Mixing control method and system for surfactant

By constructing the solution space and roulette model of surfactant and intelligently adjusting the mixing mode, the problem of single surfactant mixing mode in the prior art is solved, the mixing performance is improved, and the needs of different application scenarios are adapted.

CN119002429AActive Publication Date: 2024-11-22JIANGSU YOUYANG PHARM CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411132148.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-22
Estimated Expiration
2044-08-19

AI Technical Summary

Technical Problem

In the prior art, the surfactant mixing mode is single, which is difficult to adapt to the needs of different application scenarios, resulting in unsatisfactory mixing effect.

Method used

By extracting the type data sets and performance data sets of surfactants, the solution space is constructed, and the solution space is traversed through the solution space based on the application scenario requirements, the roulette model is constructed, the mixed mode is generated, and the mixing and evaluation is performed. Through the optimization search Adjust the mixing mode to improve performance.

Benefits of technology

It realizes intelligent adjustment of the mixing mode according to the needs of the target scenario to improve the mixing performance of the surfactant, and solves the problem of unsatisfactory results caused by the single mixing mode.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119002429A_ABST
    Figure CN119002429A_ABST
Patent Text Reader

Abstract

The invention discloses a surfactant mixing control method and system, and relates to the technical field of active agent mixing control. The method comprises the following steps: extracting a type data set and a performance data set of a surfactant, and initializing to obtain a surfactant solution space; traversing the surfactant solution space to obtain a plurality of types of data; constructing a roulette model, and inputting the multiple types of data into the roulette model to obtain a first mixed mode; performing mixing based on the first mixing mode to generate a first mixed surfactant, and performing mixing evaluation to generate a first mixing score; and optimizing the first mixing mode to obtain a second mixing mode, and carrying out mixing control on the surfactant. The technical problems that in the prior art, the mixing mode is single, different application scene requirements are difficult to adapt, and the mixing effect is not ideal are solved, and the technical effects that the mixing mode is intelligently adjusted according to the target scene requirements, and the surfactant mixing performance is improved are achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of surfactant mixing control, and in particular to a surfactant mixing control method and system. Background Art

[0002] In modern chemical industry and daily life, surfactants play a vital role in detergents, cosmetics, medicines, coatings, oilfield chemistry and other fields by reducing the surface tension of liquids and changing the properties of interfaces. However, with the advancement of science and technology and the increasing requirements of consumers for product performance, a single surfactant is often difficult to meet the complex and changing performance requirements. In order to meet the requirements for surfactant performance in different application scenarios, performance is optimized by mixing different types of surfactants. Mixed surfactants can not only combine the advantages of different types of surfactants, but also produce synergistic effects through intermolecular interactions, thereby improving overall performance. In the process of mixing surfactants, surfactants of different types and properties will interact with each other when mixed, affecting the performance of the final mixed product. Traditional surfactant mixing control methods are often based on fixed formulas and mixing ratios, which are difficult to adapt to the diverse needs of different application scenarios. Summary of the invention

[0003] The embodiments of the present application provide a surfactant mixing control method and system, which solve the technical problems in the prior art that the mixing mode is single and difficult to adapt to the requirements of different application scenarios, resulting in unsatisfactory mixing effect.

[0004] In view of the above problems, an embodiment of the present application provides a surfactant mixing control method and system.

[0005] A first aspect of an embodiment of the present application provides a method for controlling the mixing of a surfactant, the method comprising: Extract the surfactant type data set and the performance data set for initialization to obtain the surfactant solution space; obtain the target scenario requirements based on the application scenario, traverse the surfactant solution space to obtain multiple surfactant type data; construct a roulette model, input the multiple type data into the roulette model to obtain a first mixing mode; mix based on the first mixing mode to generate a first mixed surfactant, perform mixing evaluation on the first mixed surfactant to generate a first mixing score; optimize the first mixing mode based on the first mixing score to obtain a second mixing mode, and perform mixing control of the surfactant according to the second mixing mode.

[0006] A second aspect of the embodiments of the present application provides a surfactant mixing control system, the system comprising: A solution space acquisition module, the solution space acquisition module is used to extract a surfactant type data set and a performance data set for initialization to obtain a surfactant solution space; a data acquisition module, the data acquisition module is used to obtain target scenario requirements based on application scenarios, and traverse the surfactant solution space to obtain multiple type data of surfactants; a model construction module, the model construction module is used to construct a roulette model, input the multiple type data into the roulette model, and obtain a first mixing mode; a mixing evaluation module, the mixing evaluation module is used to mix based on the first mixing mode to generate a first mixed surfactant, perform mixing evaluation on the first mixed surfactant, and generate a first mixing score; an optimization module, the optimization module is used to optimize the first mixing mode based on the first mixing score to obtain a second mixing mode, and perform mixing control of surfactants according to the second mixing mode.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: First, extract the type data set and performance data set of surfactants for initialization to obtain the surfactant solution space. Then, obtain the target scenario requirements based on the application scenario, and traverse the surfactant solution space to obtain multiple type data of surfactants. By constructing a roulette model, multiple type data are input into the roulette model to obtain the first mixing mode. Next, mix based on the first mixing mode to generate a first mixed surfactant, perform a mixing evaluation on the first mixed surfactant, and generate a first mixing score. Finally, optimize the first mixing mode based on the first mixing score to obtain the second mixing mode, and perform surfactant mixing control according to the second mixing mode. The technical problem that the mixing mode in the prior art is single and difficult to adapt to the requirements of different application scenarios, resulting in unsatisfactory mixing effect is solved, and the technical effect of intelligently adjusting the mixing mode according to the target scenario requirements and improving the mixing performance of the surfactant is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic flow chart of a surfactant mixing control method provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a surfactant mixing control system provided in an embodiment of the present application.

[0010] Explanation of the reference numerals: solution space acquisition module 11, data acquisition module 12, model construction module 13, hybrid evaluation module 14, optimization module 15. DETAILED DESCRIPTION

[0011] The embodiments of the present application provide a surfactant mixing control method and system to solve the technical problems in the prior art that the mixing mode is single and difficult to adapt to the requirements of different application scenarios, resulting in unsatisfactory mixing effect.

[0012] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0013] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0014] Embodiment 1 like Figure 1 As shown, an embodiment of the present application provides a method for controlling the mixing of surfactants, wherein the method comprises: The surfactant type data set and performance data set are extracted for initialization to obtain the surfactant solution space.

[0015] In the process of surfactant research and development and application, in order to optimize the performance of surfactants and meet the needs of specific application scenarios, a detailed analysis of the types and properties of surfactants is required. Specifically, by extracting the type data set and performance data set of surfactants and initializing them, a surfactant solution space is constructed. The type data set contains surfactants of different chemical types; the performance data set contains the corresponding properties of different types of surfactants, such as cleaning power, foam stability, emulsification ability, biodegradability, etc.; the surfactant solution space contains all surfactant types and corresponding performance data.

[0016] The target scenario requirements are obtained based on the application scenario, and the surfactant solution space is traversed to obtain multiple types of surfactant data.

[0017] Different application scenarios correspond to different requirements. For example, in detergent applications, high cleaning power, low foaming, and environmentally friendly biodegradability may be required; in cosmetic applications, more attention may be paid to mildness, stability, and compatibility with the skin. The target scenario requirements usually require one or more surfactants to meet the requirements. According to the target scenario requirements, the surfactant solution space is traversed to obtain multiple types of surfactant data. In the process of traversing the solution space, the surfactant type data that meets the requirements will be screened out according to the target scenario requirements. The surfactant type data includes one or more surfactants, each with its own unique performance characteristics and advantages.

[0018] Furthermore, based on the application scenario, the target scenario requirement is obtained, and the surfactant solution space is traversed to obtain multiple types of surfactant data, the method includes: A performance data interval is set based on the target scenario requirements; the surfactant solution space is traversed to perform random iterative extraction, and a data list is constructed based on the extracted data, wherein the data list includes a first type of surfactant, a second type of surfactant...an nth type of surfactant; it is determined whether the performance data of the first type of surfactant satisfies the performance data interval; if the performance data of the first type of surfactant satisfies the performance data interval, the first type of surfactant is marked and added to a candidate data group, thereby iterating to obtain the candidate data group, integrating the data of the candidate data group, and obtaining the multiple types of data of the surfactant.

[0019] In order to obtain a combination of surfactants according to the requirements of the target scenario, it is necessary to first set the performance data interval and perform random iterative extraction in the surfactant solution space to construct a list of surfactant type data that meets the performance requirements. Specifically, according to the requirements of the target scenario, set the performance data interval of each key performance indicator (such as cleaning power, foam stability, biodegradability, etc.), and the performance data interval reflects the specific requirements of the target scenario for the performance of the surfactant; perform random iterative extraction in the surfactant solution space until all solutions in the solution space are extracted; for each iteratively extracted data, construct a data list, the data list contains the first type of surfactant, the second type of surfactant...the nth type of surfactant, wherein each type of surfactant corresponds to at least one performance data; for each surfactant in the data list (for example, the first type of surfactant), check whether its performance data meets the previously set performance data interval; if the performance data of a certain type of surfactant meets the performance data interval, mark it and add it to a candidate data group, which will contain all surfactant types that meet the performance requirements; repeat the above process, from the first type of surfactant to the nth type of surfactant; perform data integration on the candidate data group to obtain a list containing multiple surfactant type data that meet the requirements of the target scenario.

[0020] A roulette model is constructed, and the plurality of types of data are input into the roulette model to obtain a first mixing mode.

[0021] In the mixing control of surfactants, the roulette model is a commonly used selection mechanism for randomly but non-uniformly selecting the most likely combination from a set of candidate solutions (multiple types of surfactants). Through the roulette model, the surfactant combination that is most likely to meet the requirements of the target scenario can be selected from multiple types of data in a random but non-uniform manner, thereby constructing the first mixing mode. The first mixing mode is also a mixing scheme, including the initial mixing ratio and mixing method.

[0022] Furthermore, the method for constructing the roulette model includes: Retrieve the historical mixing information library, traverse the multiple types of surfactant data for matching, and obtain a mixing ratio data set and a mixing concentration data set; define a mixing ratio optimization variable and a mixing concentration optimization variable based on the mixing ratio data set and the mixing concentration data set; perform weight training according to the multiple types of data and the mixing ratio optimization variable to obtain the weight coefficient of the mixing ratio; construct an optimization objective function based on the weight coefficient of the mixing ratio, the mixing ratio optimization variable, and the mixing concentration optimization variable in combination with the multiple types of data; perform mixing performance calculation based on the optimization objective function to obtain a target performance indicator; construct a fitness function based on the mixing ratio optimization variable, the mixing concentration optimization variable, and the target performance indicator; calculate multiple area areas on the roulette wheel according to the target performance indicator, and the multiple area areas have a corresponding relationship with the multiple types of data; construct the roulette wheel model based on the multiple area areas and the fitness function.

[0023] In the mixing control of surfactants, in order to obtain an optimized mixing formula, the historical mixing information library can be used, and multiple types of data can be matched and trained to construct an optimization objective function and a roulette model. Specifically, the surfactant mixing records similar to the current application scenario are extracted from the historical mixing information library, including the mixing ratio data set and the mixing concentration data set; multiple types of surfactant data are traversed and matched with the data in the historical mixing information library. Through matching, the historical mixing ratio and mixing concentration data related to the current type data can be obtained. Based on the mixing ratio data set and the mixing concentration data set, the mixing ratio optimization variables and the mixing concentration optimization variables are defined. These variables will be used in the subsequent optimization process to adjust the mixing ratio and concentration of the surfactant. The machine learning algorithm is used to perform weight training according to multiple types of data and mixing ratio optimization variables. Through training, the weight coefficients of the mixing ratio can be obtained. These weight coefficients reflect the importance of different types of surfactants in mixing. According to the weight coefficients of the mixing ratio, the mixing ratio optimization variables, and the mixing concentration optimization variables, multiple types of data are combined to construct an optimization objective function. Based on the optimization objective function, the mixing performance is calculated to find the optimal mixing ratio and concentration, that is, the target performance index. According to the mixing ratio optimization variables, mixing concentration optimization variables and target performance indicators, a fitness function is constructed to evaluate the advantages and disadvantages of different mixing formulas. According to the target performance indicators, the areas of multiple regions on the roulette wheel are calculated, that is, according to the mixing ratio of each surfactant, the area of ​​each surfactant on the roulette wheel is calculated. Among them, there is a corresponding relationship between the areas of multiple regions and multiple types of data, and the size of the area reflects the importance of the corresponding type of data in the mixing. Combining multiple area areas and fitness functions, a roulette model is constructed. In the roulette model, each area represents a type of data, and the area of ​​the area is proportional to its importance in the mixing. By simulating the process of roulette wheel rotation, a mixing formula can be randomly but non-uniformly selected from multiple types of data.

[0024] Furthermore, the optimization objective function is: ;in, is the target performance indicator, For multiple types of surfactant data, For the The weight coefficient of the mixing ratio of the surfactants, For the The mixing ratio of the surfactants, For the The mixed concentration of the surfactants.

[0025] The optimization objective function can be used to find a set of optimal mixing ratios and concentrations to maximize the target performance index. In the optimization objective function, is the target performance indicator, For multiple types of surfactant data, For the The weight coefficient of the mixing ratio of the surfactants, For the The mixing ratio of the surfactants, For the The mixed concentration of the surfactants.

[0026] Furthermore, the plurality of types of data are input into the roulette model to obtain a first mixing mode, the method comprising: The fitness function is used to calculate the fitness of the multiple types of data to generate multiple selection probabilities, and the multiple selection probabilities have a one-to-one correspondence with the multiple types of data; the multiple selection probabilities are accumulated to obtain a cumulative probability.

[0027] The steps of making roulette selection based on the cumulative probability are: A1: randomly generate a pseudo-random number based on a preset interval; A2: compare the pseudo-random number with the cumulative probability, select the type data that contains the pseudo-random number within the cumulative probability, repeat A1 and A2 until the number of type data meets the preset threshold, and obtain the type data set; based on the mixing ratio optimization variable and the mixing concentration optimization variable, combined with the type data set, obtain the first mixing mode.

[0028] In surfactant mixing control, a roulette model is used to obtain the first mixing mode. Specifically, the fitness of each type of data is calculated by the fitness function. The higher the fitness value, the greater the probability of the type of data being selected. The fitness values ​​of all type of data are normalized to generate multiple selection probabilities, and each selection probability has a one-to-one correspondence with a type of data. Starting from the first type of data, its selection probability is accumulated with the selection probability of all previous type of data to obtain the cumulative probability of the type of data. The cumulative probability of the first type of data is its selection probability itself, and the cumulative probability of the subsequent type of data is the sum of its selection probability and the cumulative probability of all previous type of data. A random number generation interval is preset (such as between 0 and 1), and then a pseudo-random number is randomly generated. Compare the generated pseudo-random number with the cumulative probability, find the type of data whose cumulative probability value is just greater than or equal to the pseudo-random number, and select the type of data. Repeat steps A1 and A2 until the number of selected type data meets the preset threshold, and these selected type data are combined into a type data set. According to the mixing ratio optimization variables and the mixing concentration optimization variables, combined with the type data set, the proportion and concentration of each surfactant in the mixture are determined, and then the first mixing mode is constructed.

[0029] Mixing is performed based on the first mixing mode to generate a first mixed surfactant, and a mixing evaluation is performed on the first mixed surfactant to generate a first mixing score.

[0030] The first mixed surfactant is generated by mixing the surfactants according to the ratio and concentration of each surfactant determined in the first mixing mode. The first mixed surfactant is mixed and evaluated to evaluate the effect and stability after mixing. A first mixed score is generated according to the evaluation result, and the first mixed score will be used as a basis for evaluating the performance of the first mixing mode.

[0031] Further, mixing is performed based on the first mixing mode to generate a first mixed surfactant, and a mixing evaluation is performed on the first mixed surfactant to generate a first mixing score, the method includes: The first mixing mode is executed by a mixing device to generate the first mixed surfactant; an evaluation test plan is designed, and a performance test is performed on the first mixed surfactant according to the evaluation test plan to obtain a first evaluation test result; the first evaluation test result is analyzed for score conversion to generate multiple scoring values, and the first mixing score is calculated based on the multiple scoring values.

[0032] The first mixing mode is input into the mixing device, and the mixing device will mix according to the first mixing mode to generate the first mixed surfactant. The performance of the first mixed surfactant is tested by designing an evaluation test plan, and the first evaluation test result is obtained. Specifically, the test objectives are determined, such as evaluating the cleaning effect, foam stability, biodegradability, etc. of the first mixed surfactant; according to the test objectives, appropriate performance indicators are selected, such as detergency, foam generation and persistence, stability, safety, etc.; test conditions close to the actual application scenario are designed, such as water temperature, water quality, washing time, type of washing, etc.; experimental operations are performed according to the test process, and the data of each performance indicator are recorded to obtain the first evaluation test result. According to the importance and weight of each performance indicator, a scoring weight is assigned to each performance indicator, and the experimental results of each performance indicator are converted into corresponding scoring values. Finally, the scoring value is multiplied by the scoring weight, and all multiplication results are added as the total score of the first mixed surfactant, that is, the first mixed score.

[0033] The first mixing mode is optimized based on the first mixing score to obtain a second mixing mode, and the mixing of the surfactant is controlled according to the second mixing mode.

[0034] The first mixing mode is optimized according to the first mixing score to obtain a better second mixing mode, and the mixing of surfactants is controlled according to the second mixing mode. Specifically, according to the analysis results of the first mixing score, the parameters in the first mixing mode, such as the component ratio, mixing time, mixing temperature, etc., are adjusted, and the performance of each second mixing mode candidate is tested according to the previously designed evaluation test plan, and the data is recorded. Based on the test data, a score is calculated for each second mixing mode candidate, and the corresponding second mixing score is obtained. The scores of each second mixing mode are compared, and the mode with the highest score is selected as the optimal second mixing mode. The mixing equipment will control the mixing of surfactants according to the second mixing mode.

[0035] Furthermore, optimizing the first hybrid mode based on the first hybrid score to obtain a second hybrid mode includes: Evaluate the first hybrid score, and define optimization target data and constraint conditions according to the evaluation result; Based on the constraint condition, taking the optimization target data as the optimization target, performing iterative optimization search on the first hybrid mode through an optimization search channel to determine a plurality of hybrid modes; Cross-validating the multiple mixed modes, identifying the mixed modes that fail the validation as variant data, and adding them to the optimization search channel for deviation correction; Performing hybrid evaluation on the hybrid mode that has passed the verification to generate a hybrid score set; Arrange the mixed score set in descending order, select the mixed score of the first rank to compare with the first mixed score, and when the mixed score of the first rank is greater than the first mixed mode, it is deemed that the stability of the mixed mode corresponding to the mixed score of the first rank is higher than the stability of the first mixed mode, and the mixed mode corresponding to the mixed score of the first rank is output as the second mixed mode.

[0036] By evaluating the first hybrid score, the performance index that should be improved, i.e., the optimization target data, can be determined, and the constraints can be determined based on professional knowledge and expert experience. Select a suitable optimization algorithm, such as genetic algorithm, particle swarm optimization algorithm, simulated annealing algorithm, etc., as the optimization search channel, and set the search range and parameters of the algorithm according to the constraints. Take the optimization target data as the optimization target, and iteratively optimize the first hybrid mode through the optimization search channel. In each iteration, multiple new hybrid mode candidate schemes are generated. The generated multiple hybrid mode candidate schemes are cross-validated to ensure that they can perform well under different conditions. The hybrid modes that fail the verification are identified as variant data and added to the optimization search channel so that the algorithm can correct these variants in subsequent iterations. The hybrid evaluation is performed on the hybrid modes that pass the cross-validation, and the performance test is performed according to the evaluation test scheme designed previously. According to the test results, the hybrid score of each hybrid mode is generated and a hybrid score set is formed. The hybrid score set is sorted in descending order, the first-rank hybrid score is selected, and the first-rank hybrid score is compared with the first hybrid score. If the mixed score of the first order is greater than the first mixed score, it is considered that the stability of the mixed mode is higher than the first mixed mode, and the mixed mode corresponding to the mixed score of the first order is output as the second mixed mode. In other words, when the mixed score of the first order is less than or equal to the first mixed mode, it may be because the first mixed mode found for the first time is already the global optimal mode, or it may be that the global optimal mode is not traversed because other anomalies have not been traversed, so a second calculation is required. If the score of the first mixed mode is still higher, then the first mixed mode is taken as the optimal mode for mixed control.

[0037] In summary, the embodiments of the present application have at least the following technical effects: First, extract the type data set and performance data set of surfactants for initialization to obtain the surfactant solution space. Then, obtain the target scenario requirements based on the application scenario, and traverse the surfactant solution space to obtain multiple type data of surfactants. By constructing a roulette model, multiple type data are input into the roulette model to obtain the first mixing mode. Next, mix based on the first mixing mode to generate a first mixed surfactant, perform a mixing evaluation on the first mixed surfactant, and generate a first mixing score. Finally, optimize the first mixing mode based on the first mixing score to obtain the second mixing mode, and perform surfactant mixing control according to the second mixing mode. The technical problem that the mixing mode in the prior art is single and difficult to adapt to the requirements of different application scenarios, resulting in unsatisfactory mixing effect is solved, and the technical effect of intelligently adjusting the mixing mode according to the target scenario requirements and improving the mixing performance of the surfactant is achieved.

[0038] Embodiment 2 Based on the same inventive concept as the mixing control method of a surfactant in the aforementioned embodiment, Figure 2 As shown, the present application provides a surfactant mixing control system, and the system and method embodiments in the present application are based on the same inventive concept. The system includes: A solution space acquisition module 11, the solution space acquisition module 11 is used to extract a surfactant type data set and a performance data set for initialization to obtain a surfactant solution space; a data acquisition module 12, the data acquisition module 12 is used to obtain target scenario requirements based on application scenarios, and traverse the surfactant solution space to obtain multiple type data of surfactants; a model construction module 13, the model construction module 13 is used to construct a roulette model, input the multiple type data into the roulette model, and obtain a first mixing mode; a mixing evaluation module 14, the mixing evaluation module 14 is used to mix based on the first mixing mode to generate a first mixed surfactant, perform mixing evaluation on the first mixed surfactant, and generate a first mixing score; an optimization module 15, the optimization module 15 is used to optimize the first mixing mode based on the first mixing score, obtain a second mixing mode, and perform mixing control of surfactants according to the second mixing mode.

[0039] Furthermore, the data acquisition module 12 is used to execute the following method: A performance data interval is set based on the target scenario requirements; the surfactant solution space is traversed to perform random iterative extraction, and a data list is constructed based on the extracted data, wherein the data list includes a first type of surfactant, a second type of surfactant...an nth type of surfactant; it is determined whether the performance data of the first type of surfactant satisfies the performance data interval; if the performance data of the first type of surfactant satisfies the performance data interval, the first type of surfactant is marked and added to a candidate data group, thereby iterating to obtain the candidate data group, integrating the data of the candidate data group, and obtaining the multiple types of data of the surfactant.

[0040] Furthermore, the model building module 13 is used to execute the following method: Retrieve the historical mixing information library, traverse the multiple types of surfactant data for matching, and obtain a mixing ratio data set and a mixing concentration data set; define a mixing ratio optimization variable and a mixing concentration optimization variable based on the mixing ratio data set and the mixing concentration data set; perform weight training according to the multiple types of data and the mixing ratio optimization variable to obtain the weight coefficient of the mixing ratio; construct an optimization objective function based on the weight coefficient of the mixing ratio, the mixing ratio optimization variable, and the mixing concentration optimization variable in combination with the multiple types of data; perform mixing performance calculation based on the optimization objective function to obtain a target performance indicator; construct a fitness function based on the mixing ratio optimization variable, the mixing concentration optimization variable, and the target performance indicator; calculate multiple area areas on the roulette wheel according to the target performance indicator, and the multiple area areas have a corresponding relationship with the multiple types of data; construct the roulette wheel model based on the multiple area areas and the fitness function.

[0041] Furthermore, the model building module 13 is used to execute the following method: ;in, is the target performance indicator, For multiple types of surfactant data, For the The weight coefficient of the mixing ratio of the surfactants, For the The mixing ratio of the surfactants, For the The mixed concentration of the surfactants.

[0042] Furthermore, the model building module 13 is used to execute the following method: Performing fitness calculation on the multiple types of data by using the fitness function to generate multiple selection probabilities, wherein the multiple selection probabilities have a one-to-one correspondence with the multiple types of data; accumulating the multiple selection probabilities to obtain a cumulative probability; The steps of making roulette selection based on the cumulative probability are: A1: randomly generate a pseudo-random number based on a preset interval; A2: compare the pseudo-random number with the cumulative probability, select the type data that contains the pseudo-random number within the cumulative probability, repeat A1 and A2 until the number of type data meets the preset threshold, and obtain the type data set; based on the mixing ratio optimization variable and the mixing concentration optimization variable, combined with the type data set, obtain the first mixing mode.

[0043] Furthermore, the hybrid evaluation module 14 is used to perform the following method: The first mixing mode is executed by a mixing device to generate the first mixed surfactant; an evaluation test plan is designed, and a performance test is performed on the first mixed surfactant according to the evaluation test plan to obtain a first evaluation test result; the first evaluation test result is analyzed for score conversion to generate multiple scoring values, and the first mixing score is calculated based on the multiple scoring values.

[0044] Furthermore, the optimization module 15 is used to execute the following method: Evaluate the first hybrid score, and define optimization target data and constraints according to the evaluation results; based on the constraints, use the optimization target data as the optimization target, perform iterative optimization search on the first hybrid mode through the optimization search channel, and determine multiple hybrid modes; cross-validate the multiple hybrid modes, identify the hybrid modes that fail the validation as variant data, and add them to the optimization search channel for correction; perform hybrid evaluation on the hybrid modes that pass the validation to generate a hybrid score set; arrange the hybrid score set in descending order, select the first-rank hybrid score for comparison with the first hybrid score, and when the first-rank hybrid score is greater than the first hybrid mode, it is deemed that the stability of the hybrid mode corresponding to the first-rank hybrid score is higher than the stability of the first hybrid mode, and the hybrid mode corresponding to the first-rank hybrid score is output as the second hybrid mode.

[0045] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0046] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0047] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for controlling the mixing of surfactants, characterized in that: The method comprises: Extract the type data set and performance data set of surfactants for initialization to obtain the surfactant solution space; Obtaining target scenario requirements based on application scenarios, and traversing the surfactant solution space to obtain multiple types of surfactant data; Constructing a roulette model, inputting the plurality of types of data into the roulette model, and obtaining a first mixing mode; Perform mixing based on the first mixing mode to generate a first mixed surfactant, and perform mixing evaluation on the first mixed surfactant to generate a first mixing score; The first mixing mode is optimized based on the first mixing score to obtain a second mixing mode, and the mixing of the surfactant is controlled according to the second mixing mode.

2. The method according to claim 1, characterized in that Obtaining target scenario requirements based on application scenarios, traversing the surfactant solution space to obtain multiple types of surfactant data, the method includes: Setting a performance data interval based on the target scenario requirements; Traversing the surfactant solution space to perform random iterative extraction, and constructing a data list based on the extracted data, wherein the data list includes a first type of surfactant, a second type of surfactant, ... an nth type of surfactant; determining whether the performance data of the first type of surfactant meets the performance data range; If the performance data of the first type of surfactant meets the performance data range, the first type of surfactant is marked and added to the candidate data group, thereby iterating to obtain the candidate data group, integrating the data of the candidate data group, and obtaining the multiple types of surfactant data.

3. The method according to claim 1, characterized in that The method for constructing a roulette model comprises: Retrieving a historical mixing information database, traversing the plurality of types of surfactant data for matching, and obtaining a mixing ratio data set and a mixing concentration data set; Based on the mixing ratio data set and the mixing concentration data set, define a mixing ratio optimization variable and a mixing concentration optimization variable; Performing weight training according to the plurality of types of data and the mixing ratio optimization variable to obtain a weight coefficient of the mixing ratio; Constructing an optimization objective function based on the weight coefficient of the mixing ratio, the mixing ratio optimization variable, and the mixing concentration optimization variable in combination with the plurality of types of data; Perform hybrid performance calculation based on the optimization objective function to obtain a target performance indicator; Constructing a fitness function based on the mixing ratio optimization variable, the mixing concentration optimization variable, and the target performance index; Calculating multiple area areas on the wheel according to the target performance index, wherein the multiple area areas correspond to the multiple types of data; The roulette model is constructed according to the areas of the multiple regions in combination with the fitness function.

4. The method according to claim 3, characterized in that The optimization objective function is: ; in, is the target performance indicator, For multiple types of surfactant data, For the The weight coefficient of the mixing ratio of the surfactants, For the The mixing ratio of the surfactants, For the The mixed concentration of the surfactants.

5. The method according to claim 3, characterized in that Inputting the plurality of category data into the roulette model to obtain a first mixing mode, the method comprising: Performing fitness calculation on the plurality of types of data by using the fitness function to generate a plurality of selection probabilities, wherein the plurality of selection probabilities and the plurality of types of data have a one-to-one correspondence relationship; Accumulating the multiple selected probabilities to obtain a cumulative probability; The steps of making roulette selection based on the cumulative probability are: A1: Generates pseudo-random numbers based on a preset interval; A2: Compare the pseudo-random number with the cumulative probability, select the type data that contains the pseudo-random number within the cumulative probability, repeat A1 and A2 until the number of type data meets the preset threshold, and obtain the type data set; Based on the mixing ratio optimization variable, the mixing concentration optimization variable, and the type data set, the first mixing mode is obtained.

6. The method according to claim 1, characterized in that The method comprises: performing mixing based on the first mixing mode to generate a first mixed surfactant, and performing a mixing evaluation on the first mixed surfactant to generate a first mixing score. executing the first mixing mode by a mixing device to generate the first mixed surfactant; Designing an evaluation test plan, performing a performance test on the first mixed surfactant according to the evaluation test plan, and obtaining a first evaluation test result; The first evaluation test result is analyzed and converted into a score to generate a plurality of scoring values, and the first mixed score is obtained by calculation according to the plurality of scoring values.

7. The method according to claim 1, characterized in that Optimizing the first hybrid mode based on the first hybrid score to obtain a second hybrid mode, the method comprising: Evaluate the first hybrid score, and define optimization target data and constraint conditions according to the evaluation result; Based on the constraint condition, taking the optimization target data as the optimization target, performing iterative optimization search on the first hybrid mode through an optimization search channel to determine a plurality of hybrid modes; Cross-validating the multiple mixed modes, identifying the mixed modes that fail the validation as variant data, and adding them to the optimization search channel for deviation correction; Performing hybrid evaluation on the hybrid mode that has passed the verification to generate a hybrid score set; Arrange the mixed score set in descending order, select the mixed score of the first rank to compare with the first mixed score, and when the mixed score of the first rank is greater than the first mixed mode, it is deemed that the stability of the mixed mode corresponding to the mixed score of the first rank is higher than the stability of the first mixed mode, and the mixed mode corresponding to the mixed score of the first rank is output as the second mixed mode.

8. A surfactant mixing control system, characterized in that: A method for controlling the mixing of a surfactant according to any one of claims 1 to 7, the system comprising: A solution space acquisition module, the solution space acquisition module is used to extract a surfactant type data set and a performance data set for initialization to obtain a surfactant solution space; A data acquisition module, the data acquisition module is used to obtain target scenario requirements based on application scenarios, and traverse the surfactant solution space to obtain multiple types of surfactant data; A model building module, the model building module is used to build a roulette model, input the plurality of types of data into the roulette model, and obtain a first mixing mode; a mixing evaluation module, the mixing evaluation module being used to perform mixing based on the first mixing mode to generate a first mixed surfactant, and to perform mixing evaluation on the first mixed surfactant to generate a first mixing score; An optimization module is used to optimize the first mixing mode based on the first mixing score, obtain a second mixing mode, and perform mixing control of the surfactant according to the second mixing mode.

Citation Information

Patent Citations

  • Surfactant flooding dynamic optimization method based on double elite differential evolution

    CN110598163A

  • Gasoline blending online optimization method based on multiple constraint objectives

    CN117711531A

  • Water-based paint additive mixing quality control method and system

    CN118320702A

  • AU2020101453A4