A method for predicting the curing temperature of black phosphorene epoxy plastic-encapsulated composite materials

Abstract

The present application relates to the field of data processing and prediction technology, and specifically to a method for predicting the curing temperature of a black phosphorene epoxy molding composite material, the method comprising: selecting raw materials, mixing and stirring to obtain a mixed liquid; pouring the mixture into a mold after vacuum degassing and curing at a set temperature; during the curing process, obtaining a curing dynamic collinearity characteristic difference coefficient based on the temperature data difference at different collection points during the curing process; obtaining a local collinearity characteristic partition coefficient based on the curing dynamic collinearity characteristic difference coefficient, obtaining a curing temperature ridge regression estimator based on the local collinearity characteristic partition coefficient, adaptively adjusting the curing temperature, and obtaining an epoxy molding nanocomposite material by cooling and demolding after curing. The present application can achieve accurate temperature prediction during the preparation process of the black phosphorene epoxy molding composite material.

Description

Technical Field

[0001] The present application relates to the technical field of data processing prediction, and in particular to a method for predicting the curing temperature of a black phosphorene epoxy plastic-encapsulated composite material. Background Art

[0002] As the frequency, power and heat generation of electronic devices become higher and higher, higher requirements are placed on the performance of electronic packaging materials and electronic substrate materials. The development of a new generation of high thermal conductivity packaging materials is of great practical significance. The most effective method at present is to add thermal conductive fillers to the plastic packaging material, but the effect of modifying its thermal conductivity is not obvious. One-dimensional materials with high thermal conductivity and large specific surface area, carbon nanotubes and classic two-dimensional materials, graphene, are also used in the field of electronic packaging. Some scholars have tried to combine graphene or carbon nanotubes with thermal conductive fillers to prepare G / GO / C thermal conductive filler composite materials, combining the advantages of the two materials to prepare composite materials with good thermal conductivity. Black phosphorene, a new type of two-dimensional material, has higher thermal conductivity than the classic two-dimensional material graphene. Compared with graphene or carbon nanotubes, black phosphorene can be used as a thermal conductive filler.

[0003] Thermally conductive fillers used in plastic encapsulation materials are mainly nano-scale fillers such as silica, alumina, aluminum nitride, and boron nitride. However, due to their small size, high surface activity, and easy agglomeration, pure nanoparticles cannot fully contact the medium, which reduces their thermal conductivity, is not conducive to improving the thermal conductivity of plastic encapsulation materials, and many of the excellent properties of nanomaterials are lost. Combining single nanomaterials into nanocomposites can solve the agglomeration problem of single nanoparticles, and the various components of nanocomposite energetic materials can achieve nanoscale contact. This composite material not only has the quantum size effect, small size effect, surface and interface effect, and macroscopic quantum tunneling effect of single nanoparticles, but also has synergistic effects, giving full play to the various excellent properties of single nanoparticles, making nanoenergetic materials practical and meeting the needs of different occasions. It also provides an effective method for the manufacture of new composite energetic materials.

[0004] The preparation process of epoxy molding compound composite materials based on black phosphorene has realized an automated production process. The specific preparation process includes the preparation of a mixed system of black phosphorene and epoxy resin, the mixing of a curing accelerator, a curing agent and a thermally conductive filler, vacuum degassing, pouring and curing, and cooling and demolding. The temperature change during the pouring and curing process directly affects the quality of the cured product. For example, uniform temperature control during the curing process can prepare high-quality epoxy molding compound composite materials. However, due to the many factors affecting the curing process, the complex correlation relationship and the difficulty in accurately setting the boundary conditions, the temperature changes unevenly during the preparation process of the epoxy molding compound composite materials, which reduces the quality of the epoxy molding compound composite materials prepared by black phosphorene. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention provides a method for predicting the curing temperature of a black phosphorene epoxy plastic-encapsulated composite material to solve the existing problems.

[0006] The present invention provides a method for predicting the curing temperature of a black phosphorene epoxy plastic-encapsulated composite material using the following technical solutions:

[0007] One embodiment of the present invention provides a method for predicting the curing temperature of a black phosphorene epoxy molding composite material, the method comprising the following steps:

[0008] The raw materials for preparing black phosphorene epoxy molding compound nanocomposite are selected, and the curing temperature is predicted during the preparation process, specifically including:

[0009] Obtain the temperature of each data collection point at each collection moment during the curing process. Based on the temperature data differences at different collection points during the curing process, combined with cluster analysis, obtain the curing dynamic collinearity characteristic difference coefficient;

[0010] Based on the curing dynamic collinearity feature difference coefficient, the local collinearity feature partition coefficient is obtained; based on the local collinearity feature partition coefficient, the curing temperature ridge regression estimator is obtained to predict the curing temperature;

[0011] After the curing process is completed, the epoxy molding compound nanocomposite material is obtained by cooling and demoulding.

[0012] In some embodiments, the preparation raw materials are black phosphorene, epoxy resin, curing agent, curing accelerator and thermal conductive filler.

[0013] In some embodiments, the method for obtaining the curing dynamic collinearity characteristic difference coefficient is:

[0014] Based on the collected temperature data, a composite material curing difference analysis sequence is constructed for each data collection point;

[0015] Calculate the range and coefficient of variation of each composite material curing difference analysis sequence respectively, use the range and coefficient of variation as the horizontal coordinate value and the vertical coordinate value respectively, take the coordinates corresponding to each composite material curing difference analysis sequence as a sample, and cluster all samples to obtain clusters;

[0016] The curing dynamic collinearity characteristic difference coefficient between any two clusters is determined based on the correlation between the composite material curing difference analysis sequences of each sample in the any two clusters.

[0017] In some embodiments, the composite material curing difference analysis sequence is constructed by: temperature data of each data collection point at different collection moments constitute the composite material curing difference analysis sequence of each data collection point.

[0018] In some embodiments, the method for determining the difference coefficient of the solidified dynamic collinearity characteristics between any two clusters is:

[0019] Analyze the distance between any two samples in any two clusters;

[0020] Analyzing the correlation coefficient between composite material curing difference analysis sequences corresponding to any two samples in any two clusters;

[0021] The solidified dynamic collinearity characteristic difference coefficient between any two clusters is positively correlated with the distance between any two samples in the any two clusters, and negatively correlated with the correlation coefficient.

[0022] In some embodiments, the method for obtaining the local collinear feature partition coefficient is:

[0023] Counting the maximum value of the curing dynamic collinearity characteristic difference coefficient between all any two clusters, and analyzing the ratio of each curing dynamic collinearity characteristic difference coefficient to the maximum value;

[0024] A local collinear feature partition coefficient is determined based on the ratio, wherein the local collinear feature partition coefficient is positively correlated with the ratio obtained by analyzing the dynamic collinear feature difference coefficients of all fixed-line phones.

[0025] In some embodiments, the curing temperature ridge regression estimator is obtained by:

[0026] Construct each sub-data sequence of each data collection point based on the local collinear feature partition coefficient and the composite material curing difference analysis sequence;

[0027] Analyze the variance expansion factors of the sub-data series of all data collection points in each time interval;

[0028] Construct a curing temperature monitoring matrix and use the ridge trace method to obtain the initial ridge regression estimator of the curing temperature monitoring matrix;

[0029] Based on the differences in variance expansion factors of different time intervals and the initial ridge regression estimator, a curing temperature ridge regression estimator is determined, wherein the curing temperature ridge regression estimator is positively correlated with the differences in variance expansion factors of all arbitrary two time intervals and the initial ridge regression estimator.

[0030] In some embodiments, the sub-data sequence construction method is: evenly divide the composite material curing difference analysis sequence of each data collection point into w sub-data sequences, wherein the value of w is the local collinear feature division coefficient.

[0031] In some embodiments, each row of the curing temperature monitoring matrix is ​​composed of temperature data of each data collection point at different collection moments.

[0032] In some embodiments, predicting the curing temperature includes:

[0033] Based on the curing temperature ridge regression estimator and the curing temperature monitoring matrix, a predicted value of the curing temperature is obtained through a ridge regression algorithm.

[0034] The present invention has at least the following beneficial effects:

[0035] The present invention prepares epoxy molding compound composite material by using black phosphorene, so that the black phosphorene epoxy molding compound composite material has good thermal conductivity, mechanical properties and flame retardant properties. Furthermore, by analyzing the dynamic change difference characteristics of the curing temperature during the preparation of the black phosphorene epoxy molding compound, the curing dynamic collinearity characteristic difference coefficient is calculated, and the dynamic change difference of the curing temperature at different collection moments during the curing process is reflected by the curing dynamic collinearity characteristic difference coefficient. Based on the dynamic change difference analysis, a local collinearity characteristic partitioning coefficient is constructed, and the time interval and sub-data sequence are divided by the local collinearity characteristic partitioning coefficient. The dynamic collinearity characteristic differences of the inter-subsequences are used to obtain the ridge regression estimator of the curing temperature, and the ridge regression estimation algorithm is used based on the curing temperature ridge regression estimator to obtain the predicted value of the curing temperature. The beneficial effect is that the time interval is divided into two parts by considering the dynamic change differences of the curing temperature at different positions during the curing process of the black phosphorene epoxy molding compound composite material. The parameters of the ridge regression algorithm are determined by the collinearity characteristic differences of different time intervals in the divided time intervals, thereby improving the accuracy of the prediction of the curing temperature using the ridge regression algorithm, and then more accurately adjusting the temperature during the curing process, thereby improving the performance and quality of the black phosphorene epoxy molding compound prepared based on black phosphorene. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 A flowchart of the steps of a method for predicting the curing temperature of a black phosphorene epoxy plastic-encapsulated composite material provided by the present invention;

[0038] Figure 2 is the SEM image of black phosphorene;

[0039] Figure 3This is a schematic diagram of the temperature-time curve of the curing temperature monitoring data sequence for curing at 100°C for 3 hours;

[0040] Figure 4 Schematic diagram of temperature-time curve of curing temperature monitoring data sequence of curing at 180°C for 3 hours;

[0041] Figure 5 A schematic diagram of the clustering results. DETAILED DESCRIPTION

[0042] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail a method for predicting the curing temperature of a black phosphorene epoxy molding composite material proposed by the present invention, including its specific implementation, structure, features, and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable form.

[0043] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0044] The specific scheme of the method for predicting the curing temperature of the black phosphorene epoxy plastic encapsulation composite material provided by the present invention is described in detail below with reference to the accompanying drawings.

[0045] Example 1 provides a method for predicting the curing temperature of a black phosphorene epoxy plastic-encapsulated composite material. For the preparation flow chart, please refer to Figure 1 , the specific preparation process is as follows:

[0046] (1) Preparation of black phosphorene-epoxy resin mixed system: Add 0.018~0.18g PNs (black phosphorene) to 10g EP (epoxy resin), wherein the epoxy resin includes one or more of biphenyl epoxy resin, o-cresol epoxy resin, bisphenol A epoxy resin, resorcinol formaldehyde epoxy resin and trishydroxyphenylmethane epoxy resin. In this embodiment, o-cresol epoxy resin is preferred. Stir manually for 10 minutes, then place in an ultrasonic cleaning machine for 5 minutes, with an ultrasonic power of 95% and a temperature of room temperature. The SEM image of the black phosphorene used is shown below. Figure 2 shown.

[0047] (2) Adding a curing agent, a curing accelerator and a thermal conductive filler: ultrasonically disperse the above-mentioned black phosphorene and epoxy resin to obtain a black phosphorene-epoxy resin mixed system, and add 0.9g of a curing agent to the black phosphorene-epoxy resin mixed system. The curing agent is one or more of linear phenolic resin, methyl hexahydrophthalic anhydride, and DDM (diaminodiphenylmethane). In this embodiment, linear phenolic resin is preferred; the curing accelerator is 2,4,6-tris(dimethylaminomethyl)phenol (DMP-30); an imidazole accelerator, such as 2-methyl One or more of 2-methylimidazole (2-MZ), preferably DMP-30 (2,4,6-tris(dimethylaminomethyl)phenol) in this embodiment, and a thermally conductive filler are added, wherein the thermally conductive filler comprises one or more of silicon dioxide (SiO2), aluminum oxide (Al2O3), aluminum nitride (AlN), boron nitride (BN), silicon carbide (SiC), silver (Ag), gold (Au) and copper (Cu), preferably silicon dioxide in this embodiment, with a mass of 13.5 g, and manually stirred for 10 minutes to mix evenly to obtain a mixed solution.

[0048] (3) Vacuum degassing and curing: Add 8 g of linear phenolic resin to the above mixture, stir manually for 10 min, mix evenly, degas under vacuum, and pour into a pre-prepared mold. Curing is carried out at 100 ° C for 3 h and 180 ° C for 3 h respectively. During the curing process, the curing temperature is predicted and analyzed to complete the curing process. The specific temperature prediction steps are as follows:

[0049] Step S001 : collecting temperature monitoring data during the curing process of the epoxy molding compound, and constructing a curing temperature monitoring matrix based on the collected temperature monitoring data.

[0050] In the process of preparing epoxy molding compound composite materials using black phosphorene, the curing process refers to pouring the mixed raw materials into the mold and curing them under a set temperature environment. Furthermore, a temperature probe sensor is used to collect temperature data at different data collection points during the curing process of the composite material. The time interval for collecting data is t (This embodiment takes the value of 0.1s), where the number of data collection points set is (This embodiment takes a value of 10). The data collected at each data collection point is sequenced in ascending time order as the curing temperature monitoring data sequence. The specific curing process is divided into two stages, namely, curing at 100°C for 3 hours and curing at 180°C for 3 hours. The temperature-time curves of the curing temperature monitoring data sequence obtained by collecting curing data in the two stages are shown as follows: Figure 3 and Figure 4 As shown in the figure, the horizontal axis is time, the unit is s, and the vertical axis is temperature, the unit is ℃.

[0051] Furthermore, each curing temperature monitoring data sequence is taken as a row of data in the matrix, and the matrix composed of the corresponding curing temperature data sequences of all the acquisition points is taken as the curing temperature monitoring matrix, wherein each element in the curing temperature monitoring matrix represents the temperature data corresponding to a collection moment at one of the data collection points, for example, the first element in the curing temperature monitoring matrix is i Rank j Column Elements , indicating that i Data collection point j The temperature data obtained at each collection moment.

[0052] At this point, the curing temperature monitoring matrix during the curing process of the black phosphorene-epoxy molding compound composite material was obtained.

[0053] Step S002: construct a curing dynamic collinearity feature difference coefficient based on the dynamic change difference characteristics between different data collection points in the curing temperature monitoring matrix, construct a local collinearity feature partition coefficient based on the curing dynamic collinearity feature difference coefficient, and calculate the curing temperature ridge regression estimator based on the local collinearity feature partition coefficient.

[0054] During the preparation of the black phosphorene-epoxy molding compound composite material, due to differences in curing temperature control, uneven temperature changes occur during the curing process, causing deviations in the structure of the black phosphorene-epoxy molding compound composite material and reducing the quality of the preparation of the black phosphorene-epoxy molding compound composite material. Specifically, as heating proceeds, the surface temperature difference of the composite material is rapidly widened. Excessive temperature differences may cause the maximum heating temperature to be reached, thereby triggering the condition to stop heating. Further, it may cause the reaction rate between the materials during the curing process to decrease, affecting the structure of the black phosphorene-epoxy molding compound composite material and, in turn, the thermal conductivity of the black phosphorene-epoxy molding compound.

[0055] Furthermore, the uneven temperature change characteristics during the curing process lead to unstable change characteristics in the curing reaction rate of the black phosphorene-epoxy molding compound composite material, and the internal structure of the prepared black phosphorene-epoxy molding compound composite material deviates, thereby reducing the thermal conductivity of the composite material. The influence of environmental changes on the curing temperature during the preparation process is a random change process, and the degree of influence of the curing temperature reflected by different data collection points during the curing process may be different. The greater the difference in the degree of influence, the more significant the curing temperature deviation characteristics of the composite material. Therefore, this embodiment will analyze the differences in the dynamic change characteristics of the curing temperature.

[0056] Specifically, the changing moments of the data collection points are divided according to the temperature change amplitude differences of each data collection point at different collection moments during the curing process of the composite material, and the local characteristics of the curing process changes are analyzed according to the division results, wherein each row of data in the curing temperature monitoring matrix is ​​arranged in a sequence from top to bottom as the composite material curing difference analysis sequence of each data collection point, that is, the temperature data of each data collection point at different collection moments constitute the composite material curing difference analysis sequence of each data collection point. Then, the range and coefficient of variation of each composite material curing difference analysis sequence are calculated, the range of the data in each composite material curing difference analysis sequence is taken as the horizontal coordinate value, the coefficient of variation of the composite material curing difference analysis sequence is taken as the vertical coordinate value, the coordinates corresponding to each composite material curing difference analysis sequence are taken as a sample, and the coordinates corresponding to all the samples in the curing temperature monitoring matrix form a sample set. Among them, the calculation method of the coefficient of variation is a prior art and will not be repeated in this embodiment. The density peak clustering algorithm is used to cluster the sample set to obtain each cluster cluster. The schematic diagram of the specific clustering result is shown as follows. Figure 5 As shown, in this embodiment, the Manhattan distance between samples is used as the measurement result of the similarity between samples. The specific calculation process of the density peak clustering algorithm is a well-known technology and will not be described in detail.

[0057] Furthermore, the clustering results of the sample set reveal the degree of interference in the curing process between different data collection points from the perspective of the temperature change differences at different data collection points at different collection times. Then, the curing dynamic collinearity characteristic difference coefficient is calculated based on the differences between different clusters in the clustering results of the sample set. The curing dynamic collinearity characteristic difference coefficient reflects the degree of uneven change in the curing process of the black phosphorene-epoxy molding compound composite material. Based on the correlation between the composite material curing difference analysis sequences of each sample in any two clusters, the curing dynamic collinearity characteristic difference coefficient between the arbitrary two clusters is determined: the distance between any two samples in the arbitrary two clusters is analyzed; the correlation coefficient between the composite material curing difference analysis sequences corresponding to any two samples in the arbitrary two clusters is analyzed; wherein the curing dynamic collinearity characteristic difference coefficient between the arbitrary two clusters is positively correlated with the distance between all arbitrary two samples in the arbitrary two clusters, and negatively correlated with the correlation coefficient.

[0058] Preferably, as an embodiment of the present application, the specific calculation formula for the curing dynamic collinearity characteristic difference coefficient can be: ;in, Indicates the b Clusters and c The coefficient of difference of solidification dynamic collinearity characteristics between clusters; Indicates the bThe first x samples, Indicates the c The first y samples, represents the Euclidean distance, express and The Euclidean distance between Indicates the b The first x Composite material curing difference analysis sequence corresponding to samples, Indicates the c The first y Composite material curing difference analysis sequence corresponding to samples, represents the Pearson correlation coefficient, express and The specific calculation process of the Pearson correlation coefficient is a well-known technology and will not be described in detail. X and Y Respectively represent b Clusters and c The number of sequences in a cluster.

[0059] It should be noted that, in this embodiment, the Pearson correlation coefficient is used as the correlation coefficient between sequences to evaluate the correlation between sequences. As other implementation methods, the implementer may also use other correlation measurement methods to analyze the correlation between sequences, and this application does not impose any special restrictions.

[0060] It should be understood that if b Clusters and c The greater the difference in the corresponding data changes of the samples between the clusters, that is, the greater the difference in the range and coefficient of variation of the data between different samples, the greater the calculated The larger the value of b Clusters and c The greater the difference in the correlation between the data of different samples in the clusters, the The smaller the value of The larger the value of b Clusters and c The number of cluster samples is significantly different, so the calculated The larger the value of b Clusters and c The coefficient of difference of the solidified dynamic collinearity characteristics between clusters The larger the value, the more significant the dynamic difference characteristics of the curing temperature of the black phosphorene-epoxy molding compound composite material.

[0061] Furthermore, the number of data intervals divided during the curing process of the black phosphorene-epoxy molding compound composite material is determined according to the curing dynamic collinearity characteristic difference coefficient, and the local dynamic collinearity characteristic analysis of the temperature data during the curing process is performed according to the number of divided data intervals; the set consisting of the curing dynamic collinearity characteristic difference coefficients between all different clusters is used as the local collinearity characteristic analysis set Q , calculate the local collinear feature partition coefficient based on the local collinear feature analysis set: Statistical local collinear feature analysis set Q The maximum value of the fixed dynamic collinearity characteristic is analyzed, and the ratio of the difference coefficient of each fixed dynamic collinearity characteristic to the maximum value is analyzed; based on the ratio, the local collinearity characteristic division coefficient is determined, wherein the local collinearity characteristic division coefficient is positively correlated with the ratio obtained by analyzing the difference coefficient of the dynamic collinearity characteristic of all fixed words.

[0062] Preferably, as an embodiment of the present application, the specific calculation formula of the local collinear feature division coefficient can be: ;in, represents the local collinear feature partition coefficient; Indicates the b Clusters and c The coefficient of difference of solidification dynamic collinearity characteristics between clusters; Q represents the local collinear feature analysis set, express Q The maximum value in ; T Indicates the number of clusters; and Both are preset constant coefficients greater than zero, which are used to map the coefficient of the difference of the solidified dynamic collinearity characteristics to the number of appropriate intervals. The empirical values ​​are 5 and 10 respectively; Represents the ceiling function.

[0063] It should be understood that if the coefficient of difference of the solidified dynamic collinearity characteristics between clusters in the clustering results of the sample set is large, the calculated The larger the value of is, the larger the calculated local collinear feature partition coefficient is. The larger the value, the greater the temperature variation at different data collection points during the curing process of the composite material, and the smaller the data interval needs to be divided to analyze the local state differences.

[0064] Furthermore, the data collected at each data collection point is evenly divided according to the local collinear feature division coefficient. For example, if the local collinear feature division coefficient is 8, the composite material curing difference analysis sequence at each data collection point is evenly divided into 8 sub-data sequences. Since the data collection between different data collection points is synchronous, the data sequences divided between different data collection points correspond to each other, that is, in each time interval, The curing temperature ridge regression estimator is calculated based on the variance expansion factors between the sub-data sequences of different data collection points corresponding to each time interval.

[0065] Specifically, first, the variance expansion factor method is used to obtain the variance expansion factor of each time interval, that is, the degree of correlation between the temperature data changes at different data collection points.

[0066] Afterwards, the initial ridge regression estimator is calculated by the variance expansion factor of different time intervals, where the input is the curing temperature monitoring matrix, and the ridge trace method is used to obtain the initial ridge regression estimator of the curing temperature monitoring matrix. The specific calculation process of the variance expansion factor method and the ridge trace method is a well-known technology and will not be repeated here.

[0067] Based on the differences in variance expansion factors of different time intervals and the initial ridge regression estimator, a curing temperature ridge regression estimator is determined, wherein the curing temperature ridge regression estimator is positively correlated with the differences in variance expansion factors of all arbitrary two time intervals and the initial ridge regression estimator.

[0068] Preferably, as an embodiment of the present application, the calculation formula of the curing temperature ridge regression estimator can be: ;in, L represents the curing temperature ridge regression estimator; represents the initial ridge regression estimator; and Respectively represent and Variance expansion factor for a time interval.

[0069] It should be understood that if the correlation variation characteristics between the sub-data series at different data collection points within the divided time interval are significant, the calculated The larger the value of is, and the correlation change characteristics of different time intervals are significantly different, the calculated The larger the value of The smaller the value of is, the better the calculated curing temperature ridge regression estimator is. LThe smaller the value of , the greater the impact of the collinearity characteristics reflected by the difference in the collinearity characteristics of the local changes analyzed by dividing the time interval. In this case, the initial ridge regression estimator is reduced to increase the strength of regularization and improve the accuracy of the prediction of the curing temperature change.

[0070] At this point, the curing temperature ridge regression estimator is obtained.

[0071] Step S003, using a ridge regression algorithm based on the curing temperature ridge regression estimator to obtain a predicted value of the curing temperature of the epoxy molding compound composite material, adjusting the curing temperature during the preparation process of the epoxy molding compound composite material according to the predicted value of the curing temperature, and completing the curing process of the epoxy molding compound composite material.

[0072] The above steps can be used to obtain the curing temperature ridge regression estimator. The curing temperature ridge regression estimator and the curing temperature monitoring matrix are used as input, and the ridge regression algorithm is used to obtain the predicted value of the curing temperature. In this embodiment, the specific process of dividing the characteristic variables and the target variables is as follows: calculating the coefficient of variation of each row of data in the curing temperature monitoring matrix, taking the row of data in the curing temperature monitoring matrix with the minimum value of all the said coefficients of variation as the target variable, and taking the remaining rows of data in the curing temperature monitoring matrix as the characteristic variables; the specific calculation process of the ridge regression algorithm is a well-known technology and will not be repeated here.

[0073] Furthermore, the temperature of the curing process of the black phosphorene-epoxy molding compound composite material is compensated according to the predicted value of the curing temperature.

[0074] Preferably, as an embodiment of the present application, if the predicted value of the curing temperature is less than or greater than the set temperature value, the curing temperature is adaptively adjusted through the temperature control system of the black phosphorene-epoxy molding compound composite material production process to ensure the suitability of the temperature during the curing process and complete the curing process.

[0075] (4) Cooling and demolding: After curing, slowly cool to room temperature and demold to obtain a black EP / PNs nanocomposite material.

[0076] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0077] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0078] The above-described embodiments are only used to illustrate the technical solutions of the present application, and not to limit them. Modifications to the technical solutions described in the aforementioned embodiments, or equivalent replacements of some of the technical features therein, do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for predicting the curing temperature of a black phosphorene epoxy plastic-encapsulated composite material, characterized in that: The method comprises the following steps: The raw materials for preparing black phosphorene epoxy molding compound nanocomposite are selected, and the curing temperature is predicted during the preparation process, specifically including: Constructing a composite material curing difference analysis sequence for each data collection point based on the collected temperature data; calculating the range and coefficient of variation of each composite material curing difference analysis sequence respectively, taking the range and coefficient of variation as the horizontal coordinate value and the vertical coordinate value respectively, taking the coordinates corresponding to each composite material curing difference analysis sequence as a sample, clustering all samples to obtain each cluster; analyzing the distance between any two samples in any two clusters; analyzing the correlation coefficient between the composite material curing difference analysis sequences corresponding to any two samples in the any two clusters; wherein the curing dynamic collinearity characteristic difference coefficient between the any two clusters is positively correlated with the distance between all any two samples in the any two clusters, and negatively correlated with the correlation coefficient; Count the maximum values ​​of the curing dynamic collinearity characteristic difference coefficients between all arbitrary two clusters, and analyze the ratios of the curing dynamic collinearity characteristic difference coefficients to the maximum values; determine the local collinearity characteristic partition coefficient based on the ratio, wherein the local collinearity characteristic partition coefficient is positively correlated with the ratio obtained by analyzing the curing dynamic collinearity characteristic difference coefficients of all the clusters; construct each sub-data sequence of each data acquisition point based on the local collinearity characteristic partition coefficient and the composite material curing difference analysis sequence; analyze the variance expansion factors of the sub-data sequences of all data acquisition points in each time interval; construct a curing temperature monitoring matrix, and use the ridge trace method to obtain the initial ridge regression estimator of the curing temperature monitoring matrix; determine the curing temperature ridge regression estimator based on the difference in variance expansion factors of different time intervals and the initial ridge regression estimator, wherein the curing temperature ridge regression estimator is positively correlated with the difference in variance expansion factors of all arbitrary two time intervals and the initial ridge regression estimator, and predict the curing temperature; After the curing process is completed, the epoxy molding compound nanocomposite material is obtained by cooling and demoulding.

2. The method for predicting the curing temperature of a black phosphorene epoxy plastic-encapsulated composite material according to claim 1, wherein: The preparation raw materials are black phosphorene, epoxy resin, curing agent, curing accelerator and thermal conductive filler.

3. The method for predicting the curing temperature of a black phosphorene epoxy plastic encapsulation composite material according to claim 1, wherein: The method for constructing the composite material curing difference analysis sequence is as follows: the temperature data of each data collection point at different collection times constitute the composite material curing difference analysis sequence of each data collection point.

4. The method for predicting the curing temperature of a black phosphorene epoxy plastic-encapsulated composite material according to claim 1, wherein: The sub-data sequence construction method is: the composite material curing difference analysis sequence of each data collection point is evenly divided into w sub-data sequences, wherein the value of w is the local collinear feature division coefficient.

5. The method for predicting the curing temperature of a black phosphorene epoxy plastic encapsulation composite material according to claim 1, wherein: Each row of the curing temperature monitoring matrix is ​​composed of temperature data of each data collection point at different collection moments.

6. The method for predicting the curing temperature of a black phosphorene epoxy plastic-encapsulated composite material according to claim 1, wherein: The method of predicting the curing temperature includes: Based on the curing temperature ridge regression estimator and the curing temperature monitoring matrix, a predicted value of the curing temperature is obtained through a ridge regression algorithm.

Images