Parameter optimization method, device, equipment and medium for full-drop bioplastic molding process

Abstract

The present invention provides a parameter optimization method, device, equipment and medium for a fully biodegradable plastic molding process, and relates to the technical field of material process optimization. The present invention uses plasma to treat nano raw materials and mix them with a fully biodegradable matrix; then, an experimental group is set up based on the response surface method and degradation rate data is recorded; then, the optimal variable ratio is determined by establishing a response surface model and performing multiple regression analysis; then, the mixing temperature and time are optimized, and a bio-based lubricant is added for mixing; finally, a final molded product that meets the specifications is obtained through multi-stage cooling and shearing equipment processing. The method improves the performance and finished product quality of fully biodegradable plastics by accurately optimizing each parameter.

Description

Technical Field

[0001] The invention relates to the technical field of material process optimization, and in particular to a parameter optimization method, device, equipment and medium for a full-drop bioplastic molding process. Background Art

[0002] Degradable biofilm materials are essential materials in water treatment processes such as sewage treatment plants, wetland construction, and rural domestic sewage treatment. Their core functions are to supplement carbon sources, enrich microorganisms, and enhance denitrification and phosphorus removal capabilities. Currently, the biofilm fillers on the market are mainly polyethylene, polypropylene, polyvinyl chloride, etc., which are difficult-to-degrade plastic materials and will eventually become white garbage. With the development of the water treatment industry, the requirements for biofilms are also increasing. The use of difficult-to-degrade plastic materials as biofilms will lead to other problems such as white pollution. Therefore, the development of a fully degradable bioplastic as a biofilm material is the future development direction of the water treatment industry.

[0003] In the prior art, publication number CN116663332B discloses a parameter optimization method, device, equipment and medium for a composite material molding process, constructs a target impregnation model of the composite material, imports the target impregnation model into PAM-RTM to construct a target porosity model, inputs multiple sets of input parameter sets of the composite material molding process into the PAM-RTM software, and obtains the porosity distribution and impregnation rate distribution of the target impregnation model; the porosity distribution includes the total porosity corresponding to each set of input parameter sets, and the impregnation rate distribution includes the impregnation rate corresponding to each set of input parameter sets, and based on the porosity distribution and the impregnation rate distribution, the parameters of the composite material molding process are optimized.

[0004] The main problems with the above scheme are: only focusing on the two parameters of porosity and impregnation rate, while ignoring other key variables, such as the mechanical properties and degradation characteristics of the material, the optimization scope is limited, and the comprehensive performance of the material is not taken into account; and through the PAM-RTM software for simulation and modeling, changes in some parameters may lead to large deviations between the simulation results and the actual results, such as temperature gradient and flow non-uniformity, which cannot truly reflect the actual production conditions.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The object of the present invention is to provide a parameter optimization method, device, equipment and medium for a full-drop bioplastic molding process to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A parameter optimization method for a full-drop bioplastic molding process, the specific steps comprising:

[0009] Step 1: treating the nano-raw material by a plasma treatment device to form polar functional groups on the surface of the nano-raw material, mixing the treated nano-raw material with a fully degradable matrix, and treating the mixture of the nano-raw material and the fully degradable matrix by an ultrasonic dispersion device;

[0010] Step 2: multiple experimental groups were set up based on the central composite design principle of the response surface methodology. In each experimental group, different variable ratios were used, and the degradation rate data of each experimental group was recorded under the same test conditions. The variables included nano raw materials, degradable matrix, biomass filler, grafting agent, compatibilizer and plasticizer;

[0011] Step 3: Establish a response surface model, substitute the experimental data into the response surface model, use statistical analysis software to perform multiple regression analysis, calculate the regression coefficients in the response surface model, verify the model obtained by regression analysis on experimental data that are not involved in modeling, check the prediction accuracy of the model, and generate the optimal variable ratio corresponding to the optimal value of the response variable by gradient descent method;

[0012] Step 4: Mix the materials according to the optimal variable ratio, test the storage modulus and loss modulus at different temperatures and times by a dynamic thermomechanical analysis instrument, place the mixed materials at different temperatures for different times, establish a relationship model between temperature and time and storage modulus and loss modulus, optimize the mixing temperature and mixing time with the goal of maximizing the storage modulus and minimizing the loss modulus, and after determining the optimal temperature and time, add the bio-based lubricant and mix in the mixing equipment;

[0013] Step 5: The temperature of the extruded compound after mixing is gradually reduced through multi-stage cooling. In each stage of cooling, the cooling temperature and cooling time combination with the least effect on the internal stress of the compound is selected through experimental verification. The cooled compound is conveyed to the shearing equipment and cut into the final molded product that meets the required specifications.

[0014] Furthermore, the processing power of the plasma processing device is 100W, the processing time is 10 minutes, and it is naturally cooled at room temperature after the processing is completed; the ultrasonic frequency of the ultrasonic dispersion equipment is 20kHz, the processing time is 30 minutes, and it is cooled and dried at room temperature after the processing is completed.

[0015] Furthermore, the response surface model is:

[0016] ;

[0017] in, represents the degradation rate, Respectively represent the proportions of nanomaterials, degradable matrix, biomass filler, grafting agent, compatibilizer and plasticizer, represents a constant term, represents the first-order regression coefficient, represents the second-order interaction coefficient, represents the second-order regression coefficient.

[0018] Furthermore, the principle for generating the optimal variable ratio corresponding to the optimal value of the response variable by the gradient descent method is:

[0019] The initial ratio is selected according to the ratio of the variables, and the variable ratio is updated according to the ratio and learning rate. The formula is:

[0020] ;

[0021] ;

[0022] in, Indicates The matching value of the iteration, The index representing the number of iterations, Respectively represent The ratio of nanomaterials, biodegradable matrix, biomass filler, grafting agent, compatibilizer and plasticizer in the first iteration, Indicates The matching value of the iteration, represents the learning rate, represents the gradient of the response variable with respect to the matching variable;

[0023] The gradient of each variable is calculated according to the formula:

[0024] ;

[0025] in, Representation variables The gradient of Indicates types of variables, An index representing the kind of variable, and , Indicates a small increment, Indicated in A unit vector with one bit being 1 and the other bits being 0;

[0026] When the gradient of the variable is less than the preset gradient threshold, the iteration stops, and the corresponding ratio value is the optimal variable ratio.

[0027] Furthermore, the principle for establishing the relationship model between temperature and time and storage modulus and loss modulus is:

[0028] ;

[0029] ;

[0030] in, represents the storage modulus, Indicates the mixing temperature, Indicates the mixing time, Regression coefficient representing the effect of temperature and time on storage modulus, represents the loss modulus, Regression coefficients representing the effects of temperature and time on loss modulus.

[0031] Furthermore, with the goal of maximizing the storage modulus and minimizing the loss modulus, the principle for optimizing the mixing temperature and mixing time is as follows:

[0032] The fitness function reflecting the mixing stability value is generated based on the formula:

[0033] ;

[0034] in, Indicates the mixing stability value, represents the weight of storage modulus, represents the weight of loss modulus, ;

[0035] Based on the optimization of genetic algorithm, the mixing temperature and time corresponding to the maximum fitness function are selected as the optimal mixing temperature and mixing time.

[0036] The present invention also provides a parameter optimization device for a full-drop bioplastic molding process, wherein the system is used to implement the parameter optimization method for the full-drop bioplastic molding process, specifically comprising:

[0037] A raw material pretreatment module is used to treat the nano raw material by a plasma treatment device, form polar functional groups on the surface of the nano raw material, mix the treated nano raw material with a fully degradable matrix, and treat the mixture of the nano raw material and the fully degradable matrix by an ultrasonic dispersion device;

[0038] A ratio detection module is used to set up multiple experimental groups based on the central composite design principle of the response surface method. In each experimental group, different variable ratios are selected, and the degradation rate data of each experimental group is recorded under the same test conditions. The variables include nano raw materials, degradable matrix, biomass filler, grafting agent, compatibilizer and plasticizer;

[0039] The ratio optimization module is used to establish a response surface model, substitute the experimental data into the response surface model, use statistical analysis software to perform multiple regression analysis, calculate the various regression coefficients in the response surface model, and verify the model obtained by regression analysis on experimental data that are not involved in modeling to check the prediction accuracy of the model. The optimal variable ratio corresponding to the response variable reaching the optimal value is generated by the gradient descent method;

[0040] The mixing optimization module is used to mix the materials according to the optimal variable ratio, test the storage modulus and loss modulus at different temperatures and times through a dynamic thermomechanical analysis instrument, place the mixed materials at different temperatures for different times, establish a relationship model between temperature and time and the storage modulus and loss modulus, optimize the mixing temperature and mixing time with the goal of maximizing the storage modulus and minimizing the loss modulus, and after determining the optimal temperature and time, add the bio-based lubricant and mix in the mixing equipment;

[0041] The cooling output module is used to gradually reduce the temperature of the compound extruded after mixing through multi-stage cooling. In each stage of cooling, the cooling temperature and cooling time combination with the least impact on the internal stress of the compound is selected through experimental verification. The cooled compound is conveyed to the shearing equipment and cut into the final molded product that meets the required specifications.

[0042] A parameter optimization device for a full-drop bioplastic molding process comprises a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the parameter optimization method for the full-drop bioplastic molding process is implemented.

[0043] A computer-readable storage medium, characterized in that a computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the above-mentioned parameter optimization method for the full-drop bioplastic molding process.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] The present invention pre-treats the nano-raw materials, improves the surface activity and hydrophilicity of the nano-raw materials, increases the binding force between the nano-raw materials and the fully degradable matrix, and avoids the agglomeration of the nano-raw materials; through the response surface method, the effects of different ratios of variables such as nano-raw materials, degradable matrix, biomass filler, grafting agent, compatibilizer and plasticizer on the degradation rate can be systematically investigated, thereby determining the best combination of variables. This provides a theoretical basis and data support for subsequent material formulations, ensures that the final product has the best degradation performance, and reduces the cost of trial and error.

[0046] The present invention also ensures that the various components are fully mixed under optimal conditions to improve the comprehensive performance of the material by accurately controlling and optimizing the mixing temperature and time, and establishes a relationship model between temperature and time and the storage modulus and loss modulus, which can achieve precise control in the production process, reduce performance fluctuations between batches, and improve product consistency and stability; after mixing, multi-stage cooling is used to avoid the formation of a large temperature gradient inside the composite, reduce the internal stress of the composite, improve the mechanical properties, dimensional stability and crack resistance of the material, and ensure the quality of the product in practical applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a schematic diagram of a method flow chart of an embodiment of the present invention;

[0048] Figure 2 Schematic diagram of a device module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0050] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0051] Example:

[0052] See also Figure 1 , the present invention provides a technical solution:

[0053] A parameter optimization method for a full-drop bioplastic molding process, the specific steps comprising:

[0054] Step 1: treating the nano-raw material by a plasma treatment device to form polar functional groups on the surface of the nano-raw material, mixing the treated nano-raw material with a fully degradable matrix, and treating the mixture of the nano-raw material and the fully degradable matrix by an ultrasonic dispersion device;

[0055] In this embodiment, the processing power of the plasma treatment device is 100W, the processing time is 10 minutes, and it is naturally cooled at room temperature after the treatment is completed; the ultrasonic frequency of the ultrasonic dispersion equipment is 20kHz, the processing time is 30 minutes, and it is cooled and dried at room temperature after the treatment is completed; the plasma treatment technology can enhance the surface activity of nano-raw materials, form polar functional groups, and improve the compatibility of nano-raw materials with biomass materials and fully degradable matrices; the ultrasonic assisted dispersion technology can significantly improve the uniform dispersion of nano-raw materials in the matrix, thereby improving the mechanical properties and stability of the material.

[0056] Step 2: multiple experimental groups were set up based on the central composite design principle of the response surface methodology. In each experimental group, different variable ratios were used, and the degradation rate data of each experimental group was recorded under the same test conditions. The variables included nano raw materials, degradable matrix, biomass filler, grafting agent, compatibilizer and plasticizer;

[0057] In this embodiment, the principle of setting multiple experimental groups based on the central composite design principle of the response surface method is:

[0058] Central composite design (CCD) is mainly composed of three types of experimental points, including factor points, axis points and center points. Factor points correspond to the lowest and highest levels of each variable and are used to estimate first-order terms and interaction terms. Axis points are located outside the range of each variable and are used to estimate second-order terms. Center points are located at the center of the variable range and are used to estimate experimental errors and model repeatability. When setting up the experimental group, first determine the variables in the experiment and the level range of each variable, select the highest and lowest values ​​of the variable levels, combine them into factor points, and then set the center point position, which can be set to (0,0). Select the axis point and set it outside the center point. Distance, under the premise of ensuring that the experimental points are evenly distributed, form a complete experimental plan.

[0059] Step 3: Establish a response surface model, substitute the experimental data into the response surface model, use statistical analysis software to perform multiple regression analysis, calculate the regression coefficients in the response surface model, verify the model obtained by regression analysis on experimental data that are not involved in modeling, check the prediction accuracy of the model, and generate the optimal variable ratio corresponding to the optimal value of the response variable by gradient descent method;

[0060] In this embodiment, the response surface model is:

[0061] ;

[0062] in, represents the degradation rate, Respectively represent the proportions of nanomaterials, degradable matrix, biomass filler, grafting agent, compatibilizer and plasticizer, represents a constant term, represents the first-order regression coefficient, represents the second-order interaction coefficient, represents the second-order regression coefficient.

[0063] Constant term Indicates the value of the response variable when all variables are 0, the first-order regression coefficient Indicates the linear effect of the variable on the response variable, the second-order regression coefficient It indicates the influence of the square term of the variable on the response variable, reflecting the nonlinear effect of the variable, and the second-order interaction coefficient It indicates the influence of the interaction between two variables on the response variable, reflecting the effect of the joint action of the two variables; multiple regression analysis is performed using the statistical analysis software SPSS to calculate the regression coefficient in the response surface model;

[0064] The principle of generating the optimal variable ratio corresponding to the optimal value of the response variable by the gradient descent method is:

[0065] The initial ratio is selected according to the ratio of the variables, and the variable ratio is updated according to the ratio and learning rate. The formula is:

[0066] ;

[0067] ;

[0068] in, Indicates The matching value of the iteration, The index representing the number of iterations, Respectively represent The ratio of nanomaterials, biodegradable matrix, biomass filler, grafting agent, compatibilizer and plasticizer in the first iteration, Indicates The matching value of the iteration, represents the learning rate, represents the gradient of the response variable with respect to the matching variable;

[0069] Initialize and set the initial ratio value. The initial ratio value can be randomly selected or determined based on expert scores. Set the learning rate. The learning rate determines the step size of each iterative update. It is usually a small positive number. The value can be 0.01. Set the gradient threshold to determine whether the gradient is small enough. The gradient threshold can be , at each iteration step, the gradient of the response variable with respect to the matching variable is calculated, and the matching value is updated using the gradient descent formula;

[0070] The gradient of each variable is calculated according to the formula:

[0071] ;

[0072] in, Representation variables The gradient of Indicates types of variables, An index representing the kind of variable, and , Indicates a small increment, which is a very small positive number, which can be 0.0001. Indicated in A unit vector with one bit being 1 and the other bits being 0;

[0073] When the gradient of the variable is less than the preset gradient threshold, the iteration stops, and the corresponding ratio value is the optimal variable ratio.

[0074] Step 4: Mix the materials according to the optimal variable ratio, test the storage modulus and loss modulus at different temperatures and times by a dynamic thermomechanical analysis instrument, place the mixed materials at different temperatures for different times, establish a relationship model between temperature and time and storage modulus and loss modulus, optimize the mixing temperature and mixing time with the goal of maximizing the storage modulus and minimizing the loss modulus, and after determining the optimal temperature and time, add the bio-based lubricant and mix in the mixing equipment;

[0075] In this embodiment, the principle for establishing the relationship model between temperature and time and storage modulus and loss modulus is:

[0076] ;

[0077] ;

[0078] in, represents the storage modulus, Indicates the mixing temperature, Indicates the mixing time, Regression coefficient representing the effect of temperature and time on storage modulus, represents the loss modulus, Regression coefficients representing the effects of temperature and time on loss modulus;

[0079] The least squares method is used to determine the regression coefficients, based on the principle that:

[0080] For the storage modulus model, construct the independent variable matrix and the response variable matrix:

[0081] ;

[0082] ;

[0083] in, represents the independent variable matrix, Indicates The mixing temperature, Indicates Mixing time, The response variable matrix representing the storage modulus, Indicates Storage modulus;

[0084] For the loss modulus model, construct the response variable matrix:

[0085] ;

[0086] in, The response matrix representing the loss modulus, Indicates The loss modulus;

[0087] The regression coefficient vectors generated based on the regression coefficients of storage modulus and loss modulus are:

[0088] ;

[0089] ;

[0090] in, represents the regression coefficient vector of storage modulus, Regression coefficient vector representing the loss modulus;

[0091] The least squares solution is obtained from the matrix based on the formula:

[0092] ;

[0093] ;

[0094] Generate a regression coefficient vector and determine the regression coefficients.

[0095] The principle for optimizing the mixing temperature and mixing time with the goal of maximizing the storage modulus and minimizing the loss modulus is:

[0096] The fitness function reflecting the mixing stability value is generated based on the formula:

[0097] ;

[0098] in, Indicates the mixing stability value, represents the weight of storage modulus, represents the weight of loss modulus, ,and ;

[0099] Based on the optimization of genetic algorithm, the mixing temperature and time corresponding to the maximum fitness function are selected as the optimal mixing temperature and mixing time. The principle of optimizing the mixing temperature and mixing time by genetic algorithm is:

[0100] Collect multiple groups of historical mixing temperatures and mixing times, establish a deep learning network model, take the historical mixing temperatures and mixing times as input, and use the mixing stability value as a label output to train the model, randomly generate an initial population based on multiple groups of mixing temperatures and mixing times, each individual in the initial population is a group of mixing temperatures and mixing times, the mixing temperature and mixing time are the genes of the individual, set the upper and lower limits of the mixing temperature and mixing time as constraints, input the individuals with the set constraints into the model, use the mixing stability value corresponding to each individual as its fitness value, select, crossover and mutate according to the fitness value, specifically, sort each individual from large to small according to the fitness value to generate a sequence, select the first 50% of the individuals in the sequence as the parent generation, perform crossover and mutation operations on the parent generation individuals to obtain new offspring individuals, integrate the new offspring individuals and the parent generation individuals into a new population, repeat the above-mentioned iterative operations of selection, crossover and mutation until a predetermined number of iterations is reached, and select the individual with the largest fitness as the optimal mixing parameter combination, including the optimal mixing temperature and the optimal mixing time.

[0101] Step 5: The temperature of the extruded compound after mixing is gradually reduced through multi-stage cooling. In each stage of cooling, the cooling temperature and cooling time combination with the least effect on the internal stress of the compound is selected through experimental verification. The cooled compound is conveyed to the shearing equipment and cut into the final molded product that meets the required specifications.

[0102] See also Figure 2 The present invention also provides a parameter optimization device for a full-drop bioplastic molding process, and the device is used to implement the parameter optimization method for the full-drop bioplastic molding process, specifically comprising:

[0103] A raw material pretreatment module is used to treat the nano raw material by a plasma treatment device, form polar functional groups on the surface of the nano raw material, mix the treated nano raw material with a fully degradable matrix, and treat the mixture of the nano raw material and the fully degradable matrix by an ultrasonic dispersion device;

[0104] A ratio detection module is used to set up multiple experimental groups based on the central composite design principle of the response surface method. In each experimental group, different variable ratios are selected, and the degradation rate data of each experimental group is recorded under the same test conditions. The variables include nano raw materials, degradable matrix, biomass filler, grafting agent, compatibilizer and plasticizer;

[0105] The ratio optimization module is used to establish a response surface model, substitute the experimental data into the response surface model, use statistical analysis software to perform multiple regression analysis, calculate the various regression coefficients in the response surface model, and verify the model obtained by regression analysis on experimental data that are not involved in modeling to check the prediction accuracy of the model. The optimal variable ratio corresponding to the response variable reaching the optimal value is generated by the gradient descent method;

[0106] The mixing optimization module is used to mix the materials according to the optimal variable ratio, test the storage modulus and loss modulus at different temperatures and times through a dynamic thermomechanical analysis instrument, place the mixed materials at different temperatures for different times, establish a relationship model between temperature and time and the storage modulus and loss modulus, optimize the mixing temperature and mixing time with the goal of maximizing the storage modulus and minimizing the loss modulus, and after determining the optimal temperature and time, add the bio-based lubricant and mix in the mixing equipment;

[0107] The cooling output module is used to gradually reduce the temperature of the compound extruded after mixing through multi-stage cooling. In each stage of cooling, the cooling temperature and cooling time combination with the least impact on the internal stress of the compound is selected through experimental verification. The cooled compound is conveyed to the shearing equipment and cut into the final molded product that meets the required specifications.

[0108] A parameter optimization device for a full-drop bioplastic molding process comprises a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the parameter optimization method for the full-drop bioplastic molding process is implemented.

[0109] A computer-readable storage medium, characterized in that a computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the above-mentioned parameter optimization method for the full-drop bioplastic molding process.

[0110] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0111] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0112] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0113] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A parameter optimization method for a full-drop bioplastic molding process, characterized in that: The specific steps include: Step 1: treating the nano-raw material by a plasma treatment device to form polar functional groups on the surface of the nano-raw material, mixing the treated nano-raw material with a fully degradable matrix, and treating the mixture of the nano-raw material and the fully degradable matrix by an ultrasonic dispersion device; Step 2: multiple experimental groups were set up based on the central composite design principle of the response surface methodology. In each experimental group, different variable ratios were used, and the degradation rate data of each experimental group was recorded under the same test conditions. The variables included nano raw materials, degradable matrix, biomass filler, grafting agent, compatibilizer and plasticizer; Step 3: Establish a response surface model, substitute the experimental data into the response surface model, use statistical analysis software to perform multiple regression analysis, calculate the regression coefficients in the response surface model, verify the model obtained by regression analysis on experimental data that are not involved in modeling, check the prediction accuracy of the model, and generate the optimal variable ratio corresponding to the optimal value of the response variable by gradient descent method; Step 4: Mix the materials according to the optimal variable ratio, test the storage modulus and loss modulus at different temperatures and times by a dynamic thermomechanical analysis instrument, place the mixed materials at different temperatures for different times, establish a relationship model between temperature and time and storage modulus and loss modulus, optimize the mixing temperature and mixing time with the goal of maximizing the storage modulus and minimizing the loss modulus, and after determining the optimal temperature and time, add the bio-based lubricant and mix in the mixing equipment; Step 5: The temperature of the extruded compound after mixing is gradually reduced through multi-stage cooling. In each stage of cooling, the cooling temperature and cooling time combination with the least effect on the internal stress of the compound is selected through experimental verification. The cooled compound is conveyed to the shearing equipment and cut into the final molded product that meets the required specifications.

2. The parameter optimization method for a full-drop bioplastic molding process according to claim 1, characterized in that: In the step 1, the processing power of the plasma treatment device is 100 W, the processing time is 10 minutes, and it is naturally cooled at room temperature after the processing is completed; the ultrasonic frequency of the ultrasonic dispersion equipment is 20 kHz, the processing time is 30 minutes, and it is cooled and dried at room temperature after the processing is completed.

3. The parameter optimization method for a full-drop bioplastic molding process according to claim 1, characterized in that: The response surface model in step 3 is: ； in, represents the degradation rate, Respectively represent the proportions of nanomaterials, degradable matrix, biomass filler, grafting agent, compatibilizer and plasticizer, represents a constant term, represents the first-order regression coefficient, represents the second-order interaction coefficient, represents the second-order regression coefficient.

4. The parameter optimization method for a full-drop bioplastic molding process according to claim 1, characterized in that: The principle for generating the optimal variable ratio corresponding to the response variable reaching the optimal value by the gradient descent method in step 3 is: The initial ratio is selected according to the ratio of the variables, and the variable ratio is updated according to the ratio and learning rate. The formula is: ； ； in, Indicates The ratio value of the iteration, The index representing the number of iterations, Respectively represent The ratio of nanomaterials, biodegradable matrix, biomass filler, grafting agent, compatibilizer and plasticizer in the first iteration, Indicates The ratio value of the iteration, represents the learning rate, represents the gradient of the response variable with respect to the matching variable; The gradient of each variable is calculated according to the formula: ； in, Representation variables The gradient of Indicates types of variables, An index representing the kind of variable, and , Indicates a small increment, Indicated in A unit vector with one bit being 1 and the other bits being 0; When the gradient of the variable is less than the preset gradient threshold, the iteration stops, and the corresponding ratio value is the optimal variable ratio.

5. The parameter optimization method for a full-drop bioplastic molding process according to claim 1, characterized in that: The principle for establishing the relationship model between temperature and time and storage modulus and loss modulus in step 4 is: ； ； in, represents the storage modulus, Indicates the mixing temperature, Indicates the mixing time, Regression coefficient representing the effect of temperature and time on storage modulus, represents the loss modulus, Regression coefficients representing the effects of temperature and time on loss modulus.

6. The parameter optimization method for a full-drop bioplastic molding process according to claim 5, characterized in that: The principle for optimizing the mixing temperature and mixing time with the goal of maximizing the storage modulus and minimizing the loss modulus is: The fitness function reflecting the mixing stability value is generated based on the formula: ； in, Indicates the mixing stability value, represents the weight of storage modulus, represents the weight of loss modulus, ,and ; Based on the optimization of genetic algorithm, the mixing temperature and time corresponding to the maximum fitness function are selected as the optimal mixing temperature and mixing time.

7. A parameter optimization device for a full-drop bioplastic molding process, characterized in that: The device is used to implement the parameter optimization method of the full-drop bioplastic molding process according to any one of claims 1 to 6, specifically comprising: A raw material pretreatment module is used to treat the nano raw material by a plasma treatment device, form polar functional groups on the surface of the nano raw material, mix the treated nano raw material with a fully degradable matrix, and treat the mixture of the nano raw material and the fully degradable matrix by an ultrasonic dispersion device; A ratio detection module is used to set up multiple experimental groups based on the central composite design principle of the response surface method. In each experimental group, different variable ratios are selected, and the degradation rate data of each experimental group is recorded under the same test conditions. The variables include nano raw materials, degradable matrix, biomass filler, grafting agent, compatibilizer and plasticizer; The ratio optimization module is used to establish a response surface model, substitute the experimental data into the response surface model, use statistical analysis software to perform multiple regression analysis, calculate the various regression coefficients in the response surface model, and verify the model obtained by regression analysis on experimental data that are not involved in modeling to check the prediction accuracy of the model. The optimal variable ratio corresponding to the response variable reaching the optimal value is generated by the gradient descent method; The mixing optimization module is used to mix the materials according to the optimal variable ratio, test the storage modulus and loss modulus at different temperatures and times through a dynamic thermomechanical analysis instrument, place the mixed materials at different temperatures for different times, establish a relationship model between temperature and time and the storage modulus and loss modulus, optimize the mixing temperature and mixing time with the goal of maximizing the storage modulus and minimizing the loss modulus, and after determining the optimal temperature and time, add the bio-based lubricant and mix in the mixing equipment; The cooling output module is used to gradually reduce the temperature of the compound extruded after mixing through multi-stage cooling. In each stage of cooling, the cooling temperature and cooling time combination with the least impact on the internal stress of the compound is selected through experimental verification. The cooled compound is conveyed to the shearing equipment and cut into the final molded product that meets the required specifications.

8. A parameter optimization device for a full-drop bioplastic molding process, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the parameter optimization method for the full-drop bioplastic molding process described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the parameter optimization method for the full-drop bioplastic molding process described in any one of claims 1-6.

Images