Intelligent control method and system for high-filled modified material production process optimization

Abstract

The application discloses an intelligent control method and system for high-filling modified material production process optimization, and relates to the technical field of production process optimization control; historical process data and product quality label sets of each production process in each production experiment are collected in advance, quality parameter labels of each production process in each production experiment are calculated, a quality prediction model is trained for each production process, quality prediction functions corresponding to the quality prediction model of each production process are collected, and a quality threshold value is preset for the kth production process; for the kth production process of the material to be produced, based on the quality parameter label of the k-1th production process, the quality threshold value of the kth production process and the quality prediction function, an optimized production parameter set of the kth process is obtained; and the application can greatly improve the qualified product rate and production efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of production process optimization control, in particular to an intelligent control method and system for high-filled modified material production process optimization. BACKGROUND

[0002] High-filled modified material is a kind of high-performance composite material, which is usually made of base resin (such as PP, PE and other thermoplastics), high-content inorganic filler (such as glass fiber, carbon fiber, etc.) and a small amount of additives (such as compatibilizer, flame retardant, etc.) through physical mixing. This kind of material has the advantages of resin processability and high strength, high rigidity of filler, and is widely used in automobile, electronic, aviation and other fields.

[0003] The production of high-filled modified material generally needs to go through three main processes:

[0004] Mixing process: the base resin, filler and additive are put into the mixer according to the ratio, and are fully mixed and homogenized under high temperature and high speed stirring.

[0005] Injection molding / extrusion molding process: the mixed composite material is injected into the mold or formed by the extruder under heating.

[0006] Cooling process: control the cooling rate to make the formed product cool and solidify and obtain the required geometric shape and performance index.

[0007] The traditional process parameters are mainly controlled by manual experience and trial and error, which cannot quantitatively consider the weight of different quality indicators, has long parameter adjustment period, high labor cost, lacks the guidance of system theory model, and is difficult to control and improve the product quality level. Human factors will also affect the parameter adjustment effect.

[0008] Therefore, the present application proposes an intelligent control method and system for high-filled modified material production process optimization. SUMMARY

[0009] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes an intelligent control method and system for high-filled modified material production process optimization, which greatly improves the qualified product rate and production efficiency.

[0010] To achieve the above purpose, an intelligent control method for high-filled modified material production process optimization is proposed, which comprises the following steps:

[0011] Step 1: preform N times of production experiments, collect the historical process data of each production process and the product quality label set in each production experiment; N is the number of selected production experiments;

[0012] Step 2: based on the product quality label set, calculate the quality parameter label of each production process in each production experiment;

[0013] Step three: for the kth production process, based on the historical process data, the quality parameter label and the product quality label set of the k-1th production process, train a quality prediction model for each production process, and collect the quality prediction function corresponding to the quality prediction model of each production process; k is the number of production processes in the production order;

[0014] Step four: preset the quality threshold for the kth production process; for the kth production process of the material to be produced, based on the quality parameter label of the k-1th production process, the quality threshold of the kth production process and the quality prediction function, obtain the optimized production parameter set of the kth process.

[0015] Specifically, the way to collect the historical process data and the product quality label set of each production process in each production experiment is:

[0016] For the kth production process of each production experiment, collect the raw material data input into the production process, and the production parameters of the production process to form the historical process data.

[0017] Specifically, for the kth production process of each production experiment, collect the parameter values of each quality parameter of the product obtained after the production process to form the product quality label set.

[0018] Specifically, for the mixing process, the quality parameters include filler dispersion uniformity and actual density.

[0019] For the injection extrusion process, the quality parameters include actual size, measured tensile strength value and appearance integrity.

[0020] For the cooling process, the quality parameters include size change rate, volume shrinkage rate, surface quality fraction, measured impact strength, measured HDT value and surface resistivity.

[0021] Specifically, the way to calculate the quality parameter label of each production process in each production experiment based on the product quality label set is:

[0022] For the mixing process, based on the filler dispersion uniformity, the actual density and the pre-calculated theoretical density, a mixing quality function is constructed, and the parameter values of each quality parameter of the mixing process of each production experiment are substituted into the mixing quality function. The calculated function value is the quality parameter label of the mixing process.

[0023] For the injection extrusion process, based on the actual size, the measured tensile strength value, the appearance integrity, the preset design size and the preset design tensile strength value, an injection extrusion quality function is constructed, and the parameter values of the quality parameters of the injection extrusion process of each production experiment are substituted into the injection extrusion quality function, and the calculated function value is the quality parameter label of the injection extrusion process;

[0024] For the cooling process, based on the size change rate, the volume shrinkage rate, the surface mass fraction, the measured impact strength, the measured HDT value and the surface resistivity, the preset allowable size change rate, the preset design shrinkage rate, the preset design impact strength and the collected use temperature, a cooling quality function is constructed, and the parameter values of the quality parameters of the cooling process of each production experiment are substituted into the cooling quality function, and the calculated function value is the quality parameter label of the cooling process.

[0025] Specifically, the way of training the quality prediction model for each production process is:

[0026] The raw material data, production parameters of the kth production process of each production experiment and the quality parameter labels of the k-1th production process are collectively composed into a set of training feature vectors;

[0027] For the kth production process, the training feature vector of each production experiment corresponding to the kth production process is taken as the input of the quality prediction model, and the quality prediction model takes the predicted value of the quality parameter of the product of the production process as the output; the quality prediction model takes the quality parameter label of the product of the production process as the prediction target, takes the difference between the predicted value of the quality parameter and the quality parameter label as the prediction error, and takes the minimization of the sum of squares of all production experiments as the training target; the quality prediction model is trained until the sum of squares of the prediction error reaches convergence, and the training is stopped; the quality prediction model is a polynomial model.

[0028] Specifically, the way of collecting the quality prediction function corresponding to the quality prediction model of each production process is:

[0029] The polynomial function expression corresponding to the quality prediction model of each production process is read as the quality prediction function.

[0030] Specifically, for the kth production process of the material to be produced, based on the quality parameter label of the k-1th production process, the quality threshold of the kth production process and the quality prediction function, the way of obtaining the optimized production parameter set of the kth process is:

[0031] Before the kth production process is performed on the material to be produced, the raw material data of the product of the (k-1)th production process is collected and marked as a raw material set A, and the parameter values of each quality parameter of the product of the (k-1)th production process are collected and marked as a quality set B;

[0032] The function expression of the quality prediction function of the kth production process is marked as Fk, Fk=fk(A, B, x); wherein fk is the function equation corresponding to the quality prediction model of the kth production process, and x is the production parameter variable set of the kth production process;

[0033] The quality threshold of the kth production process is marked as Yk;

[0034] The quality threshold is substituted into the quality prediction function to construct an optimization constraint condition: Yk

[0035] An intelligent control system for optimizing the production process of high-filling modified materials is proposed, which includes a test data collection module, a quality calculation module, a model training module, and a production control module; wherein each module is connected through electrical means;

[0036] The test data collection module collects historical process data and product quality label sets of each production process in N production experiments in advance, and sends the historical process data and product quality label sets to the model training module, and sends the product quality label sets to the quality calculation module;

[0037] The quality calculation module calculates the quality parameter label of each production process in each production experiment based on the product quality label set, and sends the quality parameter label to the model training module;

[0038] The model training module trains a quality prediction model for each production process based on the historical process data, the quality parameter label, and the product quality label set of the (k-1)th production process for the kth production process, and collects the quality prediction function corresponding to the quality prediction model of each production process, and sends the quality prediction function to the production control module;

[0039] The production control module presets a quality threshold for the kth production process; for the kth production process of the material to be produced, the quality parameter label of the (k-1)th production process, the quality threshold of the kth production process, and the quality prediction function are used to obtain the optimized production parameter set of the kth process.

[0040] An electronic device is provided, comprising a processor and a memory, wherein the memory stores a computer program that can be invoked by the processor;

[0041] The processor executes the intelligent control method for high-filling modified material production process optimization by invoking the computer program stored in the memory.

[0042] A computer readable storage medium is provided, which stores an erasable computer program;

[0043] When the computer program runs on the computer device, the computer device executes the intelligent control method for high-filling modified material production process optimization.

[0044] Compared with the prior art, the beneficial effects of the present application are:

[0045] The present application collects historical process data and product quality label set of each production process in each production experiment by pre-performing N times of production experiment, N is the number of selected production experiment, based on the product quality label set, calculates the quality parameter label of each production process in each production experiment, for the kth production process, based on the historical process data, the quality parameter label and the product quality label set of the k-1th production process, trains the quality prediction model for each production process, and collects the quality prediction function corresponding to the quality prediction model of each production process, and presets the quality threshold for the kth production process, for the kth production process of the material to be produced, based on the quality parameter label of the k-1th production process, the quality threshold of the kth production process and the quality prediction function, obtains the optimization production parameter set of the kth process, quantifies the weight of different quality parameters by constructing a reasonable quality score function, collects historical process data and quality detection data, and automatically analyzes these big data by using machine learning technology, trains the quality prediction model for each process, and then combines the quality threshold, and automatically calculates the optimal production parameter set of each process by using the optimization algorithm, thereby greatly improving the qualified product rate and production efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 The flow chart of the intelligent control method for high-filling modified material production process optimization in embodiment 1 of the present application is provided;

[0047] Figure 2 The module connection relationship diagram of the intelligent control system for high-filling modified material production process optimization in embodiment 2 of the present application is provided;

[0048] Figure 3 The structure schematic diagram of the electronic device in embodiment 3 of the present application is provided;

[0049] Figure 4The computer readable storage medium structure diagram in embodiment 4 of the present application. DETAILED DESCRIPTION

[0050] The technical solutions of the present application will be described clearly and completely in combination with embodiments. Obviously, the described embodiments are only some of the embodiments of the present application, but not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0051] Embodiment 1

[0052] As shown in the intelligent control method for production process optimization of high-filled modified materials, the method comprises the following steps: Figure 1

[0053] Step 1: Preparing N production experiments, collecting historical process data and product quality label set of each production process in each production experiment; N is the number of selected production experiments;

[0054] Step 2: Based on the product quality label set, calculating the quality parameter label of each production process in each production experiment;

[0055] Step 3: For the kth production process, based on the historical process data, the quality parameter label and the product quality label set of the k-1th production process, training a quality prediction model for each production process, and collecting the quality prediction function corresponding to the quality prediction model of each production process; k is the number of production processes in production order;

[0056] Step 4: Pre-setting the quality threshold for the kth production process; for the kth production process of the material to be produced, based on the quality parameter label of the k-1th production process, the quality threshold of the kth production process and the quality prediction function, obtaining the optimized production parameter set of the kth process.

[0057] Among them, each production process in the production process of high-filled modified materials includes mixing process, injection extrusion process and cooling process.

[0058] In each production experiment, a plurality of raw materials for producing high-filled modified materials are selected as test materials, and the production process from the test materials to the high-filled modified materials is completed by actively controlling each production parameter in each production process by the test personnel, so as to record each production parameter of each production process and the product quality of each production process in each production experiment.

[0059] Among them, the way of collecting historical process data and product quality label set of each production process in each production experiment is: ​

[0060] For the kth production process of each production experiment, collect the raw material data input into the production process, and the production parameters of the production process to form a historical process data;

[0061] The raw material data is determined according to the physical properties of the production results of the previous production process. For example, for the mixing process, the raw material data includes but is not limited to the raw material ratio, the melt flowability (MFR) and density of the base resin, the size, aspect ratio, density and chemical composition of the filler, and the polarity, molecular weight, melting point of the auxiliary agent, etc. For the injection molding and extrusion process, the raw material data includes but is not limited to the flowability and wettability of the mixed high-filling composite material, etc. For the cooling process, the raw material data includes but is not limited to the crystallinity, residual stress and micro-porosity of the high-temperature molded product after injection molding / extrusion, etc.

[0062] For the kth production process of each production experiment, collect the parameter values of the quality parameters of the product obtained after the production process, to form a product quality label set;

[0063] Specifically, for the mixing process, the quality parameters include filler dispersion uniformity, actual density;

[0064] For the injection molding and extrusion process, the quality parameters include actual size, measured tensile strength value, and appearance integrity;

[0065] For the cooling process, the quality parameters include size change rate, volume shrinkage rate, surface quality fraction, measured impact strength, measured HDT value, and surface resistivity.

[0066] It should be noted that for each quality parameter, the corresponding measurement means is used to measure after each production process is completed. The measurement method of each quality parameter is a conventional method in the art, which will not be described herein. For some subjective quality parameters, such as appearance integrity, the surface crack number can be set, the appearance integrity can be set as the difference between the product shape and the expected shape, and the surface quality fraction can be set as the crack number and flatness of the surface of the final product.

[0067] Further, the quality parameter label of each production process in each production experiment is calculated based on the product quality label set in the following manner:

[0068] For the mixing process, a mixing quality function is constructed based on the filler dispersion uniformity, the actual density, and the pre-calculated theoretical density. The parameter values of the quality parameters of the mixing process of each production experiment are substituted into the mixing quality function, and the calculated function value is the quality parameter label of the mixing process;

[0069] For the injection molding extrusion process, based on the actual size, the measured tensile strength value, the appearance integrity, the preset design size and the preset design tensile strength value, an injection molding extrusion quality function is constructed, and the parameter values of each quality parameter of the injection molding extrusion process of each production experiment are substituted into the injection molding extrusion quality function, and the calculated function value is the quality parameter label of the injection molding extrusion process;

[0070] For the cooling process, based on the size change rate, the volume shrinkage rate, the surface mass fraction, the measured impact strength, the measured HDT value and the surface resistivity, the preset allowable size change rate, the preset design shrinkage rate, the preset design impact strength and the collected use temperature, a cooling quality function is constructed, and the parameter values of each quality parameter of the cooling process of each production experiment are substituted into the cooling quality function, and the calculated function value is the quality parameter label of the cooling process.

[0071] In a preferred embodiment, the mixing quality function can be set as: Q_mix=30×U+20×(100-5×|Dm-Dt|); wherein: Q_mix is the mixing quality function, U is the filler dispersion uniformity fraction, Dm is the actual density, Dt is the theoretical density;

[0072] The injection molding extrusion quality fraction formula can be set as: Wherein: Q_mold is the injection molding extrusion quality function, L is the actual size, Lt is the design size, Ts is the measured tensile strength value, Td is the design tensile strength value, Wg is the appearance integrity;

[0073] The cooling quality function can be set as:

[0074] Wherein, Q_final is the cooling quality function, Sv is the size change rate, Sd is the allowable size change rate, Vr is the volume shrinkage rate, Vd is the design shrinkage rate, S is the surface mass fraction, Is is the measured impact strength, Id is the design impact strength, Ht is the measured HDT value, Hu is the use temperature, Rs is the surface resistivity.

[0075] It should be noted that the design principle of the proportion of each parameter in the mixing quality function, the injection molding extrusion quality function and the cooling quality function and the mathematical formula is:

[0076] For the mixing process, the filler dispersion uniformity and the density are the two most critical indicators, and their importance in production accounts for 60% and 40%, respectively;

[0077] The injection / extrusion process is mainly judged by dimensional accuracy (35%), tensile strength (35%) and appearance (30%), and their importance in production is 35%, 35% and 30%, respectively;

[0078] In the cooling quality function, the dimensional change rate (25%) and the volume shrinkage rate (25%) are the key indicators of the cooling process, accounting for half of the total score, reflecting their important influence on the quality of the final product. Surface quality (15%) is next, because good surface quality is also a basic requirement for many applications. Impact strength (25%) and heat distortion temperature HDT (20%) are two key mechanical indicators reflecting the impact resistance and thermal performance of the final product, accounting for a high proportion. Other properties, such as surface resistivity (15%), although less important than the above, cannot be ignored.

[0079] The rationality of the mathematical expression design includes:

[0080] |Dm-Dt| represents the absolute deviation of density from the theoretical value, and 5 is an empirical penalty coefficient.

[0081] A score of 1 is given for a dimensional error within 0.05 mm, and a linear deduction is made for exceeding the line.

[0082] The ratio of tensile strength to design value is represented by 1, and a full score is given for a value greater than 1, and a proportional deduction is made for a value less than 1.

[0083] 1-10×|Sv-Sd| and 1-10×|Vr-Vd| are in the form of making dimensional change and shrinkage strictly controlled within the allowed range, and a serious deduction will be made for exceeding the range.

[0084] The ratio of impact strength to design value is represented by 1, and a proportional score is given.

[0085] A score of 1 is given for a difference of 30% or more between HDT and the use temperature, and a linear deduction is made for a difference less than 30%.

[0086] |Log(Rs)-5.5| represents a score of 1 for a resistivity within the range of (10 5 ,10 12 ) ohms, and a deduction is made for a deviation from this range according to the logarithmic difference.

[0087] It can be understood that the mixed quality function, the injection extrusion quality function and the cooling quality function are actual values calculated by the established physical parameters after the product is produced, and the quality parameters of the product in each production process are determined by the raw material data, the production parameters and the quality of the raw material (i.e. the quality parameters of the last production process), so a model is needed to predict the quality parameters of the next production process.

[0088] Further, the way of training the quality prediction model for each production process based on the historical process data, the quality parameter label and the product quality label set of the k-1th production process is:

[0089] The raw material data, the production parameters of the kth production process and the quality parameter labels of the k-1th production process in each production experiment are collectively composed into a set of training feature vectors;

[0090] For the kth production process, the training feature vector of each production experiment corresponding to the kth production process is taken as the input of the quality prediction model, and the quality prediction model takes the predicted value of the quality parameter of the product of the production process as the output; the quality prediction model takes the quality parameter label of the product of the production process as the prediction target, takes the difference between the predicted value of the quality parameter and the quality parameter label as the prediction error, and takes the minimization of the sum of squares of the prediction errors of all production experiments as the training target; the quality prediction model is trained until the sum of squares of the prediction errors reaches convergence, and the training is stopped; the quality prediction model is a polynomial model.

[0091] Further, the way of collecting the quality prediction function corresponding to the quality prediction model of each production process is:

[0092] The polynomial function expression corresponding to the trained quality prediction model of each production process is read as the quality prediction function;

[0093] It can be understood that the quality prediction function is a polynomial function with the quality parameter as the dependent variable and the raw material data, the production parameters and the quality of the raw material as the independent variables.

[0094] Further, the quality threshold is the minimum threshold of each quality parameter of the product of each production process, and only the product that reaches the quality threshold can be considered as a qualified product.

[0095] For the kth production process of the material to be produced, based on the quality parameter label of the k-1th production process, the quality threshold of the kth production process and the quality prediction function, the way of obtaining the optimized production parameter set of the kth production process is:

[0096] Before the kth production process, the raw material data of the product of the (k-1) th production process is collected and marked as a raw material set A, and the parameter values of each quality parameter of the product of the (k-1) th production process are collected and marked as a quality set B;

[0097] The function expression of the quality prediction function of the kth production process is marked as Fk, Fk=fk(A, B, x); wherein fk is the function equation corresponding to the quality prediction model of the kth production process, and x is the production parameter variable set of the kth production process;

[0098] The quality threshold of the kth production process is marked as Yk;

[0099] The quality threshold is substituted into the quality prediction function to construct an optimization constraint condition: Yk

[0100] It can be understood that the combination of each production parameter in the obtained feasible solution set can control each production parameter in the kth production process based on the raw material data and the quality of the raw material, so as to ensure that qualified products are obtained in the production process.

[0101] Embodiment 2

[0102] As shown in Figure 2 The intelligent control system for optimizing the production process of high-filling modified materials includes a test data collection module, a quality calculation module, a model training module, and a production control module; wherein each module is connected through electrical connection;

[0103] The test data collection module collects historical process data and product quality label sets of each production process in each production experiment through N times of production experiments in advance, and sends the historical process data and product quality label sets to the model training module, and sends the product quality label sets to the quality calculation module;

[0104] The quality calculation module calculates the quality parameter label of each production process in each production experiment based on the product quality label set, and sends the quality parameter label to the model training module;

[0105] The model training module trains a quality prediction model for each production process based on the historical process data, the quality parameter label, and the product quality label set of the (k-1) th production process, collects the quality prediction function corresponding to the quality prediction model of each production process, and sends the quality prediction function to the production control module;

[0106] The production control module presets a quality threshold for the kth production process. For the kth production process of the material to be produced, based on the quality parameter label of the k-1th production process, the quality threshold of the kth production process, and the quality prediction function, an optimized production parameter set of the kth process is obtained.

[0107] Embodiment 3

[0108] Figure 3 is a schematic diagram of an electronic device structure according to an embodiment of the present application. As shown in Figure 3 According to another aspect of the present application, an electronic device 100 is also provided. The electronic device 100 can include one or more processors and one or more memories. The memory stores computer readable code which, when executed by the one or more processors, can perform the intelligent control method for high-fill modified material production process optimization as described above.

[0109] The method or device according to the embodiments of the present application can also be implemented by means of Figure 3 The architecture of the electronic device is shown. As shown in Figure 3 The electronic device 100 can include a bus 101, one or more CPUs 102, a ROM 103, a RAM 104, a communication port 105 connected to a network, an input / output component 106, a hard disk 107, etc. The storage device in the electronic device 100, such as the ROM 103 or the hard disk 107, can store the intelligent control method for high-fill modified material production process optimization provided by the present application.

[0110] Further, the electronic device 100 can also include a user interface 108. Of course, Figure 3 The architecture shown is only exemplary, and when implementing different devices, one or more components of the electronic device shown can be omitted according to actual needs. Figure 3

[0111] Embodiment 4

[0112] Figure 4 is a schematic diagram of a computer readable storage medium structure according to an embodiment of the present application. As shown in Figure 4 ​Fig. 8 shows a computer readable storage medium 200 according to an embodiment of the present application. The computer readable storage medium 200 stores computer readable instructions. When the computer readable instructions are run by a processor, the intelligent control method for high-filled modified material production process optimization according to an embodiment of the present application described above with reference to the accompanying drawings can be executed. The computer readable storage medium 200 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM), cache memory, and the like. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, and the like.

[0113] In addition, according to the embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, the present application provides a non-transitory machine readable storage medium storing machine readable instructions executable by a processor to perform instructions corresponding to the method steps provided by the present application, which perform the above-mentioned functions defined in the method of the present application when the computer program is executed by a central processing unit (CPU).

[0114] The methods and apparatuses, devices of the present application can be implemented in many ways. For example, the methods and apparatuses, devices of the present application can be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-mentioned order of steps for the method is only for illustration, and the steps of the method of the present application are not limited to the above-mentioned order, unless otherwise specifically described. In addition, in some embodiments, the present application can also be implemented as a program recorded in a recording medium, which includes machine readable instructions for implementing the method according to the present application. Thus, the present application also covers the recording medium storing the program for executing the method according to the present application.

[0115] In addition, the part of the above-mentioned technical solutions provided in the embodiments of the present application that is consistent with the implementation principle of the corresponding technical solutions in the prior art is not described in detail, so as not to be too verbose.

[0116] The specific embodiments described above further illustrate the objects, technical solutions and beneficial effects of the present application. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0117] The above-mentioned preset parameters or preset thresholds are set by a person skilled in the art according to actual conditions or obtained by a large amount of data simulation.

[0118] The above examples are only used to illustrate the technical method of the present application but not limit the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present application can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present application.

Claims

1. A method for intelligent control for optimization of high filled modified material production process characterized by, The method comprises the following steps: Step 1: Preparing N production experiments, collecting historical process data and product quality label set of each production process in each production experiment; N is the number of selected production experiments; Step 2: Based on the product quality label set, calculating the quality parameter label of each production process in each production experiment; for the mixing process, based on the filling material dispersion uniformity, actual density and pre-calculated theoretical density, a mixing quality function is constructed; for the injection extrusion process, based on the actual size, measured tensile strength value, appearance integrity, pre-set design size and pre-set design tensile strength value, an injection extrusion quality function is constructed; for the cooling process, based on the size change rate, volume shrinkage rate, surface quality fraction, measured impact strength, measured HDT value and surface resistivity, pre-set allowable size change rate, pre-set design shrinkage rate, pre-set design impact strength and collected use temperature, a cooling quality function is constructed; the quality parameter labels of the mixing process, the injection extrusion process and the cooling process are calculated respectively; Step 3: For the kth production process, based on the historical process data, the quality parameter label and the product quality label set of the k-1th production process, a quality prediction model is trained for each production process, and a quality prediction function corresponding to the quality prediction model of each production process is collected; k is the number of production processes in the production order; Step 4: Pre-setting a quality threshold for the kth production process; for the kth production process of the material to be produced, based on the quality parameter label of the k-1th production process, the quality threshold of the kth production process and the quality prediction function, an optimized production parameter set of the kth process is obtained; The way of calculating the quality parameter label of each production process in each production experiment based on the product quality label set is: The parameter values of each quality parameter of the mixing process of each production experiment are substituted into the mixing quality function, and the calculated function value is the quality parameter label of the mixing process; The parameter values of each quality parameter of the injection extrusion process of each production experiment are substituted into the injection extrusion quality function, and the calculated function value is the quality parameter label of the injection extrusion process; The parameter values of each quality parameter of the cooling process of each production experiment are substituted into the cooling quality function, and the calculated function value is the quality parameter label of the cooling process.

2. The intelligent control method for high filled modified material production process optimization as claimed in claim 1 wherein, For the kth production process of each production experiment, the raw material data input into the production process and the production parameters of the production process are collected to form the historical process data.

3. The intelligent control method for high filled modified material production process optimization as claimed in claim 1 wherein, For the kth production process of each production experiment, the parameter values of each quality parameter of the product obtained after the production process are collected to form the product quality label set.

4. The intelligent control method for high filled modified material production process optimization as claimed in claim 3, wherein, The way of training the quality prediction model for each production process is: The raw material data, production parameters of the kth production process of each production experiment and the quality parameter labels of the k-1th production process are collectively composed into a group of training feature vectors; For the kth production process, the training feature vector of each production experiment corresponding to the kth production process is taken as the input of the quality prediction model, and the quality prediction model takes the predicted value of the quality parameter of the product of the production process as the output; the quality prediction model takes the quality parameter label of the product of the production process as the prediction target, takes the difference between the predicted value of the quality parameter and the quality parameter label as the prediction error, and takes the minimization of the sum of squares of the prediction errors of all production experiments as the training target; the quality prediction model is trained until the sum of squares of the prediction errors converges, and the training is stopped; the quality prediction model is a polynomial model.

5. The intelligent control method for high filled modified material production process optimization as claimed in claim 4 wherein, The way to collect the quality prediction function corresponding to the quality prediction model of each production process is: Read the polynomial function expression corresponding to the trained quality prediction model of each production process as the quality prediction function.

6. The intelligent control method for high filled modified material production process optimization as claimed in claim 5 wherein, The way to obtain the optimized production parameter set of the kth production process based on the quality parameter label of the k-1th production process, the quality threshold of the kth production process and the quality prediction function is: Before the kth production process is performed on the material to be produced, collect the raw material data of the product of the k-1th production process and mark it as a raw material set A, and collect the parameter values of each quality parameter of the product of the k-1th production process and mark it as a quality set B; The function expression of the quality prediction function of the kth production process is marked as Fk, Fk=fk(A, B, x); wherein fk is the function equation corresponding to the quality prediction model of the kth production process, and x is the production parameter variable set of the kth production process; The quality threshold of the kth production process is marked as Yk; The quality threshold is substituted into the quality prediction function to construct the optimization constraint condition: Yk 7. An intelligent control system for high filled modified material production process optimization for implementing the intelligent control method for high filled modified material production process optimization according to any one of claims 1 to 6, characterized in that, The test data collection module, the quality calculation module, the model training module and the production control module are connected through electrical connection; The test data collection module collects historical process data and product quality label set of each production process in each production experiment by performing N production experiments in advance, and sends the historical process data and product quality label set to the model training module, and sends the product quality label set to the quality calculation module; The quality calculation module calculates the quality parameter label of each production process in each production experiment based on the product quality label set, and sends the quality parameter label to the model training module; The model training module trains a quality prediction model for each production process based on the historical process data, the quality parameter label and the product quality label set of the k-1th production process, collects the quality prediction function corresponding to the quality prediction model of each production process, and sends the quality prediction function to the production control module; The production control module presets a quality threshold for the kth production process, and obtains an optimized production parameter set for the kth process based on the quality parameter tag of the k-1th production process, the quality threshold of the kth production process and a quality prediction function.

8. An electronic device, comprising: Comprise: A processor and a memory, The memory stores a computer program that can be called by the processor; The processor executes the intelligent control method for optimizing the production process of high-filled modified materials in the background by calling the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that, A computer program is stored thereon and can be erased and written; When the computer program runs on the computer device, the computer device executes the intelligent control method for optimizing the production process of high-filled modified materials in the background.

Images