CN115938518A

CN115938518A - Preparation process optimization method and system of degradable food packaging material

Info

Publication number: CN115938518A
Application number: CN202211675274.1A
Authority: CN
Inventors: 吴国忠; 张玉; 吴梦怡; 吴瑛; 杨静静
Original assignee: Suzhou Heng Fu Packing Product Co ltd
Current assignee: Suzhou Heng Fu Packing Product Co ltd
Priority date: 2022-12-26
Filing date: 2022-12-26
Publication date: 2023-04-07
Anticipated expiration: 2042-12-26
Also published as: CN115938518B

Abstract

The embodiment of the specification provides a preparation process optimization method of a degradable food packaging material, which comprises the steps of obtaining product demand data, wherein the product demand data comprises food storage demand data, food transportation demand data and process demand data; determining a target material property energetication index based on the product demand data; determining a target raw material combination based on the target material property energetic index; the target raw material comprises a support material, a first degradable material and a second degradable material; the first degradable material and the second degradable material both comprise at least one of polybutylene succinate, polylactic acid, polyhydroxyalkanoate and polybutylene adipate-terephthalate; the target raw material combination comprises a support material, a first degradable material and the proportion thereof, and a second degradable material and the proportion thereof; preparation parameters are determined based on the target raw material combination and product demand data.

Description

Preparation process optimization method and system of degradable food packaging material

Technical Field

The specification relates to the field of packaging material preparation, in particular to a preparation process optimization method and system of a degradable food packaging material.

Background

In the field of food package production, a plurality of manufacturers begin to produce degradable food packages, but due to the fact that the cost of used degradable raw materials is high, the production cost of the degradable food packages is greatly improved, and the capacity of the degradable food packages is limited.

Therefore, it is desirable to provide a method for optimizing the preparation process of the degradable food packaging material, and the prepared food packaging material can meet the food quality guarantee requirement and reduce the production cost of the degradable food packaging material.

Disclosure of Invention

One or more embodiments of the present disclosure provide a method for optimizing a preparation process of a degradable food packaging material. The preparation process optimization method of the degradable food packaging material comprises the following steps: acquiring product demand data, wherein the product demand data comprises food storage demand data, food transportation demand data and process demand data; determining a target material property energeticization index based on the product demand data; determining a target raw material combination based on the target material performance energetic index; the target raw material comprises a support material, a first degradable material and a second degradable material; the first degradable material is a degradable material included in the lining material; the second degradable material is a degradable material contained in the film covering material; the lining material comprises a first degradable material and a first auxiliary material; the film covering material comprises a second degradable material and a second auxiliary material; the first degradable material and the second degradable material both comprise at least one of polybutylene succinate, polylactic acid, polyhydroxyalkanoate and polybutylene adipate-terephthalate; the target raw material combination comprises a support material, a first degradable material and the proportion thereof, and a second degradable material and the proportion thereof; preparation parameters are determined based on the target raw material combination and product demand data.

One or more embodiments of the present disclosure provide a system for optimizing a manufacturing process of a degradable food packaging material. The preparation process optimization system of the degradable food packaging material comprises the following steps: the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring product demand data, and the product demand data comprises food storage demand data, food transportation demand data and process demand data; the first determination module is used for determining a target material property energetication index based on the product demand data; the second determination module is used for determining a target raw material combination based on the target material performance energetic index; the target raw material comprises a support material, a first degradable material and a second degradable material; the first degradable material is a degradable material included in the lining material; the second degradable material is a degradable material contained in the film covering material; the lining material comprises a first degradable material and a first auxiliary material; the film covering material comprises a second degradable material and a second auxiliary material; the first degradable material and the second degradable material both comprise at least one of polybutylene succinate, polylactic acid, polyhydroxyalkanoate and polybutylene adipate-terephthalate; the target raw material combination comprises a support material, a first degradable material and the proportion thereof, and a second degradable material and the proportion thereof; a third determination module for determining the production parameters based on the target feedstock combination and the product demand data.

One or more embodiments of the present specification provide a preparation process optimization apparatus for a degradable food packaging material, including a processor for executing a preparation process optimization method for the degradable food packaging material.

One or more embodiments of the present specification provide a computer-readable storage medium storing computer instructions, and when the computer reads the computer instructions in the storage medium, the computer executes a method for optimizing a manufacturing process of a degradable food packaging material.

Drawings

The present description will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:

FIG. 1 is a block diagram of a system for optimizing a manufacturing process for degradable food packaging material according to some embodiments of the present disclosure;

FIG. 2 is an exemplary flow chart illustrating the determination of production parameters according to some embodiments of the present description;

FIG. 3 is an exemplary flow diagram illustrating the determination of a target combination of materials according to some embodiments of the present description;

FIG. 4 is a model structure diagram of a degradation rate determination model according to some embodiments described herein;

FIG. 5 is a model structure diagram of a performance prediction model in accordance with certain embodiments of the present description;

FIG. 6 is a model structure diagram of a first parameter determination model according to some embodiments of the present description;

FIG. 7 is a model architecture diagram of a second parameter determination model in accordance with certain embodiments of the present description.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only examples or embodiments of the present description, and that for a person skilled in the art, the present description can also be applied to other similar scenarios on the basis of these drawings without inventive effort. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system", "apparatus", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this specification and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of the present specification. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

Fig. 1 is a block diagram of a system for optimizing a manufacturing process of a degradable food packaging material according to some embodiments of the present disclosure. In some embodiments, the system 100 for optimizing a manufacturing process of a degradable food packaging material may include an acquisition module 110, a first determination module 120, a second determination module 130, and a third determination module 140.

The acquisition module 110 may be used to acquire product demand data. The product demand data comprises food storage demand data, food transportation demand data and process demand data. More descriptions of product demand data, food storage demand data, food transportation demand data, and process demand data can be found in relation to FIG. 2.

The first determination module 120 may be used to determine a target material property energetics index based on product demand data. More descriptions of the target material property energetics can be found in the description related to fig. 2.

The second determination module 130 may be used to determine a target feedstock combination based on a target material properties energetics index. The target raw material comprises a support material, a first degradable material and a second degradable material; the first degradable material is a degradable material included in the lining material; the second degradable material is a degradable material contained in the film covering material; the lining material comprises a first degradable material and a first auxiliary material; the film covering material comprises a second degradable material and a second auxiliary material; the first degradable material and the second degradable material both comprise at least one of polybutylene succinate, polylactic acid, polyhydroxyalkanoate and polybutylene adipate-terephthalate; the target raw material combination comprises the support material, the first degradable material and the proportion thereof, and the second degradable material and the proportion thereof. More descriptions about the combination of the target material, the support material, the first degradable material, the second degradable material, the lining material, the coating material, the first auxiliary material, the second auxiliary material and the target material can be found in the description related to fig. 2.

The third determination module 140 may be used to determine preparation parameters based on the target raw material combination and product demand data. Further description of the preparation parameters can be found in relation to FIG. 2.

It should be noted that the above description of the system for optimizing the preparation process of the degradable food packaging material and the modules thereof is only for convenience of description and should not limit the present specification to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the teachings of the present system, any combination of modules or sub-system configurations may be used to connect to other modules without departing from such teachings. In some embodiments, the obtaining module, the first determining module, the second determining module and the third determining module disclosed in fig. 1 may be different modules in one system, or may be one module to implement the functions of two or more modules. For example, each module may share one memory module, and each module may have its own memory module. Such variations are within the scope of the present disclosure.

FIG. 2 is an exemplary flow chart illustrating the determination of preparation parameters according to some embodiments of the present description. As shown in fig. 2, the process 200 includes the following steps. In some embodiments, the process 200 may be performed by the system 100 for optimizing a manufacturing process of a degradable food packaging material.

Step 210, product demand data is obtained. In some embodiments, step 210 may be performed by acquisition module 110.

The product requirement data may refer to data on the quality and appearance requirements to be met for food packages produced using the degradable food packaging material. In some embodiments, the product demand data may include food storage demand data, food transport demand data, process demand data.

The food storage requirement data may refer to data of quality requirements to be achieved in terms of food storage of food packages produced using the degradable food packaging material. The quality requirement to be achieved in the aspect of food storage may be that the food packaged by the food package does not deteriorate during its shelf life. For example, the food storage requirement data may be "light-blocking, low temperature resistant, with good sealability.

The food transportation requirement data can refer to the data of the quality requirement of the produced food packaging product in the aspect of food transportation. The quality requirement to be achieved in the aspect of food transportation can be that the food package does not crack, deform or melt in the normal transportation process of the food. For example, the food transport demand data may be "have good resistance to compression, tearing, and certain resistance to falls.

The process demand data may refer to data on the appearance requirements to be achieved for the food packaging product being produced. For example, the process requirement data may be data related to requirements for printing fineness of characters and patterns on the outer surface or requirements for gold stamping, where gold stamping may refer to a process of stamping an electrochemical aluminum foil onto the outer surface of a food packaging product at a certain temperature and pressure.

Step 220, determining a target material property energeticization index based on the product demand data. In some embodiments, step 220 may be performed by the first determination module 120.

The target material property energetically index can refer to the evaluation standard of each physical and chemical property of a supporting material, a lining material and a film coating material when the food packaging product can meet the requirement of product demand data. For example, the target material property energetics index may be "the burst strength of the support material (one of the determinants of the hardness of the support material) ≥ 420g/m ² The transverse ring crush index (one of determinants of the hardness of the supporting material) is more than or equal to 12 (N.m)/g, and the heat conductivity coefficient (determinants of the heat insulation property of the supporting material)) Not more than 0.14W/(m.K), the arithmetic mean deviation of the contour (a determining factor of the surface roughness of the supporting material) is not less than 120 mu m, the estimated ink coloring degree is not less than 80 percent, and the surface tension is not less than 40dyn/cm; the water vapor permeability of the lining material (the determining factor of the water vapor barrier rate of the lining material) is less than or equal to 2 g/(m) ² 24 h), oxygen transmission rate (determinant of oxygen barrier rate of the lining material) of less than or equal to 500cm ³ /(m ² 24 h.0.1 MPa), the antibacterial rate is more than or equal to 90 percent, and the limit heat-resistant temperature (a determinant factor of the heat resistance of the lining material) is more than or equal to 100 ℃; the tensile strength of the film-coated material is more than or equal to 220MPa, the elongation at break is more than or equal to 200%, the transparency is more than or equal to 90%, and the surface tension is more than or equal to 30dyn/cm.

The support material may refer to a material that supports the outer shape of the food packaging product and may be made of corrugated or grey board paper or kraft paper.

The inner liner material may refer to a film material located inside the food packaging product, in direct contact with the food, and may be of the type of plastic film, and may include a first degradable material and a first excipient in its composition.

The first degradable material can refer to the type of degradable material used for preparing the lining material, and the type of degradable material included in the first degradable material can be at least one of polybutylene succinate, polylactic acid, polyhydroxyalkanoate and polybutylene adipate-terephthalate.

The first auxiliary material can refer to the types of auxiliary materials used in the preparation of the lining material, and can comprise a plasticizer, a lubricant, a reinforcing material, a barrier material, an antibacterial agent and the like, wherein the plasticizer can be acetylated citric acid, epoxidized soybean oil, citric acid, glycerol, sorbitol and the like; the lubricant can be butyl stearate, ethylene bisoleic acid amide, stearic acid, calcium stearate; the reinforcing material can be glass fiber, talcum powder, mica, calcium carbonate, kaolin, carbon fiber and the like; the barrier material can be ethylene-vinyl alcohol copolymer, polyvinylidene chloride, polyacrylonitrile, etc.; the silver glass and the antibacterial agent can be silver-zinc glass, silver-zinc zeolite and the like.

The film-coated material may refer to a film material located at the outer side of the food packaging product, and the material type may be a transparent plastic film, and the components thereof may include a second degradable material and a second auxiliary material.

The second degradable material can refer to the type of the degradable material used for preparing the film covering material, and the type of the degradable material can be at least one of polybutylene succinate, polylactic acid, polyhydroxyalkanoate and polybutylene adipate-terephthalate.

The second auxiliary material can refer to the types of auxiliary materials used in the preparation of the film-coating material, and can comprise a plasticizer, a lubricant, a reinforcing material, a barrier material, an antibacterial agent and the like, wherein the plasticizer can be acetylated citric acid, epoxidized soybean oil, citric acid, glycerol, sorbitol and the like; the lubricant can be butyl stearate, ethylene bisoleic acid amide, stearic acid, calcium stearate; the reinforcing material can be glass fiber, talcum powder, mica, calcium carbonate, kaolin, carbon fiber and the like; the barrier material can be ethylene-vinyl alcohol copolymer, polyvinylidene chloride, polyacrylonitrile, etc.; the antimicrobial agent may be silver glass, silver-zinc zeolite, or the like.

In some embodiments, the target material property energetics index may be preset based on product demand data and production experience.

Step 230, determining a target raw material combination based on the target material property energetic index. In some embodiments, step 230 may be performed by the second determination module 130.

The raw materials may include support materials, liner materials and film-covering materials for producing food packaging products.

The target material may include the types of materials selected for the buttress material, the first degradable material and the second degradable material. For example, the target material may be "the support material is corrugated paper, and the first degradable material and the second degradable material each include polybutylene succinate, polylactic acid, polyhydroxyalkanoate, and polybutylene adipate-terephthalate".

The target raw material combination can be a raw material combination which meets the performance and energy conversion indexes of a target material and is used for producing food packaging products, and can comprise a supporting material, a first degradable material and the proportion thereof, and a second degradable material and the proportion thereof. The proportion of the first degradable material may refer to the mass proportion of each degradable material included in the first degradable material; the blending ratio of the second degradable material can refer to the mass proportion of each degradable material included in the second degradable material. For example, the target stock combination may be "the support material is corrugated paper; the first degradable material comprises 25% of polybutylene succinate, 30% of polylactic acid, 40% of polyhydroxyalkanoate and 5% of polybutylene adipate-terephthalate in mass ratio; the second degradable material comprises polybutylene succinate, polylactic acid, polyhydroxyalkanoate and polybutylene adipate-terephthalate, and the mass percentages of the second degradable material and the second degradable material are respectively 10%, 25%, 40% and 25%. In some embodiments, the mass fraction ratio of the partial species of degradable material comprised by the first and second degradable materials may be 0.

At step 240, preparation parameters are determined based on the target raw material combination and product demand data. In some embodiments, step 240 may be performed by the third determination module 140.

In some embodiments, the preparation parameters may be determined from production experience based on the target feedstock combination and product demand data.

In some embodiments, the production parameters may include extrusion parameters, appearance process parameters, and lamination parameters. The extrusion parameters can comprise the proportion of the first auxiliary material, the proportion of the second auxiliary material and extrusion equipment parameters; the parameters of the extrusion equipment can be determined based on the proportion of the first degradable material, the physicochemical properties of the first degradable material, the proportion of the first auxiliary material, the proportion of the second degradable material, the physicochemical properties of the second degradable material and the proportion of the second auxiliary material; the appearance process parameters can be determined based on the proportion of the first degradable material, the proportion of the first auxiliary material, the proportion of the second degradable material, the proportion of the second auxiliary material and the process demand data; the film pressing parameters can be determined based on the estimated performance of the supporting material, the estimated performance of the lining material and the estimated performance of the film covering material; lamination parameters may include internal and external lamination parameters. The relative descriptions of the estimated properties of the support material, the estimated properties of the liner material, and the estimated properties of the film-coating material can be found in the description related to FIG. 3.

In some embodiments, determining the ratio of the first adjuvant and the ratio of the second adjuvant may include:

and determining the proportion of the first auxiliary material and the proportion of the second auxiliary material through a preset algorithm based on the first degradable material and the proportion thereof, the second degradable material and the proportion thereof, and the first auxiliary material and the second auxiliary material in the target raw material combination.

The preparation parameters may refer to parameters related to the process of preparing the raw materials into the food packaging product, and may include extrusion parameters, appearance process parameters, and film pressing parameters.

The extrusion parameters may refer to parameters related to an extrusion process for preparing the food packaging product, and may include a ratio of the first auxiliary material, a ratio of the second auxiliary material, and extrusion equipment parameters.

The proportion of the first auxiliary material can refer to the mass proportion of various auxiliary materials included in the first auxiliary material. For example, the first auxiliary material may be in a ratio of "the first auxiliary material includes 10%, 25%, 35%, 25%, and 5% by mass of the plasticizer, the lubricant, the reinforcing material, the barrier material, and the antibacterial agent, respectively". In some embodiments, the first auxiliary material may include a part of the auxiliary material of the kind having a mass ratio of 0.

The proportion of the second auxiliary material can refer to the mass proportion of various auxiliary materials included in the second auxiliary material. For example, the second auxiliary material may be in a ratio of "the second auxiliary material includes 20%, 25%, 23%,25%, and 7% by mass of the plasticizer, the lubricant, the reinforcing material, the barrier material, and the antibacterial agent, respectively". In some embodiments, the second auxiliary material may include a part of the auxiliary material of the kind having a mass ratio of 0.

In some embodiments, the ratio of the first auxiliary material and the ratio of the second auxiliary material may be determined based on manufacturing experience.

In some embodiments, the ratio of the first auxiliary material and the ratio of the second auxiliary material may be determined based on a predetermined algorithm. The preset algorithm can predict the estimated performance of the target lining material or the estimated performance of the film coating material corresponding to each to-be-optimized ratio after each iteration update by performing at least one iteration update on a plurality of to-be-optimized ratios, further determine the satisfaction degree of food storage requirement data or the satisfaction degree of food transportation requirement data or the satisfaction degree of process requirement data, and determine the ratio of the first auxiliary material and the ratio of the second auxiliary material based on the satisfaction degrees. The relevant description of the estimated performance and the satisfaction can be referred to the relevant description of fig. 3.

Taking the determination process of the ratio of the first auxiliary material as an example, the preset algorithm may include the following steps:

a plurality of initial ratios of the first auxiliary materials to be optimized (hereinafter referred to as the first ratios to be optimized) are established. The proportion of various auxiliary materials in the initial first proportion to be optimized can be a random value or an artificial preset value. In some embodiments, the initial first to-be-optimized proportion may be characterized by an initialization vector. An exemplary procedure for initialization of the initial first to-be-optimized ratio correspondence vector is as follows: for several (assuming that the number is D) auxiliary materials, the number of the initial first to-be-optimized ratios can be set to be N, at this time, the dimension of each initial first to-be-optimized ratio is D (the element value of each dimension corresponds to the mass ratio of one auxiliary material), and then the vector corresponding to the ith initial first to-be-optimized ratio

Can be expressed as:

n vectors corresponding to the initial first ratio to be optimized

Can be expressed as:

wherein 0 is an identifier (representing the 0 th iteration, that is, an initial value of the iteration which has not started yet), and i is a number of the initial first ratio to be optimized, wherein i is greater than or equal to 1 and less than or equal to N.

Performing at least one round of iterative updating on each initial first ratio to be optimized; and aiming at each iteratively updated first ratio to be optimized, determining the estimated performance of the lining material corresponding to the iteratively updated first ratio to be optimized based on the iteratively updated first ratio to be optimized, and further determining the satisfaction degree of the food storage demand data based on the estimated performance of the lining material. The method for determining the estimated performance of the liner material can be seen in the description associated with fig. 3 and 5. Specific details of the iterative update may include:

for each first ratio to be optimized, in the process of iteratively updating the first ratio to be optimized, the first ratio to be optimized may correspond to a multidimensional increment. The multidimensional increment can refer to the adjustment amplitude of the mass ratio of each auxiliary material contained in the first mixture to be optimized in each iteration.

In the first iteration, the initial first ratio to be optimized may be updated based on the initial multidimensional increment, resulting in an updated first ratio to be optimized. And determining the updated first ratio to be optimized as the first ratio to be optimized to be processed, and determining the initial multi-dimensional increment as the multi-dimensional increment to be processed in the next round. The initial multidimensional increment can be a system default value set according to actual requirements, an empirical value, a manually preset value, and the like or any combination thereof.

And in each subsequent iteration, updating the to-be-processed multidimensional increment of the iteration to obtain the updated multidimensional increment. And updating the first to-be-optimized ratio to be processed based on the updated multidimensional increment to obtain the updated first to-be-optimized ratio. And determining the updated first ratio to be optimized as the next round of ratio to be optimized, and determining the updated multidimensional increment as the next round of multidimensional increment to be processed.

In some embodiments, updating the to-be-processed multidimensional delta may be accomplished by updating a to-be-processed delta element. Where an increment element is an element of each dimension of a multidimensional increment, the multidimensional increment may comprise a plurality of increment elements. There may be a correspondence between each auxiliary material in the first to-be-optimized proportion to be processed and each increment element. The increment element can be used to characterize the magnitude of the adjustment of the mass fraction of the corresponding auxiliary material.

In some embodiments, the to-be-processed delta element may be updated based on the current loss of the previous round, and the updated delta element is used as the to-be-processed delta element of the next round. And determining the current loss of the previous round based on the action difference between the element value of the first ratio to be optimized obtained in the previous round and the element value of the historical optimal first ratio to be optimized. The historical optimal first ratio to be optimized may refer to the maximum satisfaction of the food storage requirement data corresponding to the predicted performance of the liner material determined based on the first ratio to be optimized.

For example, after the k +1 th iteration, the updated increment element can be calculated by the following formula (1):

wherein i represents the number of the first mixture ratio to be optimized, wherein i is more than or equal to 1 and less than or equal to N; d represents the number of the type of auxiliary material (e.g., number 1 corresponds to the plasticizer and number 2 corresponds to the lubricant), wherein 1. Ltoreq. D.ltoreq.D. k represents the number of iteration rounds, wherein k is more than or equal to 0.

And representing the increment element to be processed obtained after the ith first ratio to be optimized is iterated in the kth round. />

The ith first ratio to be optimized obtained after the kth iteration is shown. ω represents the inertial weight constant. c. C ₁ Representing an individual learning factor, c ₂ Representing a population learning factor. r is ₁ And r ₂ Is the interval [0,1]Any value within, for enhancing randomness. />

After the k-th iteration, the ith first ratio to be optimized isThe mass fraction value of the d auxiliary material of the optimal solution in the process of the past iterations. The optimal solution at this time may be a set of mass ratios of various auxiliary materials corresponding to the first ratio to be optimized when the satisfaction degree of the first ratio to be optimized in the past iterations is the maximum value among the satisfaction degrees of the multiple pieces of food storage requirement data correspondingly determined based on the estimated performance of the lining material determined by the ith first ratio to be optimized after the kth iteration (i.e., an individual historical optimal solution). />

The mass ratio value of the d auxiliary material is the optimal solution of all the first to-be-optimized mixture ratios in the processes of the previous iterations after the k iteration. The optimal solution at this time may be a set of mass ratios of various auxiliary materials corresponding to the first to-be-optimized ratio with the maximum satisfaction degree of the food storage demand data among the aforementioned plurality of first to-be-optimized ratios with individual historical optimal solutions in past iterations (i.e., a group historical optimal solution) after the k-th iteration.

The inertia weight constant ω and the individual learning factor c ₁ Group learning factor c ₂ And a random constant r ₁ And r ₂ And the system default value, the empirical value, the artificial preset value and the like or any combination thereof can be set according to actual requirements.

In some embodiments, the maximum absolute value of the delta element in each iteration may be v _max I.e. the maximum adjustment amplitude representing the mass fraction of each auxiliary material. In the (k + 1) th iteration, the mass ratio of each auxiliary material is adjusted to form a multidimensional increment V _i Can be expressed as (v) _i1 ,v _i2 ,…,v _iD ). The vector of the multidimensional increments corresponding to the N first to-be-optimized matches can be represented as ((v) ₁₁ ,v ₁₂ ,…,v _1D ),(v ₂₁ ,v ₂₂ ,…,v _2D ),…,(v _N1 ,v _N2 ,…,v _ND )). Wherein, the value of any increment element in the vector can be a negative value, but the absolute value is not more than v _max 。

In some embodiments, each of the first to-be-optimized formulations to be processed may be updated based on the delta elements in the updated multidimensional delta. For example, after the k +1 th iteration, the updated first ratio to be optimized may be calculated by the following formula (2):

for example, after the first iteration, the updated ith first ratio to be optimized can be calculated by the following formula (3):

the vector expression form corresponding to the N updated first to-be-optimized ratios can be calculated by the following formula (4):

in some embodiments, the mass ratio X of each auxiliary material is for the initial first ratio to be optimized and the first ratio to be optimized updated for each iteration _id Constraints may exist. The constraints are shown in equations (5) and (6):

X _id ≤S _d (5)

Q＝∑(X _id )＝(X _i1 +X _i2 +X _i3 ,…,+X _iD )＝100％ (6)

wherein, X _id The mass ratio of the d auxiliary material in the ith first mixture ratio to be optimized is shown. S _d Represents the upper limit of the mass ratio of the d-th auxiliary material. Q represents the sum of the mass proportions of all the auxiliary materials in the ith first proportioning to be optimized. In some embodiments, S _d May be an empirical value or a manually preset value, etc., or any combination thereof.

In some embodiments, if a certainAfter the iteration, the mass ratio X of certain auxiliary material in certain first to-be-optimized proportioning _id Is greater than S _d The mass fraction of the auxiliary material in the first ratio to be optimized can be reset to S _d . For example, after the third iteration, the first to-be-optimized ratio No. 7

Wherein->

Can then be taken>

Reset to S ₂ 。

In some embodiments, if after an iteration the sum Q of the mass fractions of all the types of auxiliary materials in a first mixture to be optimized has a value not equal to 100%, the mass fraction of each type of auxiliary material in the first mixture to be optimized can be adjusted proportionally (1/Q). For example, after the fourth iteration, the first to-be-optimized ratio No. 9

The sum of the mass ratios of all the corresponding auxiliary materials:

then will be

The adjustment is as follows:

in some embodiments, the first ratio to be optimized may be continuously updated iteratively through the preset algorithm until a preset condition is met, and the iterative updating is ended. The preset condition may be that the number of iterations reaches a preset value, or that a ratio of a satisfaction degree of the first to-be-optimized proportion obtained by the algorithm corresponding to the obtained food storage demand data to a preset theoretical maximum satisfaction degree is greater than a threshold.

After the iterative updating is finished, the first to-be-optimized ratios after the iterative updating can converge to a target first auxiliary material ratio. The target first auxiliary material proportion comprises the mass ratio of various auxiliary materials contained in a group of first auxiliary materials for preparing the lining material. At this time, the satisfaction degree of the food storage demand data obtained based on the target first auxiliary material ratio should be the maximum value among the satisfaction degrees of the food storage demand data correspondingly obtained by the plurality of first to-be-optimized ratios iteratively updated in the past.

In the flow for determining the proportion of the second auxiliary material, compared with the flow for determining the proportion of the first auxiliary material, the estimated performance of the lining material can be replaced by the estimated performance of the film-coated material, the satisfaction degree of the food storage demand data is replaced by the satisfaction degree of the food transportation demand data and the satisfaction degree of the process demand data, and other flows are the same as the flow for determining the proportion of the first auxiliary material.

Extrusion equipment parameters may refer to the operating parameters of the extruder used to perform the extrusion process. For example, the parameters of the extrusion equipment can be that the temperature is 200 ℃ when the lining material is extruded, the extrusion pressure is 60MPa, and the rotating speed of an extrusion screw is 20r/min; when the laminating material is extruded, the temperature is 210 ℃, the extrusion pressure is 62MPa, and the rotating speed of an extrusion screw is 19 r/min.

In some embodiments, the parameters of the extrusion equipment can be set according to the proportion and the physicochemical characteristics of the first degradable material, the proportion of the first auxiliary material, the proportion and the physicochemical characteristics of the second degradable material, and the proportion of the second auxiliary material based on production experience.

In some embodiments, the extrusion device parameters may be determined based on the first parameter determination model processing the target raw material combination, the proportioning ratio of the first auxiliary material, the proportioning ratio of the second auxiliary material, the physicochemical properties of the first degradable material and the physicochemical properties of the second degradable material. The relevant description of the first parameter determination model can be found in relation to fig. 6.

The appearance process parameters may refer to parameters associated with printing and post-printing process flows for preparing food packaging products. Wherein, the post-printing process can comprise at least one of gold stamping, die cutting indentation, UV process and embossing. For example, the appearance process parameters may be "the concentration of ink used for printing is 80%, the printing pressure is 20 filaments, the gold stamping temperature is 110 ℃, the height of the indentation steel wire is 23.3mm, the spectrum of the UV light source is 400nm, and the embossing pressure is 20N".

In some embodiments, the parameters of the extrusion equipment may be set based on production experience according to the blending ratio and physicochemical properties of the first degradable material, the blending ratio of the first auxiliary material, the blending ratio and physicochemical properties of the second degradable material, the blending ratio of the second auxiliary material, and process requirement data.

In some embodiments, the appearance process parameters may be determined based on the first parameter determination model processing the target raw material combination, the blending ratio of the first auxiliary material, the blending ratio of the second auxiliary material, the physicochemical properties of the first degradable material, the physicochemical properties of the second degradable material, and the process demand data. The physicochemical properties of the first degradable material and the second degradable material can be explained by referring to the description in relation to fig. 3. The relevant description of the first parameter determination model can be found in relation to fig. 6.

The film pressing parameters can refer to working parameters of the film pressing equipment when the lining material is pressed in the supporting material and the film covering material is pressed outside the supporting material. The lamination parameters may include inner and outer lamination parameters. For example, the lamination parameters may be "internal lamination parameters including: the coating weight of the adhesive is 6 μm, and the composite pressure is 100kg/m ² The compounding temperature is 100 ℃, the drying temperature is 90 ℃, and the film covering speed is 15m/min; the external pressure membrane parameters include: the coating weight of the adhesive is 5.9 μm, and the composite pressure is 105kg/m ² The compounding temperature is 100 ℃, the drying temperature is 90 ℃ and the film covering speed is 14 m/min.

In some embodiments, the extrusion equipment parameters may be set based on production experience based on the estimated properties of the liner material, the estimated properties of the film-covering material, and the estimated properties of the support material.

In some embodiments, the estimated performance of the liner material, the estimated performance of the film-coating material, and the estimated performance of the support material may be processed based on the second parameter determination model to determine the film lamination parameters. The relevant description of the second parameter determination model can be found in relation to fig. 7.

In some embodiments of the present description, the process for preparing the food packaging product enables the produced food packaging product to meet the requirements of quality guarantee and transportation of food, and reduces the production cost of degradable food packaging; the method for determining the preparation parameters used in the process enables the determined preparation parameters to better meet production requirements, wherein the ratio of the first auxiliary material to the second auxiliary material is determined through a preset algorithm, so that a target raw material combination can exert excellent performance; each parameter in the preparation parameters is determined through the model, so that the efficiency of parameter determination work and the accuracy of the determined parameters can be effectively improved.

It should be noted that the above description related to the flow 200 is only for illustration and description, and does not limit the applicable scope of the present specification. Various modifications and alterations to flow 200 will be apparent to those skilled in the art in light of this description. However, such modifications and variations are still within the scope of the present specification. For example, other methods are used to determine a target material property energetics index.

FIG. 3 is an exemplary flow chart illustrating the determination of a target combination of materials according to some embodiments of the present description.

At step 310, at least one set of candidate raw material combinations is determined based on the target material property energetics index.

The candidate material combination may refer to a sample material combination for determining candidates of the target material combination, and may include a candidate support material, a first degradable material and a candidate proportion thereof, and a second degradable material and a candidate proportion thereof. For example, a set of candidate stock combinations may be "the candidate support material is grey board; the first degradable material comprises polybutylene succinate, polylactic acid, polyhydroxyalkanoate and polybutylene adipate-terephthalate, and the candidate mass percentages of the first degradable material are respectively 25%, 30% and 15%; the second degradable material comprises polybutylene succinate, polylactic acid, polyhydroxyalkanoate and polybutylene adipate-terephthalate, and the candidate mass percentages of the second degradable material are respectively 15%, 25%, 35% and 25%. In some embodiments, the candidate mass fraction ratio of the partial species of degradable material comprised by the first degradable material and the second degradable material may be 0.

In some embodiments, at least one set of candidate feedstock combinations may be manually set based on production experience according to a target material property energetics index. The relevant description about the target material property energy-based index can refer to the relevant description of fig. 2.

And step 320, evaluating the evaluation scores of each group of candidate raw material combination.

The evaluation score may refer to a numerical value that reflects the superiority and inferiority of the performance of the food packaging product produced based on the candidate ingredient combination. The evaluation score may be a value in the range of [0,100], with a larger value representing a better performance of the food packaging product produced based on the candidate ingredient combination.

In some embodiments, the evaluation score may be determined based on the demand satisfaction, the average cost, the degradation rate of the candidate liner material, and the degradation rate of the candidate cover material. Candidate liner materials may refer to liner materials prepared based on a candidate formulation of a first degradable material in a combination of a first adjuvant and a candidate raw material. The candidate coating material may refer to a coating material prepared based on a candidate blending ratio of the second auxiliary material and the second degradable material in the candidate raw material combination. The relevant description of the first and second excipients can be found in relation to figure 2.

In some embodiments, the evaluation score of the candidate feedstock combination may be determined based on equation (7) as follows:

A＝w ₁ ·Y+w ₂ ·(V ₁ +V ₂ )-w ₃ ·P (7)

wherein A is an evaluation score; y is the demand satisfaction degree; v ₁ 、V ₂ Respectively representing the degradation rate of the candidate lining material and the degradation rate of the candidate coating material; p represents the average cost; w is a ₁ 、w ₂ 、w ₃ Is greater than 0A constant, the value of which is pre-settable. In some embodiments, w ₁ 、w ₂ 、w ₃ Can satisfy w ₁ >w ₂ And w ₁ >w ₃ . Further details regarding the satisfaction of the requirements, the degradation rate of the candidate liner material, the degradation rate of the candidate coating material and the average manufacturing cost and methods for determining the same are provided below.

The demand satisfaction can refer to the degree to which product demand data is satisfied. The related description of the product demand data can be referred to the related description of fig. 2.

In some embodiments, the degree of demand satisfaction may be determined by manually estimating, based on production experience, a performance of a food packaging product produced based on the candidate combination of raw materials and determining the degree of demand satisfaction based on the estimated performance.

In some embodiments, the demand satisfaction may be determined based on the satisfaction of the food storage demand data, the satisfaction of the food transport demand data, and the satisfaction of the process demand data. The relevant description of the food storage requirement data, the food transportation requirement data and the process requirement data can be referred to the relevant description of fig. 2.

The satisfaction of the food storage requirement data may be determined based on the predicted performance of the candidate liner material; the satisfaction degree of the food transportation demand data can be determined based on the estimated performance of the candidate film-coated material and the estimated performance of the candidate support material; the satisfaction degree of the process demand data can be determined based on the estimated performance of the candidate film-coated material and the estimated performance of the candidate support material;

the estimated performance of the candidate lining material can comprise at least one of estimated water vapor barrier rate, estimated oxygen barrier rate, estimated antibacterial rate and estimated heat resistance; the estimated performance of the candidate film-coated material may include at least one of an estimated tensile strength, an estimated elongation at break, an estimated transparency, and an estimated surface tension; the estimated properties of the candidate support material may include at least one of an estimated hardness, an estimated thermal insulation, an estimated surface roughness, an estimated ink staining, and an estimated surface tension.

The satisfaction degree of the food storage requirement data can refer to the satisfaction degree of the quality requirement of the food packaging product in the aspect of food storage.

The satisfaction of the food storage requirement data can be determined based on the predicted performance of candidate liner materials for food packaging products produced from the candidate raw material combinations.

The predicted properties of the candidate liner material may include a predicted water vapor transmission rate, a predicted oxygen transmission rate, a predicted antimicrobial rate, and a predicted ultimate heat resistance temperature. In some embodiments, the predicted performance of the candidate liner material may be data in the form of a vector. For example, the predicted performance of a candidate liner material may be (1.8, 450,0.9, 100), which is represented by: the estimated water vapor transmission rate of the food packaging product produced based on the corresponding candidate raw material combination is 1.8 g/(m) ² 24 h), estimated oxygen transmission rate of 450cm ³ /(m ² 24h 0.1 MPa), the estimated antibacterial rate is 90%, and the estimated ultimate heat-resistant temperature is 100 ℃.

In some embodiments, the candidate blending ratio of the first degradable material, the blending ratio of the first auxiliary material, and the extrusion equipment parameters may be processed based on a performance prediction model to determine the predicted performance of the candidate liner material. The relevant description of the performance prediction model can be found in relation to fig. 5. The candidate blending ratio of the first degradable material may refer to the blending ratio of the first degradable material in the candidate raw material group. The related descriptions of the proportioning of the first degradable material, the proportioning of the first auxiliary material and the parameters of the extrusion equipment can be referred to the related description of fig. 2.

In some embodiments, satisfaction of the food storage requirement data may be correlated with an estimated water vapor transmission rate, an estimated oxygen transmission rate, an estimated antimicrobial rate, and an estimated ultimate heat resistant temperature of the candidate liner material. For example, the satisfaction of the food storage requirement data may be negatively correlated with both the estimated water vapor transmission rate and the estimated oxygen transmission rate of the candidate liner material, and positively correlated with both the estimated antimicrobial rate and the estimated ultimate heat resistance temperature.

In some embodiments, the satisfaction of the food storage demand data may be determined based on equation (8) as follows:

Y ₁ ＝(Y ₁₁ +Y ₁₂ +Y ₁₃ +Y ₁₄ )/4 (8)

wherein Y is ₁ Representing the satisfaction of food storage demand data; y is ₁₁ Representing the satisfaction degree of the water vapor transmission rate; y is ₁₂ Represents the degree of satisfaction of the oxygen transmission rate; y is ₁₃ Representing the degree of satisfaction of the antibacterial rate; y is ₁₄ Represents the satisfaction of the ultimate heat-resistant temperature. The satisfaction degree of the water vapor permeability, the satisfaction degree of the oxygen permeability, the satisfaction degree of the antibacterial rate and the satisfaction degree of the ultimate heat-resisting temperature can respectively refer to the satisfaction degrees of the water vapor permeability, the oxygen permeability, the antibacterial rate and the ultimate heat-resisting temperature of the food packaging product on the energetic indexes of the target material property.

Further, the satisfaction of the water vapor transmission rate and the satisfaction of the oxygen transmission rate may be determined based on the following formula (9-1):

wherein i =1 (representing water vapor transmission rate) or 2 (representing oxygen transmission rate); y is ₁₁ And Y ₁₂ The meaning of the representation is the same as that of formula (8); x is the number of ₁₁ Representing the estimated water vapor transmission rate, x ₁₂ Representing the estimated oxygen transmission rate; m is ₁₁ Water vapor transmission rate, m, in an energetically significant measure of the target material properties ₁₂ Representing the oxygen transmission rate in an energetic indicator of the target material properties.

The satisfaction of the antibacterial ratio and the satisfaction of the ultimate heat-resistant temperature can be determined based on the following formula (10-1):

wherein i =3 (representing antibacterial ratio) or 4 (representing ultimate heat-resistant temperature); y is ₁₃ And Y ₁₄ The meaning of the representation is the same as that of formula (8); x is the number of ₁₃ Representing the estimated antibacterial ratio, x ₁₄ Representing the predicted ultimate heat resistance temperature; m is a unit of ₁₃ Representing the antibacterial rate in the energetic index of the target material property, m ₁₄ Represents the ultimate heat-resistant temperature in the energetic index of the target material property.

In some embodiments, the satisfaction of the food storage requirement may also be correlated to an estimated food storage duration. For example, the satisfaction of food storage requirements may be inversely related to the estimated length of time that the food is stored.

In some embodiments, the estimated food storage period may be related to the satisfaction of the process demand data and the heat of consumption of the food packaged by the food packaging product. For example, the estimated storage time of the food may be inversely related to the satisfaction degree of the process demand data, and may be inversely related to the consumption heat degree of the food packaged by the food packaging product, that is, the larger the satisfaction degree of the process demand data is, the larger the consumption heat degree of the food is, the smaller the estimated storage time of the food is. For an explanation of the satisfaction of the process demand data, reference is made to the description below. The consumption heat of the food packaged by the food packaging product can refer to data capable of reflecting the sales volume of the food in unit time, and the higher the sales volume of the food in unit time is, the greater the consumption heat is, and the smaller the estimated storage time of the food is.

The satisfaction degree of the food transportation requirement data can refer to the satisfaction degree of the quality requirement of the food packaging product in the aspect of food transportation.

The satisfaction degree of the food transportation requirement data can be determined based on the estimated performance of the candidate film coating material and the estimated performance of the candidate supporting material of the food packaging product produced by the candidate raw material combination.

The estimated properties of the candidate film-coating material may include an estimated tensile strength, an estimated elongation at break, an estimated transparency, and an estimated surface tension. In some embodiments, the predicted properties of the candidate film-coating material may be data in the form of vectors. For example, the predicted performance of a candidate coating material may be (220, 2,0.1, 30), which means: the estimated tensile strength of a food packaging product produced based on the corresponding candidate raw material combination is 220MPa, the estimated elongation at break is 200%, the estimated transparency is 10%, and the estimated surface tension of the film coating material is 30dyn/cm.

In some embodiments, the candidate blending ratio of the second degradable material, the blending ratio of the second auxiliary material and the extrusion equipment parameters may be processed based on the performance prediction model to determine the predicted performance of the candidate film coating material. The candidate blending ratio of the second degradable material can refer to the blending ratio of the second degradable material in the candidate raw material group. The relevant description of the performance prediction model can be found in relation to fig. 5. The related descriptions of the proportioning of the second degradable material, the proportioning of the second auxiliary material and the parameters of the extrusion equipment can be found in the related description of fig. 2.

In some embodiments, the satisfaction of the food transport demand data may be correlated to the estimated tensile strength and the estimated elongation at break of the candidate film-covered material. For example, the satisfaction of the food transportation requirement data may be positively correlated to both the estimated tensile strength and the estimated elongation at break of the candidate film-coated material.

The estimated properties of the candidate support material may include estimated hardness (characterized by an estimated burst strength and an estimated lateral ring pressure index), estimated thermal insulation (characterized by an estimated thermal conductivity), estimated surface roughness (characterized by an estimated arithmetic mean deviation of the profile), estimated ink staining, and estimated surface tension. In some embodiments, the predicted properties of the candidate support material may be data in the form of vectors. For example, the predicted properties of the candidate support material may be (400, 12,0.14, 120,0.8, 40), which is represented by: the estimated bursting strength of the food packaging product produced based on the corresponding candidate raw material combination is 420g/m ² The estimated transverse ring pressure index is 12 (N.m)/g, the estimated thermal conductivity is 0.14W/(m.K), the estimated arithmetic mean deviation of the profile is 120 mu m, the estimated coloring degree of the ink is 80%, and the estimated surface tension of the support material is 40dyn/cm.

In some embodiments, the candidate proportions of the first degradable material, the candidate proportions of the second degradable material, the proportions of the first auxiliary material, the proportions of the second auxiliary material, the extrusion equipment parameters, and the candidate support materials in the candidate raw material combination may be processed based on a performance prediction model to determine the predicted performance of the candidate support materials. The relevant description of the performance prediction model can be found in relation to fig. 5.

In some embodiments, satisfaction of the food transport demand data may be correlated to the estimated stiffness and the estimated insulation of the candidate support material. For example, the satisfaction of the food transport demand data may be positively correlated with both the estimated burst and the estimated lateral ring crush index of the candidate support material, and negatively correlated with the estimated thermal conductivity.

In some embodiments, the satisfaction of the food transport demand data may be determined based on the following equation (11):

Y ₂ ＝(Y ₂₁ +Y ₂₂ +Y ₂₃ +Y ₂₄ +Y ₂₅ ) /5 (11) wherein Y ₂ Representing the satisfaction of food transport demand data; y is ₂₁ Represents the degree of satisfaction of tensile strength; y is ₂₂ Represents the degree of satisfaction of the elongation at break; y is ₂₃ Represents the degree of satisfaction of the burst strength; y is ₂₄ Representing the satisfaction degree of the transverse ring pressure index; y is ₂₅ Representing the degree of satisfaction of heat resistance. The satisfaction degree of tensile strength, the satisfaction degree of elongation at break, the satisfaction degree of bursting strength, the satisfaction degree of transverse ring crush index and the satisfaction degree of heat resistance can respectively refer to the satisfaction degrees of tensile strength, elongation at break, bursting strength, transverse ring crush index and heat conductivity coefficient of the food packaging product in the energetic indexes of target material properties.

Further, the satisfaction of tensile strength, the satisfaction of elongation at break, the satisfaction of bursting strength, and the satisfaction of ring crush index in the transverse direction may be determined based on the following formula (12-1):

wherein i =1 (representing tensile strength) or 2 (representing elongation at break) or 3 (representing burst) or 4 (representing ring crush index in transverse direction); y is ₂₁ 、Y ₂₂ 、Y ₂₃ And Y ₂₄ The meaning of the representation is the same as that of formula (11); x is the number of ₂₁ Representing the predicted tensile strength, x ₂₂ Representing the estimated elongation at break, x ₂₃ Representing the estimated burst, x ₂₄ Representing the predicted transverse ring pressure index; m is ₂₁ Representing tensile strength, m, in an energetically oriented index of target material properties ₂₂ Representing elongation at break, m, in an energetically oriented index of target material properties ₂₃ Representing the degree of breakage in the energetic index of the target Material, m ₂₄ Represents the transverse ring crush index in the target material property energetic index.

The satisfaction of the heat resistance can be determined based on the following formula (13-1):

wherein, Y ₂₅ The meaning of the representation is the same as that of formula (11); x is the number of ₂₅ Representing the estimated thermal conductivity; m is ₂₅ Represents the thermal conductivity in the energetic index of the target material property.

The satisfaction degree of the process requirement data can refer to the satisfaction degree of the appearance requirement of the food packaging product in the aspect of appearance process.

The satisfaction of the process demand data may be determined based on the estimated properties of the candidate film-coated material and the estimated properties of the candidate support material of the food packaging product produced from the candidate raw material combination.

In some embodiments, the satisfaction of the process demand data may be related to the estimated surface roughness, the estimated ink staining, and the estimated surface tension of the candidate support material, and to the estimated transparency and the estimated surface tension of the candidate film covering material. For example, the satisfaction of the process demand data may be positively correlated with the estimated arithmetic mean deviation of the profile, the estimated surface tension and the estimated ink coloration of the candidate support material, and the estimated transparency and the estimated surface tension of the candidate film-coating material.

In some embodiments, the satisfaction of the process demand data may be determined based on the following equation (14):

Y ₃ ＝(Y ₃₁ +Y ₃₂ +Y ₃₃ +Y ₃₄ +Y ₃₅ ) /5 (14) wherein Y ₃ Representing the satisfaction of process demand data; y is ₃₁ Represents satisfaction of transparency; y is ₃₂ A satisfaction degree representing a surface tension of the candidate coating material; y is ₃₃ A satisfaction representing a degree of surface roughness; y is ₃₄ Representing the degree of satisfaction of the degree of coloration of the ink; y is ₃₅ Representing the satisfaction of the surface tension of the candidate support material. The satisfaction of the transparency, the satisfaction of the surface tension of the candidate coating material, the satisfaction of the surface roughness, the satisfaction of the ink coloration, and the satisfaction of the surface tension of the candidate support material may respectively refer to the satisfaction of the transparency, the surface tension of the coating material, the arithmetic mean deviation of the profile, the ink coloration, and the surface tension of the support material in the energetically energetic index of the target material for the food packaging product.

Further, the satisfaction of the transparency, the satisfaction of the surface tension of the candidate coating material, the satisfaction of the coloring degree of the ink, and the satisfaction of the surface tension of the candidate support material may be determined based on the following formula (15-1):

wherein i =1 (representing the transparency of the candidate coating material) or 2 (representing the surface tension of the candidate coating material) or 4 (representing the degree of ink coloration) or 5 (representing the surface tension of the candidate support material); y is ₃₁ 、Y ₃₂ 、Y ₃₄ And Y ₃₅ The meaning of the representation is the same as that of formula (14); x is the number of ₃₁ Representing estimated transparency, x, of candidate coating materials ₃₂ Estimated surface tension, x, representing candidate coating materials ₃₄ Representing the estimated ink colourity, x ₃₅ An estimated surface tension representative of the candidate support material; m is ₃₁ Representing the transparency, m, of the coating material in the energetic index of the target material properties ₃₂ Surface tension, m, of the coating material in the energetic index representing the target Material Property ₃₄ Representing the ink coloring degree in an energetic index of the target Material, m ₃₅ Represents the surface tension of the support material in the target material property energetics index.

The satisfaction of the degree of surface roughness may be determined based on the following formula (16-1):

wherein Y is ₃₃ The meaning of the representation is the same as that of formula (14); x is the number of ₃₃ Representing the arithmetic mean deviation of the predicted profile; m is ₃₃ Represents the arithmetic mean deviation of the profile in the target material property energetics index.

In some embodiments, when the magnitude relationship between the estimated term in the estimated performance and the corresponding term in the target material performance measure satisfies a certain condition (the condition of each estimated term is specifically distinguished in the following formula), the gradient of the corresponding satisfaction degree gradually decreases and approaches to 0 infinitely.

Accordingly, at this time, the above-mentioned equations (9-1), (10-1), (12-1), (13-1), (15-1) and (16-1) can be adjusted to equations (9-2), (10-2), (12-2), (13-2), (15-2) and (16-2), respectively, as follows:

wherein i =1 (representing water vapor transmission rate) or 2 (representing oxygen transmission rate); y is ₁₁ And Y ₁₂ The meaning represented is the same as in formula (8); x is a radical of a fluorine atom ₁₁ Representing the estimated water vapor transmission rate, x ₁₂ Representing the estimated oxygen transmission rate; m is ₁₁ Water vapor transmission rate, m, in an energetically significant measure of the target material properties ₁₂ Representing the oxygen transmission rate in the energetic index of the target material property;

wherein i =3 (representing antibacterial ratio) or 4 (representing ultimate heat-resistant temperature); y is ₁₃ And Y ₁₄ The meaning of the representation is the same as that of formula (8); x is the number of ₁₃ Representing the estimated antibacterial ratio, x ₁₄ Representing the predicted ultimate heat resistance temperature; m is ₁₃ Representing the antibacterial rate in the energetic index of the target material property, m ₁₄ Representing the ultimate heat-resisting temperature in the target material property energy-based index;

wherein i =1 (representing tensile strength) or 2 (representing elongation at break) or 3 (representing burst) or 4 (representing ring crush index in transverse direction); y is ₂₁ 、Y ₂₂ 、Y ₂₃ And Y ₂₄ The meaning of the representation is the same as that of formula (11); x is the number of ₂₁ Representing the predicted tensile strength, x ₂₂ Representing the estimated elongation at break, x ₂₃ Representing the estimated burst, x ₂₄ Representing the pre-estimated transverse ring crush index; m is ₂₁ Representing tensile strength, m, in an energetically oriented index of target material properties ₂₂ Representing elongation at break, m, in an energetically oriented index of target material properties ₂₃ Representing the degree of breakage in the energetic index of the target Material, m ₂₄ Representing the transverse ring crush index in the target material performance energetic index;

wherein, Y ₂₅ The meaning of the representation is the same as that of formula (11); x is the number of ₂₅ Representing the estimated heat conductivity coefficient; m is a unit of ₂₅ Representing the thermal conductivity in the target material property energeticization index;

wherein i =1 (representing the transparency of the candidate coating material) or 2 (representing the surface tension of the candidate coating material) or 4 (representing the degree of ink coloration) or 5 (representing the surface tension of the candidate support material); y is ₃₁ 、Y ₃₂ 、Y ₃₄ And Y ₃₅ The meaning represented is the same as in formula (14); x is the number of ₃₁ Representing estimated transparency, x, of candidate coating materials ₃₂ Estimated surface tension, x, representing candidate coating materials ₃₄ Representing the estimated ink colourity, x ₃₅ An estimated surface tension representative of the candidate support material; m is ₃₁ Representing the transparency, m, of the coating material in the energetic index of the target material properties ₃₂ Representing the surface tension, m, of the coating material in the energetic index of the target material properties ₃₄ Representing the ink coloring degree in an energetic index of the target Material, m ₃₅ Representing the surface tension of the support material in the target material property energetics index;

wherein, Y ₃₃ The meaning of the representation is the same as that of formula (14); x is the number of ₃₃ Representing the arithmetic mean deviation of the predicted profile; m is ₃₃ Represents the arithmetic mean deviation of the profile in the target material property energetics index.

In some embodiments, the demand satisfaction may be determined by a method based on the following equation (17):

Y＝(Y ₁ +Y ₂ +Y ₃ )/3 (17)

wherein Y represents the degree of satisfaction of demand, Y ₁ 、Y ₂ 、Y ₃ See the description above.

The average manufacturing cost may refer to a price per unit mass of a food packaging product prepared based on the corresponding candidate raw material combination. For example, the average cost may be 2 ten thousand dollars per ton. The average cost may be determined based on the record of purchases of the various degradable materials.

The degradation rate of a candidate liner material may refer to the average rate at which the liner material is naturally decomposed when a food packaging product produced based on the candidate material combination is in a natural environment. For example, the degradation rate of the candidate liner material may be 20%/month, meaning that the mass of the liner material of a food packaging product produced based on the candidate material combination that is naturally decomposed per month accounts for 20% of its original total mass (i.e., the time required for the liner material of the food packaging product to completely decompose is 5 months).

The degradation rate of the candidate coating material may refer to the average rate at which the coating material is naturally decomposed when a food packaging product produced based on the candidate material combination is in a natural environment. For example, the degradation rate of the candidate film-coating material may be 10%/month, which means that the film-coating material of the food packaging product produced based on the candidate material combination is naturally decomposed 10% of its original total mass per month (i.e., the time required for the inner liner material of the food packaging product to be completely decomposed is 10 months).

In some embodiments, the candidate blending ratio of the first degradable material, the candidate blending ratio of the second degradable material, the blending ratio of the first auxiliary material and the second auxiliary material may be processed based on a degradation rate determination model to determine a degradation rate of the candidate liner material and a degradation rate of the candidate coating material. The relevant description of the degradation rate determination model can be found in relation to fig. 4.

In some embodiments, the degradation rate of the candidate liner material may also be related to the formulation ratio of the first excipient, and the degradation rate of the candidate coating material may also be related to the formulation ratio of the second excipient. Specifically, the proportion of the first degradable material and the proportion of the second degradable material, and the proportion of the first auxiliary material and the proportion of the second auxiliary material may be processed based on the degradation rate determination model to determine the degradation rate of the candidate lining material and the degradation rate of the candidate coating material.

In some embodiments, the degradation rate of the candidate liner material and the degradation rate of the candidate film-covering material may also be correlated to an estimated environmental characteristic of the food packaging product as it degrades. Specifically, the proportion of the first degradable material, the proportion of the second degradable material, the proportion of the first auxiliary material, the proportion of the second auxiliary material and the estimated environmental characteristics may be processed based on the degradation rate determination model, and the degradation rate of the candidate lining material and the degradation rate of the candidate coating material may be determined.

The estimated environmental characteristics may refer to characteristics of the environment at a location where the food packaging product may be discarded, buried, or stacked. The estimated environmental characteristics can be set manually according to experience based on the average humidity, the average humidity and the average pH value of soil in the region where the food packaged in the same batch of food packaging products is sold. Wherein the average temperature and the average humidity of the region can be determined based on the meteorological records of the region; the soil average pH may be determined based on geological survey records for the region.

And step 330, determining a target raw material combination based on the evaluation scores.

In some embodiments, the candidate material combination with the highest evaluation score may be determined as the target material combination. The first degradable material and the candidate proportion thereof, the second degradable material and the candidate proportion thereof and the candidate support material in the candidate raw material combination respectively correspond to the first degradable material and the proportion thereof, the second degradable material and the proportion thereof and the support material in the target raw material combination.

In some embodiments of the present description, the above method for determining the target raw material combination enables the multi-aspect performance of the degradable packaging product produced based on the target raw material combination to reach a high level; the proportion of the auxiliary materials and the environmental characteristics are introduced when the degradation rate is determined, so that the determined degradation rate is more accurate.

In some embodiments of the present description, by the above method for determining a requirement satisfaction degree, accuracy and adaptability of the determined requirement satisfaction degree are improved; by introducing the estimated food storage duration when the satisfaction degree of the food storage requirement is determined, the accuracy of meeting the determined food storage requirement can be improved, and the accuracy of the determined requirement satisfaction degree is further improved; the adaptability of the determined requirement satisfaction degree can be further improved by controlling the gradient of the data when the requirement satisfaction degree is determined.

It should be noted that the above description of the process 300 is for illustration and description only and is not intended to limit the scope of the present disclosure. Various modifications and changes to flow 300 will be apparent to those skilled in the art in light of this description. However, such modifications and variations are intended to be within the scope of the present description. For example, candidate material combinations are determined using other means.

FIG. 4 is a model architecture diagram of a degradation rate determination model in accordance with certain embodiments of the present description.

In some embodiments, the second determination module 130 may process the candidate proportions of the first degradable material and the candidate proportions of the second degradable material based on a degradation rate determination model to determine a degradation rate of the candidate liner material and a degradation rate of the candidate overlay material. The relevant description about the candidate proportioning of the first degradable material and the candidate proportioning of the second degradable material can be seen from the relevant description of fig. 3.

The degradation rate determination model may refer to a machine learning model for determining the degradation rate of the candidate liner material and the degradation rate of the candidate cover material. In some embodiments, the degradation rate determination model may include any one or combination of various feasible models, such as a Recurrent Neural Network (RNN) model, a Deep Neural Network (DNN) model, a Convolutional Neural Network (CNN) model, and the like.

As shown in fig. 4, the inputs to the degradation rate determination model 450 may include a candidate ratio 430 for a first degradable material and a candidate ratio 440 for a second degradable material, and the outputs may include a degradation rate 460 for a candidate liner material and a degradation rate 470 for a candidate coating material.

In some embodiments, the degradation rate determination model 450 may be trained using a plurality of first training samples labeled with a first label. For example, a plurality of first training samples with first labels may be input into an initial degradation rate determination model, a loss function may be constructed from the first labels and the results of the initial degradation rate determination model, and parameters of the initial degradation rate determination model may be iteratively updated based on the loss function. And finishing the model training when the loss function of the initial degradation rate determination model meets the preset condition of finishing the training to obtain the trained degradation rate determination model. The preset condition for finishing the training may be that the loss function converges, the number of iterations reaches a threshold, and the like.

In some embodiments, the first training sample may include a formula of the sample first degradable material and a formula of the second sample second degradable material. The first label may include an actual degradation rate of the liner material and an actual degradation rate of the cover material corresponding to the first training sample. The ratio of the sample first degradable material and the ratio of the sample second degradable material can be determined based on the ratio of the first degradable material and the ratio of the second degradable material used in the historical production process of the food packaging product. The first label may be determined based on a manual annotation.

In some embodiments, the inputs to the degradation rate determination model 450 may also include a first adjuvant formulation 410 and a second adjuvant formulation 420. The related descriptions of the ratio of the first auxiliary material and the ratio of the second auxiliary material can be found in the related description of fig. 2. Correspondingly, the first training sample may further include a ratio of the sample first auxiliary material and a ratio of the sample second auxiliary material. The ratio of the sample first adjuvant and the ratio of the sample second adjuvant may be preset based on the ratio of the first adjuvant and the ratio of the second adjuvant used in the historical production process of the food packaging product.

In some embodiments, the inputs to the degradation rate determination model 450 may also include estimated environmental characteristics 480. The relevant description of the predicted environmental characteristics can be found in relation to fig. 3. Accordingly, the first training sample may also include sample environmental features. The sample environmental characteristics may be preset based on environmental characteristics of a region where the food packaging product has been historically sold.

In some embodiments of the present description, the degradation rate of the candidate lining material and the degradation rate of the candidate coating material are determined by the model, which can not only ensure the accuracy of the determination result, but also improve the efficiency of the determination work.

FIG. 5 is a model architecture diagram of a performance prediction model in accordance with some embodiments of the present description.

In some embodiments, the second determination module 130 may process the candidate proportions of the first degradable material, the candidate proportions of the second degradable material, and the candidate support material based on the performance prediction model to determine the predicted performance of the candidate liner material, the predicted performance of the candidate film-covering material, and the predicted performance of the candidate support material. For the candidate proportion of the first degradable material, the candidate proportion of the second degradable material, the candidate support material, the estimated performance of the candidate lining material, the estimated performance of the candidate film covering material and the estimated performance of the candidate support material, the relevant description can be found in fig. 3.

The performance prediction model may refer to a machine learning model used to determine the predicted performance of the candidate liner material, the predicted performance of the candidate film-covering material, and the predicted performance of the candidate support material. In some embodiments, the performance prediction model may include any one or combination of various feasible models, such as a Recurrent Neural Network (RNN) model, a Deep Neural Network (DNN) model, a Convolutional Neural Network (CNN) model, and so on.

As shown in fig. 5, the inputs of the performance prediction model 580 may include a candidate ratio 511 of the first degradable material and a candidate ratio 512 of the second degradable material, and the outputs may include an estimated performance 551 of the candidate liner material, an estimated performance 552 of the candidate film covering material, and an estimated performance 570 of the candidate support material.

In some embodiments, performance prediction model 580 may include multiple processing layers. As shown in fig. 5, performance prediction model 580 may include first vector embedding layer 521, second vector embedding layer 522, liner performance prediction layer 541, overlay film performance prediction layer 542, and support performance prediction layer 560.

The first vector embedding layer 521 may determine a first proportioning vector based on processing the candidate proportioning of the first degradable material. As shown in fig. 5, the input of the first vector embedding layer 521 may be the candidate matching 511 of the first degradable material, and the output may be the first matching vector 531.

The first matching vector may refer to data in the form of a vector of matching features determined based on the candidate matching of the first degradable material that may reflect the candidate matching of the first degradable material. For example, the first blending ratio vector can be (20%, 32%,38%, 10%) and represents the meaning of "the candidate blending ratios of polybutylene succinate, polylactic acid, polyhydroxyalkanoate, and polybutylene adipate-terephthalate in the first degradable material are 20%,32%,38%, and 10%, respectively".

The second vector embedding layer 522 may determine a second proportioning vector based on processing a candidate proportioning for the second degradable material. As shown in fig. 5, the input of the second vector embedding layer 522 may be the candidate proportion 512 of the second degradable material, and the output may be the first proportion vector 532.

The second matching vector may refer to data in the form of a vector of matching features that may reflect the candidate matching of the second degradable material, determined based on the candidate matching of the second degradable material. For example, the second blending ratio vector can be (31%, 24%,35%, 10%) and represents the meaning of "the candidate blending ratios of polybutylene succinate, polylactic acid, polyhydroxyalkanoate, and polybutylene adipate-terephthalate in the second degradable material are 31%,24%,35%, and 10%, respectively".

Liner performance prediction layer 541 may determine a predicted performance of the candidate liner material based on processing the first proportioning vector. As shown in FIG. 5, the input to the liner performance prediction layer 541 may be a first proportioning vector 531 and the output may be the predicted performance 551 of the candidate liner material.

The film property prediction layer 542 may determine the predicted properties of the candidate film materials based on processing the first proportioning vector. As shown in fig. 5, the input of the film property prediction layer 542 may be the first composition vector 532, and the output may be the predicted property 552 of the candidate film material.

The support property prediction layer 560 may determine the predicted properties of the candidate support material based on processing the predicted properties of the candidate support material, the candidate liner material, and the predicted properties of the candidate coating material. As shown in FIG. 5, the inputs to the support property prediction layer 560 may include the predicted properties of the candidate support material 513, the candidate liner material 551, and the candidate film coating material 552, and the output may be the predicted properties of the candidate support material 570.

In some embodiments, the first vector embedding layer 521, the second vector embedding layer 522, the liner performance prediction layer 541, the overlay film performance prediction layer 542, and the support performance prediction layer 560 of the performance prediction model 580 may be obtained by joint training. The sample data of the joint training may be a plurality of second training samples labeled with second labels. The second training sample may include a formula for the sample first degradable material and a formula for the sample second degradable material. The second label may include the actual properties of the candidate liner material, the actual properties of the candidate cover material, and the actual properties of the candidate support material for the second training sample. The proportion of the sample first degradable material and the proportion of the sample second degradable material can be obtained based on the proportion of the first degradable material and the proportion of the second degradable material used in the historical production process of the food packaging product. The second label may be determined based on a manual annotation.

An exemplary joint training process may be: inputting the proportion of a sample first degradable material into an initial first vector embedding layer to obtain a first proportion vector output by the initial first vector embedding layer; inputting a first matching vector output by the initial first vector embedding layer as training sample data into the initial lining performance prediction layer to obtain the predicted performance of the candidate lining material output by the initial lining performance prediction layer; inputting the proportion of the sample second degradable material into the initial second vector embedding layer to obtain a second proportion vector output by the initial second vector embedding layer; inputting a second matching vector output by the initial second vector embedding layer as training sample data into the initial film covering performance prediction layer to obtain the predicted performance of the candidate film covering material output by the initial film covering performance prediction layer; taking the estimated performance of the candidate lining material output by the initial lining performance prediction layer and the estimated performance of the candidate film covering material output by the initial film covering performance prediction layer as training sample data, and inputting the training sample data and the sample candidate supporting material into the initial supporting performance prediction layer together to obtain the estimated performance of the candidate supporting material output by the initial supporting performance prediction layer; inputting the estimated performance of the candidate lining material output by the initial lining performance prediction layer and the actual performance of the candidate lining material included by the second label into a first loss function; inputting the estimated performance of the candidate film covering material output by the initial film covering performance prediction layer and the actual performance of the candidate film covering material included by the second label into a second loss function; inputting the estimated performance of the candidate support material output by the initial support performance prediction layer and the actual performance of the candidate support material included by the second label into a third loss function; updating an initial first vector embedding layer and an initial liner performance prediction layer based on a first penalty function; updating the initial second vector embedding layer and the initial film covering performance prediction layer based on the second loss function; and updating the initial support performance prediction layer based on the third loss function until a preset condition is met so as to obtain a trained performance prediction model. The preset condition may include that the loss function is smaller than a threshold, convergence, or a training period reaches a threshold, etc.

In some embodiments, as shown in fig. 5, the input to the first vector embedding layer 521 of the performance prediction model 580 may also include a recipe 514 of the first excipient, and the input to the second vector embedding layer 522 may also include a recipe 515 of the second excipient. Based on this, the second training sample may further include a ratio of the sample first auxiliary material and a ratio of the sample second auxiliary material. The ratio of the sample first adjuvant and the ratio of the sample second adjuvant may be preset based on the ratio of the first adjuvant and the ratio of the second adjuvant used in the historical production process of the food packaging product.

In some embodiments, as shown in fig. 5, the inputs to the first vector embedding layer 521 and the second vector embedding layer 522 of the performance prediction model 580 may also include the extrusion device parameters 516. Based on this, the second training sample may also include sample extrusion device parameters. The sample extrusion apparatus parameters may be determined based on extrusion apparatus parameters used in a historical production process of the food packaging product.

In some embodiments of the specification, the predicted performance of the candidate lining material, the predicted performance of the candidate film-coating material and the predicted performance of the candidate support material are predicted through the performance prediction model, so that the accuracy of the predicted result can be ensured, and the efficiency of prediction work can be improved; the accuracy of the pre-estimated result is improved through the combined training of each processing layer of the performance prediction model; the accuracy of the pre-estimated result is further improved by introducing the proportion of the first auxiliary material and the proportion of the second auxiliary material into the input of the performance prediction model; by introducing the parameters of the extrusion equipment into the input of the performance prediction model, the accuracy of the prediction result is further improved.

FIG. 6 is a model structure diagram of a first parameter determination model according to some embodiments described herein.

In some embodiments, the third determination module 140 may determine the appearance process parameter and the extrusion equipment parameter based on the first parameter determination model processing the target raw material combination, the blending ratio of the first auxiliary material, the blending ratio of the second auxiliary material, the physicochemical property of the first degradable material, the physicochemical property of the second degradable material, and the process demand data. For the relevant descriptions of the target raw material combination, the ratio of the first auxiliary material, the ratio of the second auxiliary material, the process requirement data, the appearance process parameters and the extrusion equipment parameters, reference may be made to the description in relation to fig. 2.

The first parameter determination model may refer to a machine learning model for determining the appearance process parameters and the extrusion apparatus parameters. In some embodiments, the first parameter determination model may include any one or combination of various feasible models, such as a Recurrent Neural Network (RNN) model, a Deep Neural Network (DNN) model, a Convolutional Neural Network (CNN) model, and so on.

The physicochemical properties of the first degradable material may refer to data that can reflect the physical and/or chemical properties of the various degradable materials that the first degradable material comprises. For example, the physicochemical property of the first degradable material may be that "the density of the first degradable material is 1.25g/cm ³ The melting temperature was 120 ℃ and the heat distortion temperature was 90 ℃.

In some embodiments, the physicochemical property of the first degradable material may be data in the form of a vector. For example, the physicochemical characteristic vector of the first degradable material generated based on the physicochemical characteristic of the first degradable material of the above example is (1.25, 120, 90).

The physicochemical properties of the second degradable material may refer to data that can reflect the physical and/or chemical properties of the various degradable materials that the second degradable material comprises. For example, the physicochemical property of the second degradable material may be that "the density of the second degradable material is 1.26g/cm ³ The melting temperature was 118 ℃ and the heat distortion temperature was 95 ℃.

In some embodiments, the physicochemical property of the second degradable material may be data in the form of a vector. For example, the physicochemical characteristic vector of the second degradable material generated based on the physicochemical characteristic of the second degradable material of the above example is (1.26, 118, 95).

As shown in fig. 6, the input of the first parameter determination model 660 may include a target raw material combination 611, a blending ratio 612 of the first auxiliary material, a blending ratio 613 of the second auxiliary material, a physicochemical characteristic 614 of the first degradable material, a physicochemical characteristic 615 of the second degradable material, and process requirement data 616, and the output may include an appearance process parameter 641 and an extrusion apparatus parameter 651.

In some embodiments, the first parameter determination model 660 may include a plurality of processing layers. As shown in fig. 6, the first parameter determination model 660 may include a process feature layer 620, a materialized feature layer 630, an appearance process parameter layer 640, and an extrusion equipment parameter layer 650.

Processing feature layer 620 may determine a processing feature vector based on processing the target raw material combination, the ratio of the first auxiliary material, and the ratio of the second auxiliary material. As shown in fig. 6, the input of the processing feature layer 620 may include a target raw material combination 611, a composition 612 of the first auxiliary material, and a composition 613 of the second auxiliary material, and the output may be a processing feature vector 621.

The processing feature vector may refer to vector-form data that is determined based on the target raw material combination, the ratio of the first auxiliary material, and the ratio of the second auxiliary material, and may comprehensively reflect the features of the target raw material combination, the ratio of the first auxiliary material, and the ratio of the second auxiliary material. For example, the processing feature vector may be (1, 21%,23%,27%,29%,22%,24%,26%,28%,22%,19%,20%,21%,18%,15%,17%,20%,23%, 25%), representing the meaning: for the element value of the 1 st dimension of the processing feature vector, 1 represents that the support material included in the target raw material combination is corrugated paper (it may be preset that 2 represents kraft paper and 3 represents grey board paper); the element values of the 2 nd to 5 th dimensions represent that the proportions of the polybutylene succinate, the polylactic acid, the polyhydroxyalkanoate and the polybutylene adipate-terephthalate in the first degradable material in the target raw material combination are respectively 21%,23%,27% and 29%; the element values of the 6 th dimension to the 9 th dimension represent that the proportions of the polybutylene succinate, the polylactic acid, the polyhydroxyalkanoate and the polybutylene adipate-terephthalate in the second degradable material included in the target raw material combination are 22%,24%,26% and 28% respectively; the element values of the 10 th to 14 th dimensions represent that the mass percentages of the plasticizer, the lubricant, the reinforcing material, the barrier material and the antibacterial agent included in the first auxiliary material are 22%,19%,20%,21% and 18%, respectively; the element values of the 15 th to 19 th dimensions represent the mass ratios of the plasticizer, lubricant, reinforcing material, barrier material and antibacterial agent included in the second auxiliary material of 15%,17%,20%,23% and 25%, respectively.

The materialized feature layer 630 may determine a materialized feature vector based on processing the materialized properties of the first degradable material and the materialized properties of the second degradable material. As shown in fig. 6, the inputs of the materialized feature layer 630 may include the materialized characteristics 614 of the first degradable material and the materialized characteristics 615 of the second degradable material, and the output may be a materialized feature vector 631.

The physicochemical characteristic vector may refer to data in the form of a vector that is determined based on the physicochemical characteristics of the first degradable material and the physicochemical characteristics of the second degradable material and that may comprehensively reflect the characteristics of the physicochemical characteristics of the first degradable material and the second degradable material. For example, the materialized feature vector may be (1.25, 120, 90,1.26, 118, 95), representing the meaning: the first degradable material has a density of 1.25g/cm ³ The melting temperature is 120 ℃, and the thermal deformation temperature is 90 ℃; the second degradable material has a density of 1.26g/cm ³ The melting temperature was 118 ℃ and the heat distortion temperature was 95 ℃.

The appearance process parameter layer 640 may determine appearance process parameters based on processing the processing feature vectors and the process demand data. As shown in fig. 6, the input of the appearance process parameter layer 640 may include the processing feature vectors 621 and the process requirement data 616, and the output may be the appearance process parameters 641.

The extrusion device parameter layer 650 may determine extrusion device parameters based on processing the processing and materialization feature vectors. As shown in fig. 6, the inputs to the extrusion device parameter layer 650 may include the processing feature vector 621 and the materialization feature vector 631, and the output may be the extrusion device parameters 651.

In some embodiments, the process feature layer 620, the materialized feature layer 630, the appearance process parameter layer 640, and the extrusion equipment parameter layer 650 of the first parameter determination model 660 may be obtained by joint training. The sample data of the joint training may be a plurality of third training samples labeled with third labels. The third training sample can comprise a sample target raw material combination, the proportion of the sample first auxiliary material, the proportion of the sample second auxiliary material, the physicochemical properties of the sample first degradable material, the physicochemical properties of the sample second degradable material and sample process requirement data. The third label may include appearance process parameters and extrusion equipment parameters corresponding to the third training sample. The sample target raw material combination may be determined using the raw material combination based on a historical production process of a better quality food packaging product. The third label may be determined based on a manual annotation. The ratio of the sample first adjuvant and the ratio of the sample second adjuvant may be preset based on the ratio of the first adjuvant and the ratio of the second adjuvant used in the historical production process of the food packaging product. The physicochemical properties of the sample first degradable material and the physicochemical properties of the sample second degradable material may be determined based on the physicochemical properties of the first degradable material and the physicochemical properties of the second degradable material used in the above-described historical production process. The sample process demand data may be determined based on historical product demand data.

An exemplary joint training process may be: inputting a sample target raw material combination, the proportion of a sample first auxiliary material and the proportion of a sample second auxiliary material into an initial processing characteristic layer to obtain a processing characteristic vector output by the initial processing characteristic layer; processing characteristic vectors output by the initial processing characteristic layer are used as training sample data and input into the initial appearance process parameter layer together with sample process demand data to obtain appearance process parameters output by the initial appearance process parameter layer; inputting the physicochemical characteristics of the first degradable material of the sample and the physicochemical characteristics of the second degradable material of the sample into the initial physicochemical characteristic layer to obtain a physicochemical characteristic vector output by the initial physicochemical characteristic layer; the physicochemical characteristic vectors output by the initial physicochemical characteristic layer are used as training sample data and input into the initial extrusion equipment parameter layer together with the processing characteristic vectors output by the initial processing characteristic layer to obtain extrusion equipment parameters output by the initial extrusion equipment parameter layer; inputting the appearance process parameters output by the initial appearance process parameter layer and the appearance process parameters included by the third label into a fourth loss function; inputting the extrusion equipment parameters output by the initial extrusion equipment parameter layer and the extrusion equipment parameters included by the third label into a fifth loss function; updating the initial appearance process parameter layer based on the fourth loss function; updating the initial materialized feature layer and the initial extrusion equipment parameter layer based on a fifth loss function; and updating the initial processing characteristic layer based on the fourth loss function and the fifth loss function until a preset condition is met so as to obtain a trained first parameter determination model. The preset condition may include that the loss function is smaller than a threshold, convergence, or a training period reaches a threshold, etc.

In some embodiments of the specification, the appearance process parameters and the extrusion equipment parameters are determined through the first parameter determination model, so that the accuracy of the determination result can be ensured, and the determination efficiency can be improved; the accuracy of the pre-estimated result is improved through the joint training of each processing layer of the first parameter determination model.

In some embodiments, the third determination module 140 may process the estimated properties of the liner material, the film-coating material, and the support material based on the second parameter determination model to determine the lamination parameters. The related description of the squeeze film parameters can be referred to the related description of fig. 2.

The predicted properties of the liner material may refer to the predicted properties of the liner material of a food packaging product produced from the target combination of raw materials. The predicted performance of the liner material may refer to the predicted performance of a candidate liner material for a food packaging product produced from a candidate raw material combination for which the target raw material combination is determined. The estimated performance of the film-coated material may refer to the estimated performance of the film-coated material of a food packaging product produced from the combination of target raw materials. The predicted performance of the film-coating material may refer to the predicted performance of a candidate liner material for a food packaging product produced from a candidate combination of materials for which the target combination of materials is determined. The predicted properties of the support material may refer to the predicted properties of the support material of a food packaging product produced from the target combination of raw materials. The estimated properties of the support material may refer to the estimated properties of candidate support materials for a food packaging product produced from the candidate raw material combination used to determine the target raw material combination. The relative descriptions of the estimated properties of the candidate liner material, the estimated properties of the candidate film-coating material and the estimated properties of the candidate support material can be found in the relative descriptions of fig. 3 and 5. The relevant description of the target raw material combination can be found in relation to fig. 2. The relevant description of the candidate material combination can be found in relation to fig. 3.

The second parameter determination model may refer to a machine learning model for determining the squeeze film parameters. In some embodiments, the second parameter determination model may include any one or combination of various feasible models, such as a Recurrent Neural Network (RNN) model, a Deep Neural Network (DNN) model, a Convolutional Neural Network (CNN) model, and the like.

As shown in fig. 7, inputs to the second parameter determination model 720 may include an estimated property 711 of the liner material, an estimated property 712 of the film coating material, and an estimated property 713 of the support material, and outputs may include film lamination parameters 730.

In some embodiments, the second parameter determination model 720 may be trained by a plurality of fourth training samples labeled with a fourth label. For example, a plurality of fourth training samples with fourth labels may be input into the initial second parameter determination model, a loss function may be constructed from the results of the fourth labels and the initial second parameter determination model, and the parameters of the initial second parameter determination model may be iteratively updated based on the loss function. And finishing the model training when the loss function of the initial second parameter determination model meets the preset condition of finishing the training to obtain the trained second parameter determination model. The preset condition for finishing the training may be that the loss function converges, the number of iterations reaches a threshold, and the like.

In some embodiments, the fourth training sample may include the actual properties of the sample liner material, the actual properties of the sample cover material, and the actual properties of the sample support material. The fourth label may include a squeeze film parameter corresponding to the fourth training sample. The actual properties of the sample liner material, the actual properties of the sample overlaminate material, and the actual properties of the sample support material may be determined based on the actual measured properties of the liner material, overlaminate material, and support material of historically produced food packaging products. The fourth label may be determined based on a manual annotation.

In some embodiments of the present description, the squeeze film parameter is determined by the second parameter determination model, so that accuracy of a determination result can be ensured, and efficiency of determination work can be improved.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, though not explicitly described herein. Such alterations, modifications, and improvements are intended to be suggested in this specification, and are intended to be within the spirit and scope of the exemplary embodiments of this specification.

Also, the description uses specific words to describe embodiments of the description. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, certain features, structures, or characteristics may be combined as suitable in one or more embodiments of the specification.

Additionally, the order in which elements and sequences are described in this specification, the use of numerical letters, or other designations are not intended to limit the order of the processes and methods described in this specification, unless explicitly stated in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the present specification, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to imply that more features than are expressly recited in a claim. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the number allows a variation of ± 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.

For each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this specification, the entire contents of each are hereby incorporated by reference into this specification. Except where the application history document does not conform to or conflict with the contents of the present specification, it is to be understood that the application history document, as used herein in the present specification or appended claims, is intended to define the broadest scope of the present specification (whether presently or later in the specification) rather than the broadest scope of the present specification. It is to be understood that the descriptions, definitions and/or uses of terms in the accompanying materials of this specification shall control if they are inconsistent or contrary to the descriptions and/or uses of terms in this specification.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present disclosure. Other variations are also possible within the scope of the present description. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the specification can be considered consistent with the teachings of the specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.

Claims

1. A preparation process optimization method of a degradable food packaging material comprises the following steps:

acquiring product demand data, wherein the product demand data comprises food storage demand data, food transportation demand data and process demand data;

determining a target material property energetics index based on the product demand data;

determining a target raw material combination based on the target material property energetically oriented index; the target material comprises a support material, a first degradable material and a second degradable material; the first degradable material is a degradable material included in the lining material; the second degradable material is a degradable material contained in the film covering material; the lining material comprises the first degradable material and a first auxiliary material; the film covering material comprises the second degradable material and a second auxiliary material; the first degradable material and the second degradable material both comprise at least one of polybutylene succinate, polylactic acid, polyhydroxyalkanoate and polybutylene adipate-terephthalate; the target raw material combination comprises the support material, the first degradable material and the proportion thereof, and the second degradable material and the proportion thereof;

determining production parameters based on the target feedstock combination and the product demand data.

2. The method of claim 1, wherein determining a target feedstock combination based on the target material properties energetics metric comprises:

determining at least one set of candidate feedstock combinations based on the target material properties energetics metric;

evaluating the evaluation score of each group of the candidate raw material combination; the evaluation score is related to the requirement satisfaction degree, the average manufacturing cost, the degradation rate of the candidate lining material and the degradation rate of the candidate coating material; a degradation rate of the candidate liner material is determined based on the first degradable material; the degradation rate of the candidate coating material is determined based on the second degradable material;

determining the target feedstock combination based on the evaluation score.

3. The method of claim 2,

the requirement satisfaction is determined based on the satisfaction of the food storage requirement data, the satisfaction of the food transportation requirement data and the satisfaction of the process requirement data;

the satisfaction of the food storage requirement data is determined based on the estimated performance of the candidate liner material; the satisfaction degree of the food transportation demand data is determined based on the estimated performance of the candidate film-coated material and the estimated performance of the candidate support material; the satisfaction degree of the process demand data is determined based on the estimated performance of the candidate film coating material and the estimated performance of the candidate support material;

the estimated performance of the candidate lining material comprises at least one of estimated water vapor barrier rate, estimated oxygen barrier rate, estimated antibacterial rate and estimated heat resistance; the estimated performance of the candidate film covering material comprises at least one of estimated tensile strength, estimated elongation at break, estimated transparency and estimated surface tension; the estimated properties of the candidate support material include at least one of an estimated hardness, an estimated thermal insulation, an estimated surface roughness, an estimated ink staining, and an estimated surface tension.

4. The method of claim 1,

the preparation parameters comprise extrusion parameters, appearance process parameters and film pressing parameters;

the extrusion parameters comprise the proportion of the first auxiliary material, the proportion of the second auxiliary material and extrusion equipment parameters; the extrusion equipment parameters are determined based on the proportion of the first degradable material, the physicochemical properties of the first degradable material, the proportion of the first auxiliary material, the proportion of the second degradable material, the physicochemical properties of the second degradable material and the proportion of the second auxiliary material;

the appearance process parameters are determined based on the proportion of the first degradable material, the proportion of the first auxiliary material, the proportion of the second degradable material, the proportion of the second auxiliary material and the process requirement data;

determining the ratio of the first auxiliary material to the ratio of the second auxiliary material comprises:

determining the proportion of the first auxiliary material and the proportion of the second auxiliary material through a preset algorithm based on the first degradable material and the proportion thereof, the second degradable material and the proportion thereof, and the first auxiliary material and the second auxiliary material in the target raw material combination;

the film pressing parameters are determined based on the estimated performance of the supporting material, the estimated performance of the lining material and the estimated performance of the film covering material; the lamination parameters comprise internal and external lamination parameters.

5. A system for optimizing a manufacturing process for a degradable food packaging material, the system comprising:

the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring product demand data, and the product demand data comprises food storage demand data, food transportation demand data and process demand data;

a first determination module for determining a target material property energetics index based on the product demand data;

a second determination module for determining a target feedstock combination based on the target material property energetics indicator; the target material comprises a support material, a first degradable material and a second degradable material; the first degradable material is a degradable material comprised by the liner material; the second degradable material is a degradable material contained in the film covering material; the lining material comprises the first degradable material and a first auxiliary material; the film covering material comprises the second degradable material and a second auxiliary material; the first degradable material and the second degradable material both comprise at least one of polybutylene succinate, polylactic acid, polyhydroxyalkanoate and polybutylene adipate-terephthalate; the target raw material combination comprises the support material, the first degradable material and the proportion thereof, and the second degradable material and the proportion thereof;

a third determination module to determine a production parameter based on the target raw material combination and the product demand data.

6. The system of claim 5, wherein the second determination module is further to:

determining the target feedstock combination based on the evaluation score.

7. The system of claim 6, wherein the second determination module is further to:

8. The system of claim 5, wherein the third determination module is further to:

the extrusion parameters comprise the proportion of the first auxiliary material, the proportion of the second auxiliary material and extrusion equipment parameters; the parameters of the extrusion equipment are determined based on the proportion of the first degradable material, the physicochemical properties of the first degradable material, the proportion of the first auxiliary material, the proportion of the second degradable material, the physicochemical properties of the second degradable material and the proportion of the second auxiliary material;

9. A preparation process optimization device of a degradable food packaging material is characterized by comprising at least one processor and at least one memory;

the at least one memory is for storing computer instructions;

the at least one processor is configured to execute at least some of the computer instructions to implement the method of any of claims 1-4.

10. A computer-readable storage medium, wherein the storage medium stores computer instructions, and when the computer instructions in the storage medium are read by a computer, the computer performs the method of any one of claims 1 to 4.