Intelligent management method and system for fermentation tank group based on optimal fermentation time of soy sauce

Abstract

The invention discloses a fermentation tank group intelligent management method and system based on the optimal fermentation time of soy sauce, and the method comprises the steps: collecting and storing the production data of a fermentation tank group as the historical production data of the fermentation tank group; preprocessing the historical production data of the fermentation tank group; calculating a correlation coefficient between the fermentation process data and a product quality index according to the preprocessed historical production data; according to the preprocessed historical production data, establishing a neural network model of a mathematical relationship between the fermentation process data and the product quality index data; taking the preprocessed historical production data as sample data, and training a neural network model by adopting a gradient descent algorithm; according to fermentation process data, collected in real time, of the fermentation tank group, outputting predicted product quality index data of the fermentation tank group by utilizing the trained neural network model; and establishing a dynamic management mathematical model by taking optimal soy sauce fermentation time and overall production quality optimization of the fermentation tank group as targets according to product quality index data, and calculating a solution of the optimal target by adopting a genetic algorithm to realize intelligent management of the fermentation tank group. According to the method, big data, a neural network model and a genetic algorithm are combined, overall optimization of quality indexes of products produced by the fermentation tank group is realized by calculating the optimal fermentation time of soy sauce, and intelligent management of the fermentation tank group is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent management of food processing, and in particular relates to an intelligent management method, system, terminal equipment and computer-readable storage medium for a fermentation tank group based on optimal fermentation time of soy sauce. Background Art

[0002] Modern soy sauce brewing technology is based on the traditional soy sauce fermentation process, and realizes the industrial production of soy sauce brewing through technologies such as mechanization and automation of the production process.

[0003] The fermentation process is the key link in soy sauce production and also the longest link. Due to the long fermentation time, soy sauce production companies need to build a large number of fermentation tanks. In daily production, companies need to dynamically manage all fermentation tanks.

[0004] At present, most soy sauce production companies use a fixed fermentation cycle and regular testing of soy sauce product quality indicators to determine the total fermentation time of each fermentation tank and manage the fermentation tank group. However, in different seasons and years, factors such as temperature, light, and cycle time will affect the fermentation effect of each fermentation tank. The fermentation process of each tank is different. If a fixed fermentation cycle is used, the quality indicators of the fermented products will be different; combined with regular testing, it can ensure that the product quality indicators are higher than the production requirements, but it is still difficult to achieve the overall optimization of the quality indicators of the fermentation tank group production products. Summary of the invention

[0005] In order to address the deficiencies of the above-mentioned prior art, the present invention provides a method, system, terminal device and computer-readable storage medium for intelligent management of a fermentation tank group based on the optimal fermentation time of soy sauce, which combines big data, a neural network model and a genetic algorithm, and realizes the overall optimization of the quality indicators of the products produced by the fermentation tank group by calculating the optimal fermentation time of soy sauce, so as to realize the intelligent management of the fermentation tank group.

[0006] The first object of the present invention is to provide an intelligent management method for a fermentation tank group based on the optimal fermentation time of soy sauce.

[0007] The second object of the present invention is to provide an intelligent management system for a group of fermentation tanks based on the optimal fermentation time of soy sauce.

[0008] The third object of the present invention is to provide a terminal device.

[0009] A fourth object of the present invention is to provide a computer-readable storage medium.

[0010] The first object of the present invention can be achieved by adopting the following technical solutions: A method for intelligent management of a fermentation tank group based on optimal fermentation time of soy sauce, the method comprising: Collecting and storing production data of the fermentation tank group as historical production data of the fermentation tank group; wherein the production data includes fermentation process data and product quality index data; Preprocess the historical production data of the fermentation tank group; Based on the historical production data after pretreatment, the correlation coefficient between the fermentation process data and the product quality index is calculated; According to the pre-processed historical production data, a neural network model of the mathematical relationship between the fermentation process data and the product quality index data is established; the pre-processed historical production data is used as sample data, and the neural network model is trained using the gradient descent algorithm; when the gradient descent algorithm is used to select the value, the iterative calculation step length is selected according to the correlation coefficient between the fermentation process data and the product quality index data to improve the calculation efficiency; Based on the fermentation process data of the fermentation tank group collected in real time, the trained neural network model is used to output the predicted product quality index data of the fermentation tank group; based on the product quality index data, with the goal of optimizing the best fermentation time of soy sauce and the overall production quality of the fermentation tank group, a dynamic management mathematical model is established, and a genetic algorithm is used to calculate the solution of the optimization goal to realize the intelligent management of the fermentation tank group.

[0011] Furthermore, the product quality index data include soy sauce ammonia nitrogen content ANN and soy sauce total nitrogen content TNN; The dynamic management mathematical model is: Where g1 and g2 are the ANN quality index and TNN quality index of the fermentation tanks involved in the genetic algorithm calculation, n is the total number of fermentation tanks involved in the genetic algorithm calculation, and ANN i 、TNN i are the predicted ANN and TNN of the i-th fermenter respectively; g3 is the overall product quality index of the fermenter group participating in the genetic algorithm calculation; a and b are the weight coefficients of the predicted total ANN and total TNN respectively.

[0012] Furthermore, in the genetic algorithm, the fermentation tanks participating in the genetic algorithm calculation are regarded as chromosomes, and the total number of all fermentation tanks participating in the genetic algorithm calculation is the number of chromosomes.

[0013] Furthermore, the pre-processed historical production data is used as sample data, and a gradient descent algorithm is used to train a neural network model, including: The soy sauce fermentation cycle is divided into three independent fermentation stages: the initial fermentation stage, the middle fermentation stage and the final fermentation stage; each fermentation stage corresponds to a neural network model, that is, a neural network model is trained using the historical production data of a fermentation stage; The construction and training methods of the three neural network models are the same, and one of the neural network models is used for illustration: The input layer neurons are fermentation process data from preprocessed historical production data; The output layer neurons are the predicted product quality index data; The square of the difference between the predicted product quality index data and the product quality index data in the preprocessed historical production data is used as the loss function, and the gradient descent algorithm is used to train the neural network model.

[0014] Furthermore, the product quality index data of the fermentation tank group is output based on the fermentation process data of the fermentation tank group collected in real time and predicted by using the trained neural network model, including: According to the real-time acquisition time, the fermentation stage is determined, and then the corresponding trained neural network model is determined; The fermentation process data of the fermentation tank group collected in real time is preprocessed and then input into the determined neural network model to output the predicted product quality index data.

[0015] Further, the fermentation process data includes the temperature inside the fermentation tank, the light intensity, the atmospheric temperature, the atmospheric humidity, the production date, and the row and column positions of the tank area where the fermentation tank is located, and the product quality index data includes the ammonia nitrogen content of soy sauce and the total nitrogen content of soy sauce; The preprocessing includes data cleaning and data standardization, wherein: Data cleaning includes: removing data that shows a negative correlation between ammonia nitrogen and time, as well as data points with temperature, humidity and light conditions that do not conform to natural laws; The data standardization process includes: integrating the temperature inside each fermenter, light intensity, atmospheric temperature, and atmospheric humidity of each fermenter every day, and classifying and digitizing the row and column positions of each fermenter.

[0016] Furthermore, the step length of iterative calculation is selected according to the correlation coefficient between the fermentation process data and the product quality index data, including: When the gradient descent algorithm is used to select values, an appropriate step length is selected for the step value of the weight of the pre-processed fermentation process data: when the absolute value of the correlation coefficient is small, the step length is appropriately increased; when the absolute value of the correlation coefficient is large, the step length is appropriately decreased.

[0017] Furthermore, the correlation coefficient is calculated using the Spearman rank correlation coefficient.

[0018] The second object of the present invention can be achieved by adopting the following technical solutions: An intelligent management system for a group of fermentation tanks based on optimal fermentation time of soy sauce, the system comprising: A data acquisition module is used to collect and store the production data of the fermentation tank group as the historical production data of the fermentation tank group; wherein the production data includes fermentation process data and product quality index data; A data preprocessing module is used to preprocess the historical production data of the fermentation tank group; A correlation coefficient calculation module is used to calculate the correlation coefficient between fermentation process data and product quality indicators based on pre-processed historical production data; The model training module is used to establish a neural network model of the mathematical relationship between the fermentation process data and the product quality index data based on the pre-processed historical production data; the pre-processed historical production data is used as sample data, and the neural network model is trained using a gradient descent algorithm; when the gradient descent algorithm is used to select the value, the iterative calculation step length is selected according to the correlation coefficient between the fermentation process data and the product quality index data to improve the calculation efficiency; The dynamic management module is used to output the predicted product quality index data of the fermentation tank group based on the fermentation process data of the fermentation tank group collected in real time by using the trained neural network model; based on the product quality index data, with the goal of optimizing the optimal fermentation time of soy sauce and the overall production quality of the fermentation tank group, a dynamic management mathematical model is established, and a genetic algorithm is used to calculate the solution of the optimization goal to realize the intelligent management of the fermentation tank group.

[0019] The third object of the present invention can be achieved by adopting the following technical solutions: A terminal device comprises a processor and a memory for storing a program executable by the processor. When the processor executes the program stored in the memory, the above-mentioned intelligent management method of a fermentation tank group based on the optimal fermentation time of soy sauce is implemented.

[0020] The fourth object of the present invention can be achieved by adopting the following technical solutions: A computer-readable storage medium stores a program, and when the program is executed by a processor, the above-mentioned intelligent management method of a fermentation tank group based on the optimal fermentation time of soy sauce is implemented.

[0021] The present invention has the following beneficial effects compared with the prior art: The present invention utilizes an intelligent algorithm combining big data, a neural network model and a genetic algorithm to achieve optimal overall product quality indicators of a fermentation tank group by calculating the optimal fermentation time of soy sauce, thereby maximizing the production efficiency of the fermentation tank group. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0023] Figure 1 This is a flow chart of an intelligent management method for a fermentation tank group based on optimal fermentation time of soy sauce according to Example 1 of the present invention; Figure 2 This is a schematic diagram of an intelligent management method for a fermentation tank group based on optimal fermentation time of soy sauce according to Example 1 of the present invention; Figure 3 This is a schematic diagram of the structure of a neural network model according to Embodiment 1 of the present invention; Figure 4 This is a flow chart of a genetic algorithm for dynamic management of a fermentation tank group according to Example 1 of the present invention; Figure 5 This is a structural block diagram of an intelligent management system for a fermentation tank group based on optimal fermentation time of soy sauce according to Example 2 of the present invention; Figure 6 This is a structural block diagram of the terminal device of embodiment 3 of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should be understood that the specific embodiments described are only used to explain the present application and are not used to limit the present application.

[0025] Embodiment 1: The present embodiment provides an intelligent management method for a fermentation tank group based on the optimal fermentation time of soy sauce. First, historical production data of the fermentation tank group is obtained, and pre-processed such as cleaning, conversion and standardization are performed on it; then, the Spearman rank correlation coefficient is calculated to calculate the correlation between the quality index of the fermentation product and the fermentation process data, and the influence of each process data on the quality index of the fermentation product is analyzed; then, the mathematical relationship between each process data and the product quality index is calculated through a neural network; with the optimization of the optimal fermentation time of soy sauce and the overall production quality of the fermentation tank group as the goal, a mathematical model is established, and the mathematical relationship between the production data and process data of the fermentation tank group collected in real time and the product quality index is combined, and the solution of the optimization target is calculated through a genetic algorithm to realize the intelligent management of the fermentation tank group.

[0026] like Figure 1 , 2 As shown, the intelligent management method of a fermentation tank group based on the optimal fermentation time of soy sauce provided in this embodiment comprises the following steps: S101. Collect and store production data of a fermentation tank group as historical production data of the fermentation tank group; wherein the production data includes fermentation process data and product quality index data.

[0027] The data that needs to be collected during the fermentation tank group production process include: 1) T I - Temperature inside the fermentation tank, detecting the material temperature at different times during the fermentation process in the fermentation tank; 2) I—light intensity, detects the sunlight intensity at different times during the fermentation process of the fermenter; 3) T o - Atmospheric temperature, detect the atmospheric temperature at different times during the fermentation process of the fermenter; 4) RH—atmospheric humidity, detects the atmospheric humidity at different times during the fermentation process of the fermenter; 5) D—Production date, which records the dates of different stages of the fermentation process in the fermenter; 6) ANN—ammonia nitrogen content of soy sauce, one of the important indicators of product quality of fermented soy sauce; 7) TNN—total nitrogen content of soy sauce, one of the important indicators of product quality of fermented soy sauce.

[0028] The above fermentation tank production process data is collected in real time through a computer-controlled data acquisition system and stored in a database as the basis for big data analysis of the fermentation tank group production.

[0029] In addition to collecting the above fermentation tank group production process data, the data acquisition system also needs to record the following data: 1) PR—row position of the tank area where the fermentation tank is located; 2) PC—The column position of the tank area where the fermentation tank is located.

[0030] S102, pre-processing the historical production data of the fermentation tank group.

[0031] Before data analysis, the historical production data of the fermentation tank group needs to be preprocessed to meet the requirements of analysis and calculation. Data preprocessing includes: 1) Data cleaning.

[0032] Remove data points where ammonia nitrogen is negatively correlated with time, and temperature, humidity, and light conditions that do not conform to natural laws.

[0033] The ANN and TNN after data cleaning are the preprocessed product quality index data.

[0034] 2) Data standardization processing.

[0035] For each fermenter, T I The data of (temperature in the fermentation tank) are integrated to obtain ∫T I ; Integrate the I (light intensity) data of each fermenter every day to obtain ∫I; For each fermenter, T o (atmospheric temperature) data is integrated to obtain ∫T o ; The RH (atmospheric humidity) data of each fermenter every day was integrated to obtain ∫RH; The PR (row position) and PC (column position) data of each fermenter were classified and digitized to obtain the PR-PC parameters of the fermenter.

[0036] ∫T I , ∫I, ∫T o , ∫RH, D, and PR–PC are the fermentation process data after pretreatment.

[0037] 3) Use big data to establish an annual temperature, humidity and light database as the basic data for trend data prediction.

[0038] S103. Calculate the correlation coefficient between the fermentation process data and the product quality index based on the historical production data after pretreatment.

[0039] The influence of each fermentation process data on product quality indicators varies. The influence of each fermentation process data on product quality indicators can be analyzed by calculating the Spearman rank correlation coefficient.

[0040] ∫T I , ∫I, ∫T o, ∫RH, D, PR-PC, respectively, are paired with ANN and TNN in turn, and the Spearman rank correlation coefficient calculation formula is used to calculate ∫T I , ∫I, ∫T o , ∫RH, D, PR-PC parameters and the Spearman rank correlation coefficient calculation values ​​of ANN and TNN.

[0041] The Spearman rank correlation coefficient calculation formula is as follows: Where: d i —The rank difference of the i-th pair of data; n—The total number of pairs.

[0042] The correlation analysis between each fermentation process data and product quality indicators is based on the following: Positive value: When the Spearman rank correlation coefficient is positive, it indicates that there is a positive correlation between the ranks of the two variables, that is, if the rank of one variable increases, the rank of the other variable also tends to increase.

[0043] Negative value: When the Spearman rank correlation coefficient is negative, it indicates that there is a negative correlation between the ranks of the two variables, that is, when the rank of one variable increases, the rank of the other variable tends to decrease.

[0044] Zero Value: When the Spearman rank correlation coefficient is zero, it indicates that there is no monotonic relationship between the ranks of the two variables.

[0045] The calculation of the Spearman rank correlation coefficient provides an important reference for the subsequent mathematical relationship fitting between the fermentation production process data and the product quality index, reduces the complexity of the fitting calculation, and improves the calculation efficiency of the system.

[0046] S104. Use the pre-processed historical production data as sample data and adopt the gradient descent algorithm to train the neural network model; when taking values ​​of the gradient descent algorithm, select the iterative calculation step size according to the correlation coefficient.

[0047] The daily fermentation process data of each fermentation tank after pretreatment is input into the neural network model, and the neural network model outputs the predicted product quality index data.

[0048] According to the historical production data after pretreatment, the fermentation process data (∫T I , ∫I, ∫T o , ∫RH, D, PR-PC) and product quality index data (ANN, TNN) is a key link in the intelligent management of fermentation tank groups and also a link with a large amount of calculation workload. The trained neural network model can determine the fermentation process data (∫T I , ∫I, ∫To , ∫RH, D, PR-PC) and product quality index data (ANN, TNN).

[0049] At different stages of soy sauce fermentation, the mathematical relationship between the fermentation process data and the product quality data varies greatly. If a relationship is used to represent the mathematical relationship between the fermentation process data and the product quality data of the entire soy sauce fermentation cycle of a fermentation tank, this relationship will be very complicated and the effect may not be good.

[0050] In this embodiment, the soy sauce fermentation cycle is divided into three independent stages, namely the initial fermentation stage, the middle fermentation stage and the final fermentation stage, which respectively account for about 1 / 4, 1 / 2 and 1 / 4 of the complete fermentation cycle, calculated in days. Three neural network models (different mathematical relationships) are used to represent the mathematical relationship between the fermentation process data and the product quality data of the three stages.

[0051] The construction and training methods of the three neural network models are the same. The following takes one of them as an example to illustrate: 1) Establish a neural network model for the relationship between fermentation process data and product quality index data.

[0052] Create a neuron mathematical expression: Where: — the jth neuron in the lth layer; — the number of neurons in the (l1)th layer; —The weight from the i-th neuron in the (l1)-th layer to the j-th neuron in the l-th layer; —The output of the i-th neuron in the (l1)-th layer; —The bias term of the jth neuron in the lth layer; g() — activation function.

[0053] like Figure 3 As shown, a two-layer neural network is used to represent the mathematical relationship between fermentation process data and product quality index data. The mathematical relationship of the neural network is as follows: in, is the input layer neuron, corresponding to the fermentation process data (∫T I , ∫I, ∫T o ,∫RH,D,PR-PC); is the middle layer neuron; z jis the output layer neuron, corresponding to the predicted product quality index data (ANN, TNN).

[0054] 2) Train the neural network model.

[0055] First construct the loss function: loss=(yp-y) 2 Where: loss—loss function value; yp—predicted value output by the neural network model, yp=z j ; y—actual value of product quality index, that is, product quality index data.

[0056] The pre-processed historical production data is used to train the neural network model through the gradient descent algorithm, so that the sum of the loss values ​​of all training data is as small as possible. According to the numerical value of the correlation coefficient between each fermentation process data and the product quality index data calculated in step S103, when the gradient descent algorithm is used for value selection, an appropriate step length is selected for the step value of the weight of the fermentation process data: 0.01 times the initial weight coefficient of the fermentation process data is used as the initial step length; the absolute value of the correlation coefficient is sorted from small to large, and the absolute value of the correlation coefficient is below the median value, and the corresponding step length is increased to 2~5 times; the absolute value of the correlation coefficient is above the median value, and the corresponding step length is reduced to 0.1~0.5 times; the training efficiency can be improved.

[0057] S105. Based on the fermentation process data of the fermentation tank group collected in real time, the trained neural network model is used to output the predicted product quality index data of the fermentation tank group; based on the product quality index data, with the optimal fermentation time of soy sauce and the optimization of the overall production quality of the fermentation tank group as the goal, a dynamic management mathematical model is established, and a genetic algorithm is used to calculate the solution of the optimization goal to realize the intelligent management of the fermentation tank group.

[0058] like Figure 4 As shown in the figure, the dynamic management genetic algorithm process of the fermentation tank group is as follows: 1) Establish a dynamic management mathematical model for the fermentation tank group.

[0059] The goal of dynamic management of the fermentation tank group is to optimize the overall product quality index of the fermentation tank group, which is used to evaluate the individual fitness of the genetic algorithm, and to establish the dynamic management mathematical model of the fermentation tank group as follows: Where: g1—ANN quality index and function of the fermenter group participating in the genetic algorithm calculation of the fermenter; n—the number of fermenters in the fermenter group that participate in the genetic algorithm calculation; ANN i - The ANN prediction value of the i-th tank fermenter; using the neural network model trained in step S104 and the fermentation process data of the i-th tank fermenter collected in real time, the ANN prediction value of the i-th tank is calculated; g2—TNN quality index and function of the fermenter group participating in the genetic algorithm calculation of the fermenter; TNN i - TNN prediction value of the i-th tank fermenter; using the neural network model trained in step S104 and the fermentation process data of the i-th tank fermenter collected in real time, the TNN prediction value of the i-th tank is calculated; g3—the overall index function of product quality of the fermentation tank group participating in the genetic algorithm calculation; a—weight coefficient of the total amount of ANN prediction value; b—The weight coefficient of the total amount of TNN prediction value.

[0060] 2) Chromosome encoding. The fermentation tanks involved in the calculation are regarded as chromosomes, and the number of fermentation tanks involved in the calculation is the number of chromosomes in the algorithm.

[0061] 3) Initialize the chromosome individuals and generate the initial population.

[0062] 4) Decode the chromosomes, calculate the fitness of each individual, and evaluate the individual fitness value.

[0063] 5) Determine whether the termination condition is met. If so, output the optimization calculation result; otherwise, go to 6).

[0064] 6) Select the next generation population based on the selection strategy.

[0065] 7) Individuals undergo crossover operations according to the crossover probability.

[0066] 8) Individuals perform mutation operations according to the mutation probability.

[0067] 9) Generate a new generation of population and return to 4).

[0068] like Figure 2As shown, the method provided in this embodiment can be implemented by a fermentation tank group intelligent management system terminal and a fermentation online control system. The fermentation online control system is the main control system for the production of the fermentation tank group. It collects production-related data of the fermentation tank group in real time, and realizes the fermentation tank production operation control by controlling the valves, delivery pumps and various actuator motors of the fermentation tank group. The fermentation tank group intelligent management system terminal is a terminal device, which receives the fermentation production data sent by the fermentation online control system through the communication port, and the algorithm calculation of each functional module of the fermentation tank group intelligent management system can be completed on the terminal device. The terminal device transmits the final optimization calculation results to the fermentation online control system, and the online control system completes the final fermentation tank production operation control.

[0069] Those skilled in the art will appreciate that all or part of the steps in the method for implementing the above embodiments may be completed by instructing related hardware through a program, and the corresponding program may be stored in a computer-readable storage medium.

[0070] It should be noted that although the method operations of the above embodiments are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted can be performed in a different order. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0071] Embodiment 2: like Figure 5 As shown, this embodiment provides an intelligent management system for a fermentation tank group based on the optimal fermentation time of soy sauce, including a data acquisition module 501, a data preprocessing module 502, a correlation coefficient calculation module 503, a model training module 504 and a dynamic management module 505, wherein: The data collection module 501 is used to collect and store the production data of the fermentation tank group as the historical production data of the fermentation tank group; wherein the production data includes fermentation process data and product quality index data; A data preprocessing module 502 is used to preprocess the historical production data of the fermentation tank group; A correlation coefficient calculation module 503 is used to calculate the correlation coefficient between the fermentation process data and the product quality index based on the pre-processed historical production data; The model training module 504 is used to establish a neural network model of the mathematical relationship between the fermentation process data and the product quality index data based on the preprocessed historical production data; the preprocessed historical production data is used as sample data, and the neural network model is trained using a gradient descent algorithm; wherein, when the gradient descent algorithm is used to select the value, the iterative calculation step length is selected according to the correlation coefficient between the fermentation process data and the product quality index data to improve the calculation efficiency; The dynamic management module 505 is used to output the predicted product quality index data of the fermentation tank group based on the fermentation process data of the fermentation tank group collected in real time by using the trained neural network model; based on the product quality index data, with the goal of optimizing the optimal fermentation time of soy sauce and the overall production quality of the fermentation tank group, a dynamic management mathematical model is established, and a genetic algorithm is used to calculate the solution of the optimization goal to realize the intelligent management of the fermentation tank group.

[0072] The specific implementation of each module in this embodiment can refer to the above-mentioned embodiment 1, which will not be described one by one here; it should be noted that the system provided in this embodiment is only illustrated by the division of the above-mentioned functional modules. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure can be divided into different functional modules to complete all or part of the functions described above.

[0073] Embodiment 3: This embodiment provides a terminal device, which can be a computer. Figure 6 As shown, a processor 602, a memory, an input device 603, a display 604 and a network interface 605 connected via a system bus 601 are provided. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium 606 and an internal memory 607. The non-volatile storage medium 606 stores an operating system, a computer program and a database. The internal memory 607 provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. When the processor 602 executes the computer program stored in the memory, the intelligent management method for a fermentation tank group based on the optimal fermentation time of soy sauce in the above-mentioned embodiment 1 is implemented as follows: Collecting and storing production data of the fermentation tank group as historical production data of the fermentation tank group; wherein the production data includes fermentation process data and product quality index data; Preprocess the historical production data of the fermentation tank group; Based on the historical production data after pretreatment, the correlation coefficient between the fermentation process data and the product quality index is calculated; According to the pre-processed historical production data, a neural network model of the mathematical relationship between the fermentation process data and the product quality index data is established; the pre-processed historical production data is used as sample data, and the neural network model is trained using the gradient descent algorithm; when the gradient descent algorithm is used to select the value, the iterative calculation step length is selected according to the correlation coefficient between the fermentation process data and the product quality index data to improve the calculation efficiency; Based on the fermentation process data of the fermentation tank group collected in real time, the trained neural network model is used to output the predicted product quality index data of the fermentation tank group; based on the product quality index data, with the goal of optimizing the best fermentation time of soy sauce and the overall production quality of the fermentation tank group, a dynamic management mathematical model is established, and a genetic algorithm is used to calculate the solution of the optimization goal to realize the intelligent management of the fermentation tank group.

[0074] Embodiment 4: This embodiment provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the method for intelligent management of a fermentation tank group based on optimal fermentation time of soy sauce in the above-mentioned embodiment 1 is implemented as follows: Collecting and storing production data of the fermentation tank group as historical production data of the fermentation tank group; wherein the production data includes fermentation process data and product quality index data; Preprocess the historical production data of the fermentation tank group; Based on the historical production data after pretreatment, the correlation coefficient between the fermentation process data and the product quality index is calculated; According to the pre-processed historical production data, a neural network model of the mathematical relationship between the fermentation process data and the product quality index data is established; the pre-processed historical production data is used as sample data, and the neural network model is trained using the gradient descent algorithm; when the gradient descent algorithm is used to select the value, the iterative calculation step length is selected according to the correlation coefficient between the fermentation process data and the product quality index data to improve the calculation efficiency; Based on the fermentation process data of the fermentation tank group collected in real time, the trained neural network model is used to output the predicted product quality index data of the fermentation tank group; based on the product quality index data, with the goal of optimizing the best fermentation time of soy sauce and the overall production quality of the fermentation tank group, a dynamic management mathematical model is established, and a genetic algorithm is used to calculate the solution of the optimization goal to realize the intelligent management of the fermentation tank group.

[0075] It should be noted that the computer-readable storage medium of the present embodiment may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0076] The above is only a preferred embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solution and inventive concept of the present invention within the scope disclosed by the present invention, which shall fall within the protection scope of the present invention.

Claims

1. An intelligent management method for a fermentation tank group based on the optimal fermentation time of soy sauce, characterized in that: The method comprises: Collecting and storing production data of the fermentation tank group as historical production data of the fermentation tank group; wherein the production data includes fermentation process data and product quality index data; Preprocess the historical production data of the fermentation tank group; Based on the historical production data after pretreatment, the correlation coefficient between the fermentation process data and the product quality index is calculated; According to the pre-processed historical production data, a neural network model of the mathematical relationship between the fermentation process data and the product quality index data is established; the pre-processed historical production data is used as sample data, and the neural network model is trained using the gradient descent algorithm; when the gradient descent algorithm is used to select the value, the iterative calculation step length is selected according to the correlation coefficient between the fermentation process data and the product quality index data to improve the calculation efficiency; Based on the fermentation process data of the fermentation tank group collected in real time, the trained neural network model is used to output the predicted product quality index data of the fermentation tank group; based on the product quality index data, with the goal of optimizing the best fermentation time of soy sauce and the overall production quality of the fermentation tank group, a dynamic management mathematical model is established, and a genetic algorithm is used to calculate the solution of the optimization goal to realize the intelligent management of the fermentation tank group.

2. The fermentation tank group intelligent management method according to claim 1, characterized in that: The product quality index data include soy sauce ammonia nitrogen content ANN and soy sauce total nitrogen content TNN; The dynamic management mathematical model is: Where g1 and g2 are the ANN quality index and TNN quality index of the fermentation tanks involved in the genetic algorithm calculation, n is the total number of fermentation tanks involved in the genetic algorithm calculation, and ANN i 、TNN i are the predicted ANN and TNN of the i-th fermenter respectively; g3 is the overall product quality index of the fermenter group participating in the genetic algorithm calculation; a and b are the weight coefficients of the predicted total ANN and total TNN respectively.

3. The intelligent management method for a fermentation tank group according to any one of claims 1 and 2, characterized in that: In the genetic algorithm, the fermentation tanks participating in the genetic algorithm calculation are regarded as chromosomes, and the total number of all fermentation tanks participating in the genetic algorithm calculation is the number of chromosomes.

4. The intelligent management method for a fermentation tank group according to claim 1, characterized in that: The pre-processed historical production data is used as sample data, and a gradient descent algorithm is used to train a neural network model, including: The soy sauce fermentation cycle is divided into three independent fermentation stages: the initial fermentation stage, the middle fermentation stage and the final fermentation stage; each fermentation stage corresponds to a neural network model, that is, a neural network model is trained using the historical production data of a fermentation stage; The construction and training methods of the three neural network models are the same, and one of the neural network models is used for illustration: The input layer neurons are fermentation process data from preprocessed historical production data; The output layer neurons are the predicted product quality index data; The square of the difference between the predicted product quality index data and the product quality index data in the preprocessed historical production data is used as the loss function, and the gradient descent algorithm is used to train the neural network model.

5. The intelligent management method for a fermentation tank group according to claim 4, characterized in that: The method of outputting predicted product quality index data of the fermentation tank group using the trained neural network model based on the fermentation process data of the fermentation tank group collected in real time includes: According to the real-time acquisition time, the fermentation stage is determined, and then the corresponding trained neural network model is determined; The fermentation process data of the fermentation tank group collected in real time is preprocessed and then input into the determined neural network model to output the predicted product quality index data.

6. The intelligent management method for a fermentation tank group according to any one of claims 1 and 5, characterized in that: The fermentation process data include the temperature in the fermentation tank, light intensity, atmospheric temperature, atmospheric humidity, production date, and the row and column position of the fermentation tank in the tank area, and the product quality index data include the ammonia nitrogen content of soy sauce and the total nitrogen content of soy sauce; The preprocessing includes data cleaning and data standardization, wherein: Data cleaning includes: removing data that shows a negative correlation between ammonia nitrogen and time, as well as data points with temperature, humidity and light conditions that do not conform to natural laws; The data standardization process includes: integrating the temperature inside the fermentation tank, light intensity, atmospheric temperature, and atmospheric humidity of each fermentation tank every day, and classifying and digitizing the row and column positions of each fermentation tank.

7. The intelligent management method for a fermentation tank group according to any one of claims 1 and 4, characterized in that: The step of selecting the iterative calculation step according to the correlation coefficient between the fermentation process data and the product quality index data comprises: When the gradient descent algorithm is used to select values, an appropriate step length is selected for the step value of the weight of the pre-processed fermentation process data: when the absolute value of the correlation coefficient is small, the step length is appropriately increased; when the absolute value of the correlation coefficient is large, the step length is appropriately decreased.

8. The intelligent management method for a fermentation tank group according to claim 1, characterized in that: The correlation coefficient was calculated using the Spearman rank correlation coefficient.

9. An intelligent management system for fermentation tank groups based on optimal fermentation time of soy sauce, characterized in that: The system comprises: A data acquisition module is used to collect and store the production data of the fermentation tank group as the historical production data of the fermentation tank group; wherein the production data includes fermentation process data and product quality index data; A data preprocessing module is used to preprocess the historical production data of the fermentation tank group; A correlation coefficient calculation module is used to calculate the correlation coefficient between fermentation process data and product quality indicators based on pre-processed historical production data; The model training module is used to establish a neural network model of the mathematical relationship between the fermentation process data and the product quality index data based on the pre-processed historical production data; the pre-processed historical production data is used as sample data, and the neural network model is trained using a gradient descent algorithm; when the gradient descent algorithm is used to select the value, the iterative calculation step length is selected according to the correlation coefficient between the fermentation process data and the product quality index data to improve the calculation efficiency; The dynamic management module is used to output the predicted product quality index data of the fermentation tank group based on the fermentation process data of the fermentation tank group collected in real time by using the trained neural network model; based on the product quality index data, with the goal of optimizing the optimal fermentation time of soy sauce and the overall production quality of the fermentation tank group, a dynamic management mathematical model is established, and a genetic algorithm is used to calculate the solution of the optimization goal to realize the intelligent management of the fermentation tank group.

10. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the intelligent management method for a fermentation tank group as described in any one of claims 1 to 8.

Images