Thermotropic liquid crystal polyester material monomer synthesis process

Abstract

The invention discloses a thermotropic liquid crystal polyester material monomer synthesis process, and relates to the technical field of thermotropic liquid crystal polyester materials, and the thermotropic liquid crystal polyester material monomer synthesis process comprises the following steps: adjusting a polymerization reaction environment by using temperature control parameters, monitoring a polymerization rate change trend, processing rate data and molecular configuration relevance by using a support vector machine algorithm, and obtaining a thermotropic liquid crystal polyester material monomer; judging a molecular chain length increasing rule under the current reaction condition; predicting a liquid crystal phase stability interval according to the molecular chain length increasing rule, and if phase parameters are in an unstable range, adjusting the monitoring frequency to improve the data acquisition density and determining an optimal reaction time window; the method comprises the following steps: collecting a continuous data sequence of molecular configuration evolution, and analyzing correlation between configuration change and arrangement density by a random forest algorithm to obtain critical condition parameters of ordered arrangement of molecules; and evaluating the final regularity of the polymer molecular chain by adopting the crystallinity standard, and determining the liquid crystal characteristic optimization degree through contrastive analysis to obtain the synthesis parameter combination of the high-performance thermotropic liquid crystal polyester material.

Description

Technical Field

[0001] This invention relates to the field of thermotropic liquid crystal polyester material monomer synthesis technology, and in particular to a process for synthesizing thermotropic liquid crystal polyester material monomers. Background Technology

[0002] Thermotropic liquid crystal polyester materials possess significant application value in aerospace, electronic devices, and high-end manufacturing due to their excellent mechanical properties, thermal stability, and chemical stability. These materials achieve unique liquid crystal properties through the ordered arrangement of monomer molecules, becoming a key driver of high-performance material development. However, existing synthesis processes have significant limitations in controlling the arrangement of monomer molecules. Traditional methods often rely on natural arrangement or simple physical guidance, making it difficult to precisely control the spatial orientation of monomer molecules. This results in insufficient orderliness of the polymer molecular chains, ultimately affecting the material's performance stability. For example, under certain high-temperature reaction conditions, monomer molecules are prone to random orientation, causing non-uniform material properties and limiting their application in high-precision fields.

[0003] The core challenge lies in achieving precise orientation control of monomer molecules during synthesis. The spatial arrangement of monomer molecules directly determines the regularity of polymer molecular chains, but current processes lack effective real-time monitoring methods to dynamically track the orientation state of monomer molecules. This makes it difficult to maintain a consistent geometric configuration of monomer molecules during the reaction. For example, in polymerization reactions, if monomer molecules are not aligned in the predetermined direction, disordered molecular chains may form, reducing the liquid crystal properties of the material. Furthermore, the lack of dynamic monitoring makes optimizing reaction conditions difficult because the changes in monomer molecule arrangement cannot be known in real time, making it impossible to adjust external field guidance parameters in a timely manner. These two factors are interconnected: insufficient orientation control leads to decreased molecular chain regularity, while the lack of real-time monitoring exacerbates the control difficulty, making it difficult for the material properties to meet expectations.

[0004] Therefore, how to ensure that monomer molecules participate in the reaction with optimal geometric configuration by introducing precise orientation control and real-time monitoring methods during the synthesis of thermotropic liquid crystal polyester monomers has become a key issue in realizing high-performance liquid crystal polyester materials. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a process for synthesizing monomers of thermotropic liquid crystal polyester materials, which addresses the shortcomings of the prior art.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: This invention provides a process for synthesizing thermotropic liquid crystal polyester material monomers, specifically comprising the following steps: Step S101: Obtain real-time spectral data of monomer molecules in the reaction system, collect molecular orientation information at different reaction time points using a polarized light microscope, and use a convolutional neural network to identify and analyze the spectral features to obtain the numerical distribution of the current molecular orientation angle. Step S102: Calculate the molecular arrangement density parameter and liquid crystal phase transition characteristics based on the molecular orientation angle numerical distribution. If the molecular orientation angle deviation exceeds the preset threshold, activate the external field control module to dynamically adjust the reaction temperature and obtain optimized temperature control parameters. Step S103: Adjust the polymerization reaction environment using the temperature control parameters, monitor the polymerization rate change trend, use support vector machine algorithm to process the correlation between rate data and molecular configuration, and determine the molecular chain length growth law under the current reaction conditions. Step S104: Based on the molecular chain length growth law, predict the stability range of the liquid crystal phase state. If the phase state parameters are in an unstable range, adjust the monitoring frequency to increase the data acquisition density and determine the optimal reaction time window. Step S105: According to the optimal reaction time window, collect continuous data sequences of molecular configuration evolution, analyze the correlation between configuration change and arrangement density using the random forest algorithm, and obtain the critical condition parameters for ordered molecular arrangement. Step S106: After obtaining the critical condition parameters, the external field intensity is adjusted in real time to maintain the stability of molecular orientation, and the phase transition temperature is monitored. If the temperature fluctuation affects the regularity of molecular arrangement, the orientation angle is dynamically corrected to determine whether the crystallinity meets the expected standard. Step S107: The final regularity of the polymer molecular chain is evaluated using the crystallinity standard, and the degree of optimization of liquid crystal properties is determined by comparative analysis to obtain the combination of synthesis parameters for high-performance thermotropic liquid crystal polyester materials.

[0007] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: This invention discloses a monomer synthesis process for thermotropic liquid crystal polyester materials. First, the invention uses a polarized light microscope to collect spectral data of monomer molecules in the reaction system in real time. Then, a convolutional neural network is used to analyze the molecular orientation angle distribution and calculate the arrangement density and liquid crystal phase transition characteristics. When the orientation angle deviation exceeds the standard, an external field control module is dynamically activated to optimize the reaction temperature. A support vector machine algorithm is used to analyze the correlation between polymerization rate and molecular configuration, predicting the molecular chain length growth law and phase stability range. If the phase is unstable, the monitoring frequency is increased to determine the optimal reaction time window. A random forest algorithm is then used to analyze the correlation between configuration change and arrangement density, obtaining the critical conditions for ordered molecular arrangement. Finally, this invention dynamically corrects the orientation angle by real-time control of the external field intensity and temperature, ensuring that the crystallinity meets the standard, significantly improving the regularity and performance of the thermotropic liquid crystal polyester material, and achieving the precise synthesis of high-performance materials. Attached Figure Description

[0008] Figure 1 This is a flowchart of a process for synthesizing a thermotropic liquid crystal polyester material monomer according to the present invention. Detailed Implementation

[0009] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0010] like Figure 1 As shown, the specific process for synthesizing a thermotropic liquid crystal polyester material monomer in this embodiment may include: S101. Obtain real-time spectral data of monomer molecules in the reaction system. Collect molecular orientation information at different reaction time points using a polarized light microscope. Use a convolutional neural network to identify and analyze the spectral features to obtain the numerical distribution of the current molecular orientation angle.

[0011] Real-time spectral data of monomer molecules in the reaction system were acquired using a high-resolution spectrometer to collect spectral signals in different wavelength ranges, resulting in a raw spectral dataset. The reaction system was imaged at different reaction time points using a polarization microscope to acquire polarization images containing molecular orientation information, resulting in a molecular orientation image set. Image processing algorithms were used to preprocess the molecular orientation image set to extract polarization intensity distribution features, resulting in an intensity distribution feature set. If the signal-to-noise ratio of the intensity distribution feature set was lower than a preset threshold, a denoising algorithm was used to optimize the intensity distribution feature set, resulting in an optimized intensity feature set. A convolutional neural network was used to jointly analyze the optimized intensity feature set and the raw spectral dataset to extract feature vectors of molecular orientation angles, resulting in an orientation angle feature set. Based on the orientation angle feature set, a regression analysis algorithm was used to calculate the numerical distribution of molecular orientation angles, resulting in the orientation angle distribution result. A visualization tool was used to perform 3D mapping of the orientation angle distribution result to generate a spatial distribution map of molecular orientation angles, resulting in the final distribution map.

[0012] In one possible implementation, a high-resolution spectrometer covering the ultraviolet to near-infrared band, such as the 200-1000 nm range, can be used to acquire real-time spectral data of monomer molecules in the reaction system. The spectrometer acquires signals at a resolution of 0.1 nm, generating a raw spectral dataset containing wavelength-intensity information.

[0013] For example, in organic molecular reaction systems, the absorption peaks of benzene ring compounds may appear in the 250-300 nm region, reflecting changes in molecular structure. Real-time acquisition can capture the dynamic changes in molecular bonds during the reaction process, which helps to reveal the reaction mechanism.

[0014] For example, by imaging a reaction system using a polarized light microscope, polarized images can be acquired at reaction time points such as 0, 5, and 10 minutes, resulting in a set of molecular orientation images. Polarized light microscopy utilizes the polarization properties of light to reveal the orientation of molecules in space.

[0015] For example, under the influence of an electric field, the long axis orientation of liquid crystal molecules changes over time, displaying bright and dark stripes in the image, reflecting the molecular arrangement. Imaging resolution can reach 1 μm, ensuring the capture of microscopic orientation details. This method can visually demonstrate the dynamic behavior of molecules during reactions.

[0016] Specifically, when preprocessing molecular orientation image sets using image processing algorithms, edge detection and grayscale analysis can be used to extract polarization intensity distribution features.

[0017] For example, a Fourier transform is performed on the polarization image of liquid crystal molecules to extract the periodic variation features of light intensity, generating a light intensity distribution feature set. If the signal-to-noise ratio of the feature set is lower than a preset threshold, such as below 3:1, a wavelet transform denoising algorithm can be used for optimization to obtain an optimized light intensity feature set. After denoising, the signal clarity is improved by approximately 30%, facilitating the accuracy of subsequent analysis of molecular orientation.

[0018] In one possible implementation, feature vectors of molecular orientation angles can be extracted by jointly analyzing and optimizing the light intensity feature set and the original spectral dataset using a convolutional neural network.

[0019] For example, the network takes a light intensity distribution matrix and spectral intensity data as input and outputs a spatial feature vector containing molecular orientation angles. When training the model, a dataset of liquid crystal molecules with known orientations, ranging from 0-180°, can be used to ensure accurate feature extraction. Joint analysis can integrate spectral and image information, improving the robustness of molecular orientation prediction.

[0020] For example, based on the orientation angle feature set, regression analysis algorithms are used to calculate the numerical distribution of molecular orientation angles. Random forest regression can handle nonlinear relationships, outputting the probability density of the angle distribution within the range of 0-90°. The results show that molecular orientations are relatively random in the early stages of the reaction, but tend to converge after 10 minutes, concentrating around 45°. Regression analysis can quantify the dynamic changes in molecular orientation, providing a basis for reaction regulation.

[0021] Specifically, by using visualization tools to perform three-dimensional mapping of the orientation angle distribution results, a spatial distribution map of molecular orientation angles can be generated.

[0022] For example, heatmaps can be used to represent the orientation angles of different regions, with colors ranging from blue to red corresponding to 0-90°. The final distribution map visually demonstrates the spatial arrangement of molecules in the reaction system, such as how liquid crystal molecules gradually form an ordered structure under an electric field. This visualization helps researchers quickly understand molecular behavior, optimize reaction conditions, and improve material properties or reaction efficiency.

[0023] S102. Based on the molecular orientation angle numerical distribution, calculate the molecular arrangement density parameter and liquid crystal phase transition characteristics. If the molecular orientation angle deviation exceeds the preset threshold, activate the external field control module to dynamically adjust the reaction temperature and obtain optimized temperature control parameters.

[0024] Molecular orientation angle data is processed using numerical distribution analysis methods to calculate orientation angle deviations and obtain deviation distribution results. If the deviation distribution results exceed a preset threshold, a temperature adjustment signal is generated through the external field control module to obtain initial temperature control parameters. Based on the initial temperature control parameters, molecular dynamics simulation algorithms are used to calculate molecular arrangement density, resulting in a density distribution dataset. Statistical analysis methods are then used to extract liquid crystal phase transition characteristics from the density distribution dataset, yielding a phase transition feature set. If the phase transition feature set indicates an abnormal phase, the reaction temperature is adjusted a second time through the external field control module to obtain optimized temperature parameters. Based on the optimized temperature parameters and the density distribution dataset, regression analysis algorithms are used to calculate the temperature control accuracy, obtaining an accuracy evaluation result. Finally, a spatial distribution map of molecular arrangement density is generated using the accuracy evaluation result and the phase transition feature set, resulting in the final distribution map.

[0025] For example, by processing molecular orientation angle data using numerical distribution analysis methods, orientation angle deviations can be calculated, generating deviation distribution results. Assume that the orientation angle data of liquid crystal molecules in the reaction system is acquired using a polarizing microscope, with an angle range of 0-180°. During analysis, statistical methods can be used, such as calculating the standard deviation of the angle data, to obtain a deviation distribution map. If the deviation exceeds a preset threshold, such as 10°, it indicates that the molecular orientation is non-uniform, which may affect material properties. In this case, the external field control module needs to be activated to adjust the temperature.

[0026] Specifically, the external field control module can generate temperature adjustment signals through thermocouples and a controller. The initial temperature control parameter is set to 50°C, with a step size of 0.5°C, to gradually optimize molecular orientation consistency. This method provides a basis for subsequent control by quantifying the deviation.

[0027] In one possible implementation, molecular dynamics simulation algorithms can be used to calculate the molecular alignment density based on initial temperature control parameters. In the simulation, the trajectories of liquid crystal molecules at 50°C are tracked, generating a three-dimensional dataset containing their positions and densities.

[0028] For example, a simulation system might be a 10nm × 10nm × 10nm cube, with higher molecular density in the central region and lower density at the edges, generating a density distribution dataset. This density distribution reflects the degree of molecular aggregation in space and helps determine the homogeneity of the system.

[0029] For example, based on density distribution datasets, statistical analysis methods can extract liquid crystal phase transition characteristics. The periodicity of molecular arrangement can be analyzed by calculating the spatial autocorrelation function of the density. If the feature set shows a weakening of periodicity, it indicates a possible phase anomaly, such as a transition from a nematic phase to an isotropic phase. In this case, the external field control module can perform secondary temperature adjustments to generate optimized temperature parameters, such as adjusting from 50°C to 48°C, to stabilize the phase. This method provides a basis for phase control through feature extraction.

[0030] In one possible implementation, a regression analysis algorithm can calculate the temperature control accuracy based on an optimized dataset of temperature parameters and density distribution. Assuming a linear regression model is used, the input density distribution and temperature data output an evaluation of the control accuracy, such as temperature deviation controlled within ±0.2°C. The accuracy evaluation reflects the reliability of the control and provides a reference for system optimization.

[0031] For example, spatial distribution maps of molecular arrangement density can be generated using accuracy assessment results and phase transition feature sets. Visualization tools, such as 3D thermograms, can then be used to display this density distribution, with high-density regions represented in red and low-density regions in blue. The final distribution map visually reflects the arrangement of molecules in the reaction system; for example, liquid crystal molecules form a more uniform nematic phase structure at optimized temperatures. This distribution map provides an intuitive basis for studying molecular arrangement behavior and helps optimize reaction conditions.

[0032] S103. The polymerization reaction environment is adjusted using the temperature control parameters, and the polymerization rate change trend is monitored. The correlation between the rate data and molecular configuration is processed by the support vector machine algorithm to determine the molecular chain length growth law under the current reaction conditions.

[0033] The polymerization rate trend is acquired by sensors, and the rate data is processed using time series analysis to obtain a dynamic polymerization rate curve. If the dynamic polymerization rate curve deviates from a preset threshold, an environmental adjustment signal is generated through a feedback control module to determine the correction values ​​for the reaction environment parameters. Based on the correction values, the temperature control parameters are adjusted to obtain an updated polymerization reaction environment configuration. The updated polymerization reaction environment configuration and molecular configuration data are analyzed using a support vector machine algorithm to obtain a molecular chain length growth prediction model. The chain length distribution pattern is extracted from the molecular chain length growth prediction model, and a chain length distribution dataset is calculated using statistical analysis methods. If the chain length distribution dataset indicates an abnormal growth pattern, the temperature control parameters are further optimized using the environmental adjustment signal to obtain the final temperature control scheme. Based on the final temperature control scheme and the chain length distribution dataset, a spatial distribution map of the molecular chain length is generated to determine the optimization results of the polymerization reaction.

[0034] For example, by collecting polymerization rate data using sensors, in-depth analysis of the polymerization reaction dynamics can be achieved. These sensors are typically high-precision spectrometers or mass rheometers, monitoring in real-time changes in the mass of molecular aggregates or the intensity of light scattering in the reaction system. The collected data is stored in time-series format, for example, recording the polymerization rate once per second over a one-hour period, generating a sequence containing 3600 data points. Time-series analysis methods can employ autoregressive moving average models to process the rate data and extract trend and fluctuation characteristics. Dynamic curves are generated using visualization tools, with time on the horizontal axis and polymerization rate on the vertical axis, for example, a rate range between 0.01 and 0.1 g / min. A smooth curve indicates a stable reaction, while abrupt changes suggest anomalies.

[0035] In one possible implementation, if the dynamic curve shows a polymerization rate exceeding a preset threshold, such as 0.08 g / min, it indicates that the polymerization is too rapid, potentially leading to uneven molecular chain lengths. The feedback control module generates an environmental adjustment signal. Based on a PID controller and sensor data, the module calculates corrective values ​​for environmental parameters, such as reducing the reaction temperature by 2°C. The initial temperature is set at 60°C, and after correction, it is adjusted to 58°C, updating the polymerization reaction environment configuration. After adjustment, the sensors continue to monitor rate changes to verify the effectiveness of the configuration.

[0036] For example, support vector machine (SVM) algorithms can be used to analyze updated environmental configuration and molecular conformation data. Conformation data, acquired via NMR, contains geometric information of the molecular chains, such as bond angles and bond lengths. The algorithm uses temperature and conformation data as input to train a chain length growth prediction model. The model output shows the trend of chain length growth over time; for example, at 58°C, the chain length increases from 100 nm to 150 nm at a stable growth rate. The chain length distribution pattern is extracted from the model to generate a dataset containing chain length values ​​and their probability densities; for example, 80% of the chain length is concentrated in the 120-140 nm range.

[0037] In one possible implementation, if the chain length distribution dataset shows anomalies, such as 10% of chains exceeding 200 nm, it indicates the presence of unexpectedly long chains affecting material uniformity. In this case, an environmental adjustment signal triggers secondary optimization, further fine-tuning the temperature to 57.5°C. The final temperature control scheme is based on multiple iterations to ensure the chain length distribution tends towards a normal distribution. The spatial distribution map of molecular chain length is generated using a 3D visualization tool, with high chain length regions represented by warm colors and low chain length regions by cool colors. The distribution map shows that the molecular chain length is uniformly distributed in the reaction system, optimizing the polymerization reaction results and providing a basis for subsequent process adjustments.

[0038] S104. Based on the molecular chain length growth law, predict the stability range of the liquid crystal phase state. If the phase state parameters are in an unstable range, adjust the monitoring frequency to increase the data acquisition density and determine the optimal reaction time window.

[0039] Feature vectors are extracted from the molecular chain length growth pattern, and a liquid crystal phase stability prediction model is constructed using a support vector machine algorithm to obtain the phase stability interval. If the phase stability interval exceeds the preset stability range, time series analysis is used to process the real-time acquired phase parameters to determine the parameter fluctuation trend. Based on the parameter fluctuation trend, the data acquisition frequency is adjusted to generate a high-density data acquisition scheme, resulting in a high-resolution phase dataset. Using the high-resolution phase dataset, k-means clustering is used to divide the reaction time interval and determine candidate reaction time windows. If the variance of the phase parameters in a candidate reaction time window exceeds a preset threshold, a frequency adjustment signal is generated through a feedback control module to optimize the data acquisition frequency, resulting in a stable reaction time dataset. Based on the stable reaction time dataset, the phase stability distribution of the time window is calculated to determine the optimal reaction time window. Using the optimal reaction time window, a reaction condition control signal is generated to adjust the polymerization reaction environment parameters, resulting in the final reaction configuration scheme.

[0040] For example, when extracting feature vectors, key parameters such as the mean chain length, variance, and growth rate can be selected from the molecular chain length growth pattern. Suppose that chain length data is obtained through NMR spectroscopy, resulting in a dataset with a mean chain length of 130 nm, a variance of 15 nm, and a growth rate ranging from 0.05 to 0.07 nm / s. These parameters constitute the feature vector, which is then input into a Support Vector Machine (SVM) algorithm. The SVM uses a classification hyperplane to correlate the chain length data with the stability of the liquid crystal phase state, predicting the stability interval.

[0041] For example, the model outputs a phase stability range of 0.8-0.95, with a preset stability range of 0.85-0.9. If the value exceeds this range, it is necessary to analyze the fluctuations in the phase parameters.

[0042] In one possible implementation, time series analysis processes real-time acquired phase parameters, such as the orientation angle of liquid crystal molecules. Using a high-precision spectrometer, orientation angle data is acquired every 5 seconds, generating a sequence of 720 data points per hour. An autoregressive model is used to extract fluctuation trends, observing whether the orientation angle remains stable within ±5°. If the fluctuation exceeds a threshold, such as ±7°, the data acquisition frequency is adjusted to once every 2 seconds, forming a high-density data acquisition scheme, generating a higher-resolution phase dataset, and improving analytical accuracy.

[0043] Specifically, high-resolution phase state datasets can be used with the k-means clustering algorithm to divide reaction time intervals. Assuming the dataset contains orientation angles and reaction times, clustering yields three candidate time windows: 0-20 min, 20-40 min, and 40-60 min. The variance of the orientation angle for each window is calculated. If the variance for the 20-40 min window is 6°, exceeding the preset threshold of 4°, a frequency adjustment signal is generated through a feedback control module to optimize the acquisition frequency to once per second, generating a stable reaction time dataset and ensuring the variance is reduced to within 3°.

[0044] For example, based on a stable reaction time dataset, the phase stability distribution is calculated. Assuming the stability distribution within a 20-40 minute window shows 90% of the orientation angles concentrated within ±3°, this is determined to be the optimal reaction time window. Through this window, reaction condition control signals are generated, and polymerization environment parameters are adjusted, such as fine-tuning the reaction temperature from 60°C to 59°C, to optimize the consistency of liquid crystal molecule orientation. The final reaction configuration scheme, based on high-resolution data and cluster analysis, ensures that phase stability is maintained within a preset range, providing a reliable basis for subsequent process optimization.

[0045] S105. Based on the optimal reaction time window, collect continuous data sequences of molecular configuration evolution, analyze the correlation between configuration changes and arrangement density using the random forest algorithm, and obtain the critical condition parameters for the ordered arrangement of molecules.

[0046] Continuous molecular configuration data sequences within the optimal reaction time window are acquired. A random forest algorithm is used to analyze the correlation between configuration changes and arrangement density, determining the critical condition parameters for ordered molecular arrangement. Based on these critical condition parameters, a molecular configuration classification model is constructed, and a decision tree algorithm is used to classify the molecular configuration data sequences, resulting in ordered and disordered configuration categories. According to the configuration category, a subset of ordered molecular configuration data is extracted, and the statistical distribution of intermolecular distance and orientation angle within the subset is calculated to determine the geometric characteristic parameters of molecular arrangement. If the variance of the geometric characteristic parameters exceeds a preset threshold, the molecular configuration data subset is processed using time series analysis to obtain the time trend of configuration changes and determine the dynamic adjustment time interval. Based on the dynamic adjustment time interval, a high-frequency data acquisition signal is generated to acquire a high-resolution molecular configuration dataset. The configuration stability index of the dataset is calculated to obtain stable configuration data. Using the stable configuration data, a k-means clustering algorithm is used to group the molecular configurations, determining the centroid parameters of the configuration groups and obtaining an optimized molecular arrangement configuration scheme. Based on the optimized configuration scheme, a reaction environment control signal is generated to adjust the polymerization reaction condition parameters and determine the final molecular arrangement configuration.

[0047] For example, when acquiring continuous molecular configuration data sequences within the optimal reaction time window, high-precision atomic force microscopy can be used to monitor changes in liquid crystal molecular configuration in real time. Assuming that molecular configuration data is collected every 10 seconds within a 40-minute reaction window, 240 data points are generated, containing information on intermolecular distance and orientation angle. The data sequence reflects the dynamic evolution of molecules during the polymerization reaction, providing a foundation for subsequent analysis.

[0048] It should be noted that molecular configuration data must have a sufficiently high temporal resolution to capture the transient characteristics of configurational changes.

[0049] In one possible implementation, when analyzing the correlation between configurational changes and permeation density using the random forest algorithm, features such as the mean intermolecular distance, the variance of the orientation angle, and the rate of configurational change can be extracted. Assuming the dataset shows a mean intermolecular distance of 2.5 nm, a variance of 0.3 nm, and a configurational change rate ranging from 0.01 to 0.03 nm / s, the random forest, through the ensemble of multiple decision trees, evaluates the contribution of each feature to the permeation density and determines critical condition parameters. For example, when the intermolecular distance is less than 2.7 nm and the variance of the orientation angle is less than 5°, the permeation density reaches an ordered state. This method ensures the robustness of the results through comprehensive multi-feature analysis.

[0050] Specifically, when constructing a molecular configuration classification model, the decision tree algorithm can divide configuration data into ordered and unordered categories. Assuming the input dataset contains 1000 configuration samples, the decision tree generates classification rules based on molecular distance and orientation angle. For example, distances less than 2.6 nm and orientation angles within ±3° are considered ordered. After classification, the ordered subset accounts for approximately 60%, providing accurate data for subsequent analysis.

[0051] It should be noted that the simple structure of decision trees makes it easy to explain classification logic and helps with process optimization.

[0052] For example, after extracting the ordered subset, the mean intermolecular distance can be calculated to be 2.4 nm with a variance of 0.2 nm, and the mean orientation angle to be 0° with a variance of 4°. If the variance exceeds a preset threshold of 3°, time series analysis, such as a moving average model, can be used to extract the configuration change trend. If the analysis shows that the configuration fluctuates significantly within 20-30 minutes, the sampling frequency can be adjusted to once every 5 seconds to generate a high-resolution dataset, improving the accuracy of the configuration stability index.

[0053] In one possible implementation, the k-means clustering algorithm groups the high-resolution dataset into three groups, with centroid parameters of 2.3 nm, 2.5 nm, and 2.8 nm. The group with a centroid of 2.3 nm is selected as the optimized configuration scheme because it has the smallest variance and the most stable configuration. Based on this scheme, a reaction environment control signal is generated, and the polymerization temperature is adjusted to 58°C to optimize the consistency of molecular arrangement. This method, through data-driven analysis, ensures the stability of molecular configuration and provides a reliable basis for optimizing liquid crystal material processes.

[0054] S106. After obtaining the critical condition parameters, the external field intensity is adjusted in real time to maintain the stability of molecular orientation, and the phase transition temperature is monitored. If the temperature fluctuation affects the regularity of molecular arrangement, the orientation angle is dynamically corrected to determine whether the crystallinity meets the expected standard.

[0055] After obtaining the critical condition parameters, the external field intensity is dynamically adjusted through the external field control module to generate molecular orientation stability data. Based on the molecular orientation stability data, a real-time monitoring system is used to collect the phase transition temperature change sequence to obtain temperature fluctuation data. If the temperature fluctuation data exceeds a preset standard threshold, an orientation angle correction value is calculated using an angle optimization algorithm to generate corrected molecular orientation data. Based on the corrected molecular orientation data, a support vector machine algorithm is used to classify the regularity of molecular arrangement and determine the regularity category. If the regularity category is lower than a preset standard, the temperature fluctuation data is processed using time series analysis to determine the dynamic adjustment time interval. Based on the dynamic adjustment time interval, a high-frequency external field control signal is generated to adjust the external field intensity parameters, obtaining optimized molecular arrangement data. Using the optimized molecular arrangement data, the crystallinity index is calculated to determine whether it meets the preset standard threshold.

[0056] For example, after obtaining the critical condition parameters, the external field control module can dynamically adjust the molecular orientation using electromagnetic or optical fields. Assuming that liquid crystal molecules need to maintain a specific orientation during the polymerization reaction, the external field control module can adjust the electromagnetic field strength to 5-10 kV / m based on real-time feedback signals, generating molecular orientation stability data. This data includes the orientation angle distribution and deviation, assuming a mean orientation angle of 0° and a standard deviation of 2°, reflecting the regularity of the molecular arrangement.

[0057] Specifically, the real-time monitoring system can acquire phase transition temperature change sequences using an infrared spectrometer. Assuming the reaction environment temperature range is 50-60°C, temperature data is acquired once per second, generating 600 data points. If the temperature fluctuation exceeds a preset standard threshold of ±0.5°C, for example, fluctuating from around 55°C to 56.2°C, it indicates that the molecular arrangement may be disturbed. The angle optimization algorithm can calculate the orientation angle correction value based on the temperature fluctuation. Assuming that least squares analysis determines that the orientation angle needs to be adjusted to within ±1°, corrected molecular orientation data is generated.

[0058] In one possible implementation, a support vector machine (SVM) algorithm can classify the corrected molecular orientation data. Assuming the dataset contains 500 samples, with features including orientation angle deviation and intermolecular distance, the classification rule is set as follows: orientation angle deviation less than 1.5° and intermolecular distance less than 2.5 nm are considered high-regularity. If the classification results show that only 50% of the samples achieve high regularity, below the preset standard of 70%, further optimization is needed. Time series analysis, such as an autoregressive model, is used to process temperature fluctuation data to determine the dynamic adjustment time interval. Assuming the analysis shows that temperature fluctuations are most intense between the 10th and 15th minute of the reaction, intensive adjustments to the external field are needed within this interval.

[0059] For example, high-frequency external field control signals can be achieved through pulsed electromagnetic fields. Adjusting the frequency to 100Hz and the intensity range to 8-12kV / m generates optimized molecular arrangement data. Based on this data, the crystallinity index is calculated. Assuming that X-ray diffraction analysis yields a crystallinity of 85%, it meets the preset standard of 80%. This method, through multi-dimensional data analysis and dynamic control, ensures the regularity and stability of the molecular arrangement, providing a reliable basis for the high-quality preparation of liquid crystal materials.

[0060] S107. The final regularity of the polymer molecular chain is evaluated using the crystallinity standard, and the degree of optimization of liquid crystal properties is determined by comparative analysis to obtain the combination of synthesis parameters for high-performance thermotropic liquid crystal polyester materials.

[0061] Polymer molecular chain structure data is acquired through a molecular chain analysis module. X-ray diffraction is used to determine the molecular chain arrangement characteristics, yielding molecular chain regularity data. Based on this regularity data, a preset crystallinity standard is used for evaluation, generating a crystallinity index to determine if the molecular chain meets the regularity requirements. If the crystallinity index is below a preset threshold, molecular dynamics simulation is used to calculate and adjust molecular chain optimization parameters, generating optimized molecular chain arrangement data. Based on the optimized molecular chain arrangement data, polarized light microscopy is used to analyze liquid crystal properties, determining the liquid crystal phase characteristics and obtaining liquid crystal property data. Based on the liquid crystal property data, a support vector machine algorithm is used to classify the liquid crystal phases, determining whether they meet the requirements for thermotropic liquid crystals, generating classification results. If the classification results do not meet the thermotropic liquid crystal standard, a parameter optimization algorithm is used to adjust the synthesis parameters, generating an optimized combination of synthesis parameters. Based on the optimized combination of synthesis parameters, a chemical reaction simulation module is used to generate high-performance thermotropic liquid crystal polyester material data, determining the final material performance indicators.

[0062] For example, when acquiring polymer molecular chain structure data through a molecular chain analysis module, nuclear magnetic resonance spectroscopy combined with X-ray diffraction can be used to analyze the chemical bond distribution and spatial configuration of the molecular chain. Nuclear magnetic resonance spectroscopy can identify the chemical shifts of repeating units in the molecular chain, generating molecular chain regularity data, reflecting the degree of order in the chain segments. Assuming that the analysis shows 90% of the repeating units in the molecular chain have a consistent chemical bond configuration, this indicates a high degree of molecular chain regularity. X-ray diffraction further determines the lattice parameters of the molecular chain, generating diffraction peak data. Assuming the main peak position is 2θ = 20° and the full width at half maximum (FWHM) is 0.5°, this reflects the orderliness of the molecular chain arrangement.

[0063] Specifically, when evaluating based on molecular chain regularity data using a preset crystallinity standard, a crystallinity threshold of 75% can be set. If, based on X-ray diffraction data, a crystallinity of 70% is calculated, which is below the threshold, it indicates insufficient molecular chain regularity. In this case, parameters can be optimized and adjusted through molecular dynamics simulations.

[0064] For example, the simulation can be set to a temperature of 300K and a simulation time of 100ns to analyze the configurational changes of molecular chains under different external field conditions and generate optimized molecular chain arrangement data, assuming that the molecular chain spacing is reduced from 3.0nm to 2.2nm after adjustment.

[0065] In one possible implementation, polarized light microscopy is used to analyze liquid crystal properties, allowing observation of birefringence of molecular chains under polarized light to generate liquid crystal phase characteristic data. Assuming striped textures are observed, this indicates the formation of a nematic phase, consistent with thermotropic liquid crystal characteristics. Based on this, a support vector machine algorithm is used to classify the liquid crystal phases, with features including birefringence intensity and phase transition temperature. The classification rule is that a birefringence intensity greater than 0.05 and a transition temperature between 80-90°C classify the liquid crystal as thermotropic. Assuming the classification results show that 60% of the samples meet the standard, lower than the expected 80%, further optimization is needed.

[0066] For example, when adjusting synthesis parameters using parameter optimization algorithms, the focus can be on polymerization temperature and catalyst concentration. Assuming an initial reaction temperature of 120°C and a catalyst concentration of 0.1 mol / L, optimization using a gradient descent algorithm yields a new parameter combination of 110°C and 0.15 mol / L. Based on these optimized parameters, the chemical reaction simulation module generates data for a high-performance thermotropic liquid crystal polyester material. The simulation shows the material retains its nematic phase at 90°C, and the transition temperature increases to 95°C, indicating that the material's performance meets the requirements for thermotropic liquid crystals. This method, through multi-dimensional analysis and optimization, ensures that molecular chain regularity and liquid crystal properties meet the expected standards, providing a reliable basis for the preparation of high-performance materials.

[0067] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A process for synthesizing thermotropic liquid crystal polyester material monomers, characterized in that, Specifically, the steps include the following: Step S101: Obtain real-time spectral data of monomer molecules in the reaction system, collect molecular orientation information at different reaction time points using a polarized light microscope, and use a convolutional neural network to identify and analyze the spectral features to obtain the numerical distribution of the current molecular orientation angle. Step S102: Calculate the molecular arrangement density parameter and liquid crystal phase transition characteristics based on the molecular orientation angle numerical distribution. If the molecular orientation angle deviation exceeds the preset threshold, activate the external field control module to dynamically adjust the reaction temperature and obtain optimized temperature control parameters. Step S103: Adjust the polymerization reaction environment using the temperature control parameters, monitor the polymerization rate change trend, use support vector machine algorithm to process the correlation between rate data and molecular configuration, and determine the molecular chain length growth law under the current reaction conditions. Step S104: Based on the molecular chain length growth law, predict the stability range of the liquid crystal phase state. If the phase state parameters are in an unstable range, adjust the monitoring frequency to increase the data acquisition density and determine the optimal reaction time window. Step S105: According to the optimal reaction time window, collect continuous data sequences of molecular configuration evolution, analyze the correlation between configuration change and arrangement density using the random forest algorithm, and obtain the critical condition parameters for ordered molecular arrangement. Step S106: After obtaining the critical condition parameters, the external field intensity is adjusted in real time to maintain the stability of molecular orientation, and the phase transition temperature is monitored. If the temperature fluctuation affects the regularity of molecular arrangement, the orientation angle is dynamically corrected to determine whether the crystallinity meets the expected standard. Step S107: The final regularity of the polymer molecular chain is evaluated using the crystallinity standard, and the degree of optimization of liquid crystal properties is determined by comparative analysis to obtain the combination of synthesis parameters for high-performance thermotropic liquid crystal polyester materials.

2. The process for synthesizing thermotropic liquid crystal polyester material monomers according to claim 1, characterized in that, The process involves acquiring real-time spectral data of monomer molecules in the reaction system, collecting molecular orientation information at different reaction time points using a polarized light microscope, and using a convolutional neural network to identify and analyze spectral features to obtain the numerical distribution of the current molecular orientation angles. This includes: Real-time spectral data of monomer molecules in the reaction system were obtained, and spectral signals in different wavelength ranges were collected using a high-resolution spectrometer to obtain the original spectral dataset. The reaction system was imaged at different reaction time points using a polarized light microscope, and polarized images containing molecular orientation information were acquired to obtain a molecular orientation image set. Image processing algorithms are used to preprocess the molecular orientation image set and extract the polarization intensity distribution features to obtain the intensity distribution feature set. If the signal-to-noise ratio of the light intensity distribution feature set is lower than the preset threshold, the light intensity distribution feature set is optimized by a noise reduction algorithm to obtain an optimized light intensity feature set. By jointly analyzing the optimized light intensity feature set and the original spectral dataset using a convolutional neural network, feature vectors of molecular orientation angles are extracted to obtain the orientation angle feature set. Based on the orientation angle feature set, a regression analysis algorithm is used to calculate the numerical distribution of molecular orientation angles, and the orientation angle distribution results are obtained. The orientation angle distribution results are processed by three-dimensional mapping using visualization tools to generate a spatial distribution map of molecular orientation angles, thus obtaining the final distribution map.

3. The process for synthesizing thermotropic liquid crystal polyester material monomers according to claim 1, characterized in that, The molecular alignment density parameter and liquid crystal phase transition characteristics are calculated based on the molecular orientation angle numerical distribution. If the molecular orientation angle deviation exceeds a preset threshold, the external field control module is activated to dynamically adjust the reaction temperature to obtain optimized temperature control parameters, including: Molecular orientation angle data are processed using numerical distribution analysis methods to calculate orientation angle deviations and obtain deviation distribution results. If the deviation distribution result exceeds the preset threshold, a temperature adjustment signal is generated through the external field control module to obtain the initial temperature control parameters; Based on the initial temperature control parameters, the molecular arrangement density is calculated using a molecular dynamics simulation algorithm to obtain a density distribution dataset; Using a density distribution dataset, statistical analysis methods were employed to extract liquid crystal phase transition characteristics, resulting in a phase transition characteristic set. If the phase transition feature set indicates an abnormal phase state, the reaction temperature is adjusted a second time through the external field control module to obtain optimized temperature parameters; Based on the optimized temperature parameters and density distribution dataset, a regression analysis algorithm is used to calculate the temperature control accuracy and obtain the accuracy evaluation results. Based on the accuracy assessment results and the phase transition feature set, a spatial distribution map of molecular arrangement density is generated, resulting in the final distribution map.

4. The process for synthesizing thermotropic liquid crystal polyester material monomers according to claim 1, characterized in that, The process involves adjusting the polymerization reaction environment using the aforementioned temperature control parameters, simultaneously monitoring the polymerization rate trend, and using a support vector machine algorithm to process the correlation between the rate data and molecular configuration to determine the molecular chain length growth pattern under the current reaction conditions. This includes: The polymerization rate variation trend is obtained by using sensors, and the rate data is processed by time series analysis to obtain a dynamic curve of the polymerization rate. If the polymerization rate dynamic curve deviates from the preset threshold, an environmental adjustment signal is generated through the feedback control module to determine the correction value of the reaction environment parameters; Based on the correction values ​​of the reaction environment parameters, the temperature control parameters are adjusted to obtain the updated polymerization reaction environment configuration. By analyzing the updated polymerization reaction environment configuration and molecular configuration data using the support vector machine algorithm, a molecular chain length growth prediction model is obtained. The chain length distribution pattern is extracted from the molecular chain length growth prediction model, and the chain length distribution dataset is calculated using statistical analysis methods. If the chain length distribution dataset indicates an abnormal growth pattern, the temperature control parameters are further optimized using environmental adjustment signals to obtain the final temperature control scheme. Based on the final temperature control scheme and chain length distribution dataset, a spatial distribution map of molecular chain length is generated to determine the optimization results of the polymerization reaction.

5. The process for synthesizing a thermotropic liquid crystal polyester material monomer according to claim 1, characterized in that, The process involves predicting the stability range of the liquid crystal phase based on the molecular chain length growth law. If the phase parameters are in an unstable range, the monitoring frequency is adjusted to increase the data acquisition density, and the optimal reaction time window is determined. This includes: Feature vectors are extracted from the molecular chain length growth law, and a liquid crystal phase stability prediction model is constructed using the support vector machine algorithm to obtain the phase stability range. If the phase stability range exceeds the preset stability range, the real-time acquired phase parameters are processed by time series analysis to determine the parameter fluctuation trend. Based on the parameter fluctuation trend, the data acquisition frequency is adjusted to generate a high-density data acquisition scheme and obtain a high-resolution phase dataset; Using a high-resolution phase state dataset, the k-means clustering algorithm was employed to divide the reaction time intervals and determine candidate reaction time windows. If the variance of the phase parameters of the candidate reaction time window exceeds the preset threshold, a frequency adjustment signal is generated through the feedback control module to optimize the data acquisition frequency and obtain a stable reaction time dataset. Based on the stable reaction time dataset, the phase stability distribution of the time window is calculated, and the optimal reaction time window is determined. By using the optimal reaction time window, reaction condition control signals are generated, polymerization reaction environment parameters are adjusted, and the final reaction configuration scheme is obtained.

6. The process for synthesizing thermotropic liquid crystal polyester material monomers according to claim 1, characterized in that, The process involves collecting continuous data sequences of molecular configuration evolution based on the optimal reaction time window, analyzing the correlation between configuration changes and arrangement density using a random forest algorithm, and obtaining critical condition parameters for ordered molecular arrangement, including: Obtain continuous molecular configuration data sequences within the optimal reaction time window, and use the random forest algorithm to analyze the correlation between configuration changes and arrangement density to determine the critical condition parameters for ordered molecular arrangement. A molecular configuration classification model is constructed by using critical condition parameters. The decision tree algorithm is used to classify the molecular configuration data sequence to obtain the configuration categories of ordered and disordered arrangements. Based on the configuration category, extract a subset of ordered molecular configuration data, calculate the statistical distribution of intermolecular spacing and orientation angle in the subset, and determine the geometric characteristic parameters of molecular arrangement; If the variance of the geometric feature parameters exceeds the preset threshold, the molecular configuration data subset is processed by time series analysis to obtain the time trend of configuration changes and determine the time interval for dynamic adjustment. Based on the dynamically adjusted time interval, a high-frequency data acquisition signal is generated to obtain a high-resolution molecular configuration dataset. The configuration stability index of the dataset is calculated to obtain stable configuration data. By using stable configuration data, the k-means clustering algorithm is used to group molecular configurations, determine the center point parameters of the configuration groups, and obtain the optimal configuration scheme of molecular arrangement. Based on the optimized configuration scheme, reaction environment control signals are generated, polymerization reaction condition parameters are adjusted, and the final molecular arrangement is determined.

7. The process for synthesizing thermotropic liquid crystal polyester material monomers according to claim 1, characterized in that, After obtaining the critical condition parameters, the external field intensity is adjusted in real time to maintain molecular orientation stability, and the phase transition temperature is monitored. If temperature fluctuations affect the regularity of molecular arrangement, the orientation angle is dynamically corrected, and it is determined whether the crystallinity meets the expected standard, including: After obtaining the critical condition parameters, the external field intensity is dynamically adjusted through the external field control module to generate molecular orientation stability data; Based on molecular orientation stability data, a real-time monitoring system was used to collect phase transition temperature change sequences to obtain temperature fluctuation data. If the temperature fluctuation data exceeds the preset standard threshold, the orientation angle correction value is calculated through the angle optimization algorithm to generate the corrected molecular orientation data; Based on the corrected molecular orientation data, the support vector machine algorithm is used to classify the regularity of molecular arrangement and determine the regularity category. If the regularity category is lower than the preset standard, the temperature fluctuation data is processed by time series analysis to determine the dynamic adjustment time interval; Based on the dynamically adjusted time interval, a high-frequency external field control signal is generated, and the external field intensity parameters are adjusted to obtain optimized molecular arrangement data; The crystallinity index is calculated using the optimized molecular arrangement data to determine whether it meets the preset standard threshold.

8. The process for synthesizing a thermotropic liquid crystal polyester material monomer according to claim 1, characterized in that, The process of evaluating the final regularity of polymer molecular chains using the crystallinity standard, determining the degree of optimization of liquid crystal properties through comparative analysis, and obtaining the combination of synthesis parameters for high-performance thermotropic liquid crystal polyester materials includes: The molecular chain structure data of polymers is obtained through the molecular chain analysis module, and the molecular chain arrangement characteristics are determined by X-ray diffraction to obtain molecular chain regularity data. Based on the molecular chain regularity data, a preset crystallinity standard is used for evaluation to generate a crystallinity index and determine whether the molecular chain meets the regularity requirements. If the crystallinity index is lower than the preset threshold, the molecular chain optimization adjustment parameters are calculated through molecular dynamics simulation to generate optimized molecular chain arrangement data. Based on the optimized molecular chain arrangement data, polarized light microscopy was used to analyze the liquid crystal properties, determine the liquid crystal phase characteristics, and obtain liquid crystal property data. Based on the liquid crystal characteristic data, the liquid crystal phase state is classified using the support vector machine algorithm to determine whether it meets the requirements of thermotropic liquid crystal and generate the classification result. If the classification result does not meet the thermotropic liquid crystal standard, the synthesis parameters are adjusted through the parameter optimization algorithm to generate an optimized combination of synthesis parameters. Based on the optimized combination of synthesis parameters, the chemical reaction simulation module was used to generate data on high-performance thermotropic liquid crystal polyester materials, and the final material performance indicators were determined.

Images