set of sample baking images and the set of sample baking qualities. First, the input baking image is passed through the convolutional layer, the pooling layer, and the fully connected layer to generate the predicted output (baking quality coefficient) of the model; then, according to the value of the loss function, the backpropagation algorithm is used to adjust the weights in the network to minimize the prediction error; then iterative training is performed until the loss function converges, and the trained baking quality recognizer is output.

[0078] Next, the baking quality recognizer is used to recognize the multiple baking images, and multiple baking quality information is output. Finally, based on the multiple baking quality information, a composite consistency calculation is performed to obtain the composite consistency parameter, where the composite consistency parameter characterizes the baking quality uniformity of the bread. For example, the variance of the multiple baking quality information can be calculated, and the composite consistency parameter can be calculated based on the variance calculation result. The variance of the quality information is inversely proportional to the composite consistency parameter, that is, the smaller the variance of the quality information, the greater the baking quality uniformity, and the larger the composite consistency parameter. For example, the reciprocal of the variance of the quality information is used as the composite consistency parameter.

[0079] Further, consistency analysis of cutting, fermentation, and decoration placement is respectively performed according to multiple dough images, multiple final fermentation parameters, and multiple decoration placement parameters to obtain a cutting consistency parameter, a fermentation consistency parameter, and a decoration consistency parameter. Combining the composite consistency parameter, a production line management parameter is analyzed and obtained. Step six of this application includes:

[0080] Randomly combine and perform similarity recognition on the multiple dough images to obtain a dough similarity set, where the similarity recognition is performed through a siamese neural network;

[0081] Based on the dough similarity set, a cutting consistency parameter is calculated;

[0082] Based on the multiple final fermentation parameters and multiple decoration placement parameters, a fermentation consistency parameter and a decoration consistency parameter are respectively calculated;

[0083] Obtain a sample cutting consistency parameter set, a sample fermentation consistency parameter set, a sample decoration consistency parameter set, and a sample composite consistency parameter set, and obtain a sample production line management parameter set;

[0084] Using the sample cutting consistency parameter set, the sample fermentation consistency parameter set, the sample decoration consistency parameter set, the sample composite consistency parameter set, and the sample production line management parameter set, a production line management decision maker is constructed based on a decision tree;

[0085] Based on the production line management decision maker, analysis and decision are performed on the composite consistency parameter, the cutting consistency parameter, the fermentation consistency parameter, and the decoration consistency parameter to obtain a production line management parameter;

[0086] Judge whether the production line management parameter is greater than the management parameter threshold. If so, adjust and optimize the management of the production line.

[0087] Specifically, first, pair the multiple dough images randomly in pairs, and identify the similarity of the combined results of the dough images to obtain a dough similarity set. The similarity of the combined results of the dough images can be identified through a Siamese neural network. A Siamese neural network is a special neural network structure composed of two or more sub-networks sharing weights. Each sub-network can be a convolutional neural network or other types of neural networks, which are used to extract features from the input images and calculate the similarity of these features. The output of the Siamese neural network is a similarity score, representing the distance between two images in the feature space. The smaller the distance between two images in the feature space, the larger the similarity score. The Siamese neural network includes an input layer, a shared convolutional network layer, and an output layer. The input data of the input layer is two dough images, and the output data of the output layer is the similarity score of the two dough images. The shared convolutional network layer is used to extract similar features through the same convolutional network (sharing parameters). By inputting paired dough images and corresponding similarity labels, and optimizing the model by calculating the loss function, through multiple rounds of training iterations, using optimization algorithms (such as Adam or SGD) to gradually optimize the model until the loss function converges, a Siamese neural network that meets the expected requirements is obtained.

[0088] Next, calculate the similarity variance based on the dough similarity set, and obtain a cutting consistency parameter based on the calculation result of the similarity variance. The cutting consistency parameter is negatively correlated with the calculation result of the similarity variance, that is, the larger the calculation result of the similarity variance, the smaller the cutting consistency parameter, and the smaller the calculation result of the similarity variance, the larger the cutting consistency parameter. For example, the reciprocal of the calculation result of the similarity variance can be set as the cutting consistency parameter.

[0089] Then, variance calculations are respectively performed according to the multiple final fermentation parameters and multiple ornament placement parameters, and a fermentation consistency parameter and an ornament consistency parameter are obtained based on the variance calculation results. The fermentation consistency parameter is the reciprocal of the variance calculation result of the fermentation parameters, and the ornament consistency parameter is the reciprocal of the variance calculation result of the ornament placement parameters. Then, a set of sample cutting consistency parameters, a set of sample fermentation consistency parameters, a set of sample ornament consistency parameters, and a set of sample composite consistency parameters are obtained, and a set of sample production line management parameters is obtained, where the sample production line management parameter characterizes the overall management quality of the production line. The larger the sample production line management parameter, the better the overall management quality of the production line. Among them, there is a mapping relationship between the sample cutting consistency parameter, the sample fermentation consistency parameter, the sample ornament consistency parameter, the sample composite consistency parameter, and the sample production line management parameter. The decision tree model splits the features of the data and gradually refines them until the optimal classification or regression result is achieved. In the scenario of production line management, the decision tree will make management decisions based on the consistency parameters. Then, based on the decision tree principle, with the cutting consistency parameter, the fermentation consistency parameter, the ornament consistency parameter, and the composite consistency parameter as input features, and the production line management parameter as the output target variable, an initial production line management decision maker is constructed. Further, the initial production line management decision maker is trained using the set of sample cutting consistency parameters, the set of sample fermentation consistency parameters, the set of sample ornament consistency parameters, the set of sample composite consistency parameters, and the set of sample production line management parameters. By recursively splitting the feature space, the best splitting condition for each node is found, and the splitting method of the node is continuously optimized to minimize the prediction error, so as to obtain a production line management decision maker that meets the expected output accuracy. Then, the composite consistency parameter, the cutting consistency parameter, the fermentation consistency parameter, and the ornament consistency parameter are input into the production line management decision maker for matching decision analysis, and the production line management parameter is output by matching. A management parameter threshold is obtained, and the management parameter threshold can be set according to the management quality requirements. The higher the required quality, the smaller the management parameter threshold. Then, it is judged whether the production line management parameter is greater than the management parameter threshold. If so, the production line is adjusted and optimized for management, such as optimizing the control parameters of the equipment in the bread production line, etc.

[0090] In summary, a composite production line management method for food processing provided by the present application has the following technical effects:

[0091] 1. By identifying multiple dough images after segmentation, multiple dough specification information and multiple preliminary fermentation information are obtained; then, based on the multiple dough specification information and multiple preliminary fermentation information, an optimization analysis of dough fermentation parameters is carried out to obtain multiple optimized final fermentation parameters for fermentation; then, after fermentation is completed, multiple fermented dough images are identified to obtain multiple fermentation specification information and multiple final fermentation information; further, based on the multiple fermentation specification information and multiple final fermentation information, an optimization analysis of the decoration placement parameters of the fermented dough is carried out to obtain multiple optimized decoration placement parameters for decoration placement and baking; and after baking is completed, a production composite consistency analysis is carried out based on multiple baking images to obtain composite consistency parameters; on the other hand, a consistency analysis of cutting, fermentation, and decoration placement is carried out based on multiple dough images, multiple final fermentation parameters, and multiple decoration placement parameters, and production line management parameters are obtained based on the cutting consistency parameters, fermentation consistency parameters, decoration consistency parameters, and composite consistency parameters. When the production line management parameters do not meet the preset management parameter threshold, the bread composite production line is adjusted and optimized. It can improve the fineness and accuracy of bread production consistency analysis, achieve the technical goal of accurately adjusting the bread production line, and achieve the technical effect of improving bread production efficiency and production quality.

[0092] 2. By optimizing the final fermentation parameters of the dough based on the dough specification information and preliminary fermentation information, and obtaining the optimized final fermentation parameters to control the dough fermentation, the adaptability of the final fermentation parameters to the current state of the dough can be improved, making the setting of the final fermentation parameters more accurate, thereby improving the dough fermentation quality.

[0093] 3. By optimizing the decoration placement parameters of the fermented dough according to the fermentation specification information and final fermentation information, the adaptability of the decoration placement parameters to the state of the fermented dough can be improved, making the decoration placement parameters more accurate, thereby improving the distribution consistency and appearance quality of the decorations on the bread after baking.

[0094] Embodiment 2

[0095] Based on a method for managing a composite production line for food processing in the foregoing embodiment with the same inventive concept, the present application also provides a system for managing a composite production line for food processing. Please refer to the appendix Figure 3 The system includes:

[0096] A dough image recognition module 11, configured to collect multiple dough images of multiple doughs after segmentation, perform recognition, and obtain multiple dough specification information and multiple preliminary fermentation information;

[0097] The fermentation parameter analysis module 12 is used to perform fermentation parameter analysis on the final fermentation of the dough respectively according to the multiple dough specification information and the multiple preliminary fermentation information, obtain multiple final fermentation parameters, and conduct fermentation;

[0098] The fermented dough image recognition module 13 is used to collect multiple fermented dough images of multiple doughs after fermentation is completed, perform recognition, and obtain multiple fermentation specification information and multiple final fermentation information;

[0099] The decoration placement parameter analysis module 14 is used to perform decoration placement parameter analysis on the fermented dough respectively according to the multiple fermentation specification information and the multiple final fermentation information, obtain multiple decoration placement parameters, and conduct decoration placement and baking;

[0100] The production composite consistency analysis module 15 is used to collect multiple baking images after baking is completed, perform production composite consistency analysis, and obtain composite consistency parameters;

[0101] The production line management parameter discrimination module 16 is used to perform consistency analysis on cutting, fermentation, and decoration placement respectively according to multiple dough images, multiple final fermentation parameters, and multiple decoration placement parameters, obtain cutting consistency parameters, fermentation consistency parameters, and decoration consistency parameters, and combine the composite consistency parameters to analyze and obtain production line management parameters for discrimination management.

[0102] Furthermore, the dough image recognition module 11 in the system is further used for:

[0103] Collecting multiple dough images of multiple doughs after segmentation is completed;

[0104] Obtaining a sample dough image set according to the historical production data of the composite production line;

[0105] Collecting and identifying the dough size specification information and preliminary fermentation information of the sample dough images to obtain a sample dough specification information set and a sample preliminary fermentation information set, where the preliminary fermentation information includes the degree of preliminary fermentation;

[0106] Using the sample dough image set, the sample dough specification information set, and the sample preliminary fermentation information set to construct a dough image recognizer, and performing recognition on the multiple dough images to obtain multiple dough specification information and multiple preliminary fermentation information.

[0107] Furthermore, the fermentation parameter analysis module 12 in the system is further used for:

[0108] Obtaining standard fermentation specification information and standard final fermentation information;

[0109] Based on the above-mentioned standard fermentation specification information and standard final fermentation information, construct a final fermentation optimization function as follows:

[0110]

[0111] where FER is the fermentation fitness, w1 is the specification weight, w2 is the fermentation weight, D y is the standard fermentation specification information, F y is the standard final fermentation information, D f is the actual fermentation specification information after fermentation according to the final fermentation parameters, F f is the actual final fermentation information after fermentation according to the final fermentation parameters;

[0112] Optimize the fermentation parameters of the final fermentation of the dough according to the above-mentioned final fermentation optimization function to obtain the above-mentioned final fermentation parameters.

[0113] Furthermore, the fermentation parameter analysis module 12 in the system is further configured to:

[0114] Obtain a sample dough specification information set and a sample preliminary fermentation information set according to the historical production data of the final fermentation of the dough, and obtain a sample final fermentation parameter set, a sample fermentation specification information set and a sample final fermentation information set, and construct a final fermentation predictor;

[0115] Randomly generate a first final fermentation parameter, and based on the final fermentation predictor, perform a final fermentation prediction according to the first final fermentation parameter to obtain a first actual fermentation specification information and a first actual final fermentation information;

[0116] Calculate and obtain a first fermentation fitness according to the final fermentation optimization function in combination with the first actual fermentation specification information and the first actual final fermentation information;

[0117] Continue to optimize until convergence, and output the final fermentation parameter with the maximum fermentation fitness.

[0118] Furthermore, the decoration placement parameter analysis module 14 in the system is further configured to:

[0119] Obtain standard decoration distribution information, where the standard decoration distribution information includes the standard distribution area of the decoration after baking;

[0120] Based on the standard decoration distribution information, construct a decoration placement optimization function as follows:

[0121]

[0122] where ORN is the decoration fitness, Z y is the standard decoration distribution information, Zk The actual distribution information of the decorations after being placed and baked according to the decoration placement parameters;

[0123] According to the decoration placement optimization function, optimize and analyze the decoration placement parameters of the fermented dough to obtain the multiple decoration placement parameters. Among them, during the optimization analysis of the decoration placement parameters, predict the decoration distribution information after baking based on the decoration placement parameters, fermentation specification information, final fermentation information, and baking parameters.

[0124] Furthermore, the production composite consistency analysis module 15 in the system is further configured to:

[0125] Collect multiple baking images after baking is completed;

[0126] Based on the historical data of bread production in the composite production line, obtain a set of sample baking images and a set of sample baking quality, and construct a baking quality recognizer;

[0127] Based on the baking quality recognizer, recognize the multiple baking images to obtain multiple baking quality information;

[0128] Calculate and obtain the composite consistency parameter according to the multiple baking quality information.

[0129] Furthermore, the production line management parameter discrimination module 16 in the system is further configured to:

[0130] Randomly combine and perform similarity recognition on the multiple dough images to obtain a set of dough similarities, where the similarity recognition is performed through a siamese neural network;

[0131] Calculate and obtain the cutting consistency parameter according to the set of dough similarities;

[0132] Calculate and obtain the fermentation consistency parameter and the decoration consistency parameter respectively according to the multiple final fermentation parameters and the multiple decoration placement parameters;

[0133] Obtain a set of sample cutting consistency parameters, a set of sample fermentation consistency parameters, a set of sample decoration consistency parameters, and a set of sample composite consistency parameters, and obtain a set of sample production line management parameters;

[0134] Using the set of sample cutting consistency parameters, the set of sample fermentation consistency parameters, the set of sample decoration consistency parameters, the set of sample composite consistency parameters, and the set of sample production line management parameters, construct a production line management decision maker based on a decision tree;

[0135] Based on the production line management decision maker, analyze and make decisions on the composite consistency parameter, the cutting consistency parameter, the fermentation consistency parameter, and the decoration consistency parameter to obtain production line management parameters;

[0136] Determine whether the production line management parameter is greater than the management parameter threshold. If so, adjust and optimize the management of the production line.

[0137] The various embodiments in this specification are described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The method and specific examples for managing a composite production line for food processing in the foregoing Embodiment 1 are equally applicable to the system for managing a composite production line for food processing in this embodiment. Through the foregoing detailed description of the method for managing a composite production line for food processing, those skilled in the art can clearly understand the system for managing a composite production line for food processing in this embodiment. Therefore, for the sake of brevity of the specification, it will not be elaborated here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For the relevant parts, reference may be made to the description in the method section.

[0138] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0139] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application also intends to include these changes and variations.

Claims

1. A management method for a composite production line used in food processing, characterized in that, The method includes: Collecting multiple dough images of multiple doughs after segmentation, performing recognition, and obtaining multiple dough specification information and multiple preliminary fermentation information; According to the multiple dough specification information and multiple preliminary fermentation information, respectively performing fermentation parameter analysis for the final fermentation of the dough to obtain multiple final fermentation parameters, and performing fermentation, including: constructing a final fermentation optimization function, optimizing the fermentation parameters for the final fermentation of the dough, and obtaining the final fermentation parameters; According to the final fermentation optimization function, optimizing the fermentation parameters for the final fermentation of the dough to obtain the final fermentation parameters, including: calculating and obtaining a fermentation fitness, performing optimization until convergence, and outputting the final fermentation parameters with the maximum fermentation fitness; After fermentation is completed, collecting multiple fermented dough images of multiple doughs, performing recognition, and obtaining multiple fermentation specification information and multiple final fermentation information; According to the multiple fermentation specification information and multiple final fermentation information, respectively performing ornament placement parameter analysis for the fermented dough to obtain multiple ornament placement parameters, and performing ornament placement and baking; After baking is completed, collecting multiple baking images, performing production composite consistency analysis, and obtaining composite consistency parameters; Respectively performing consistency analysis of cutting, fermentation, and ornament placement according to multiple dough images, multiple final fermentation parameters, and multiple ornament placement parameters to obtain cutting consistency parameters, fermentation consistency parameters, and decoration consistency parameters, and combining the composite consistency parameters, analyzing and obtaining production line management parameters, and performing discriminant management, including: performing similarity recognition through a twin neural network, obtaining a sample production line management parameter set, constructing a production line management decision maker, obtaining production line management parameters based on the production line management decision maker, and determining whether the production line management parameters are greater than the management parameter threshold. If so, adjusting and optimizing the management of the production line.

2. The method according to claim 1, wherein Collecting multiple dough images of multiple doughs after segmentation, performing recognition, and obtaining multiple dough specification information and multiple preliminary fermentation information, including: Collecting multiple dough images of multiple doughs after segmentation; Obtaining a sample dough image set according to the historical production data of the composite production line; Collecting and identifying the dough size specification information and preliminary fermentation information of the sample dough images to obtain a sample dough specification information set and a sample preliminary fermentation information set, where the preliminary fermentation information includes the degree of preliminary fermentation; Using the sample dough image set, the sample dough specification information set, and the sample preliminary fermentation information set to construct a dough image recognizer, and performing recognition on the multiple dough images to obtain multiple dough specification information and multiple preliminary fermentation information.

3. The method according to claim 1, characterized in that, According to the multiple dough specification information and multiple preliminary fermentation information, respectively performing fermentation parameter analysis for the final fermentation of the dough to obtain multiple final fermentation parameters, and performing fermentation, including: Obtaining standard fermentation specification information and standard final fermentation information; Based on the standard fermentation specification information and standard final fermentation information, constructing a final fermentation optimization function as follows: ； Among them, FER is the fermentation fitness, is the specification weight, is the fermentation weight, is the standard fermentation specification information, is the standard final fermentation information, is the actual fermentation specification information after fermentation according to the final fermentation parameters, is the actual final fermentation information after fermentation according to the final fermentation parameters; According to the final fermentation optimization function, optimizing the fermentation parameters for the final fermentation of the dough to obtain the final fermentation parameters.

4. The method according to claim 3, characterized in that According to the final fermentation optimization function, optimize the fermentation parameters of the final dough fermentation to obtain the final fermentation parameters, including: According to the historical production data of the final dough fermentation, obtain the sample dough specification information set and the sample preliminary fermentation information set, and obtain the sample final fermentation parameter set, the sample fermentation specification information set and the sample final fermentation information set, and construct a final fermentation predictor; Randomly generate the first final fermentation parameter, and based on the final fermentation predictor, perform final fermentation prediction according to the first final fermentation parameter to obtain the first actual fermentation specification information and the first actual final fermentation information; According to the final fermentation optimization function, combine the first actual fermentation specification information and the first actual final fermentation information, and calculate to obtain the first fermentation fitness; Continue to optimize until convergence, and output the final fermentation parameter with the maximum fermentation fitness.

5. The method according to claim 1, characterized in that, According to the multiple fermentation specification information and the multiple final fermentation information, respectively perform analysis on the decoration placement parameters of the fermented dough, including: Obtain the standard decoration distribution information, where the standard decoration distribution information includes the standard distribution area of the decoration after baking; Based on the standard decoration distribution information, construct an optimization function for decoration placement as follows: ； where ORN is the ornament fitness, is the standard ornament distribution information, is the actual ornament distribution information after being placed and baked according to the ornament placement parameters; According to the optimization function for decoration placement, perform optimization analysis on the decoration placement parameters of the fermented dough to obtain the multiple decoration placement parameters. During the optimization analysis of the decoration placement parameters, predict the decoration distribution information after baking based on the decoration placement parameters, the fermentation specification information, the final fermentation information and the baking parameters.

6. The method according to claim 1, characterized in that Collect multiple baking images and perform production composite consistency analysis to obtain composite consistency parameters, including: Collect multiple baking images after baking is completed; Based on the historical data of bread production in the composite production line, obtain the sample baking image set and obtain the sample baking quality set, and construct a baking quality identifier; Based on the baking quality identifier, identify the multiple baking images to obtain multiple baking quality information; According to the multiple baking quality information, calculate to obtain the composite consistency parameter.

7. The method according to claim 1, characterized in that, Respectively perform consistency analysis on cutting, fermentation and decoration placement according to multiple dough images, multiple final fermentation parameters and multiple decoration placement parameters to obtain cutting consistency parameters, fermentation consistency parameters and decoration consistency parameters, and combine the composite consistency parameters to analyze and obtain production line management parameters, including: Perform random combination and similarity recognition on the multiple dough images to obtain a dough similarity set, where similarity recognition is performed through a siamese neural network; According to the dough similarity set, calculate to obtain the cutting consistency parameter; According to the multiple final fermentation parameters and the multiple decoration placement parameters, respectively calculate to obtain the fermentation consistency parameter and the decoration consistency parameter; Obtain the sample cutting consistency parameter set, the sample fermentation consistency parameter set, the sample decoration consistency parameter set and the sample composite consistency parameter set, and obtain the sample production line management parameter set; Using the sample cutting consistency parameter set, sample fermentation consistency parameter set, sample decoration consistency parameter set, sample composite consistency parameter set, and sample production line management parameter set, a production line management decision maker is constructed based on a decision tree; Based on the production line management decision maker, the composite consistency parameters, cutting consistency parameters, fermentation consistency parameters, and decoration consistency parameters are analyzed and decided to obtain production line management parameters; It is judged whether the production line management parameters are greater than the management parameter threshold. If so, the production line is adjusted and optimized for management.

8. A composite production line management system for food processing, characterized in that, For implementing the steps of the method according to any one of claims 1 to 7, the system includes: A dough image recognition module, configured to collect multiple dough images of multiple doughs after segmentation, perform recognition, and obtain multiple dough specification information and multiple preliminary fermentation information; A fermentation parameter analysis module, configured to perform fermentation parameter analysis of the final fermentation of the dough respectively according to the multiple dough specification information and the multiple preliminary fermentation information, obtain multiple final fermentation parameters, and perform fermentation; A fermented dough image recognition module, configured to collect multiple fermented dough images of multiple doughs after fermentation is completed, perform recognition, and obtain multiple fermentation specification information and multiple final fermentation information; A decoration placement parameter analysis module, configured to perform decoration placement parameter analysis of the fermented dough respectively according to the multiple fermentation specification information and the multiple final fermentation information, obtain multiple decoration placement parameters, and perform decoration placement and baking; A production composite consistency analysis module, configured to collect multiple baking images after baking is completed, perform production composite consistency analysis, and obtain composite consistency parameters; A production line management parameter discrimination module, configured to perform consistency analysis of cutting, fermentation, and decoration placement respectively according to multiple dough images, multiple final fermentation parameters, and multiple decoration placement parameters, obtain cutting consistency parameters, fermentation consistency parameters, and decoration consistency parameters, and analyze and obtain production line management parameters in combination with the composite consistency parameters for discrimination management; The fermentation parameter analysis module is further configured to: Obtain standard fermentation specification information and standard final fermentation information; Based on the standard fermentation specification information and the standard final fermentation information, a final fermentation optimization function is constructed as follows: ； where FER is the fermentation fitness, is the specification weight, is the fermentation weight, is the standard fermentation specification information, is the standard final fermentation information, is the actual fermentation specification information after fermentation according to the final fermentation parameters, is the actual final fermentation information after fermentation according to the final fermentation parameters; According to the final fermentation optimization function, the fermentation parameters of the final fermentation of the dough are optimized to obtain the final fermentation parameters; According to the historical production data of the final fermentation of the dough, a sample dough specification information set and a sample preliminary fermentation information set are obtained, and a sample final fermentation parameter set, a sample fermentation specification information set, and a sample final fermentation information set are obtained to construct a final fermentation predictor; Randomly generate a first final fermentation parameter, and based on the final fermentation predictor, perform final fermentation prediction according to the first final fermentation parameter to obtain first actual fermentation specification information and first actual final fermentation information; According to the final fermentation optimization function, in combination with the first actual fermentation specification information and the first actual final fermentation information, calculate and obtain a first fermentation fitness; Continue to optimize until convergence, and output the final fermentation parameter with the maximum fermentation fitness; The production line management parameter discrimination module is further configured to: Randomly combine and identify the similarity of the multiple dough images to obtain a dough similarity set, wherein the similarity is identified by a siamese neural network; Calculate a cutting consistency parameter according to the dough similarity set; Calculate a fermentation consistency parameter and a decoration consistency parameter respectively according to the multiple final fermentation parameters and the multiple decoration placement parameters; Obtain a sample cutting consistency parameter set, a sample fermentation consistency parameter set, a sample decoration consistency parameter set, and a sample composite consistency parameter set, and obtain a sample production line management parameter set; Use the sample cutting consistency parameter set, the sample fermentation consistency parameter set, the sample decoration consistency parameter set, the sample composite consistency parameter set, and the sample production line management parameter set to construct a production line management decision maker based on a decision tree; Based on the production line management decision maker, analyze and make decisions on the composite consistency parameter, the cutting consistency parameter, the fermentation consistency parameter, and the decoration consistency parameter to obtain production line management parameters; Judge whether the production line management parameter is greater than the management parameter threshold. If so, adjust and optimize the management of the production line.

Images