A method for predicting the color change of conjugated polymer microspheres with ultra-wide color gamut

Abstract

The present invention discloses a method for predicting the color change of ultra-wide color gamut conjugated polymer microspheres, comprising: collecting solution mass ratio data of previous three-primary color polymer solutions; obtaining annealing condition data corresponding to the solution mass ratio data; obtaining color change data of conjugated polymer microspheres under the annealing condition data; using the above data as sample data to train a neural network model to form a color change prediction model; inputting new solution mass ratio data and annealing condition data as target data into the color change prediction model for prediction; converting new color temperature data and brightness data output by the prediction color change model into three primary color values ​​through a blackbody radiation RGB conversion formula to complete the prediction. Through this method, the prediction model can quickly predict the color temperature and brightness of conjugated polymer microspheres, and industrial personnel can quickly prepare conjugated polymer materials whose colors and brightness are adapted to their specific industrial application fields based on the new target data and prediction results.

Description

Technical Field

[0001] The invention relates to a method for predicting the color brightness of conjugated polymer microspheres, in particular to a method for predicting the color change of ultra-wide color gamut conjugated polymer microspheres. Background Art

[0002] The color and optical properties of conjugated polymer microspheres are often affected by their synthesis conditions, such as the mass ratio of the three primary color polymer solution, annealing pressure, annealing temperature and annealing time. Under the influence of different influencing parameters, the color and optical properties of conjugated polymer microspheres may be different. Conjugated polymer microspheres are widely used in fields such as simulated microbial transport, light-emitting diodes (LEDs), solar cells and light sensors due to their excellent photoelectric properties. Different application fields have specific requirements for the color temperature and brightness of conjugated polymer microspheres. This requires the preparation personnel to ensure that the color temperature and brightness of the conjugated polymer microspheres change to adapt to their application fields when preparing conjugated polymer microspheres for use in different fields.

[0003] In the process of preparing conjugated polymer materials in the factory, there are too many factors that affect the color and optical properties of the conjugated polymer microspheres. Therefore, relying on conventional means to judge whether the color and brightness of the prepared conjugated polymer materials meet expectations is not only time-consuming and labor-intensive, but also has problems such as low judgment accuracy. As a result, when the preparation personnel are preparing the conjugated polymer microspheres and controlling the color and brightness of the conjugated polymer microspheres to evolve toward the expected color and brightness, the color and brightness of the prepared conjugated polymer microspheres may not meet the expected color and brightness, thereby causing the prepared conjugated polymer material to be unsuitable for its specific industrial application field.

[0004] Therefore, designing a method that can efficiently and standardizedly predict the color and brightness changes of conjugated polymer microspheres to ensure that the color of the prepared conjugated polymer microspheres is suitable for their specific industrial application fields has become an urgent problem to be solved. Summary of the invention

[0005] In order to at least overcome the deficiencies in the prior art, the purpose of the present application is to provide a method for predicting the color change of conjugated polymer microspheres with an ultra-wide color gamut.

[0006] The present application embodiment provides a method for predicting the color change of ultra-wide color gamut conjugated polymer microspheres, comprising:

[0007] Collecting solution mass ratio data of three primary color polymer solutions for making conjugated polymer microspheres over multiple experimental cycles;

[0008] Acquire annealing condition data corresponding to the solution mass ratio data, wherein the annealing condition data is annealing pressure data, annealing temperature data and annealing time data in the process of preparing conjugated polymer microspheres from the three primary color polymer solution;

[0009] Acquire color change data of the conjugated polymer microspheres under the annealing condition data, where the color change data is color temperature data and brightness data corresponding to the annealing condition data;

[0010] The solution mass ratio data, annealing condition data and color change data are used as sample data to train a neural network model to form a color change prediction model, wherein the input data of the color change prediction model are the solution mass ratio data and the annealing condition data, and the output data of the color change prediction model are the color temperature data and the brightness data;

[0011] The solution mass ratio data and annealing condition data under the new experimental environment are input as target data into the color change prediction model for prediction;

[0012] Through the blackbody radiation RGB conversion formula, the new color temperature data and brightness data output by the predicted color change model are converted into three primary color values ​​to complete the prediction.

[0013] In scientific practice, the inventors found that when preparing conjugated polymer materials, there are too many influencing parameters that affect their color and optical properties. For example, in the initial stage of preparing conjugated polymer microspheres, the main influencing parameter is the solution mass ratio of the three primary color polymer solution. The conjugated polymer microspheres prepared from the three primary color polymer solutions with different solution mass ratios have different color performances, optical properties, physical structures and thermal properties of the microspheres. In the overpressure annealing stage, different annealing condition influencing parameters will also affect the changes in the color and brightness of the conjugated polymer microspheres, such as annealing pressure, annealing temperature and annealing time. Appropriate annealing time usually helps to promote the rearrangement and crystallization of polymer chains and improve their optical and electrical properties, while too long annealing time will lead to degradation and structural morphology changes of the polymer microspheres, thereby affecting their color changes and optical properties. Different annealing pressures will affect the formation or removal of bubbles in the polymer microspheres, thereby affecting their color changes and optical properties. Different annealing temperatures, It has a significant impact on the glass transition temperature (Tg) of polymer microspheres. Appropriate annealing temperature can enhance the compatibility and uniformity of polymer microspheres, thereby improving their emission spectrum and brightness, while too high annealing temperature may cause degradation or color distortion of polymer microspheres. It can be seen that under the influence of different influencing parameters, the color and optical properties of conjugated polymer microspheres will produce different changes, and the color and optical properties of conjugated polymer microspheres can reflect the structural properties, thermal properties and electrical properties of polymer microspheres in the current state. However, the traditional method of preparing conjugated polymer materials in factories usually relies on visual observation to judge whether the color and brightness of the prepared conjugated polymer materials meet expectations. This judgment method is not scientific and rigorous, and it is easy for the color and brightness of the prepared conjugated polymer microspheres to fail to meet the expected color and brightness, which in turn causes the prepared conjugated polymer materials to be unsuitable for their specific industrial application fields, causing irreparable economic losses.

[0014] Based on this, the inventors have designed a method for predicting the color change of conjugated polymer microspheres by combining experimental data from multiple historical experimental cycles with a neural network model. The neural network model is trained with a large amount of previous experimental data from the laboratory to form a prediction model that can predict the color change of conjugated polymer microspheres. The large amount of experimental data includes solution mass ratio data, annealing condition data corresponding to the solution mass ratio data, and color change data corresponding to the solution mass ratio data and the annealing condition data. The color change prediction model uses the solution mass ratio data and the annealing condition data as input features and the color change data as labels for training. After the training is completed, the solution mass ratio data and the annealing condition data under the new experimental environment are input into the color change prediction model. The color change prediction model outputs the corresponding color temperature value and brightness value in each annealing time period, thereby reflecting the color temperature of each annealing time period. The changes in color and color temperature of the conjugated polymer microspheres within the segment are predicted by this prediction method combined with the neural network model. When it is necessary to produce conjugated polymer materials suitable for specific industrial fields, the user only needs to input the numerical values ​​of the influencing parameters as input features into the color prediction network model. The color prediction network model predicts the color range interval values ​​and brightness range interval values ​​of the conjugated polymer microspheres in each overpressure annealing period; at this time, the preparation personnel select the appropriate color range interval values ​​and brightness range interval values ​​according to the prediction results given by the color prediction network model, and use the solution mass ratio data corresponding to the appropriate range interval values ​​to proportion and manufacture the conjugated polymer microspheres. In the overpressure annealing stage, the annealing time, temperature and pressure are controlled according to the annealing condition data corresponding to the appropriate range interval values ​​to manufacture the conjugated polymer materials suitable for specific industrial fields.

[0015] Further, the step of obtaining the color change data of the conjugated polymer microspheres under the annealing condition data includes:

[0016] In multiple experimental cycles, the conjugated polymer microspheres with different solution mass ratios were annealed under the same annealing time, annealing pressure and annealing temperature conditions;

[0017] The annealing time is divided into time periods by preset time intervals;

[0018] The color temperature data of the color change of the conjugated polymer microspheres and the brightness data of the brightness change in each time period are recorded.

[0019] When implementing this embodiment, the controlled variable method is adopted in multiple experimental cycles, the solution mass ratio of the three primary color polymer solution is set as the independent variable, the color temperature and brightness of the conjugated polymer microspheres are set as the dependent variables, and the annealing time, annealing pressure, annealing temperature and annealing time interval are set as predetermined values.

[0020] Under the condition that the annealing duration (i.e., annealing time) is a constant value, the annealing duration is divided into time periods using preset time intervals. During the annealing operation of the conjugated polymer, the color temperature interval value and the brightness interval value of the conjugated polymer in each same annealing time period are recorded. The color temperature interval value is the range interval of the maximum color temperature value and the minimum color temperature value corresponding to the time period, and the brightness interval value is the range interval of the maximum brightness value and the minimum brightness value corresponding to the time period.

[0021] By setting the solution mass ratio of the three primary color polymer solution as the independent variable, and the color temperature and brightness of the conjugated polymer microspheres as the dependent variables, and setting the annealing time, annealing pressure, annealing temperature and annealing time interval to predetermined values, this method can systematically analyze the influence of different solution ratios on the optical properties, ensure the reliability of the experiment, ensure the accuracy of the experimental data, and provide assistance for the subsequent training of the neural network model based on the experimental data. Accurate experimental data provides a guarantee for the prediction accuracy of the neural network model.

[0022] Furthermore, the step of obtaining the color change data of the conjugated polymer microspheres under the annealing condition data also includes:

[0023] In multiple experimental cycles, the conjugated polymer microspheres were annealed at different annealing pressures under the same solution mass ratio, annealing time and annealing temperature conditions;

[0024] The annealing time is divided into time periods by preset time intervals;

[0025] The color temperature data of the color change of the conjugated polymer microspheres and the brightness data of the brightness change in each time period are recorded.

[0026] Furthermore, the step of obtaining the color change data of the conjugated polymer microspheres under the annealing condition data also includes:

[0027] In multiple experimental cycles, the conjugated polymer microspheres were annealed at different annealing temperatures under the same solution mass ratio, annealing time and annealing pressure conditions;

[0028] The annealing time is divided into time periods by preset time intervals;

[0029] The color temperature data of the color change of the conjugated polymer microspheres and the brightness data of the brightness change in each time period are recorded.

[0030] Furthermore, the step of obtaining the color change data of the conjugated polymer microspheres under the annealing condition data also includes:

[0031] In multiple experimental cycles, the conjugated polymer microspheres were annealed at different annealing times under the same solution mass ratio, annealing pressure and annealing temperature conditions;

[0032] Different annealing times are divided into time periods by presetting time intervals;

[0033] The color temperature data of the color change of the conjugated polymer microspheres and the brightness data of the brightness change in each time period are recorded.

[0034] Furthermore, the steps of training the neural network model include:

[0035] The solution mass ratio data, annealing pressure data, annealing temperature data and annealing time data are used as input features X, and the color temperature data and brightness data are used as labels Y;

[0036] Assign the input feature X and label Y to the input layer of the color change prediction model for standardization and normalization;

[0037] The hidden layer receives the input features X processed by each input layer and uses the weighted input calculation formula to calculate the weighted input of each hidden layer;

[0038] The weighted input of each hidden layer is calculated by the first activation function to obtain the output value of each hidden layer neuron;

[0039] The output layer receives the output value of each hidden layer neuron and uses the weighted input calculation formula to calculate the weighted input of each output layer;

[0040] The color temperature data and brightness data corresponding to each time period are predicted by the second activation function, and the predicted color temperature data and brightness data are evaluated by using the loss function until the evaluation is qualified;

[0041] After evaluation, optimize the predictive ability of the color change prediction model;

[0042] The output layer outputs the qualified predicted color temperature data and predicted brightness data as the final result value.

[0043] Furthermore, the weighted input calculation formula is:

[0044] ;

[0045] in, is the weighted input of the jth neuron in the current layer; is the weight from the i-th neuron in the previous layer to the j-th neuron in the current layer, is the input feature of the i-th neuron in the previous layer, is the bias of the jth neuron in the current layer.

[0046] Furthermore, the formula of the first activation function is:

[0047] ;

[0048] in, is the output value of the i-th neuron in the hidden layer; is the weighted input of the i-th neuron in the hidden layer.

[0049] Furthermore, the formula of the second activation function is:

[0050] ;

[0051] in, The predicted color temperature data and predicted brightness data output by the output layer are: is the weighted input of the output layer.

[0052] Furthermore, the model parameters are updated through the back-propagation algorithm, and the prediction ability of the color change prediction model is optimized through the new model parameters.

[0053] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0054] The invention discloses a method for predicting the color change of conjugated polymer microspheres with an ultra-wide color gamut. The method combines a neural network model with experimental data in multiple historical experimental cycles, and trains the neural network model in large quantities through the historical experimental data to form a color change prediction model. The trained color change prediction model can quickly predict the color temperature and brightness value of the conjugated polymer microspheres in each annealing time period according to the input experimental condition data. Industrial personnel can quickly prepare conjugated polymer materials whose colors and optical properties are suitable for specific industrial application fields according to the experimental condition data and the prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0056] Figure 1 A step diagram of a method for predicting color change of conjugated polymer microspheres;

[0057] Figure 2 A diagram of the training steps for training a neural network model to form a color change prediction model;

[0058] Figure 3 This is a structural diagram of the neural network model. DETAILED DESCRIPTION

[0059] To make the purpose, technical scheme and advantages of the embodiment of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the embodiment of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0060] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0061] Please refer to Figure 1 , a method for predicting the color change of ultra-wide color gamut conjugated polymer microspheres, the prediction method comprising the following steps:

[0062] Collecting solution mass ratio data of three primary color polymer solutions for making conjugated polymer microspheres over multiple experimental cycles;

[0063] Acquire annealing condition data corresponding to the solution mass ratio data, wherein the annealing condition data is annealing pressure data, annealing temperature data and annealing time data in the process of preparing conjugated polymer microspheres from the three primary color polymer solution;

[0064] Acquire color change data of the conjugated polymer microspheres under the annealing condition data, wherein the color change data is color temperature data and brightness data corresponding to the annealing condition data;

[0065] Using the solution mass ratio data, the annealing condition data and the color change data as sample data to train a neural network model to form a color change prediction model, wherein the input data of the color change prediction model are the solution mass ratio data and the annealing condition data, and the output data of the color change prediction model are the color temperature data and the brightness data;

[0066] Inputting the solution mass ratio data and annealing condition data under the new experimental environment as target data into the color change prediction model for prediction;

[0067] The new color temperature data and brightness data output by the predicted color change model are converted into three primary color values ​​through the blackbody radiation RGB conversion formula to complete the prediction.

[0068] When the embodiment of the present application is implemented, the solution mass ratio of the three primary color polymer solution is a preset solution mass ratio. The masses of the three polymer solutions are weighed respectively by a precision balance, and their respective mass ratios are calculated according to the formula; the annealing time is recorded by a timer, and the annealing time is taken as the preset annealing time; the annealing temperature is monitored by a temperature sensor, and the annealing temperature is the preset annealing temperature; the annealing pressure is monitored by a pressure sensor, and the annealing pressure is the preset annealing pressure; before the experiment starts, the annealing time needs to be divided into time periods according to the preset time intervals to ensure that the duration of each time period is equal, so that the corresponding time in each time period is recorded for subsequent experiments The color temperature range interval value and the brightness range interval value are prepared, the color temperature range value is the range interval of the maximum color temperature value and the minimum color temperature value corresponding to the time period, and the brightness range value is the range interval of the maximum brightness value and the minimum brightness value corresponding to the time period. In this embodiment, the color temperature value and the brightness value are recorded by a camera, a photometer, a spectrometer, a fluorescence spectrometer and a colorimeter. The image of the conjugated polymer microsphere sample from the formation of microspheres to the annealing stage and then to the completion of the production is continuously taken by a camera, and then the brightness value is measured by a photometer, and then the spectral characteristics are analyzed by a spectrometer and a fluorescence spectrometer, and finally the color standard is compared with a colorimeter. Through the cooperation of the above-mentioned equipment, the color temperature value and the brightness value of the conjugated polymer microsphere from the preparation to the completion stage during the test can be obtained.

[0069] In this embodiment, an n-fold strategy is adopted to divide the sample data into n parts, use n-1 parts for model training, and use the remaining 1 part for actual measurement and verification, and repeat this process n+1 times. This method helps prevent the model from overfitting.

[0070] When this embodiment is implemented, the blackbody radiation RGB conversion formula is:

[0071] ;

[0072] ;

[0073] ;

[0074] in, To predict color temperature data; To predict brightness data; , and is a function related to color temperature; , and are the converted three primary color values.

[0075] Characterizing the color of the conjugated polymer microspheres by the three primary color values ​​allows the preparation personnel to more intuitively understand and analyze the current color luminescence characteristics of the conjugated polymer microspheres, making it convenient for subsequent experiments and applications of preparing conjugated polymer microspheres based on the above-mentioned input characteristics.

[0076] Furthermore, the step of obtaining the color change data of the conjugated polymer microspheres under the annealing condition data comprises:

[0077] In multiple experimental cycles, the conjugated polymer microspheres with different solution mass ratios were annealed under the same annealing time, annealing pressure and annealing temperature conditions;

[0078] Dividing the annealing time into time periods according to preset time intervals;

[0079] The color temperature data of the color change and the brightness data of the brightness change of the conjugated polymer microspheres corresponding to each time period are recorded.

[0080] In the implementation of this embodiment, poly [2-methoxy-5- (2-ethylhexyloxy) -p-phenylene] is selected as the blue polymer solution (BP), poly- ((1E, 1'E- (2,5-bis (2-ethylhexyloxy) -1,4-phenylene) bis (ethylene-2,1-diyl)) bis (2,5-dimethoxybenzene) -4,4'-diyl) is selected as the green polymer solution (GP) and poly [2-methoxy-5- (2-ethylhexyloxy) -1,4-phenylene -ethylene] is selected as the red polymer solution (RP); multiple groups of conjugated polymer microspheres are prepared by using polymer solutions with different mass ratios of the solutions, and then, they are allowed to flow at 95% and 5% Annealing is carried out under an overpressure of a mixed gas.

[0081] When implementing this embodiment, the controlled variable method is adopted in multiple experimental cycles, the solution mass ratio of the three primary color polymer solution is set as the independent variable, the color temperature and brightness of the conjugated polymer microspheres are set as the dependent variables, and the annealing time, annealing pressure, annealing temperature and annealing time interval are set as predetermined values.

[0082] Under the condition that the annealing duration (i.e., annealing time) is a constant value, the annealing duration is divided into time periods using preset time intervals. During the annealing operation of the conjugated polymer, the color temperature interval value and the brightness interval value of the conjugated polymer in each same time period are recorded. The color temperature interval value is the range interval of the maximum color temperature value and the minimum color temperature value corresponding to the time period, and the brightness interval value is the range interval of the maximum brightness value and the minimum brightness value corresponding to the time period.

[0083] By setting the solution mass ratio of the three primary color polymer solution as the independent variable, and the color temperature and brightness of the conjugated polymer microspheres as the dependent variables, and setting the annealing time, annealing pressure, annealing temperature and annealing time interval to predetermined values, this method can systematically analyze the influence of different solution ratios on the optical properties, ensure the reliability of the experiment, ensure the accuracy of the experimental data, and provide assistance for the subsequent training of the neural network model based on the experimental data. Accurate experimental data provides a guarantee for the training neural network model to predict accurate results.

[0084] Furthermore, the step of obtaining the color change data of the conjugated polymer microspheres under the annealing condition data further includes:

[0085] In multiple experimental cycles, the conjugated polymer microspheres were annealed at different annealing pressures under the same solution mass ratio, annealing time and annealing temperature conditions;

[0086] Dividing the annealing time into time periods according to preset time intervals;

[0087] The color temperature data of the color change and the brightness data of the brightness change of the conjugated polymer microspheres corresponding to each time period are recorded.

[0088] Furthermore, the step of obtaining the color change data of the conjugated polymer microspheres under the annealing condition data further includes:

[0089] In multiple experimental cycles, the conjugated polymer microspheres were annealed at different annealing temperatures under the same solution mass ratio, annealing time and annealing pressure conditions;

[0090] Dividing the annealing time into time periods according to preset time intervals;

[0091] The color temperature data of the color change and the brightness data of the brightness change of the conjugated polymer microspheres corresponding to each time period are recorded.

[0092] Furthermore, the step of obtaining the color change data of the conjugated polymer microspheres under the annealing condition data further includes:

[0093] In multiple experimental cycles, the conjugated polymer microspheres were annealed at different annealing times under the same solution mass ratio, annealing pressure and annealing temperature conditions;

[0094] Dividing the different annealing durations into time periods by preset time intervals;

[0095] The color temperature data of the color change and the brightness data of the brightness change of the conjugated polymer microspheres corresponding to each time period are recorded.

[0096] For further information, please refer to Figure 2 and Figure 3 , the steps of training the neural network model include:

[0097] The solution mass ratio data, the annealing pressure data, the annealing temperature data and the annealing time data are used as input features X, and the color temperature data and the brightness data are used as labels Y;

[0098] Assigning the input feature X and the label Y to the input layer of the color change prediction model for standardization and normalization;

[0099] The hidden layer receives the input feature X processed by each input layer, and uses the weighted input calculation formula to calculate the weighted input of each hidden layer;

[0100] The weighted input of each hidden layer is calculated by the first activation function to obtain the output value of each hidden layer neuron;

[0101] The output layer receives the output value of each hidden layer neuron and uses the weighted input calculation formula to calculate the weighted input of each output layer;

[0102] Predicting the color temperature data and brightness data corresponding to each time period by using the second activation function, and evaluating the predicted color temperature data and brightness data by using the loss function until the evaluation is qualified;

[0103] After the evaluation is qualified, optimizing the predictive ability of the color change prediction model;

[0104] The output layer outputs the qualified predicted color temperature data and predicted brightness data as the final result value.

[0105] When this embodiment is implemented, the neural network model is a feedforward neural network model. In addition, a convolutional neural network model can also be selected for training to predict the color change of conjugated polymer microspheres.

[0106] Furthermore, the weighted input calculation formula is:

[0107] ;

[0108] in, is the weighted input of the jth neuron in the current layer; is the weight from the i-th neuron in the previous layer to the j-th neuron in the current layer, is the input feature of the i-th neuron in the previous layer, is the bias of the jth neuron in the current layer.

[0109] Furthermore, the formula of the first activation function is:

[0110] ;

[0111] in, is the output value of the i-th neuron in the hidden layer; is the weighted input of the i-th neuron in the hidden layer.

[0112] Furthermore, the formula of the second activation function is:

[0113] ;

[0114] in, The predicted color temperature data and predicted brightness data output by the output layer are: is the weighted input of the output layer.

[0115] Furthermore, the model parameters are updated through a back-propagation algorithm, and the prediction capability of the color change prediction model is optimized through the new model parameters.

[0116] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for predicting the color change of ultra-wide color gamut conjugated polymer microspheres, characterized in that: The prediction method comprises the following steps: Collecting solution mass ratio data of three primary color polymer solutions for making conjugated polymer microspheres over multiple experimental cycles; Acquire annealing condition data corresponding to the solution mass ratio data, wherein the annealing condition data is annealing pressure data, annealing temperature data and annealing time data in the process of preparing conjugated polymer microspheres from the three primary color polymer solution; Acquire color change data of the conjugated polymer microspheres under the annealing condition data, wherein the color change data is color temperature data and brightness data corresponding to the annealing condition data; Using the solution mass ratio data, the annealing condition data and the color change data as sample data to train a neural network model to form a color change prediction model, wherein the input data of the color change prediction model are the solution mass ratio data and the annealing condition data, and the output data of the color change prediction model are the color temperature data and the brightness data; Inputting the solution mass ratio data and annealing condition data under the new experimental environment as target data into the color change prediction model for prediction; The new color temperature data and brightness data output by the color change prediction model are converted into three primary color values ​​through the blackbody radiation RGB conversion formula to complete the prediction.

2. The method for predicting color change of ultra-wide color gamut conjugated polymer microspheres according to claim 1, characterized in that: The step of obtaining the color change data of the conjugated polymer microspheres under the annealing condition data comprises: In multiple experimental cycles, the conjugated polymer microspheres with different solution mass ratios were annealed under the same annealing time, annealing pressure and annealing temperature conditions; Dividing the annealing time into time periods according to preset time intervals; The color temperature data of the color change and the brightness data of the brightness change of the conjugated polymer microspheres corresponding to each time period are recorded.

3. The method for predicting color change of ultra-wide color gamut conjugated polymer microspheres according to claim 1, characterized in that: The step of obtaining the color change data of the conjugated polymer microspheres under the annealing condition data further includes: In multiple experimental cycles, the conjugated polymer microspheres were annealed at different annealing pressures under the same solution mass ratio, annealing time and annealing temperature conditions; Dividing the annealing time into time periods according to preset time intervals; The color temperature data of the color change and the brightness data of the brightness change of the conjugated polymer microspheres corresponding to each time period are recorded.

4. The method for predicting color change of ultra-wide color gamut conjugated polymer microspheres according to claim 1, characterized in that: The step of obtaining the color change data of the conjugated polymer microspheres under the annealing condition data further includes: In multiple experimental cycles, the conjugated polymer microspheres were annealed at different annealing temperatures under the same solution mass ratio, annealing time and annealing pressure conditions; Dividing the annealing time into time periods according to preset time intervals; The color temperature data of the color change and the brightness data of the brightness change of the conjugated polymer microspheres corresponding to each time period are recorded.

5. The method for predicting color change of ultra-wide color gamut conjugated polymer microspheres according to claim 1, characterized in that: The step of obtaining the color change data of the conjugated polymer microspheres under the annealing condition data further includes: In multiple experimental cycles, the conjugated polymer microspheres were annealed at different annealing times under the same solution mass ratio, annealing pressure and annealing temperature conditions; Dividing the different annealing durations into time periods by preset time intervals; The color temperature data of the color change and the brightness data of the brightness change of the conjugated polymer microspheres corresponding to each time period are recorded.

6. The method for predicting color change of ultra-wide color gamut conjugated polymer microspheres according to claim 1, characterized in that: The steps of training the neural network model include: The solution mass ratio data, the annealing pressure data, the annealing temperature data and the annealing time data are used as input features X, and the color temperature data and the brightness data are used as labels Y; Assigning the input feature X and the label Y to the input layer of the color change prediction model for standardization and normalization; The hidden layer receives the input feature X processed by each input layer, and uses the weighted input calculation formula to calculate the weighted input of each hidden layer; The weighted input of each hidden layer is calculated by the first activation function to obtain the output value of each hidden layer neuron; The output layer receives the output value of each hidden layer neuron and uses the weighted input calculation formula to calculate the weighted input of each output layer; Predicting the color temperature data and brightness data corresponding to each time period by using the second activation function, and evaluating the predicted color temperature data and brightness data by using the loss function until the evaluation is qualified; After the evaluation is qualified, optimizing the predictive ability of the color change prediction model; The output layer outputs the qualified predicted color temperature data and predicted brightness data as the final result value.

7. The method for predicting color change of ultra-wide color gamut conjugated polymer microspheres according to claim 6, characterized in that: The weighted input calculation formula is: ； in, is the weighted input of the jth neuron in the current layer; is the weight from the i-th neuron in the previous layer to the j-th neuron in the current layer, is the input feature of the i-th neuron in the previous layer, is the bias of the jth neuron in the current layer.

8. The method for predicting color change of ultra-wide color gamut conjugated polymer microspheres according to claim 6, characterized in that: The formula of the first activation function is: ； in, is the output value of the i-th neuron in the hidden layer; is the weighted input of the i-th neuron in the hidden layer.

9. The method for predicting color change of ultra-wide color gamut conjugated polymer microspheres according to claim 6, characterized in that: The formula of the second activation function is: ； in, The predicted color temperature data and predicted brightness data output by the output layer are: is the weighted input of the output layer.

10. The method for predicting color change of ultra-wide color gamut conjugated polymer microspheres according to claim 6, characterized in that: The model parameters are updated through a back-propagation algorithm, and the prediction capability of the color change prediction model is optimized through the new model parameters.

Images