A method, device, and storage medium for optimizing a rubber formulation

Abstract

The present invention discloses a method, device and storage medium for optimizing a rubber formulation. The method includes: obtaining parameter information of the rubber, and constructing an optimization model for the rubber formulation according to the parameter information; determining the constraint conditions of the optimization model for the rubber formulation, and establishing an objective function; using a preset estimation of distribution algorithm to optimize the objective function, and obtaining a formulation with a smaller cost and degree of violation of chemical components under the condition of meeting the constraint conditions; evaluating the obtained formulation, creating a data set according to the evaluation result, and training a classification model by using the data set; guiding the selection process of the estimation of distribution algorithm according to the classification model to select more formulations with classification results. The present invention measures the problem of rubber formulation design by establishing a mathematical model for optimizing the rubber formulation, and uses the estimation of distribution algorithm to optimize the cost of the formulation and the degree of violation of chemical component constraints, so as to obtain a formulation with a small cost and chemical violation degree, which can be widely applied to the field of rubber formulation design.

Description

Technical Field

[0001] The present invention relates to the field of rubber formulation design, and particularly to a method, device, and storage medium for optimizing rubber formulations. Background Art

[0002] Rubber is an industrial product made by mixing various materials and kneading them at high temperatures. Rubber products have penetrated all aspects of our lives and have become one of the essential materials. Rubbers with different functions are fired according to different formulations. Rubber formulation design includes the selection of raw material types and the determination of ratios, which have a great impact on the physical and chemical properties of the final rubber product.

[0003] Currently, the difficulties in rubber formulation design are manifested in the following four aspects. First, the problems existing in rubber formulation design are not clearly described, and the optimization objectives are not clear. Second, for each newly designed rubber formulation, it is necessary to knead out the rubber finished product, and the design and kneading processes consume a large amount of manpower and material resources. Third, the evaluation of rubber formulations usually only applies simple chemical composition detection and expert judgment, lacking an evaluation model. Fourth, the selection of raw materials and the determination of ratios together constitute an NP-hard combinatorial optimization problem, which cannot be solved by traditional mathematical optimization methods.

[0004] In the design of rubber formulations in production, when designing a rubber formulation optimization method, the following three challenging problems are also considered. 1) It is necessary to consider various constraints, including the ratio limits of each category, each material, and each chemical component, because in the refining process, a little overstepping the boundary will cause great losses. 2) Since the experimental cost of refining products is very high, the evaluation of rubber formulations is also expensive. At the same time, the data of historical rubber formulations is limited. Therefore, it is difficult to train an effective formulation evaluation model. 3) The rubber industry has a long history, and the rubber formulation design method needs to be combined with the long-term accumulated experience of humans, and the obtained rubber formulations also need to conform to the opinions of experts. The above problems urgently need to be solved. Summary of the Invention

[0005] To at least to some extent solve one of the technical problems existing in the prior art, the purpose of the present invention is to provide a method, device, and storage medium for optimizing rubber formulations.

[0006] The technical solution adopted by the present invention is as follows:

[0007] A method for optimizing a rubber formulation, comprising the following steps:

[0008] S1. Obtain the parameter information of the rubber, and construct a rubber formulation optimization model according to the parameter information;

[0009] S2. Determine the constraint conditions of the rubber formulation optimization model, use the cost of the rubber formulation and the degree of violation of the chemical composition constraints of the rubber formulation as evaluation indicators, and establish an objective function;

[0010] S3. Use the preset estimation of distribution algorithm to optimize the objective function, and obtain a formulation with a smaller cost and a degree of violation of the chemical composition under the satisfaction of the constraint conditions;

[0011] S4. Evaluate the obtained formulation, create a data set according to the evaluation results, and train a classification model using the data set;

[0012] S5. Guide the selection process of the estimation of distribution algorithm according to the classification model to select more formulations with classification results; repeat steps S3 - S4 until the number of formulations with the highest classification results reaches the preset quantity.

[0013] Furthermore, the parameter information of the rubber includes: rubber raw material information, raw material category information, raw material cost, raw material chemical content information, conditions that the raw material ratio needs to meet, conditions that the category ratio needs to meet, and conditions that the final formulation chemical content ratio needs to meet;

[0014] The determination of the constraint conditions of the rubber formulation optimization model includes:

[0015] Use the intervals that the raw material ratio needs to meet and the intervals that the category ratio needs to meet as constraint conditions;

[0016] Take the minimum degree of violation of the formulation cost and chemical composition constraints as the optimization objective.

[0017] Furthermore, the expression of the rubber formulation optimization model is:

[0018]

[0019] Among them, in the rubber formulation optimization model, m raw materials are selected from multiple raw materials, and then the ratio X i ; g e (X) is the calculation formula for the degree of violation of the e-th chemical composition, f e (X) is the calculation formula for the e-th chemical composition content of the raw material, F(X) is the objective function of the degree of violation of the chemical composition, Q is the objective function of the price; q i represents the price of the i-th raw material, p ei represents the content of the e-th chemical composition of the i-th raw material, lc e and uc e are the lower and upper limits of the e-th chemical composition; C k is the k-th category, L k and U kThey are the lower and upper limits of the k-th category, respectively, l i and u i represent the lower and upper limits of the i-th raw material.

[0020] Furthermore, the step S3 specifically includes:

[0021] S31. Taking all rubber formulations as individuals, encoding the individuals, and randomly initializing the population;

[0022] S32. Generating new individuals in the population, sampling from a preset selection matrix to determine the raw material serial numbers of the individuals; if the currently selected individual sequence does not meet the raw material constraints or category constraints, the serial numbers will be resampled through the selection matrix;

[0023] S33. Before determining the ratio, determining the feasible range of the ratio of the selected raw material;

[0024] S34. According to the estimation of distribution algorithm, establishing a Gaussian distribution for each optional raw material, sampling the ratio corresponding to the selected raw material through the Gaussian distribution, and ensuring that the ratio is within the feasible range;

[0025] S35. Merging the individuals of the parent generation and the offspring generation, and screening the merged population according to two optimization objectives: the formula cost and the violation degree of the chemical composition;

[0026] S36. Updating the selection matrix according to the population obtained by screening;

[0027] S37. Updating the Gaussian distribution of each raw material according to the population obtained by screening;

[0028] S38. Repeating steps S32 - S37 until the number of individuals whose violation degrees of both the cost and the chemical constraints are less than the preset threshold reaches the preset number.

[0029] Furthermore, the sampling from the preset selection matrix to determine the raw material serial numbers of the individuals includes:

[0030] Each raw material number corresponds to a row in the matrix, and the initial raw material corresponding matrix is the diagonal;

[0031] The sampling of the raw material is based on the rule of binary tournament: the first raw material is selected according to the values on the diagonal of the matrix. Randomly select two numbers, compare the values of the two numbers on the diagonal, and select the number with the larger value as the serial number of the first raw material; the subsequent raw materials are selected according to the previous raw material. In the row of the matrix of the previous raw material, randomly select two numbers, compare the values of the two numbers in that row, and select the number with the larger value as the serial number of the subsequent raw material.

[0032] Further, the selection matrix is updated using the following formula:

[0033]

[0034] where i and j are the adjacent raw material numbers in the raw material sequence of the selected individuals; τ ij is the element in the i-th row and j-th column of the matrix, p i is the proportion of the i-th raw material in the individual, p j is the proportion of the j-th raw material in the individual, rank represents the level of the individual; τ ii is the i-th diagonal element of the matrix, the set synthesized by the first L largest elements in the i-th row of the A matrix, τ t is an element in the set A; τ min and τ max are the lower and upper limits of the value of the element in the matrix respectively; a and β are parameters controlling the update amplitude.

[0035] Further, the Gaussian distribution of each raw material is updated in the following manner:

[0036]

[0037]

[0038] where and are the mean and deviation of the proportion of the i-th raw material; H is the number of individuals selecting the i-th raw material in the population, p h is the proportion corresponding to the i-th raw material in each individual; l i and u i are the lower and upper bounds of the i-th raw material respectively; θ is a coefficient controlling the update speed, and ε is a coefficient to prevent the deviation increment from being zero.

[0039] Further, guiding the selection process of the distribution estimation algorithm using the classification model includes:

[0040] Modifying the objective function of the distribution optimization algorithm according to the classification result of the classification model, and the expression is as follows:

[0041]

[0042] where F(X) is the objective function of the degree of violation of chemical components, F ′ (X) is the modified objective function, cl is the classification result of the individual, and k is the coefficient controlling the objective function.

[0043] Another technical solution adopted by the present invention is:

[0044] A rubber formula optimization device, comprising:

[0045] At least one processor;

[0046] At least one memory for storing at least one program;

[0047] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0048] Another technical solution adopted by the present invention is:

[0049] A computer-readable storage medium storing a program executable by a processor, the program executable by the processor being used to execute the method as described above when executed by the processor.

[0050] The beneficial effects of the present invention are: By establishing a mathematical model for rubber formula optimization, the present invention quantifies the problems in rubber formula design, and uses the estimation of distribution algorithm to optimize the formula cost and the violation degree of chemical composition constraints, obtaining a formula with low cost and low chemical violation degree, and solving the problems of high consumption of manpower and material resources and difficult evaluation in traditional rubber formulas. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following introduces the drawings related to the technical solutions in the embodiments of the present invention or the prior art. It should be understood that the drawings introduced below are only for conveniently and clearly expressing some embodiments of the technical solutions in the present invention, and those skilled in the art can also obtain other drawings based on these drawings without creative efforts.

[0052] Figure 1 is a flowchart of an interactive rubber formula optimization method based on the estimation of distribution algorithm in an embodiment of the present invention;

[0053] Figure 2 is a flowchart block diagram of an improved estimation of distribution algorithm for an interactive rubber formula optimization method in an embodiment of the present invention;

[0054] Figure 3 is a schematic diagram of individual coding of an improved estimation of distribution algorithm for an interactive rubber formula optimization method in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] Embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present invention and should not be construed as a limitation to the present invention. For the step numbers in the following embodiments, they are only set for the convenience of elaboration and explanation, and no limitation is imposed on the order between the steps. The execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0056] In the description of the present invention, it should be understood that for the orientation description, such as the orientation or positional relationship indicated by up, down, front, back, left, right, etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention.

[0057] In the description of the present invention, the meaning of several is one or more, the meaning of multiple is two or more, greater than, less than, exceeding, etc. are understood as not including the present number, and above, below, within, etc. are understood as including the present number. If there is a description of first and second, it is only for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features or implicitly indicating the sequence relationship of the indicated technical features.

[0058] In the description of the present invention, unless otherwise clearly defined, words such as setting, installing, connecting, etc. should be understood in a broad sense. Those skilled in the art can reasonably determine the specific meanings of the above words in the present invention in combination with the specific content of the technical solution.

[0059] Evolutionary computation is an effective technique for solving optimization problems based on the concept of natural biological evolution, especially combinatorial optimization problems such as the traveling salesman problem (TSP), scheduling problems, etc. In actual production, many multi-objective optimization problems can be solved by applying evolutionary computation. As an algorithm of evolutionary computation, the estimation of distribution algorithm is a stochastic optimization technique that explores the space of potential solutions by building and sampling an explicit probability model of candidate solutions. The essence of the estimation of distribution algorithm is that in each iteration, it selects individuals with better fitness to estimate the probability model and samples individuals from the probability distribution model for the next iteration. As this iterative process progresses, the probability model will obtain the probability distribution information of being able to sample individuals with high fitness and gradually become efficient. Such a gradient-free optimizer can meet the requirements of rubber formulation design in terms of raw material combination and proportion allocation.

[0060] As Figure 1As shown in the figure, this embodiment provides an interactive rubber formula optimization method based on the estimation of distribution algorithm to solve the problems of low efficiency and high cost in the existing rubber formula design, inability to consider multi - category and material constraints, and lack of an evaluation model integrating expert experience. The method specifically includes the following steps:

[0061] S1: Obtain the information of rubber raw materials available for selection, the category information of raw materials, the cost of raw materials, the chemical content information of raw materials, the conditions that the raw material ratio needs to meet, the conditions that the category ratio needs to meet, and the conditions that the final formula chemical content ratio needs to meet.

[0062] S2: According to the above - mentioned parameter information, construct a mathematical model for rubber formula optimization; among them, the intervals that the raw material ratio needs to meet and the intervals that the category ratio needs to meet are used as constraint conditions; two objective functions are established with the cost of the rubber formula and the degree of violation of the chemical composition constraints of the rubber formula as evaluation indicators, and the minimum of the formula cost and the degree of violation of the chemical composition constraints is used as the optimization goal.

[0063] S3: Use the improved estimation of distribution algorithm to optimize the above - mentioned two objectives, and obtain a batch of formulas with lower cost and lower degree of violation of chemical composition under the conditions of meeting the raw material ratio constraints and category ratio constraints.

[0064] S4: Send the obtained formulas to expert evaluation, create a data set according to the evaluation results, and train a classification model relying on the accumulated data set. The higher the result evaluated by the expert, the better the classification result of the formula.

[0065] S5: Use the classification model trained in step S4 to guide the selection process of the improved estimation of distribution algorithm in step S3, and select more formulas with better classification results. Repeat steps S3 to S4 until the number of formulas with the highest classification results reaches a certain amount.

[0066] Among them, the mathematical model in step S2 can be expressed as follows:

[0067]

[0068] The rubber formula optimization mathematical model of this embodiment of the invention selects m raw materials from n raw materials, and then determines the ratio X of the i - th raw material i . g e (X) is the calculation formula for the degree of violation of the e - th chemical component, f e (X) is the calculation formula for the content of the e - th chemical component of the raw material, F(X) is the objective function of the degree of violation of the chemical composition, and Q is the objective function of the price. In the function, q i represents the price of the i - th raw material, p ei represents the content of the e - th chemical component of the i - th raw material, lce and uc e are the lower and upper limits of the e-th chemical component; C k is the k-th category, L k and U k are the lower and upper limits of the k-th classification respectively, l i and u i represent the lower and upper limits of the i-th raw material. The optimization objective of the mathematical model is to minimize the cost of the formula and the degree of violation of the chemical components. The lower the cost and the smaller the degree of violation of the chemical components, the better the effect of the formula and the better the physical and chemical properties of the fired finished product.

[0069] Due to the limited historical rubber formula data, in step S3, the rubber formula optimization method obtains a batch of formulas with relatively low cost and small degree of violation of chemical component constraints by applying an improved distribution optimization algorithm. In step S4, the method interacts with people, sends the obtained batch of formulas to an expert team for evaluation, and accumulates them with past data. Through machine learning methods, a classification model is trained. This classification model can classify or evaluate the individuals of the improved distribution optimization algorithm, and those with high classification results are considered to have good evaluation results.

[0070] In step S5, the objective function of the improved distribution optimization algorithm is modified by the following method.

[0071]

[0072] F(X) is the objective function of the degree of violation of chemical components, F ′ (X) is the modified objective function, where cl is the classification result of the individual and k is the coefficient controlling the two objective functions.

[0073] As an optional implementation manner, the classification model of this embodiment can be implemented by using an existing classification model, such as a decision tree or a multi-layer perceptron.

[0074] The following combines Figure 2 and Figure 3 to elaborate on the above-mentioned improved estimation of distribution algorithm in detail.

[0075] See Figure 2 , the above step S3 specifically includes the following steps S31 - S38:

[0076] S31: Use all rubber formulas as individuals, and use the raw material serial numbers selected by the rubber formula and the corresponding proportion values of the raw materials as the values of the dimensions to encode the individuals, and randomly initialize the population.

[0077] The encoding of the individual is as Figure 3As shown, in the individual coding, the first m - dimension part is the serial number of the selected raw materials, and the latter m - dimension part is the proportion corresponding to the selected raw materials.

[0078] S32: Generate new individuals in the population. First, sample from the selection matrix to determine the serial number of the raw materials for the individual. The selection matrix is designed specifically to handle the discrete problem of rubber raw material selection in the improved estimation of distribution algorithm. Each raw material number corresponds to a row in the matrix, and the initial raw materials correspond to the diagonal of the matrix. The N×N - dimension selection matrix is as follows:

[0079]

[0080] Where N is the number of selectable raw materials.

[0081] The sampling of raw materials is based on the rules of the binary tournament: The first raw material is selected according to the values on the diagonal of the matrix. Randomly select two numbers, compare their values on the diagonal, and then select the number with the larger value as the serial number of the first raw material. The subsequent raw materials are selected based on the previous raw material. In the row corresponding to the previous raw material in the matrix, randomly select two numbers, compare their values in that row, and then select the number with the larger value as the serial number of the subsequent raw material. If the currently selected individual sequence does not meet the raw material constraints or category constraints, the serial number will be resampled through the selection matrix.

[0082] S33: Before determining the proportion, due to the existence of raw material constraints and category constraints, it is also necessary to determine in advance the feasible range of the proportion of the selected raw material.

[0083] As a further optional implementation, step S33 specifically includes:

[0084] Calculate the actual constraints of the already - assigned categories from the raw materials with already - assigned proportions.

[0085] Determine the impact of the unassigned raw materials on the constraints of the category where the currently assigned raw materials are located.

[0086] Calculate the feasible range of the proportion of the currently selected raw material from the constraints of the category where the currently assigned raw material is located and the raw material constraints of the currently assigned raw material.

[0087] S34: According to the estimation of distribution algorithm, a Gaussian distribution is established for each optional raw material Where and are the mean and deviation of the proportion of the i - th raw material. Sample the proportion corresponding to the selected raw materials through the Gaussian distribution and ensure that the proportion is within the feasible range. Thus, the serial number of the raw materials and the corresponding proportions of the individual are all determined.

[0088] S35: Combine the individuals of the parent generation and the offspring according to the elite strategy. Determine the levels of the individuals in the population and obtain the Pareto front through non-dominated sorting and crowding degree calculation based on the two optimization objectives of the formulation cost and the degree of violation of chemical components. Select the higher-level half of the individuals in the combined population and eliminate the lower-level half of the individuals.

[0089] S36: Update the selection matrix in step S32 according to the individuals selected in step S35. The formula is as follows:

[0090]

[0091] where i and j are adjacent raw materials in the raw material sequence of the individuals selected in step S34. τ ij is the element in the i-th row and j-th column of the matrix, p i is the proportion of the i-th raw material in the individual, p j is the proportion of the j-th raw material in the individual, rank represents the level of the individual; τ ii is the i-th diagonal element of the matrix, the set synthesized by the first L largest elements in the i-th row of the A matrix, τ t is an element in the set A; τ min and τ max are the lower and upper limits of the value of the element in the matrix respectively; α and β are parameters controlling the update amplitude.

[0092] S37: Update the Gaussian distribution of each raw material in step S34 according to the selection in step S35. The formula is as follows:

[0093]

[0094]

[0095] where and are the mean and deviation of the proportion of the i-th raw material; H is the number of individuals selecting the i-th raw material in the population, p h is the proportion corresponding to the i-th raw material in each individual; l i and u i are the lower and upper bounds of the i-th raw material respectively; θ is the coefficient controlling the update speed, and ε is the coefficient to prevent the deviation increment from being zero.

[0096] S38: Repeat steps S32 to S37 until the number of individuals whose violation degrees of cost and chemical constraints are both less than their respective thresholds reaches a certain quantity.

[0097] In summary, compared with the prior art, this embodiment has at least the following advantages and beneficial effects: The method of this embodiment performs mathematical modeling based on rubber raw material information, raw material category information, raw material costs, raw material chemical content information, conditions that the raw material ratio needs to meet, conditions that the category ratio needs to meet, and conditions that the final formula chemical content ratio needs to meet. Two objective functions are established using the cost of the rubber formula and the degree of violation of the chemical composition constraints of the rubber formula as evaluation indicators. An improved estimation of distribution algorithm is used to obtain a batch of formulas with smaller objective functions. The obtained formulas are sent for expert evaluation, a data set is created based on the evaluation results, and a classification model is trained relying on the accumulated data set. Using the classification model to guide the selection process of the improved estimation of distribution algorithm, increasing the number of formulas with better expert evaluation results during the evolution process. The formulas finally obtained by this method have low cost and low chemical violation degree, and high expert evaluation results, solving the problems of high consumption of manpower and material resources and difficult evaluation in traditional rubber formulas.

[0098] This embodiment also provides a rubber formula optimization device, including:

[0099] At least one processor;

[0100] At least one memory for storing at least one program;

[0101] When the at least one program is executed by the at least one processor, the at least one processor is caused to implement Figure 1 The method shown.

[0102] A rubber formula optimization device of this embodiment can execute a rubber formula optimization method provided by an embodiment of the present invention, can execute any combination of implementation steps of the method embodiment, and has the corresponding functions and beneficial effects of the method.

[0103] This application embodiment also discloses a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to execute Figure 1 The method shown.

[0104] This embodiment also provides a storage medium storing instructions or a program that can execute a rubber formula optimization method provided by an embodiment of the present invention. When the instructions or the program are run, any combination of implementation steps of the method embodiment can be executed, and the corresponding functions and beneficial effects of the method are provided.

[0105] In some alternative embodiments, the functions / operations recited in the block diagrams may not occur in the order presented in the operational illustrations. For example, depending on the functions / operations involved, two consecutive blocks shown may actually be executed substantially simultaneously or the blocks may sometimes be executed in reverse order. Further, the embodiments presented and described in the flowcharts of the present invention are provided by way of example for the purpose of providing a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logical flows presented herein. Alternative embodiments are contemplated in which the order of various operations is altered and in which sub-operations described as part of a larger operation are executed independently.

[0106] Moreover, although the present invention has been described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the described functions and / or features may be integrated in a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It should also be understood that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, given the attributes, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the modules will be understood within the ordinary skill of an engineer. Accordingly, those of ordinary skill in the art will be able to implement the present invention as set forth in the claims without undue experimentation. It should also be understood that the particular concepts disclosed are illustrative only and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0107] If the functions are implemented in the form of software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention, in essence or the part that contributes to the prior art or part of the technical solution, may be embodied in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs.

[0108] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definitional sequence of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device. As used in this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

[0109] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, as the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0110] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

[0111] In the above description of this specification, the descriptions referring to the terms "one embodiment / example", "another embodiment / example", or "certain embodiments / examples", etc., mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0112] Although embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the claims and their equivalents.

[0113] The above has specifically described the preferred embodiments of the present invention, but the present invention is not limited to the above embodiments. Those skilled in the art can also make various equivalent deformations or substitutions without departing from the spirit of the present invention, and these equivalent deformations or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A method for optimizing a rubber formulation, characterized in that, It includes the following steps: S1. Obtain the parameter information of the rubber, and construct an optimization model for the rubber formula according to the parameter information; S2. Determine the constraint conditions of the rubber formula optimization model, and establish an objective function with the cost of the rubber formula and the degree of violation of the chemical composition constraints of the rubber formula as the evaluation indexes; S3. Use the preset estimation of distribution algorithm to optimize the objective function, and obtain the formula with the minimum cost and the degree of violation of the chemical composition under the condition of meeting the constraint conditions; S4. Evaluate the obtained formula, create a data set according to the evaluation results, and train a classification model by using the data set; S5. Guide the selection process of the estimation of distribution algorithm according to the classification model to select more formulas with classification results; repeat steps S3 - S4 until the number of formulas with the highest classification results reaches the preset number; The specific steps of step S3 include: S31. Take all rubber formulas as individuals, encode the individuals, and randomly initialize the population; S32. Generate new individuals in the population, sample from the preset selection matrix, and determine the raw material serial numbers of the individuals; S33. Before determining the proportioning, determine the feasible range of the proportioning of the selected raw materials; S34. According to the estimation of distribution algorithm, establish a Gaussian distribution for each optional raw material, sample the corresponding proportioning of the selected raw materials through the Gaussian distribution, and ensure that the proportioning is within the feasible range; S35. Combine the individuals of the parent generation and the offspring generation, and screen the combined population according to the two optimization objectives of the formula cost and the degree of violation of the chemical composition; S36. Update the selection matrix according to the population obtained by screening; S37. Update the Gaussian distribution of each raw material according to the population obtained by screening; S38. Repeat steps S32 - S37 until the number of individuals whose degree of violation of the cost and chemical constraints is less than the preset threshold reaches the preset number; Guiding the selection process of the estimation of distribution algorithm according to the classification model includes: Modify the objective function of the estimation of distribution algorithm according to the classification result of the classification model, and the expression is as follows: Among them, F(X) is the objective function of the degree of violation of the chemical composition, F′(X) is the modified objective function, cl is the classification result of the individual, and k is the coefficient controlling the objective function.

2. A rubber formulation optimization method according to claim 1, characterized in that The parameter information of the rubber includes: rubber raw material information, raw material category information, raw material cost, raw material chemical content information, conditions that the raw material proportioning needs to meet, conditions that the category proportioning needs to meet, and conditions that the final formula chemical content ratio needs to meet; Determining the constraint conditions of the rubber formula optimization model includes: Taking the intervals that the raw material proportioning needs to meet and the intervals that the category proportioning needs to meet as the constraint conditions; Taking the minimum degree of violation of the formula cost and chemical composition constraints as the optimization objective.

3. A rubber formulation optimization method according to claim 1, characterized in that The expression of the rubber formula optimization model is: Among them, the rubber formulation optimization model selects m raw materials from a variety of raw materials, and then determines the proportion X of the i-th raw material i ; g e (X) is the calculation formula for the violation degree of the e-th chemical component, f e (X) is the calculation formula for the content of the e-th chemical component of the raw material, F(X) is the objective function of the chemical component violation degree, and Q is the objective function of the price; q i represents the price of the i-th raw material, p ei represents the content of the e-th chemical component of the i-th raw material, lc e and uc e are the lower and upper limits of the e-th chemical component; C k is the k-th category, L k and U k are the lower and upper limits of the k-th classification respectively, l i and u i represent the lower and upper limits of the i-th raw material.

4. A method for optimizing a rubber formulation according to claim 1, characterized in that, Sampling from the preset selection matrix to determine the raw material serial numbers of the individuals includes: Each raw material number corresponds to a row in the matrix, and the initial raw materials correspond to the diagonal of the matrix; Sampling of raw materials is based on the rules of a binary tournament: The first raw material is selected according to the values on the diagonal of the matrix. Two numbers are randomly selected, the values of these two numbers on the diagonal are compared, and the number with the larger value is selected as the serial number of the first raw material. Subsequent raw materials are selected based on the previous raw material. In the row of the matrix corresponding to the previous raw material, two numbers are randomly selected, the values of these two numbers in that row are compared, and the number with the larger value is selected as the serial number of the subsequent raw material.

5. A method for optimizing a rubber formulation according to claim 1, characterized in that The selection matrix is updated using the following formula: Among them, i and j are the adjacent raw material numbers in the raw material sequence of the selected individuals; τ ij is the element in the i-th row and j-th column of the matrix, p i is the proportion of the i-th raw material in the individual, p j is the proportion of the j-th raw material in the individual, rank represents the level of the individual; τ ii is the i-th diagonal element in the matrix, the set synthesized by the first L largest elements in the i-th row of the A matrix, τ t is an element in the set A; τ min and τ max are respectively the lower limit and upper limit of the value of the element in the matrix; α and β are respectively the parameters controlling the update amplitude.

6. A method for optimizing a rubber formulation according to claim 1, characterized in that, The Gaussian distribution of each raw material is updated in the following manner: where and are the mean and deviation of the proportion of the i-th raw material; H is the number of individuals selecting the i-th raw material in the population, and p h is the proportion corresponding to the i-th raw material in each individual; l i and u i are the lower and upper bounds of the i-th raw material respectively; θ is the coefficient controlling the update speed, and ε is the coefficient to prevent the deviation increment from being zero.

7. A rubber formula optimization device, characterized in that, Including: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1-6.

8. A computer-readable storage medium storing a program executable by a processor, characterized in that, The program executable by the processor is used to execute the method according to any one of claims 1-6 when executed by the processor.

Images