Optimized control method and system of vinasse conveying mechanism for wine making

Abstract

The invention relates to an optimal control method and system for a vinasse conveying mechanism for wine brewing, and the method comprises the steps: M1, collecting the data information of historical working state parameters of the vinasse conveying mechanism in the working process of the vinasse conveying mechanism for wine brewing, and obtaining the data information of the vinasse access amount and the data information of the vinasse output amount in real time, and predicting the work bearing capacity of the vinasse conveying mechanism by adopting an improved time sequence prediction algorithm based on an LTTM (Long Short-Term Memory) neural network to obtain predicted data information of the work bearing capacity of the vinasse conveying mechanism. According to the method, the LTTM can be utilized to effectively capture the long-term dependency relationship, and the gradient disappearance problem of traditional TNN is avoided through a gating mechanism of the LTTM, so that the working time sequence data of the vinasse conveying mechanism can be processed, intelligent adjustment can be performed according to the input quantity of the vinasse, the energy consumption is reduced, and the vinasse conveying efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of distiller's grains conveying equipment control, and in particular to an optimized control method and system for a distiller's grains conveying mechanism for brewing. Background Art

[0002] In the production process of brewing, a large amount of distiller's grains will be produced. Distiller's grains, also known as red distiller's grains, fermented grains, dregs, etc., are the residues remaining after brewing rice, wheat, sorghum, etc. Among them, the crude protein content can reach about 25%. It is a good choice to use it as feed for cows or other animals. However, directly feeding distiller's grains to cows or other animals not only fails to fully utilize the nutritional value, but also has a poor taste. Therefore, it is safer and better to ferment it with a lactic acid bacteria fermenting agent before feeding cows or other animals. Such feed has more complete nutrition and better taste.

[0003] Thus, during the production process of distiller's grains, when the distiller's grains are transported in batches for bagging and selling, a distiller's grains conveying mechanism is required, including a receiving hopper, a conveying component, and a discharging hopper. The distiller's grains enter the receiving hopper and reach the discharging hopper after being conveyed by the conveying component. During this process, the incoming quantity of the receiving hopper and the outgoing quantity of the discharging hopper cannot be coordinated. When the incoming quantity is small and the conveying efficiency of the conveying component is high, it will lead to energy consumption. When the incoming quantity is large and the conveying efficiency of the conveying component is low, it will lead to a small outgoing quantity, reducing the overall conveying efficiency of the distiller's grains. Therefore, how to optimize the control of the distiller's grains conveying mechanism has become an urgent problem for us to solve. Summary of the Invention

[0004] In view of the above problems, the present invention provides an optimized control method and system for a distiller's grains conveying mechanism for brewing, which can not only effectively capture long-term dependencies by using LTTM and avoid the gradient disappearance problem of the traditional TNN through its gating mechanism, thereby being able to process the working time series data of the distiller's grains conveying mechanism, but also can be intelligently adjusted according to the input quantity of the distiller's grains, reducing energy consumption and improving the conveying efficiency of the distiller's grains.

[0005] To achieve the above object and other related objects, the technical solutions provided by the present invention are as follows:

[0006] An optimized control method for a distiller's grains conveying mechanism for brewing, the method comprising:

[0007] M1. During the working process of the distiller's grains conveying mechanism for brewing, collect the data information of the historical working state parameters of the distiller's grains conveying mechanism, and obtain the data information of the incoming quantity of the distiller's grains and the data information of the outgoing quantity of the distiller's grains in real time;

[0008] M2. Based on the data information of the distillers' grains access volume and the data information of the distillers' grains output volume, an improved time series prediction algorithm based on the LTTM long short-term memory neural network is used to predict the working load capacity of the distillers' grains conveying mechanism, and the data information of the predicted working load capacity of the distillers' grains conveying mechanism is obtained;

[0009] M3. Based on the data information of the predicted working load capacity of the distillers' grains conveying mechanism and the data information of the historical working state parameters of the distillers' grains conveying mechanism, an improved salp swarm optimization algorithm based on chaotic mapping is used to optimize the working parameters of the distillers' grains conveying mechanism, and the data information of the optimized working parameters of the distillers' grains conveying mechanism is obtained;

[0010] M4. Based on the data information of the optimized working parameters of the distillers' grains conveying mechanism, an optimized control function R of the distillers' grains conveying mechanism is constructed, and the control parameters of each component of the distillers' grains conveying mechanism are deduced to obtain the data information of the optimized control of the distillers' grains conveying mechanism.

[0011] Further, in step M2, the use of the improved time series prediction algorithm based on the LTTM long short-term memory neural network to predict the working load capacity of the distillers' grains conveying mechanism includes:

[0012] M21. Based on the data information of the distillers' grains access volume and the data information of the distillers' grains output volume, a dynamic characterization function Q of the distillers' grains access volume and output volume is established,

[0013]

[0014] where x is the data information of the distillers' grains access volume, y is the data information of the distillers' grains output volume, and α1, α2, and α3 are weight coefficients, which characterize the dynamic time series of the distillers' grains access volume and output volume to obtain the data information of the dynamic time series of the distillers' grains access volume and output volume;

[0015] M22. Input the data information of the dynamic time series of the distillers' grains access volume and output volume into the LTTM long short-term memory neural network model for training and learning to determine the prediction function W of the working load capacity of the distillers' grains conveying mechanism of the model,

[0016]

[0017] where z is the data information of the dynamic time series of the distillers' grains access volume and output volume, and β1, β2, and β3 are the bias parameters of the neurons to obtain a trained LTTM long short-term memory neural network model;

[0018] M23. Based on the trained LTTM long short-term memory neural network model, input the data information of the dynamic time series of the distiller's grains access amount and output amount, predict the working load capacity of the distiller's grains conveying mechanism, and obtain the data information of the predicted working load capacity of the distiller's grains conveying mechanism.

[0019] Further, the bias parameters β1, β2, and β3 of the neuron are

[0020]

[0021]

[0022] where z is the data information of the dynamic time series of the distiller's grains access amount and output amount.

[0023] Further, the constraint function f of the weight coefficients α1, α2, and α3 is

[0024]

[0025] where the value range of the constraint function f is (0, 1).

[0026] Further, in step M3, the use of the improved salp swarm optimization algorithm based on chaotic mapping to optimize the working parameters of the distiller's grains conveying mechanism includes:

[0027] M31. Based on the data information of the predicted working load capacity of the distiller's grains conveying mechanism and the data information of the historical working state parameters of the distiller's grains conveying mechanism, construct a chaotic mapping function P of the working state of the distiller's grains conveying mechanism,

[0028]

[0029] where r1 is the data information of the predicted working load capacity of the distiller's grains conveying mechanism, r2 is the data information of the historical working state parameters of the distiller's grains conveying mechanism, and δ1, δ2, and δ3 are constant parameters of the chaotic mapping, which characterize the chaotic mapping sequence of the working state of the distiller's grains conveying mechanism, and obtain the data information of the chaotic mapping sequence of the working state of the distiller's grains conveying mechanism;

[0030] M32. Based on the data information of the chaotic mapping sequence of the working state of the distiller's grains conveying mechanism, initialize the salp swarm, determine the population parameters and the maximum number of iterations L, and obtain the data information of the initialized salp population;

[0031] M33. Based on the data information of the initialized salp population, establish a fitness function S for the population individuals,

[0032]

[0033] Among them, q is the data information of the initialized salp swarm population, and the fitness value of the population individuals is deduced to obtain the data information of the fitness value of the population individuals;

[0034] M34. Based on the data information of the fitness value of the population individuals, a target optimization function F is established,

[0035]

[0036] Among them, a is the data information of the fitness value of the population individuals, λ1, λ2, and λ3 are optimization constant parameters, and the working parameters of the distiller's grains conveying mechanism are optimized to obtain the data information of the optimized working parameters of the distiller's grains conveying mechanism.

[0037] Further, the optimization constant parameters λ1, λ2, and λ3 are,

[0038]

[0039] Among them, a is the data information of the fitness value of the population individuals.

[0040] Further, the optimization control function R of the distiller's grains conveying mechanism is,

[0041]

[0042] Among them, g is the data information of the optimized working parameters of the distiller's grains conveying mechanism, and μ1, μ2, and μ3 are the fuzzy control factors of the distiller's grains conveying mechanism.

[0043] Further, the fuzzy control factors μ1, μ2, and μ3 of the distiller's grains conveying mechanism are,

[0044]

[0045] Among them, g is the data information of the optimized working parameters of the distiller's grains conveying mechanism.

[0046] To achieve the above and other related purposes, the present invention also provides a system for implementing the optimization control method of the distiller's grains conveying mechanism for brewing described in any one of the above, and the system includes:

[0047] A working data acquisition module of the distiller's grains conveying mechanism, which is used to collect the data information of the historical working state parameters of the distiller's grains conveying mechanism, and to obtain the data information of the distiller's grains access amount and the data information of the distiller's grains output amount in real time;

[0048] The prediction module for the carrying capacity of the distillers' grains conveying mechanism, which is connected to the working data acquisition module of the distillers' grains conveying mechanism, is used to predict the working carrying capacity of the distillers' grains conveying mechanism by using an improved time series prediction algorithm based on the LTTM long short-term memory neural network, and obtain the data information of the predicted working carrying capacity of the distillers' grains conveying mechanism;

[0049] The working parameter optimization module of the distillers' grains conveying mechanism, which is connected to the prediction module for the carrying capacity of the distillers' grains conveying mechanism, is used to optimize the working parameters of the distillers' grains conveying mechanism by using an improved salp swarm optimization algorithm based on chaotic mapping, and obtain the data information of the optimized working parameters of the distillers' grains conveying mechanism;

[0050] The optimization control module of the distillers' grains conveying mechanism, which is connected to the working parameter optimization module of the distillers' grains conveying mechanism, is used to construct the optimization control function R of the distillers' grains conveying mechanism, calculate the control parameters of each component of the distillers' grains conveying mechanism, and obtain the data information of the optimization control of the distillers' grains conveying mechanism.

[0051] To achieve the above and other related purposes, the present invention also provides a computer-readable storage medium, on which a computer program is stored that is programmed or configured to execute the optimization control method of the distillers' grains conveying mechanism for brewing according to any one of the above.

[0052] The present invention has the following positive effects:

[0053] 1. By using an improved time series prediction algorithm based on the LTTM long short-term memory neural network to predict the working carrying capacity of the distillers' grains conveying mechanism and combining with an improved salp swarm optimization algorithm based on chaotic mapping to optimize the working parameters of the distillers' grains conveying mechanism, the present invention can not only effectively capture long-term dependencies by LTTM and avoid the gradient disappearance problem of the traditional TNN through its gating mechanism, so as to be able to process the working time series data of the distillers' grains conveying mechanism, but also optimize the working parameters of the distillers' grains conveying mechanism to ensure the stability of the distillers' grains conveying process, thereby improving the overall conveying efficiency of the distillers' grains and reducing energy loss.

[0054] 2. By constructing the optimization control function R of the distillers' grains conveying mechanism and calculating the control parameters of each component of the distillers' grains conveying mechanism, the present invention can not only make intelligent adjustments according to the input amount of the distillers' grains, reduce energy consumption and improve the conveying efficiency of the distillers' grains, but also does not require manual participation throughout the process, reducing the labor intensity and cost of labor. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a schematic flow chart of the method of the present invention;

[0056] Figure 2Schematic flow chart of the improved time series prediction algorithm based on the LTTM long short-term memory neural network of the present invention;

[0057] Figure 3 Schematic flow chart of the improved salp swarm optimization algorithm based on chaotic mapping of the present invention;

[0058] Figure 4 Schematic diagram of the system framework of the present invention;

[0059] Figure 5 Schematic diagram of the structure of the distillers' grains conveying mechanism of the present invention.

[0060] Description of reference numerals in the figure: 1 - receiving hopper, 2 - discharging hopper, 3 - conveying component. Detailed implementation manners

[0061] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0062] Embodiment 1: As Figure 1 shown, an optimization control method for a distillers' grains conveying mechanism for brewing, the method includes:

[0063] M1. During the working process of the distillers' grains conveying mechanism for brewing, collect the data information of the historical working state parameters of the distillers' grains conveying mechanism, and obtain the data information of the distillers' grains access amount and the data information of the distillers' grains output amount in real time;

[0064] M2. Based on the data information of the distillers' grains access amount and the data information of the distillers' grains output amount, use the improved time series prediction algorithm based on the LTTM long short-term memory neural network to predict the working load capacity of the distillers' grains conveying mechanism, and obtain the data information of the predicted working load capacity of the distillers' grains conveying mechanism;

[0065] M3. Based on the data information of the predicted working load capacity of the distillers' grains conveying mechanism and the data information of the historical working state parameters of the distillers' grains conveying mechanism, use the improved salp swarm optimization algorithm based on chaotic mapping to optimize the working parameters of the distillers' grains conveying mechanism, and obtain the data information of the optimized working parameters of the distillers' grains conveying mechanism;

[0066] M4. Based on the data information of the working parameters of the optimized distiller's grains conveying mechanism, construct the optimized control function R of the distiller's grains conveying mechanism, deduce the control parameters of each component of the distiller's grains conveying mechanism, and obtain the data information of the optimized control of the distiller's grains conveying mechanism.

[0067] In this embodiment, as Figure 2 shown, in step M2, the prediction of the working load capacity of the distiller's grains conveying mechanism by using the improved time series prediction algorithm based on the LTTM long short-term memory neural network includes:

[0068] M21. Based on the data information of the distiller's grains access amount and the data information of the distiller's grains output amount, establish the dynamic characterization function Q of the distiller's grains access amount and output amount,

[0069]

[0070] where x is the data information of the distiller's grains access amount, y is the data information of the distiller's grains output amount, and α1, α2, and α3 are weight coefficients, which characterize the dynamic time series of the distiller's grains access amount and output amount, and obtain the data information of the dynamic time series of the distiller's grains access amount and output amount;

[0071] M22. Input the data information of the dynamic time series of the distiller's grains access amount and output amount into the LTTM long short-term memory neural network model for training and learning, and determine the prediction function W of the working load capacity of the distiller's grains conveying mechanism of the model,

[0072]

[0073] where z is the data information of the dynamic time series of the distiller's grains access amount and output amount, and β1, β2, and β3 are the bias parameters of the neurons, and obtain the trained LTTM long short-term memory neural network model;

[0074] M23. Based on the trained LTTM long short-term memory neural network model, input the data information of the dynamic time series of the distiller's grains access amount and output amount, and predict the working load capacity of the distiller's grains conveying mechanism to obtain the data information of the predicted working load capacity of the distiller's grains conveying mechanism.

[0075] In this embodiment, the bias parameters β1, β2, and β3 of the neurons are

[0076]

[0077] where z is the data information of the dynamic time series of the distiller's grains access amount and output amount.

[0078] In this embodiment, the constraint function f of the weight coefficients α1, α2, and α3 is

[0079]

[0080] Among them, the value range of the constraint function f is (0, 1).

[0081] In this embodiment, as Figure 3 shown, in step M3, optimizing the working parameters of the distiller's grains conveying mechanism by using the improved salp swarm optimization algorithm based on chaotic mapping includes:

[0082] M31. Based on the data information of the predicted working load capacity of the distiller's grains conveying mechanism and the data information of the historical working state parameters of the distiller's grains conveying mechanism, construct a chaotic mapping function P of the working state of the distiller's grains conveying mechanism,

[0083]

[0084] Among them, r1 is the data information of the predicted working load capacity of the distiller's grains conveying mechanism, r2 is the data information of the historical working state parameters of the distiller's grains conveying mechanism, and δ1, δ2, and δ3 are constant parameters of the chaotic mapping, which characterize the chaotic mapping sequence of the working state of the distiller's grains conveying mechanism, and obtain the data information of the chaotic mapping sequence of the working state of the distiller's grains conveying mechanism;

[0085] M32. Based on the data information of the chaotic mapping sequence of the working state of the distiller's grains conveying mechanism, initialize the salp swarm, determine the population parameters and the maximum number of iterations L, and obtain the data information of the initialized salp population;

[0086] M33. Based on the data information of the initialized salp population, establish a fitness function S for the population individuals,

[0087]

[0088] Among them, q is the data information of the initialized salp population, and the fitness value of the population individuals is deduced to obtain the data information of the fitness value of the population individuals;

[0089] M34. Based on the data information of the fitness value of the population individuals, establish an objective optimization function F,

[0090]

[0091] Among them, a is the data information of the fitness value of the population individuals, and λ1, λ2, and λ3 are optimization constant parameters, which optimize the working parameters of the distiller's grains conveying mechanism to obtain the data information of the optimized working parameters of the distiller's grains conveying mechanism.

[0092] In this embodiment, the optimization constant parameters λ1, λ2, and λ3 are

[0093]

[0094] Among them, a is the data information of the fitness value of the population individuals.

[0095] Embodiment 2: On the basis of the optimized control method of a distiller's grains conveying mechanism for brewing in Embodiment 1, the present invention will be further described and illustrated below.

[0096] As Figure 1 shown, an optimized control method of a distiller's grains conveying mechanism for brewing, the method includes:

[0097] M1. During the working process of the distiller's grains conveying mechanism for brewing, collect the data information of the historical working state parameters of the distiller's grains conveying mechanism, and obtain the data information of the distiller's grains access amount and the data information of the distiller's grains output amount in real time;

[0098] M2. Based on the data information of the distiller's grains access amount and the data information of the distiller's grains output amount, use an improved time series prediction algorithm based on the LTTM long short-term memory neural network to predict the working load capacity of the distiller's grains conveying mechanism, and obtain the data information of the predicted working load capacity of the distiller's grains conveying mechanism;

[0099] M3. Based on the data information of the predicted working load capacity of the distiller's grains conveying mechanism and the data information of the historical working state parameters of the distiller's grains conveying mechanism, use an improved salp swarm optimization algorithm based on chaotic mapping to optimize the working parameters of the distiller's grains conveying mechanism, and obtain the data information of the optimized working parameters of the distiller's grains conveying mechanism;

[0100] M4. Based on the data information of the optimized working parameters of the distiller's grains conveying mechanism, construct an optimized control function R of the distiller's grains conveying mechanism, calculate the control parameters of each component of the distiller's grains conveying mechanism, and obtain the data information of the optimized control of the distiller's grains conveying mechanism.

[0101] In this embodiment, the optimized control function R of the distiller's grains conveying mechanism is

[0102]

[0103] Among them, g is the data information of the optimized working parameters of the distiller's grains conveying mechanism, and μ1, μ2, and μ3 are the fuzzy control factors of the distiller's grains conveying mechanism.

[0104] In this embodiment, the fuzzy control factors μ1, μ2, and μ3 of the distiller's grains conveying mechanism are

[0105] Among them, g is the data information of the optimized working parameters of the distiller's grains conveying mechanism.

[0106] In this embodiment, as Figure 4 shown, the present invention provides a system for implementing an optimization control method for a distillers' grains conveying mechanism for brewing described in any one of the above, the system comprising:

[0107] A working data acquisition module of the distillers' grains conveying mechanism, configured to collect data information of historical working state parameters of the distillers' grains conveying mechanism, and to obtain in real time data information of the distillers' grains access amount and data information of the distillers' grains output amount;

[0108] A prediction module of the load capacity of the distillers' grains conveying mechanism, connected to the working data acquisition module of the distillers' grains conveying mechanism, and configured to predict the working load capacity of the distillers' grains conveying mechanism by using an improved time series prediction algorithm based on the LTTM long short-term memory neural network, so as to obtain data information of the predicted working load capacity of the distillers' grains conveying mechanism;

[0109] A working parameter optimization module of the distillers' grains conveying mechanism, connected to the prediction module of the load capacity of the distillers' grains conveying mechanism, and configured to optimize the working parameters of the distillers' grains conveying mechanism by using an improved salp swarm optimization algorithm based on chaotic mapping, so as to obtain data information of the optimized working parameters of the distillers' grains conveying mechanism;

[0110] An optimization control module of the distillers' grains conveying mechanism, connected to the working parameter optimization module of the distillers' grains conveying mechanism, and configured to construct an optimization control function R of the distillers' grains conveying mechanism, and to calculate the control parameters of each component of the distillers' grains conveying mechanism, so as to obtain data information of the optimization control of the distillers' grains conveying mechanism.

[0111] In this embodiment, as Figure 5 shown, the distillers' grains conveying mechanism includes a receiving hopper 1, a conveying component 3 and a discharging hopper 2. The distillers' grains enter the receiving hopper 1 and reach the discharging hopper 2 after being conveyed by the conveying component 3.

[0112] In this embodiment, the present invention provides a computer-readable storage medium, on which a computer program is stored that is programmed or configured to execute the optimization control method for a distillers' grains conveying mechanism for brewing described in any one of the above.

[0113] Any reference to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct rambus dynamic RAM (DRDRAM), and rambus dynamic RAM (RDRAM), etc.

[0114] In summary, the present invention can not only effectively capture long-term dependencies using LTTM and avoid the gradient vanishing problem of traditional TNN through its gating mechanism, thereby being able to process the working time series data of the distillers grains conveying mechanism, but also can be intelligently adjusted according to the input amount of distillers grains, reducing energy consumption and improving the conveying efficiency of distillers grains.

[0115] The above specific embodiments do not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. An optimized control method for a distiller's grains conveying mechanism used in wine brewing, characterized in that, The method includes: M1. During the working process of the distillers' grains conveying mechanism for brewing, collect the data information of the historical working state parameters of the distillers' grains conveying mechanism, and obtain the data information of the distillers' grains access amount and the data information of the distillers' grains output amount in real time; M2. Based on the data information of the distillers' grains access amount and the data information of the distillers' grains output amount, use an improved time series prediction algorithm based on the LTTM long short-term memory neural network to predict the working load capacity of the distillers' grains conveying mechanism, and obtain the data information of the predicted working load capacity of the distillers' grains conveying mechanism; M3. Based on the data information of the predicted working load capacity of the distillers' grains conveying mechanism and the data information of the historical working state parameters of the distillers' grains conveying mechanism, use an improved salp swarm optimization algorithm based on chaotic mapping to optimize the working parameters of the distillers' grains conveying mechanism, and obtain the data information of the optimized working parameters of the distillers' grains conveying mechanism; M4. Based on the data information of the optimized working parameters of the distillers' grains conveying mechanism, construct an optimized control function R for the distillers' grains conveying mechanism, deduce the control parameters of each component of the distillers' grains conveying mechanism, and obtain the data information of the optimized control of the distillers' grains conveying mechanism.

2. The optimized control method of the distiller's grains conveying mechanism for brewing according to claim 1, characterized in that, In step M2, the using of the improved time series prediction algorithm based on the LTTM long short-term memory neural network to predict the working load capacity of the distillers' grains conveying mechanism includes: M21. Based on the data information of the distillers' grains access amount and the data information of the distillers' grains output amount, establish a dynamic characterization function Q for the distillers' grains access amount and output amount, where x is the data information of the distillers' grains access amount, y is the data information of the distillers' grains output amount, α1, α2, and α3 are weight coefficients, and the dynamic time series of the distillers' grains access amount and output amount is characterized to obtain the data information of the dynamic time series of the distillers' grains access amount and output amount; M22. Input the data information of the dynamic time series of the distillers' grains access amount and output amount into the LTTM long short-term memory neural network model for training and learning, and determine the prediction function W of the working load capacity of the distillers' grains conveying mechanism of the model, where z is the data information of the dynamic time series of the distillers' grains access amount and output amount, β1, β2, and β3 are the bias parameters of the neurons, and obtain the trained LTTM long short-term memory neural network model; M23. Based on the trained LTTM long short-term memory neural network model, input the data information of the dynamic time series of the distillers' grains access amount and output amount, and predict the working load capacity of the distillers' grains conveying mechanism to obtain the data information of the predicted working load capacity of the distillers' grains conveying mechanism.

3. The optimized control method of the distiller's grains conveying mechanism for brewing according to claim 2, wherein: The bias parameters β1, β2, and β3 of the neurons are where z is the data information of the dynamic time series of the distillers' grains access amount and output amount.

4. The optimized control method of the distiller's grains conveying mechanism for brewing according to claim 2, characterized in that: The constraint function f of the weight coefficients α1, α2, and α3 is where the value range of the constraint function f is (0, 1).

5. The optimized control method of the distiller's grains conveying mechanism for brewing according to claim 1, characterized in that, In step M3, the using of the improved salp swarm optimization algorithm based on chaotic mapping to optimize the working parameters of the distillers' grains conveying mechanism includes: M31. Based on the data information of the predicted working load capacity of the distillers' grains conveying mechanism and the data information of the historical working state parameters of the distillers' grains conveying mechanism, construct the chaotic mapping function P of the working state of the distillers' grains conveying mechanism, where r1 is the data information of the predicted working load capacity of the distillers' grains conveying mechanism, r2 is the data information of the historical working state parameters of the distillers' grains conveying mechanism, and δ1, δ2, and δ3 are the constant parameters of the chaotic mapping, which characterize the chaotic mapping sequence of the working state of the distillers' grains conveying mechanism, and obtain the data information of the chaotic mapping sequence of the working state of the distillers' grains conveying mechanism; M32. Based on the data information of the chaotic mapping sequence of the working state of the distillers' grains conveying mechanism, initialize the salp swarm, determine the population parameters and the maximum number of iterations L, and obtain the data information of the initialized salp population; M33. Based on the data information of the initialized salp population, establish the fitness function S of the population individuals, where q is the data information of the initialized salp population, and calculate the fitness values of the population individuals to obtain the data information of the fitness values of the population individuals; M34. Based on the data information of the fitness values of the population individuals, establish the target optimization function F, where a is the data information of the fitness values of the population individuals, and λ1, λ2, and λ3 are the optimization constant parameters, and optimize the working parameters of the distillers' grains conveying mechanism to obtain the data information of the optimized working parameters of the distillers' grains conveying mechanism.

6. The optimized control method of the distiller's grains conveying mechanism for brewing, characterized in that: The optimization constant parameters λ1, λ2, and λ3 are where a is the data information of the fitness values of the population individuals.

7. The optimized control method for the distiller's grains conveying mechanism used in wine brewing according to claim 1, characterized in that: The optimized control function R of the distillers' grains conveying mechanism is where g is the data information of the optimized working parameters of the distillers' grains conveying mechanism, and μ1, μ2, and μ3 are the fuzzy control factors of the distillers' grains conveying mechanism.

8. The optimized control method for the distiller's grains conveying mechanism for brewing, characterized in that: The fuzzy control factors μ1, μ2, and μ3 of the distillers' grains conveying mechanism are where g is the data information of the optimized working parameters of the distillers' grains conveying mechanism.

9. A system for implementing an optimized control method of the distiller's grains conveying mechanism for brewing as described in any one of claims 1-8, characterized in that, The system includes: The working data acquisition module of the distillers' grains conveying mechanism is used to collect the data information of the historical working state parameters of the distillers' grains conveying mechanism, and to obtain the data information of the distillers' grains access amount and the data information of the distillers' grains output amount in real time; The prediction module of the working load capacity of the distillers' grains conveying mechanism is connected to the working data acquisition module of the distillers' grains conveying mechanism, and is used to predict the working load capacity of the distillers' grains conveying mechanism by using an improved time series prediction algorithm based on the LTTM long short-term memory neural network, and obtain the data information of the predicted working load capacity of the distillers' grains conveying mechanism; The working parameter optimization module of the distillers' grains conveying mechanism is connected to the prediction module of the working load capacity of the distillers' grains conveying mechanism, and is used to optimize the working parameters of the distillers' grains conveying mechanism by using an improved salp swarm optimization algorithm based on chaotic mapping, and obtain the data information of the optimized working parameters of the distillers' grains conveying mechanism; The optimization control module of the distillers' grains conveying mechanism, which is connected to the working parameter optimization module of the distillers' grains conveying mechanism, is used to construct the optimization control function R of the distillers' grains conveying mechanism, calculate the control parameters of each component of the distillers' grains conveying mechanism, and obtain the optimized control data information of the distillers' grains conveying mechanism.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium and is programmed or configured to execute the optimization control method of the distillers' grains conveying mechanism for brewing according to any one of claims 1 to 8.

Images