Phase change microcapsule design system and method based on artificial intelligence

Abstract

The invention provides an artificial intelligence-based phase change microcapsule design system and method.The artificial intelligence-based phase change microcapsule design system comprises a machine learning module, a data establishment module, a target input module, a machine screening module and a target output module, the machine learning module is used for collecting raw material composition, synthesis process and performance data of existing phase change microcapsules; the data establishing module is used for collecting types of organic materials and inorganic materials and preparation processes of the materials; the target input module is used for inputting the phase change temperature, the phase change enthalpy value, the coating rate and the core material type of the phase change microcapsule to be designed; the machine screening module is used for screening appropriate wall materials and emulsifiers from the data establishing module according to the machine learning result and the data of the target input module; and the target output module is used for outputting the designed phase change microcapsules. The design module provided by the method adopts a machine learning mode to design the phase change microcapsules, so that the labor cost is effectively saved, and the research and development time is shortened.

Description

Technical Field

[0001] The present invention relates to the technical field of phase change materials, and in particular to a phase change microcapsule design system and method based on artificial intelligence. Background Art

[0002] Phase change microcapsules are a special type of microcapsules whose core contains one or more phase change materials. When the ambient temperature changes, these phase change materials absorb or release heat, thereby regulating the temperature around the microcapsules. This characteristic makes phase change microcapsules widely used in many fields, especially in situations where precise temperature control is required. There are many types of wall materials, core materials, and emulsifiers used to prepare phase change microcapsules. Selecting suitable wall materials, core materials, and emulsifiers usually requires a lot of experimental verification. For example, the paper "The Effect of Different Emulsifiers on the Performance of Dodecyl Stearate Phase Change Microcapsules" records the use of three different emulsifiers, sodium dodecylbenzene sulfonate / polyvinyl alcohol (SDBS / PVA), Tween 20, and octylphenol polyoxyethylene ether (OP-10). Phase change microcapsules with dodecyl stearate (DS) phase change material as the core and melamine-urea-formaldehyde resin (MUF) as the shell were prepared by in-situ polymerization. The preparation time of different emulsifiers is more than 24 hours, and performance characterization is required after preparation, which is time-consuming and costly.

[0003] With the development of modern technologies such as big data, machine learning, artificial intelligence and high-performance computing, it is an inevitable trend in future materials science research to study the properties of various materials in a data-driven way and provide reliable support for material property prediction and design through the processing and analysis of large-scale data. In this context, it is very important to provide a phase change microcapsule design system based on artificial intelligence. Summary of the invention

[0004] The present invention provides a phase change microcapsule design method based on artificial intelligence to solve the problem in the related art that the phase change microcapsule design process is complicated and requires a large number of experiments.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: A phase change microcapsule design system based on artificial intelligence includes a machine learning module, a data establishment module, a target input module, a machine screening module and a target output module. The machine learning module is used to collect raw material composition, synthesis process and performance data of existing phase change microcapsules. The data establishment module is used to collect types of organic materials, inorganic materials and material preparation processes; the target input module is used to input the phase change temperature, phase change enthalpy value, coverage rate and core material type of the phase change microcapsules to be designed; the machine screening module is used to screen out suitable wall materials and emulsifiers from the data establishment module according to the machine learning results and the data of the target input module; the target output module is used to output the designed phase change microcapsules.

[0006] The above-mentioned data establishment module includes a material type data unit and a synthesis process data unit. The material type data unit includes the existing inorganic material and organic material types and corresponding parameter data, and the synthesis process data unit includes the preparation process and preparation conditions of the existing materials.

[0007] The above-mentioned machine screening module includes a wall material screening unit, an emulsifier screening unit and a synthesis process screening unit. The wall material screening unit screens out wall materials that meet the requirements from the material type data unit, the emulsifier screening unit screens out emulsifiers that meet the requirements from the material type data unit, and the synthesis process screening unit screens out synthesis processes that meet the requirements from the synthesis process data unit based on the screened wall materials and emulsifier types.

[0008] The method of using the above-mentioned artificial intelligence-based phase change microcapsule design system comprises the following steps: S1. Send the raw material composition, synthesis process and performance data of the existing phase change microcapsules to the machine learning module for machine learning; S2. Collect the types of organic materials and inorganic materials and the preparation processes of the materials, and establish material type data units and synthesis process data units; S3, providing and inputting the phase change temperature, phase change enthalpy, coverage and type of core material of the phase change microcapsule to be designed; S4. Calculate the parameters of the wall material and the emulsifier according to the machine learning results and the phase change temperature, phase change enthalpy, coverage and core material type of the phase change microcapsule to be designed, and select the wall material and emulsifier that meet the requirements from the material type data unit according to the parameters corresponding to the wall material and the emulsifier; S5. Output the wall material, emulsifier type and dosage of phase change microcapsules.

[0009] The specific process of the above step S1 is: A set number of types of phase change microcapsules are selected from an Internet database, and original data sets are constructed according to the raw material composition, preparation process and performance parameters of these phase change microcapsules, specifically a raw material composition data set, a preparation process data set, and a performance parameter data set; The original data set is divided into a training set and a test set according to a set ratio. The data of the training set is used to train the GBRT model. During the training process, the data of the raw material composition and the preparation process are used as input objects, and the performance parameter data are used as targets. After the training is completed, the raw material composition data and the preparation process data of the test set are substituted into the machine learning model to obtain the predicted value of the test set. The actual value of the test set is compared with the predicted value to evaluate the prediction performance of the machine learning model. Based on the machine learning model, the mathematical model of the performance parameters of phase change microcapsules was constructed using the data-driven method SISSO, specifically: ; ; ; Where F(CR) represents the coverage of phase change microcapsules, X b1 Indicates the density of the wall material in g / cm 3 ,X r1 Indicates the molecular weight of the emulsifier in g / mol, X r2 Indicates the density of the emulsifier in g / cm 3 ,X c Indicates the usage ratio of core material and wall material, X t represents the reaction temperature, in °C; F(PTT) represents the phase change temperature of the phase change microcapsule, in °C; X x1 Indicates the density of the core material in g / cm 3 ;X x2 Indicates the melting point of the core material in °C, X b2 Indicates the specific heat capacity of the wall material, in J / (g·℃), X x3 Indicates the specific heat capacity of the core material, in J / (g·℃); X r3 Indicates the mass percentage of emulsifier; X r4 Indicates the HLB value of the emulsifier; X b3 It represents the molecular weight of the wall material, in g / mol; F(LHPC) represents the phase change enthalpy of the phase change microcapsule, in J / g.

[0010] The specific process of the above step S4 is: According to the data of the coverage rate, phase change temperature, phase change enthalpy value of the phase change microcapsule to be designed and the type of core material, combined with the mathematical model constructed in S1, iterative calculation is performed. The results of two consecutive iterations meet the following conditions: ∆F(CR) ≤±0.005, ∆F(PTT) ≤±0.5, ∆F(LHPC) ≤±1, then the calculation can be stopped, and the density of the wall material, the specific heat capacity of the wall material, the molecular weight of the wall material, the molecular weight of the emulsifier, the density of the emulsifier, the mass percentage of the emulsifier, the HLB value of the emulsifier, the dosage ratio of the core material to the wall material and the reaction temperature are obtained. The specific type of the wall material is determined according to the density of the wall material, the specific heat capacity of the wall material and the molecular weight of the wall material, and the specific type of the emulsifier is determined according to the density of the emulsifier, the HLB value of the emulsifier and the molecular weight of the emulsifier; the dosage of the wall material and the core material in the preparation process is determined according to the dosage ratio of the core material to the wall material; the dosage of the emulsifier is determined according to the mass percentage of the emulsifier; and the temperature required for the reaction process is determined according to the reaction temperature.

[0011] In the above step S1, 1000 phase change microcapsules are selected from the Internet database; the original data set is divided into a training set and a test set in a ratio of 80:20.

[0012] The present invention provides a phase change microcapsule design system and method based on artificial intelligence, and the beneficial effects are as follows: In traditional methods, the process of designing phase change microcapsules that meet performance requirements according to needs is cumbersome and requires manual query of a large amount of literature data and experimental verification, which is time-consuming. Using the design module provided in this application and using machine learning to design phase change microcapsules effectively saves labor costs and shortens research and development time. Using the system of this application, the design of a phase change microcapsule material with composite performance requirements can be completed in 10-20 seconds. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The present invention will be further described below in conjunction with the accompanying drawings and embodiments: Figure 1 A schematic flow chart of the method for the artificial intelligence-based phase-change microcapsule design system provided in this application; Figure 2 A microscope schematic diagram of a phase-change microcapsule designed using the artificial intelligence-based phase-change microcapsule design system provided in the present application; Figure 3 A schematic diagram of the phase change enthalpy value of phase change microcapsules designed using the artificial intelligence-based phase change microcapsule design system provided in this application. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical solutions and advantages of the present invention clearer, the following content will systematically and completely describe the specific technical solutions of the present invention in combination with the drawings provided according to the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0015] A phase change microcapsule design system based on artificial intelligence includes a machine learning module, a data establishment module, a target input module, a machine screening module and a target output module. The machine learning module is used to collect raw material composition, synthesis process and performance data of existing phase change microcapsules. The data establishment module is used to collect types of organic materials, inorganic materials and material preparation processes; the target input module is used to input the phase change temperature, phase change enthalpy value, coverage rate and core material type of the phase change microcapsules to be designed; the machine screening module is used to screen out suitable wall materials and emulsifiers from the data establishment module according to the machine learning results and the data of the target input module; the target output module is used to output the designed phase change microcapsules.

[0016] The above-mentioned data establishment module includes a material type data unit and a synthesis process data unit. The material type data unit includes the existing inorganic material and organic material types and corresponding parameter data, and the synthesis process data unit includes the preparation process and preparation conditions of the existing materials.

[0017] The above-mentioned machine screening module includes a wall material screening unit, an emulsifier screening unit and a synthesis process screening unit. The wall material screening unit screens out wall materials that meet the requirements from the material type data unit, the emulsifier screening unit screens out emulsifiers that meet the requirements from the material type data unit, and the synthesis process screening unit screens out synthesis processes that meet the requirements from the synthesis process data unit based on the screened wall materials and emulsifier types.

[0018] refer to Figure 1 , using the above-mentioned method of a phase change microcapsule design system based on artificial intelligence, comprising the following steps: S1. Send the raw material composition, synthesis process and performance data of the existing phase change microcapsules to the machine learning module for machine learning; S2. Collect the types of organic materials and inorganic materials and the preparation processes of the materials, and establish material type data units and synthesis process data units; S3, providing and inputting the phase change temperature, phase change enthalpy, coverage and type of core material of the phase change microcapsule to be designed; S4. Calculate the parameters of the wall material and the emulsifier according to the machine learning results and the phase change temperature, phase change enthalpy, coverage and core material type of the phase change microcapsule to be designed, and select the wall material and emulsifier that meet the requirements from the material type data unit according to the parameters corresponding to the wall material and the emulsifier; S5. Output the wall material, emulsifier type and dosage of phase change microcapsules.

[0019] The specific process of the above step S1 is: 1000 phase change microcapsules were selected from the Internet database, and original data sets were constructed according to the raw material composition, preparation process and performance parameters of these phase change microcapsules, specifically raw material composition data set, preparation process data set and performance parameter data set; The original data set was divided into a training set and a test set in a ratio of 80:20. The data of the training set was used to train the GBRT model. During the training process, the raw material composition and preparation process data were used as input objects, and the performance parameter data were used as targets. After the training was completed, the raw material composition data and preparation process data of the test set were substituted into the machine learning model to obtain the predicted value of the test set. The true value of the test set was compared with the predicted value to evaluate the prediction performance of the machine learning model. The mean absolute error MAE of the machine learning model was 0.058 eV / atom, and the determination coefficient R 2 =0.87, indicating that the machine learning model has high accuracy; Based on the machine learning model, the mathematical model of the performance parameters of phase change microcapsules was constructed using the data-driven method SISSO, specifically: ; ; ; Where F(CR) represents the coverage of phase change microcapsules, X b1 Indicates the density of the wall material in g / cm 3 ,X r1 Indicates the molecular weight of the emulsifier in g / mol, X r2 Indicates the density of the emulsifier in g / cm 3 ,X c Indicates the usage ratio of core material and wall material, X t represents the reaction temperature, in °C; F(PTT) represents the phase change temperature of the phase change microcapsule, in °C; X x1 Indicates the density of the core material in g / cm 3 ;X x2 Indicates the melting point of the core material in °C, X b2 Indicates the specific heat capacity of the wall material, in J / (g·℃), X x3Indicates the specific heat capacity of the core material, in J / (g·℃); X r3 Indicates the mass percentage of emulsifier; X r4 Indicates the HLB value of the emulsifier; X b3 It represents the molecular weight of the wall material, in g / mol; F(LHPC) represents the phase change enthalpy of the phase change microcapsule, in J / g.

[0020] SISSO can combine machine learning models to find out the most important few features that characterize the performance parameters of phase change microcapsules from various features. In this application, the most important features that characterize the coverage rate of phase change microcapsules are: the density of the wall material, the molecular weight of the emulsifier, the density of the emulsifier, the mass percentage of the emulsifier, the molecular weight of the wall material, and the amount ratio of the core material to the wall material. The most important features that characterize the phase change temperature of the phase change microcapsules are: the density of the core material, the melting point of the core material, the density of the emulsifier, the density of the wall material, the reaction temperature, the amount ratio of the core material to the wall material, and the mass percentage of the emulsifier; the most important features that characterize the phase change enthalpy of the phase change microcapsules are: the amount ratio of the core material to the wall material, the specific heat capacity of the wall material, the mass percentage of the emulsifier, the reaction temperature, the HLB value of the emulsifier, the specific heat capacity of the core material, and the melting point of the core material.

[0021] The specific process of the above step S4 is: According to the data of the coverage rate, phase change temperature, phase change enthalpy value of the phase change microcapsule to be designed and the type of core material, combined with the mathematical model constructed in S1, iterative calculation is performed. The results of two consecutive iterations meet the following conditions: ∆F(CR) ≤±0.005, ∆F(PTT) ≤±0.5, ∆F(LHPC) ≤±1, then the calculation can be stopped, and the density of the wall material, the specific heat capacity of the wall material, the molecular weight of the wall material, the molecular weight of the emulsifier, the density of the emulsifier, the mass percentage of the emulsifier, the HLB value of the emulsifier, the dosage ratio of the core material to the wall material and the reaction temperature are obtained. The specific type of the wall material is determined according to the density of the wall material, the specific heat capacity of the wall material and the molecular weight of the wall material, and the specific type of the emulsifier is determined according to the density of the emulsifier, the HLB value of the emulsifier and the molecular weight of the emulsifier; the dosage of the wall material and the core material in the preparation process is determined according to the dosage ratio of the core material to the wall material; the dosage of the emulsifier is determined according to the mass percentage of the emulsifier; and the temperature required for the reaction process is determined according to the reaction temperature.

[0022] Embodiment 1: (1) Using the keyword “phase change microcapsule” to screen and search the Internet big data database, 1,000 sets of raw material composition, synthesis process and performance data of phase change microcapsules were obtained, and the search results were exported in a table form and sent to the machine learning module; (2) Collect all existing inorganic and organic material types and corresponding parameter data, material preparation processes and preparation conditions, and import them into the data establishment module; (3) In the target input module, set the phase change temperature of the phase change microcapsules to be designed to 30-40 °C, the phase change enthalpy to 180-220 J / g, the coverage to 85%-95%, and the core material type to polyethylene glycol 1000; (4) The machine screening module selects suitable wall materials and emulsifiers from the data establishment module according to the data of the target input module; (5) The target output module outputs the wall material, emulsifier type and dosage of the designed phase change microcapsules.

[0023] Using the system provided by the present invention, after inputting the phase change temperature, phase change enthalpy value, coverage rate and core material, after 15 seconds, the output result of the target output module is: the wall material is gelatin with a molecular weight of 60,000, the emulsifier is sodium dodecyl sulfate, the reaction temperature is X t =60℃, the ratio of core material to wall material is X c =0.4, mass percentage of emulsifier X r3 =0.03, the coverage rate of phase change microcapsules F(CR)=90.2%, the phase change temperature of phase change microcapsules F(PTT)=39.27℃, and the phase change enthalpy value of phase change microcapsules F(LHPC)=210.16J / g.

[0024] Experimental verification: According to the wall material type, emulsifier type, core material and wall material usage ratio, and emulsifier mass percentage provided in Example 1, phase change microcapsules were prepared by emulsion polymerization, and the performance of the prepared phase change microcapsules was tested. The coverage rate of the prepared phase change microcapsules was 89.5%. The microscopic display of the phase change microcapsules is shown in FIG. Figure 2 , phase change enthalpy diagram see Figure 3 ,from Figure 3 It can be seen that the phase change temperature of the phase change microcapsules prepared according to the raw materials provided by the design system is 39.69°C, and the phase change enthalpy is 209.29J / g, which are highly consistent with the phase change temperature and phase change enthalpy output by the design system, indicating that the design system provided in this application can accurately complete the designed phase change enthalpy of the phase change microcapsules.

Claims

1. A phase change microcapsule design system based on artificial intelligence, characterized in that: It includes a machine learning module, a data establishment module, a target input module, a machine screening module and a target output module. The machine learning module is used to collect the raw material composition, synthesis process and performance data of the existing phase change microcapsules. The data establishment module is used to collect the types of organic materials and inorganic materials and the preparation process of the materials. The target input module is used to input the phase change temperature, phase change enthalpy value, coverage rate and core material type of the phase change microcapsules to be designed. The machine screening module is used to screen out suitable wall materials and emulsifiers from the data establishment module according to the machine learning results and the data of the target input module; the target output module is used to output the designed phase change microcapsules.

2. According to the artificial intelligence-based phase change microcapsule design system described in claim 1, it is characterized in that: The data establishment module includes a material type data unit and a synthesis process data unit. The material type data unit includes the existing inorganic material and organic material types and corresponding parameter data, and the synthesis process data unit includes the preparation process and preparation conditions of the existing materials.

3. According to the artificial intelligence-based phase change microcapsule design system described in claim 2, it is characterized in that: The machine screening module includes a wall material screening unit, an emulsifier screening unit and a synthesis process screening unit. The wall material screening unit screens out wall materials that meet the requirements from the material type data unit, the emulsifier screening unit screens out emulsifiers that meet the requirements from the material type data unit, and the synthesis process screening unit screens out synthesis processes that meet the requirements from the synthesis process data unit based on the screened wall materials and emulsifier types.

4. A method for using the artificial intelligence-based phase-change microcapsule design system as claimed in claim 3, characterized in that: The following steps are involved: S1. Send the raw material composition, synthesis process and performance data of the existing phase change microcapsules to the machine learning module for machine learning; S2. Collect the types of organic materials and inorganic materials and the preparation processes of the materials, and establish material type data units and synthesis process data units; S3, providing and inputting the phase change temperature, phase change enthalpy, coverage and core material type of the phase change microcapsule to be designed; S4. Calculate the parameters of the wall material and the emulsifier according to the machine learning results and the phase change temperature, phase change enthalpy, coverage and core material type of the phase change microcapsule to be designed, and select the wall material and emulsifier that meet the requirements from the material type data unit according to the parameters corresponding to the wall material and the emulsifier; S5. Output the wall material, emulsifier type and dosage of phase change microcapsules.

5. The method for designing a phase-change microcapsule system based on artificial intelligence according to claim 4, characterized in that: The specific process of step S1 is as follows: A set number of types of phase change microcapsules are selected from an Internet database, and original data sets are constructed according to the raw material composition, preparation process and performance parameters of these phase change microcapsules, specifically a raw material composition data set, a preparation process data set, and a performance parameter data set; The original data set is divided into a training set and a test set according to a set ratio. The data of the training set is used to train the GBRT model. During the training process, the data of raw material composition and preparation process are used as input objects, and the performance parameter data are used as targets. After the training is completed, the raw material composition data and preparation process data of the test set are substituted into the machine learning model to obtain the predicted value of the test set; the actual value of the test set is compared with the predicted value to evaluate the prediction performance of the machine learning model; Based on the machine learning model, the mathematical model of the performance parameters of phase change microcapsules was constructed using the data-driven method SISSO, specifically: ； ； ； Where F(CR) represents the coverage of phase change microcapsules, X b1 Indicates the density of the wall material in g / cm 3 ,X r1 Indicates the molecular weight of the emulsifier in g / mol, X r2 Indicates the density of the emulsifier in g / cm 3 ,X c Indicates the usage ratio of core material and wall material, X t represents the reaction temperature, in °C; F(PTT) represents the phase change temperature of the phase change microcapsule, in °C; X x1 Indicates the density of the core material in g / cm 3 ;X x2 Indicates the melting point of the core material in °C, X b2 Indicates the specific heat capacity of the wall material, in J / (g·℃), X x3 Indicates the specific heat capacity of the core material, in J / (g·℃); X r3 Indicates the mass percentage of emulsifier; X r4 Indicates the HLB value of the emulsifier; X b3 It represents the molecular weight of the wall material, in g / mol; F(LHPC) represents the phase change enthalpy of the phase change microcapsule, in J / g.

6. The method for designing a phase-change microcapsule system based on artificial intelligence according to claim 5, characterized in that: The specific process of step S4 is as follows: According to the data of the coverage rate, phase change temperature, phase change enthalpy value of the phase change microcapsule to be designed and the type of core material, combined with the mathematical model constructed in S1, iterative calculation is performed. The results of two consecutive iterations meet the following conditions: ∆F(CR) ≤±0.005, ∆F(PTT) ≤±0.5, ∆F(LHPC) ≤±1, then the calculation can be stopped, and the density of the wall material, the specific heat capacity of the wall material, the molecular weight of the wall material, the molecular weight of the emulsifier, the density of the emulsifier, the mass percentage of the emulsifier, the HLB value of the emulsifier, the dosage ratio of the core material to the wall material and the reaction temperature are obtained. The specific type of the wall material is determined according to the density of the wall material, the specific heat capacity of the wall material and the molecular weight of the wall material, and the specific type of the emulsifier is determined according to the density of the emulsifier, the HLB value of the emulsifier and the molecular weight of the emulsifier; the dosage of the wall material and the core material in the preparation process is determined according to the dosage ratio of the core material to the wall material; the dosage of the emulsifier is determined according to the mass percentage of the emulsifier; and the temperature required for the reaction process is determined according to the reaction temperature.

7. The method for designing a phase-change microcapsule system based on artificial intelligence according to claim 6, characterized in that: In the step S1, 1000 phase change microcapsules are selected from an Internet database; the original data set is divided into a training set and a test set in a ratio of 80:20.

Images