Intelligent preparation method of cyanuric acid / melamine complex based on molecular self-assembly technology

Abstract

The present invention relates to an intelligent preparation method of a cyanuric acid / melamine complex based on molecular self-assembly technology, and relates to the field of preparation of flame-retardant complexes, including: a communication molecular self-assembly controller that receives preparation genotype factors; through a user terminal, configuring preparation phenotype factors and seed material types; constructing a trait mapping function according to the seed material type; constructing a flame-retardant quality evaluation function; based on the backtracking of the seed material type, constructing the first population of genes for the preparation of the cyanuric acid / melamine complex; based on the trait mapping function and the flame-retardant quality evaluation function, optimizing the first population of genes for the preparation of the cyanuric acid / melamine complex to obtain recommended genotype factor eigenvalue combinations, and initializing the molecular self-assembly controller for preparation control. It solves the technical problem of low efficiency in the prior art where multiple experiments are carried out by controlling variables to achieve the optimal configuration of the control elements in the molecular self-assembly process.

Description

Technical Field

[0001] The present invention relates to the technical field of flame retardant composite preparation, and particularly to an intelligent preparation method of cyanuric acid / melamine composite based on molecular self-assembly technology. Background Art

[0002] An important application of cyanuric acid / melamine composite is to add the cyanuric acid / melamine composite to the surface of a target product through molecular self-assembly technology to form a flame retardant layer, thereby improving the flame retardant performance of the target product.

[0003] In order to ensure the stability of the flame retardant performance, it is particularly important to set the control elements of the molecular self-assembly process, such as temperature, inhibitor content, cyanuric acid content, and melamine content. When preparing traditional cyanuric acid / melamine composites, multiple experiments are carried out by controlling variables to achieve the optimal configuration of the control elements of the molecular self-assembly process. However, the disadvantages are high cost, low efficiency, and strong instability. Summary of the Invention

[0004] In view of the technical problem of low efficiency caused by multiple experiments through controlling variables to achieve the optimal configuration of the control elements of the molecular self-assembly process in the prior art, the present invention provides an intelligent preparation method of cyanuric acid / melamine composite based on molecular self-assembly technology to solve this problem.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] In a first aspect, the present invention provides an intelligent preparation method of cyanuric acid / melamine composite based on molecular self-assembly technology, including:

[0007] A communication molecular self-assembly controller receives a preparation genotype factor, where the preparation genotype factor is used to characterize molecular self-assembly control parameters;

[0008] Through a user terminal, a preparation phenotype factor and a type of seed material are configured, where the preparation phenotype factor is used to characterize an index for evaluating the quality of the composite;

[0009] According to the type of seed material, a trait mapping function from the preparation genotype factor to the preparation phenotype factor is constructed;

[0010] Based on the preparation phenotype factor, a flame retardant quality evaluation function is constructed;

[0011] Based on the type of seed material, a preparation backtracking of cyanuric acid / melamine composite is carried out to construct a first population of genes for preparing cyanuric acid / melamine composite;

[0012] Based on the trait mapping function and the flame retardant quality evaluation function, optimize the first population of melamine cyanurate / melamine composite preparation genes to obtain a recommended combination of genotype factor characteristic values;

[0013] Initialize the molecular self-assembly controller according to the recommended combination of genotype factor characteristic values for preparation control.

[0014] In a second aspect, the present invention provides an electronic device, including:

[0015] A memory for storing computer software programs;

[0016] A processor for reading and executing the computer software program, thereby implementing the intelligent preparation method of melamine cyanurate / melamine composite based on molecular self-assembly technology described in the first aspect.

[0017] In a third aspect, the present invention provides a non-transitory computer-readable storage medium, in which a computer software program is stored, and when the computer software program is executed by a processor, it implements the intelligent preparation method of melamine cyanurate / melamine composite based on molecular self-assembly technology described in the first aspect.

[0018] The beneficial effects of the present invention are as follows: By setting various control elements of the molecular self-assembly controller as preparation genotype factors; setting the elements for evaluating flame retardant performance as preparation phenotype factors; then, according to the type of seed material of the target product for which a flame retardant layer needs to be prepared, constructing a trait mapping function from the preparation genotype factors to the preparation phenotype factors; further, constructing a flame retardant quality evaluation function; then, based on the type of seed material, performing a backtracking of the melamine cyanurate / melamine composite preparation to construct the first population of melamine cyanurate / melamine composite preparation genes; finally, based on the trait mapping function and the flame retardant quality evaluation function, optimizing the first population of melamine cyanurate / melamine composite preparation genes to obtain a recommended combination of genotype factor characteristic values for guiding the preparation of melamine cyanurate / melamine composite. Using machine learning combined with an optimization algorithm, virtual iterative optimization of molecular self-assembly control is realized, shortening the time loss of physical experiments, and achieving the technical effect of improving the configuration efficiency of molecular self-assembly control elements. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a schematic flowchart of the intelligent preparation method of melamine cyanurate / melamine composite based on molecular self-assembly technology provided by the present invention;

[0020] Figure 2 It is a schematic flowchart of the construction process of the trait mapping function of the intelligent preparation method of melamine cyanurate / melamine composite based on molecular self-assembly technology provided by the present invention;

[0021] Figure 3 Structural schematic diagram of the electronic device provided by the present invention;

[0022] Figure 4 Structural schematic diagram of a computer-readable storage medium provided by the present invention.

[0023] In the drawings, the list of components represented by each reference numeral is as follows:

[0024] Electronic device 500, memory 510, processor 520, computer program 511, computer-readable storage medium 600, computer program 611. Detailed implementation manners

[0025] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0026] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more unless otherwise specifically defined.

[0027] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or having more advantages than other embodiments. In order for any person skilled in the art to implement and use the present invention, the following description is given. In the following description, details are set forth for purposes of explanation. It should be understood that those skilled in the art can recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0028] Embodiment 1:

[0029] As Figure 1 shown, the embodiment of the present invention provides an intelligent preparation method of cyanuric acid / melamine composite based on molecular self-assembly technology, including the steps:

[0030] S10: A communication molecule self-assembly controller receives a genotype factor for preparation, where the genotype factor for preparation is used to characterize molecular self-assembly control parameters.

[0031] Specifically, the molecule self-assembly controller refers to a control terminal for controlling the technical elements of molecular self-assembly. Preferably, the molecule self-assembly controller is communicatively connected to a molecule self-assembly device. The molecular self-assembly process of the cyanuric acid / melamine complex is as follows: Raw materials: cyanuric acid and melamine; seeds; inhibitors (used to control the reaction rate to achieve controllable crystal form under controllable speed conditions); Solvent: water

[0032] Step 1: Add water to the reaction vessel of the molecule self-assembly device. Water is the solvent, providing an environment for molecular self-assembly.

[0033] Step 2: Add a quantitative inhibitor to the reaction vessel of the molecule self-assembly device. The inhibitor is used to control the reaction rate to achieve controllable crystal form under controllable speed conditions.

[0034] Step 3: Add seeds of a set size to the reaction vessel of the molecule self-assembly device, i.e., the target product.

[0035] Step 4: Add a quantitative amount of cyanuric acid and a quantitative amount of melamine to the reaction vessel of the molecule self-assembly device, control the temperature of the reaction vessel, and carry out the reaction to obtain the target product.

[0036] In the above process, the mass of cyanuric acid added, the mass of melamine added, the time sequence information of the reaction temperature, the mass of the inhibitor added, and the surface area of the target product are all element quantities to be controlled, that is, the genotype factor for preparation. By adjusting the mass of cyanuric acid added, the mass of melamine added, the time sequence information of the reaction temperature, the mass of the inhibitor added, and the surface area of the target product, different molecular growth states can be caused, thereby affecting the performance of the final complex and the flame retardant performance of the target product.

[0037] S20: Configure a phenotype factor for preparation and a type of seed material through the user terminal, where the phenotype factor for preparation is used to characterize an index for evaluating the quality of the complex.

[0038] Specifically, the phenotype factor for preparation is used to characterize an index for evaluating the quality of the complex. In the embodiments of the present application, the cyanuric acid / melamine complex is mainly used to enhance the flame retardant performance and is grown on the target product in real time through molecular self-assembly technology, which will cause certain losses to the product. Therefore, it is preferable to set four indexes, namely, the mass loss ratio of the target product, the generation rate of the cyanuric acid / melamine complex, the uniformity of the distribution of the cyanuric acid / melamine complex, and the distribution density of the cyanuric acid / melamine complex, to evaluate the quality of the complex.

[0039] The seed material type characterizes the surface material type of the target product. This is because the molecular self-assembly process may result in different flame retardant properties due to differences in the seed type. By retrieving the seed material type, more accurate evaluation of the composite quality can be achieved.

[0040] S30: Construct a trait mapping function from the preparation genotype factors to the preparation phenotype factors according to the seed material type;

[0041] Further, as Figure 2 shown, constructing a trait mapping function from the preparation genotype factors to the preparation phenotype factors according to the seed material type, step S30 includes the steps:

[0042] S31: Collect the preparation log of the cyanuric acid / melamine composite according to the seed material type, where the preparation log of the cyanuric acid / melamine composite includes a data set of genotype factor recorded values and a data set of phenotype factor recorded values;

[0043] S32: Construct a trait mapping function network architecture, where the trait mapping function network architecture has input nodes with the same dimension as the preparation genotype factors, and the trait mapping function network architecture has output nodes with the same dimension as the preparation phenotype factors;

[0044] S33: Use the data set of phenotype factor recorded values as the supervised true value, and use the data set of genotype factor recorded values as the input data to train the trait mapping function network architecture to generate the trait mapping function.

[0045] Further, using the data set of phenotype factor recorded values as the supervised true value, and using the data set of genotype factor recorded values as the input data to train the trait mapping function network architecture to generate the trait mapping function, step S33 includes the steps:

[0046] S331: Construct a trait mapping loss evaluation formula:

[0047]

[0048] where LOSS represents the trait mapping loss value, x i represents the predicted value of the i-th attribute phenotype factor, x i0 represents the recorded value data of the i-th attribute phenotype factor, N represents the dimension of the phenotype factor attributes, and a represents the mean loss threshold;

[0049] S332: Using the phenotypic factor recorded value dataset as the supervised true value, and using the genotype factor recorded value dataset as the input data, train the trait mapping function network architecture according to the trait mapping loss evaluation formula to generate the trait mapping function.

[0050] Specifically, the trait mapping function is used to realize the prediction from the preparation genotype factor to the preparation phenotypic factor on the premise of restricting the seed material type. The trait mapping function is the core functional component of the embodiments of the present application. The traditional process requires analyzing different characteristic values of the preparation genotype factor through experiments, and then obtaining the experimental results and recording the preparation phenotypic factor.

[0051] Preferably, the trait mapping function is a neural network model, and its training process is as follows:

[0052] According to the seed material type, collect the historical dataset of the preparation of cyanuric acid / melamine complexes of the same seed material type, and store it as the cyanuric acid / melamine complex preparation log. Any cyanuric acid / melamine complex preparation log includes the genotype factor recorded value dataset set in the historical experiment and the phenotypic factor recorded value dataset detected in the historical experiment.

[0053] Further, construct the trait mapping loss evaluation formula:

[0054] Part is the mean loss value, is the fluctuation parameter of the overall loss. The greater the fluctuation, the greater the loss. The greater the mean loss, the greater the loss. Therefore, when the mean loss is greater than or equal to the a value, it is directly regarded as unable to converge, and its loss is infinite. When the mean loss is less than the a value, the fluctuation parameter of the overall loss is used as the trait mapping loss.

[0055] Furthermore, using the phenotypic factor recorded value dataset as the supervised true value, and using the genotype factor recorded value dataset as the input data, train the trait mapping function network architecture according to the trait mapping loss evaluation formula. When training for a continuous preset number of times, if the mapping loss of at least 95% or more of the training times is less than or equal to the convergence threshold, generate the trait mapping function.

[0056] The embodiments of the present application complete this process through the trait mapping function, saving labor and material costs. The results obtained need to be verified by manual periodic experiments, and adjustments are required if deviations occur.

[0057] S40: Based on the preparation phenotypic factor, construct a flame retardant quality evaluation function;

[0058] Further, based on the prepared phenotypic factors, a flame retardant quality evaluation function is constructed. Step S40 includes the following steps:

[0059] S41: Normalize the prepared phenotypic factors to obtain the normalized indicators of the phenotypic factors;

[0060] S42: Through the user terminal, traverse the normalized indicators of the phenotypic factors and configure the threshold values of the normalized indicators of the phenotypic factors;

[0061] S43: Construct the flame retardant quality evaluation function according to the threshold values of the normalized indicators of the phenotypic factors and the normalized indicators of the phenotypic factors:

[0062]

[0063] where Q represents the flame retardant quality score, y i represents the eigenvalue of the normalized indicator of the phenotypic factor in the i-th dimension, y i0 represents the threshold value of the normalized indicator of the phenotypic factor in the i-th dimension, N represents the dimension of the normalized indicator of the phenotypic factor, and b represents a small constant.

[0064] Specifically, the flame retardant quality evaluation function is another key point of the technical solution of this embodiment of the present application. It is used to integrate the prepared phenotypic factors and comprehensively evaluate the flame retardant performance. In order to ensure that the larger the overall evaluation value, the better the flame retardant performance. First, the prepared phenotypic factors are normalized to obtain the normalized indicators of the phenotypic factors. Preferably, if it is originally a normalized indicator, no processing is required. If it is a non-normalized indicator, it can be changed to the reciprocal of the original indicator. The threshold value of the normalized indicator of the phenotypic factor is the minimum expected value set by the user through the user terminal for the normalized indicator of the phenotypic factor, that is, the final flame retardant performance must exceed or be equal to the corresponding threshold value. According to the threshold value of the normalized indicator of the phenotypic factor and the normalized indicator of the phenotypic factor, the flame retardant quality evaluation function is constructed:

[0065] It can be seen from the flame retardant quality evaluation function that is, the proportion of indicators greater than or equal to the threshold value of the normalized indicator of the phenotypic factor, when the direct fitness is equal to 0, when then, use as the fitness evaluation value. Since is necessarily ≥0, the minimum value is equal to 1. Therefore, the logic of is to find the optimal among the qualified ones to ensure obtaining the best flame retardant layer.

[0066] S50: Based on the type of the seed material, perform a backtracking of the preparation of the cyanuric acid / melamine complex, and construct the first population of genes for the preparation of the cyanuric acid / melamine complex;

[0067] Further, based on the type of the seed material, perform a backtracking of the preparation of the cyanuric acid / melamine complex, and construct the first population of genes for the preparation of the cyanuric acid / melamine complex. Step S50 includes the steps:

[0068] S51: Based on the type of the seed material, perform a backtracking of the preparation of the cyanuric acid / melamine complex, and obtain the historical eigenvalue of the first preparation genotype factor and the historical eigenvalue of the second preparation genotype factor;

[0069] S52: When the distance deviation parameter between the historical eigenvalue of the first preparation genotype factor and the historical eigenvalue of the second preparation genotype factor is greater than or equal to the distance deviation parameter threshold, add the historical eigenvalue of the first preparation genotype factor and the historical eigenvalue of the second preparation genotype factor to the first population of genes for the preparation of the cyanuric acid / melamine complex;

[0070] S53: When the distance deviation parameter between the historical eigenvalue of the first preparation genotype factor and the historical eigenvalue of the second preparation genotype factor is less than the distance deviation parameter threshold, randomly select one of the historical eigenvalue of the first preparation genotype factor and the historical eigenvalue of the second preparation genotype factor, and add it to the first population of genes for the preparation of the cyanuric acid / melamine complex.

[0071] Specifically, the first population of genes for the preparation of the cyanuric acid / melamine complex is a solution set composed of the eigenvalue of the historical genotype factor, that is, the set of control element eigenvalues of the molecular self-assembly in the historical preparation process. Based on the type of the seed material, perform a backtracking of the preparation of the cyanuric acid / melamine complex, and any two sets of control elements for the molecular self-assembly preparation of the cyanuric acid / melamine complex with respect to the type of the seed material can be collected and stored as the historical eigenvalue of the first preparation genotype factor and the historical eigenvalue of the second preparation genotype factor respectively; then, by analyzing the distance deviation parameter between the historical eigenvalue of the first preparation genotype factor and the historical eigenvalue of the second preparation genotype factor, the distance deviation parameter characterizes the degree of difference between the two.

[0072] When the distance deviation parameter between the historical eigenvalue of the first preparation genotype factor and the historical eigenvalue of the second preparation genotype factor is greater than or equal to the distance deviation parameter threshold preset by the user, add the historical eigenvalue of the first preparation genotype factor and the historical eigenvalue of the second preparation genotype factor to the first population of genes for the preparation of the cyanuric acid / melamine complex;

[0073] When the distance deviation parameter between the first prepared genotype factor historical eigenvalue and the second prepared genotype factor historical eigenvalue is less than the distance deviation parameter threshold, by default, the distance deviation parameter threshold is 0.5, randomly select one of the first prepared genotype factor historical eigenvalue and the second prepared genotype factor historical eigenvalue, and add it to the first population of the cyanuric acid / melamine complex preparation gene.

[0074] For the above content, by sorting individuals with a large degree of dispersion in the initial distribution distance to construct a population, more solutions can be traversed during the subsequent optimization, so as to approach the global optimum as soon as possible and achieve the global optimal configuration of genotype factors.

[0075] Further, the evaluation step S52 of the distance deviation parameter includes the steps:

[0076] S521: Traverse the genotype factors and configure the genotype factor threshold;

[0077] S522: Compare the first prepared genotype factor historical eigenvalue and the second prepared genotype factor historical eigenvalue for the same attribute to obtain the genotype factor deviation distance;

[0078] S523: When the genotype factor deviation distances are all less than or equal to the genotype factor threshold, set the distance deviation parameter to 0;

[0079] S524: When any one of the genotype factor deviation distances is greater than the genotype factor threshold, set the distance deviation parameter to 1.

[0080] Specifically, the evaluation process of the distance deviation parameter is preferably as follows:

[0081] Through the user terminal, configure the deviation threshold of each genotype factor and store it as the genotype factor threshold. If it is greater than the genotype factor threshold, it is considered that the corresponding index has a deviation, otherwise it is considered that there is no deviation. Compare the first prepared genotype factor historical eigenvalue and the second prepared genotype factor historical eigenvalue for the same attribute to obtain the genotype factor deviation distance of each attribute, that is, the absolute value of the deviation of the same attribute comparison; when the genotype factor deviation distances are all less than or equal to the genotype factor threshold, set the distance deviation parameter to 0; when any one of the genotype factor deviation distances is greater than the genotype factor threshold, set the distance deviation parameter to 1.

[0082] S60: Based on the trait mapping function and the flame retardant quality evaluation function, optimize the first population of the cyanuric acid / melamine complex preparation gene to obtain a recommended genotype factor eigenvalue combination;

[0083] S70: Initialize the molecular self-assembly controller according to the recommended genotype factor eigenvalue combination for preparation control.

[0084] Specifically, the above-mentioned trait mapping function that can predict the preparation phenotype factor eigenvalue from the genotype factor eigenvalue, and the flame retardant quality evaluation function that fuses the preparation phenotype factor eigenvalue to generate the flame retardant quality score are constructed. Therefore, by cascading the trait mapping function and the flame retardant quality evaluation function, a fitness evaluation pipeline can be obtained. There are two nodes on the pipeline. Node 1 is the trait mapping function, and Node 2 is the flame retardant quality evaluation function. The fitness is the output value of the flame retardant quality evaluation function.

[0085] Through the fitness evaluation pipeline, the quality of the individuals in the first population of the melamine cyanurate / melamine complex preparation gene can be evaluated, and then the sorting of the individuals can be realized to obtain the recommended genotype factor eigenvalue combination.

[0086] Furthermore, initialize the molecular self-assembly controller according to the recommended genotype factor eigenvalue combination, and then perform the preparation of the melamine cyanurate / melamine complex on the surface of the target product with the target size.

[0087] Furthermore, based on the trait mapping function and the flame retardant quality evaluation function, optimize the first population of the melamine cyanurate / melamine complex preparation gene to obtain the recommended genotype factor eigenvalue combination. Step S60 includes the steps:

[0088] S61: Cascading the trait mapping function and the flame retardant quality evaluation function to construct a fitness evaluation pipeline;

[0089] S62: Process the first population of the melamine cyanurate / melamine complex preparation gene according to the fitness evaluation pipeline to obtain a set of fitness evaluation values;

[0090] S63: Based on the set of fitness evaluation values, perform directed gene mutation on the first population of the melamine cyanurate / melamine complex preparation gene to obtain the second population of the melamine cyanurate / melamine complex preparation gene;

[0091] S64: Based on the trait mapping function and the flame retardant quality evaluation function, perform cyclic iteration on the second population of the melamine cyanurate / melamine complex preparation gene;

[0092] S65: Until the Kth population of the melamine cyanurate / melamine complex preparation gene is output, extract the historical fitness maximum value to construct the recommended genotype factor eigenvalue combination.

[0093] Specifically, according to the fitness evaluation pipeline, individuals in the first population of genes for preparing cyanuric acid / melamine complexes are all processed to obtain a set of fitness evaluation values. Based on the set of fitness evaluation values, the first population of genes for preparing cyanuric acid / melamine complexes is subjected to directed gene mutation according to the following process to obtain the second population of genes for preparing cyanuric acid / melamine complexes:

[0094] Further, based on the set of fitness evaluation values, the first population of genes for preparing cyanuric acid / melamine complexes is subjected to directed gene mutation to obtain the second population of genes for preparing cyanuric acid / melamine complexes. Step S63 includes the steps of:

[0095] S631: Sort the first population of genes for preparing cyanuric acid / melamine complexes from largest to smallest based on the set of fitness evaluation values to obtain the individual sorting result of the first population of genes for preparing cyanuric acid / melamine complexes;

[0096] S632: Sort the first number of head individuals in the individual sorting result, and sort the second number of tail individuals in the individual sorting result;

[0097] S633: Using the first number of head individuals as the mutation target, guide the second number of tail individuals to perform gene co-dimensional crossover mutation and co-dimensional progression mutation to obtain the second population of genes for preparing cyanuric acid / melamine complexes.

[0098] Specifically, sort the first population of genes for preparing cyanuric acid / melamine complexes from largest to smallest based on the set of fitness evaluation values to obtain the individual sorting result of the first population of genes for preparing cyanuric acid / melamine complexes; sort the first number of head individuals in the individual sorting result, and sort the second number of tail individuals in the individual sorting result. Preferably, the number of the first number of head individuals is 5 - 10, and the number of the second number of tail individuals is 50 - 100. Using the first number of head individuals as the mutation target, guide the second number of tail individuals to perform gene co-dimensional crossover mutation and co-dimensional progression mutation to obtain the second population of genes for preparing cyanuric acid / melamine complexes. Specifically:

[0099] Randomly select an individual from the first quantity of head individuals as the target individual; randomly select an individual from the second quantity of tail individuals as the starting individual. Cross the genotype characteristic values of the same attributes of the starting individual and the target individual to generate the second population of genes for preparing cyanuric acid / melamine complexes. Alternatively, adjust the genotype characteristic value of a certain attribute of the starting individual to approach the genotype characteristic value of the corresponding attribute of the target individual, and search according to the preset step length set by the user. For each search, an individual of the second population of genes for preparing cyanuric acid / melamine complexes is generated. The above-mentioned crossing and moving methods can be used simultaneously or separately.

[0100] Further, based on the trait mapping function and the flame retardant quality evaluation function, perform cyclic iteration on the second population of genes for preparing cyanuric acid / melamine complexes to obtain the third population of genes for preparing cyanuric acid / melamine complexes. Repeat the cycle until the second population of genes for preparing cyanuric acid / melamine complexes is obtained, where K is the preset convergence iteration number set by the user. When satisfied, output the genotype characteristic value of the individual with the maximum fitness of all populations as the recommended genotype factor characteristic value combination.

[0101] Through virtual iteration, global and efficient configuration of genotype factor characteristic values can be achieved. Subsequently, the user can directly use the recommended genotype factor characteristic value combination to prepare cyanuric acid / melamine complexes, or can select samples to test the recommended genotype factor characteristic value combination and then prepare cyanuric acid / melamine complexes after passing the test, both of which improve the efficiency of preparing cyanuric acid / melamine complexes.

[0102] The intelligent preparation method for cyanuric acid / melamine complexes based on the molecular self-assembly technology provided by the embodiments of the present invention has at least the following technical effects:

[0103] By setting each control element of the molecular self-assembly controller as a preparation genotype factor; setting the elements for evaluating the flame retardant performance as preparation phenotype factors; then constructing a trait mapping function from the preparation genotype factors to the preparation phenotype factors according to the type of seed material of the target product for which a flame retardant layer needs to be prepared; further, constructing a flame retardant quality evaluation function; then performing a backtracking for the preparation of cyanuric acid / melamine complexes based on the type of seed material to construct the first population of genes for preparing cyanuric acid / melamine complexes; finally, optimizing the first population of genes for preparing cyanuric acid / melamine complexes based on the trait mapping function and the flame retardant quality evaluation function to obtain a recommended genotype factor characteristic value combination for guiding the preparation of cyanuric acid / melamine complexes. Using machine learning combined with an optimization algorithm to achieve virtual iteration optimization of molecular self-assembly control, shortening the time loss of physical experiments, and achieving the technical effect of improving the configuration efficiency of molecular self-assembly control elements.

[0104] Example Two:

[0105] Please refer to Figure 3 , Figure 3 which is a schematic diagram of an embodiment of an electronic device provided by an embodiment of the present invention. As Figure 3 shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a computer program 511 stored on the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 511, the following steps are implemented:

[0106] A communication molecule self-assembly controller receives a preparation genotype factor, where the preparation genotype factor is used to characterize molecule self-assembly control parameters;

[0107] Through a user terminal, a preparation phenotype factor and a seed material type are configured, where the preparation phenotype factor is used to characterize an index for evaluating the quality of a composite;

[0108] According to the seed material type, a trait mapping function from the preparation genotype factor to the preparation phenotype factor is constructed;

[0109] Based on the preparation phenotype factor, a flame retardant quality evaluation function is constructed;

[0110] Based on the seed material type, a backtracking of the preparation of cyanuric acid / melamine composite is performed to construct a first population of genes for the preparation of cyanuric acid / melamine composite;

[0111] Based on the trait mapping function and the flame retardant quality evaluation function, the first population of genes for the preparation of cyanuric acid / melamine composite is optimized to obtain a recommended combination of genotype factor eigenvalue;

[0112] According to the recommended combination of genotype factor eigenvalue, the molecule self-assembly controller is initialized for preparation control.

[0113] Example Three:

[0114] Please refer to Figure 4 , Figure 4 which is a schematic diagram of an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. As Figure 4 shown, this embodiment provides a computer-readable storage medium 600, on which a computer program 611 is stored. When the computer program 611 is executed by a processor, the following steps are implemented:

[0115] A communication molecule self-assembly controller receives a preparation genotype factor, where the preparation genotype factor is used to characterize molecule self-assembly control parameters;

[0116] Through the client, configure the preparation phenotype factor and the seed material type, where the preparation phenotype factor is used to characterize the index for evaluating the quality of the composite;

[0117] According to the seed material type, construct a trait mapping function from the preparation genotype factor to the preparation phenotype factor;

[0118] Based on the preparation phenotype factor, construct a flame retardant quality evaluation function;

[0119] Based on the seed material type, perform a backtracking of the preparation of the cyanuric acid / melamine composite, and construct the first population of genes for the preparation of the cyanuric acid / melamine composite;

[0120] Based on the trait mapping function and the flame retardant quality evaluation function, optimize the first population of genes for the preparation of the cyanuric acid / melamine composite to obtain a recommended combination of genotype factor characteristic values;

[0121] According to the recommended combination of genotype factor characteristic values, initialize the molecular self-assembly controller for preparation control.

[0122] It should be noted that in the above embodiments, the descriptions of each embodiment have their own emphases. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0123] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0124] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0125] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means embodying the function specified in the flowchart(s) Figure 1 or flowcharts and / or block(s) Figure 1 or blocks.

[0126] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing steps for implementing the function specified in the flowchart(s) Figure 1 or flowcharts and / or block(s) Figure 1 or blocks.

[0127] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic inventive concept.

[0128] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent preparation method of cyanuric acid / melamine complex based on molecular self-assembly technology, characterized in that Comprising: A communication molecule self-assembly controller that receives a preparation genotype factor, where the preparation genotype factor is used to characterize molecular self-assembly control parameters; Through a user terminal, configure a preparation phenotype factor and a seed material type, where the preparation phenotype factor is used to characterize an index for evaluating the quality of a complex; According to the seed material type, construct a trait mapping function from the preparation genotype factor to the preparation phenotype factor; Based on the preparation phenotype factor, construct a flame retardant quality evaluation function; Based on the seed material type, perform a backtracking of the preparation of the cyanuric acid / melamine complex, and construct a first population of genes for the preparation of the cyanuric acid / melamine complex; Based on the trait mapping function and the flame retardant quality evaluation function, optimize the first population of genes for the preparation of the cyanuric acid / melamine complex to obtain a recommended combination of genotype factor eigenvalue; Initialize the molecular self-assembly controller according to the recommended combination of genotype factor eigenvalue for preparation control; Among them, according to the seed material type, constructing a trait mapping function from the preparation genotype factor to the preparation phenotype factor includes: According to the seed material type, collect the preparation log of the cyanuric acid / melamine complex, where the preparation log of the cyanuric acid / melamine complex includes a dataset of genotype factor recorded values and a dataset of phenotype factor recorded values; Construct a trait mapping function network architecture, where the trait mapping function network architecture has input nodes with the same dimension as the preparation genotype factor, and the trait mapping function network architecture has output nodes with the same dimension as the preparation phenotype factor; Using the dataset of phenotype factor recorded values as the supervised true value and the dataset of genotype factor recorded values as input data, train the trait mapping function network architecture to generate the trait mapping function; Among them, using the dataset of phenotype factor recorded values as the supervised true value and the dataset of genotype factor recorded values as input data, training the trait mapping function network architecture to generate the trait mapping function includes: Construct a trait mapping loss evaluation formula: Among them, LOSS represents the trait mapping loss value, and x i represents the predicted value of the phenotypic factor of the i-th attribute, and x i0 represents the recorded value data of the phenotypic factor of the i-th attribute, N represents the dimensionality of the phenotypic factor attributes, and a represents the mean loss threshold; Using the dataset of phenotype factor recorded values as the supervised true value and the dataset of genotype factor recorded values as input data, train the trait mapping function network architecture according to the trait mapping loss evaluation formula to generate the trait mapping function; Among them, based on the preparation phenotype factor, constructing a flame retardant quality evaluation function includes: Perform a positive processing on the preparation phenotype factor to obtain a positive index of the phenotype factor; Through the user terminal, traverse the positive index of the phenotype factor and configure a threshold for the positive index of the phenotype factor; According to the threshold of the positive index of the phenotype factor and the positive index of the phenotype factor, construct the flame retardant quality evaluation function: Among them, Q represents the flame retardant quality score, and y i represents the eigenvalue of the positive index of the phenotypic factor in the i-th dimension, and y i0 represents the threshold of the positive index of the phenotypic factor in the i-th dimension, N represents the dimension of the positive index of the phenotypic factor, and b represents a small constant.

2. The method according to claim 1, characterized in that, Based on the seed material type, perform a backtracking of the preparation of the cyanuric acid / melamine complex, and construct a first population of genes for the preparation of the cyanuric acid / melamine complex, including: Based on the type of seed material, perform a backtracking of the preparation of the cyanuric acid / melamine complex to obtain the historical eigenvalue of the first preparation genotype factor and the historical eigenvalue of the second preparation genotype factor; When the distance deviation parameter between the historical eigenvalue of the first preparation genotype factor and the historical eigenvalue of the second preparation genotype factor is greater than or equal to the distance deviation parameter threshold, add the historical eigenvalue of the first preparation genotype factor and the historical eigenvalue of the second preparation genotype factor to the first population of genes for the preparation of the cyanuric acid / melamine complex; When the distance deviation parameter between the historical eigenvalue of the first preparation genotype factor and the historical eigenvalue of the second preparation genotype factor is less than the distance deviation parameter threshold, randomly select one of the historical eigenvalue of the first preparation genotype factor and the historical eigenvalue of the second preparation genotype factor and add it to the first population of genes for the preparation of the cyanuric acid / melamine complex.

3. The method according to claim 2, wherein The evaluation steps of the distance deviation parameter include: Traverse the genotype factors and configure the genotype factor threshold; Perform a comparison of the same attributes on the historical eigenvalue of the first preparation genotype factor and the historical eigenvalue of the second preparation genotype factor to obtain the genotype factor deviation distance; When the genotype factor deviation distances are all less than or equal to the genotype factor threshold, set the distance deviation parameter to 0; When any one of the genotype factor deviation distances is greater than the genotype factor threshold, set the distance deviation parameter to 1.

4. The method according to claim 1, characterized in that, Based on the trait mapping function and the flame retardant quality evaluation function, optimize the first population of genes for the preparation of the cyanuric acid / melamine complex to obtain a recommended combination of genotype factor eigenvalues, including: Concatenate the trait mapping function and the flame retardant quality evaluation function to construct a fitness evaluation pipeline; According to the fitness evaluation pipeline, process the first population of genes for the preparation of the cyanuric acid / melamine complex to obtain a set of fitness evaluation values; Based on the set of fitness evaluation values, perform directed gene mutation on the first population of genes for the preparation of the cyanuric acid / melamine complex to obtain a second population of genes for the preparation of the cyanuric acid / melamine complex; Based on the trait mapping function and the flame retardant quality evaluation function, perform cyclic iteration on the second population of genes for the preparation of the cyanuric acid / melamine complex; Until the Kth population of genes for the preparation of the cyanuric acid / melamine complex is output, extract the maximum historical fitness value and construct the recommended combination of genotype factor eigenvalues.

5. The method according to claim 4, characterized in that, Based on the set of fitness evaluation values, perform directed gene mutation on the first population of genes for the preparation of the cyanuric acid / melamine complex to obtain a second population of genes for the preparation of the cyanuric acid / melamine complex, including: Sort the first population of genes for the preparation of the cyanuric acid / melamine complex from largest to smallest based on the set of fitness evaluation values to obtain the individual sorting result of the first population of genes for the preparation of the cyanuric acid / melamine complex; Sort the first number of head individuals of the individual sorting result and sort the second number of tail individuals of the individual sorting result; Taking the first quantity of head individuals as the mutation target, guiding the second quantity of tail individuals to perform gene same-dimensional crossover mutation and same-dimensional progression mutation, and obtaining the second population of genes for preparing the cyanuric acid / melamine complex.

6. An electronic device, characterized in that, Comprising: A memory for storing a computer software program; A processor for reading and executing the computer software program, thereby implementing the intelligent preparation method of the cyanuric acid / melamine complex based on the molecular self-assembly technology according to any one of claims 1 to 5.

7. A non-transitory computer-readable storage medium, characterized in that, A computer software program is stored in the storage medium, and when the computer software program is executed by a processor, the intelligent preparation method of the cyanuric acid / melamine complex based on the molecular self-assembly technology according to any one of claims 1 to 5 is implemented.

Images