Polypropylene purification reactor temperature control method

Abstract

The present application relates to the technical field of reaction kettle temperature control, and particularly relates to a reaction kettle temperature control method for polypropylene purification. The method acquires state data of a reaction kettle in a polypropylene purification process; acquires a degassing initial moment based on changes in temperature data of each purification; acquires a reference historical purification of the current purification based on similar conditions of the state data; acquires predicted material viscosity data according to changes in material viscosity data in a specified time period after the degassing initial moment of the reference historical purification, material viscosity data of the current moment of the current purification, and combines changes in the material viscosity data and pressure data in the reference historical purification to acquire predicted pressure data; and controls the temperature of the reaction kettle of the current purification based on the predicted material viscosity data and the predicted pressure data. The present application accurately acquires predicted temperature data, which is conducive to controlling the temperature of the reaction kettle in advance and effectively reduces the hysteresis and inaccuracy of temperature control.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of reaction kettle temperature control, and in particular to a reaction kettle temperature control method for polypropylene purification. BACKGROUND

[0002] Polypropylene is an important thermoplastic polymer, which is widely used in packaging, automobile, fiber and chemical industry due to its excellent mechanical properties, chemical stability and processability. The performance of polypropylene products, such as mechanical strength, transparency and heat resistance, depends largely on its purity. Therefore, it is crucial to purify polypropylene efficiently to remove residual monomers, solvents and other low molecular weight impurities in the post-processing link of the production process.

[0003] Currently, reaction kettles are generally used as core equipment for polypropylene purification in industry. The polypropylene purification process includes stages of melting preheating, vacuum degassing, impurity evaporation, condensation separation and cooling solidification. Among them, the vacuum degassing and impurity evaporation stages are the key links that determine the purification effect. The polypropylene material needs to be heated to 160-170℃ (close to its melting point interval), and a negative pressure environment is maintained in the kettle. Through the synergistic effect of heating and pressure reduction, the low-boiling-point impurities in the material are rapidly volatilized, realizing the separation of impurities and polypropylene matrix. Temperature and pressure are the core parameters for regulating the polypropylene purification process, and there is a close coupling relationship between them. The temperature directly determines the melting state of the material and the evaporation rate of the impurities, and the pressure affects the removal efficiency of the impurities by changing the boiling point of the impurities. Fluctuations in either parameter can lead to incomplete purification or material degradation, ultimately affecting product quality.

[0004] Currently, the existing reaction kettle temperature control methods are mostly based on traditional control strategies, using temperature detection values as the single control basis, without fully considering the dynamic coupling relationship between temperature, pressure and material viscosity. In actual production, the impurity content and viscosity of different purification batches of raw materials differ, and the impurity evaporation rate changes dynamically with the reaction process during the purification process. These factors can break the heat balance and pressure stability in the kettle, leading to significant regulation time lag and overshoot problems in the traditional control system, which cannot predict the working condition changes in advance, thus causing inaccurate temperature control, ultimately leading to decreased polypropylene purification efficiency and poor batch quality consistency of the product. SUMMARY

[0005] In order to solve the technical problems of reaction kettle temperature control lag and inaccuracy, which lead to unstable polypropylene purification, the purpose of the present application is to provide a reaction kettle temperature control method for polypropylene purification, and the technical solution adopted is as follows:

[0006] The present application provides a reaction kettle temperature control method for polypropylene purification, which comprises the following steps:

[0007] Real-time acquisition of state data in the polypropylene purification process reactor; the state data includes temperature data, pressure data and material viscosity data;

[0008] Based on the change of temperature data of each purification, the degassing initial time of each purification is obtained; according to the similarity of state data at the degassing initial time of the current purification and the historical purification, and the similarity of the initial material weight, the reference historical purification of the current purification is obtained;

[0009] According to the change of material viscosity data of each reference historical purification in a specified time period after the degassing initial time, and the material viscosity data of the current purification at the current time, the predicted material viscosity data of the current purification at the future time is obtained;

[0010] Based on the predicted material viscosity data, and the lag of the change of material viscosity data and the change of pressure data in the reference historical purification, the predicted pressure data of the current purification at the future time is obtained;

[0011] Based on the predicted material viscosity data and the predicted pressure data, the predicted temperature data of the current purification at the future time is obtained through the temperature prediction model;

[0012] Based on the predicted temperature data, the temperature of the reactor in the current purification process is controlled.

[0013] Further, the degassing initial time acquisition method is:

[0014] For any time of any purification, the difference between the standard deviation of the temperature data of the purification in the first preset time period and the second preset time period of the time is obtained as the degassing reference value of the time; wherein the first preset time period and the second preset time period have the same length, the end time of the first preset time period is the time, and the start time of the second preset time period is the time;

[0015] The degassing reference value of each time of the purification is obtained, and the time corresponding to the maximum degassing reference value is taken as the degassing initial time of the purification.

[0016] Further, the reference historical purification acquisition method is:

[0017] For any historical purification and any state data, the result of normalizing the difference of the state data between the current purification and the degassing initial time of the historical purification is taken as the first difference of the state data;

[0018] The result of normalizing the difference of the initial material weight data between the current purification and the historical purification is taken as the initial weight difference;

[0019] The negative correlation and normalized result of adding the first difference of all kinds of state data and the initial weight difference is taken as the similarity degree of the current purification and the historical purification;

[0020] When the similarity degree is greater than the preset similarity degree threshold, the corresponding historical purification is the reference historical purification of the current purification.

[0021] Further, the method for obtaining the predicted material viscosity data is:

[0022] According to the unit change of the material viscosity data of each reference historical purification in a specified time period after the degassing initial time point of the reference historical purification, a reference unit viscosity change value at a current time point of the current purification is obtained; wherein the current time point is located after the degassing initial time point of the current purification, and the initial time point of the specified time period and the current time point are both equal in time length to the corresponding degassing initial time point;

[0023] A time period formed by taking the current time point as the starting point and the time length of the specified time period is taken as the first prediction time period of the current purification;

[0024] The time points in the first prediction time period are all taken as first future time points;

[0025] For any first future time point, the time length of the first future time point from the current time point is taken as a first time length;

[0026] The product of the reference unit viscosity change value and the first time length is taken as a viscosity reference change value;

[0027] The addition result of the material viscosity data at the current time point of the current purification and the viscosity reference change value is taken as the predicted material viscosity data at the first future time point.

[0028] Further, the method for obtaining the reference unit viscosity change value is:

[0029] For any reference historical purification, the difference between the material viscosity data at each time point in the specified time period of the reference historical purification and the material viscosity data at the previous adjacent time point is taken as a second difference;

[0030] The average of the ratio of all second differences to the time length between the corresponding time points is taken as the unit viscosity change rate of the specified time period of the reference historical purification;

[0031] The average of the unit viscosity change rates of the specified time periods of all reference historical purifications is taken as the reference unit viscosity change value at the current time point of the current purification.

[0032] Further, the method for obtaining the predicted pressure data is:

[0033] Based on the lag between changes in material viscosity data and pressure data in historical purification processes, the lag time of pressure data relative to material viscosity data is obtained.

[0034] The moment that is located after the current moment and whose time interval is the change lag time is taken as the initial second future moment;

[0035] Starting from the initial second future time, the time period consisting of a specified duration is taken as the second prediction time period for the current purification; all times within the second prediction time period are taken as second future times; wherein, one second future time corresponds to one first future time, and the interval between each second future time and its corresponding first future time is the change lag time.

[0036] Each first future moment is taken as the first historical reference moment in each reference history purification process; wherein, the time between each first future moment and its corresponding first historical reference moment and the corresponding degassing initial moment is the same.

[0037] Each second future moment is taken as the second historical reference moment in each reference history purification process; wherein, the time between each second future moment and its corresponding second historical reference moment and the corresponding degassing initial moment is the same.

[0038] The material viscosity data and vacuum valve position setting value at each first historical reference time in the reference historical purification, as well as the initial material weight data of the reference historical purification, are used as independent variables; the pressure data at the second historical reference time corresponding to each first historical reference time in the reference historical purification are used as dependent variables; a set of stable reference regression coefficients are obtained by performing multiple linear regression analysis using the least squares method. ;in, This is the basic pressure compensation item, which represents the initial pressure data of the reactor when there is no material and no evacuation. The viscosity coefficient represents the weight of the influence of material viscosity data on the predicted pressure data. The valve position control coefficient represents the weight of the influence of the vacuum valve position on the predicted pressure data. The material weight coefficient represents the weight of the initial material weight data on the predicted pressure data.

[0039] Then, the trained regression equation is determined: In the formula, For the first Predicted pressure data at the corresponding time point; The duration of the change lag; This represents the material viscosity data at time t. is the vacuum valve position set value at the tth time; B is the initial material weight data;

[0040] The predicted material viscosity data and the vacuum valve position set value at each first future time, and the initial material weight data of the current purification are input into the trained regression equation to obtain predicted pressure data at a corresponding second future time.

[0041] Further, the method for obtaining the change hysteresis length is:

[0042] For each reference historical purification, the material viscosity data of the reference historical purification is arranged in time sequence to obtain a viscosity data sequence;

[0043] The pressure data of the reference historical purification is arranged in time sequence to obtain a pressure data sequence;

[0044] The cross-correlation function of the viscosity data sequence and the pressure data sequence is calculated, and the time shift amount that makes the cross-correlation function reach a maximum value is taken as the reference hysteresis length corresponding to the reference historical purification;

[0045] The mean value of the reference hysteresis lengths corresponding to all reference historical purifications is taken as the change hysteresis length of the pressure data relative to the material viscosity data.

[0046] Further, the method for obtaining the predicted temperature data is:

[0047] The predicted material viscosity data and the predicted pressure data in the predicted reference time period are sequentially input into the trained temperature prediction model to output predicted temperature data at each future time in the reference time period.

[0048] Further, the method for controlling the temperature of the reaction kettle in the current purification process is:

[0049] When the predicted temperature data indicates that the future temperature will exceed the preset upper temperature limit, the heating power of the reaction kettle is reduced in advance;

[0050] When the predicted temperature data indicates that the future temperature will be lower than the preset lower temperature limit, the heating power of the reaction kettle is increased in advance.

[0051] Further, the temperature prediction model is a multi-layer feedforward neural network with ReLU activation function, which is trained by minimizing the mean square error between the predicted temperature and the actual temperature.

[0052] The present application has the following beneficial effects:

[0053] The present application firstly obtains the degassing initial time of each purification based on the change of temperature data of each purification, accurately determines the start time of the vacuum degassing and impurity evaporation stage of each purification, effectively enhances the accuracy of comparison of subsequent different purification processes, and prepares for subsequent temperature prediction, thereby improving the reliability of temperature prediction; in order to improve the accuracy of current purification temperature prediction, the reference historical purification of the current purification is obtained according to the state data similarity of the degassing initial time of the current purification and the historical purification and the initial material weight similarity, which is beneficial to provide a reliable reference for the current purification, and effectively improves the accuracy and reliability of all subsequent prediction steps of the current purification; then, the predicted material viscosity data at the future time of the current purification is obtained according to the material viscosity data change of each reference historical purification in a specified time period after the degassing initial time and the material viscosity data at the current time of the current purification, which accurately reflects the change of the impurity content in the material and can predict the change of the material state caused by impurity removal in advance, thereby laying a foundation for subsequent control process and fundamentally changing the situation of passive response; further, the predicted pressure data at the future time of the current purification is obtained based on the predicted material viscosity data and the lag of the material viscosity data change and the pressure data change in the reference historical purification, which effectively avoids the problem that the pressure data fluctuates sharply and is difficult to directly model and predict due to direct regulation, improves the stability and reliability of the predicted pressure data prediction, and is beneficial to subsequent accurate temperature prediction; then, the predicted temperature data at the future time of the current purification is obtained based on the predicted material viscosity data and the predicted pressure data through a temperature prediction model, which accurately infers the future temperature change, is beneficial to actively adjusting the heating power before the actual temperature deviation occurs, effectively avoids the problems of inaccurate temperature control and response lag, significantly reduces the phenomenon of temperature overshoot or low temperature, and greatly improves the accuracy of temperature control and the stability of the process; then, the temperature of the reaction kettle in the current purification process is accurately controlled based on the predicted temperature data, so as to ensure that the polypropylene purification process stably operates under the optimal process parameters, and significantly improves the purity, consistency and energy efficiency level of the final product. BRIEF DESCRIPTION OF DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort.

[0055] Figure 1 A schematic flow chart of a reaction kettle temperature control method for polypropylene purification provided by an embodiment of the present application;

[0056] Figure 2 A structure diagram of a reaction kettle temperature control system for purifying polypropylene according to an embodiment of the present application is provided.

[0057] Figure 3 A schematic diagram of a computer device according to an embodiment of the present application is provided. DETAILED DESCRIPTION

[0058] In order to further clarify the technical means and effects taken by the present application to achieve the predetermined object of the application, the following describes in detail the specific implementation, structure, features and effects of a reaction kettle temperature control method for purifying polypropylene according to the present application, combined with the preferred embodiments and the accompanying drawings. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0060] The specific scheme of the reaction kettle temperature control method for purifying polypropylene according to the present application is described in detail below in combination with the accompanying drawings.

[0061] Embodiment 1:

[0062] The present application proposes a reaction kettle temperature control method for purifying polypropylene, please refer to Figure 1 which shows a schematic flow chart of a reaction kettle temperature control method for purifying polypropylene according to an embodiment of the present application, which includes the following steps:

[0063] Step S1: Real-time acquisition of state data in the reaction kettle during the polypropylene purification process; the state data includes temperature data, pressure data and material viscosity data.

[0064] Specifically, it is known that the polypropylene purification process covers stages such as melting preheating, vacuum degassing, impurity evaporation, condensation separation and cooling solidification, among which the vacuum degassing and impurity evaporation stages are the core and key of the entire purification process. This embodiment mainly analyzes the vacuum degassing and impurity evaporation stages to ensure accurate dynamic coordination control of the temperature and pressure in the reaction kettle, effectively improving the purity of polypropylene.

[0065] The principle of the vacuum degassing and impurity evaporation stage is that after preliminary melting and preheating, the polypropylene material is transported into the reaction kettle and gradually heated to a temperature close to the melting point of the polypropylene material (usually between 160°C and 170°C); at the same time, a certain vacuum degree (negative pressure state) is applied and maintained in the reaction kettle by the vacuum pump and pressure regulating valve system. Under this condition, the impurities such as residual solvent, low molecular weight hydrocarbons and unreacted monomers in the material can be efficiently volatilized and removed at a relatively low temperature, realizing the purification of the polypropylene material. The temperature control in the vacuum degassing and impurity evaporation stage directly determines the melting uniformity of the material and the evaporation rate of the impurities, and the pressure control dominates the boiling characteristics and removal efficiency of the impurities. The two are closely coupled and related, and together determine the efficiency of the purification process and the key quality indicators such as purity, mechanical properties and transparency of the final polypropylene product.

[0066] To ensure stable operation of the process, the reaction kettle is equipped with a complete supporting system and detection device. The heating system (heating jacket or electric heating jacket) provides a stable heat source to ensure accurate temperature control; the vacuum pump and pressure regulating valve system cooperates to maintain and dynamically adjust the negative pressure state in the reaction kettle to meet the evaporation needs of impurities; the mechanical stirrer continuously operates to ensure uniform mixing of the molten polypropylene and avoid process fluctuations caused by local overheating or bubble retention. At the same time, the reaction kettle is equipped with multi-dimensional detection equipment to obtain real-time state data of the polypropylene purification process in the reaction kettle. The state data includes temperature data, pressure data and material viscosity data, i.e. the temperature data in the reaction kettle is monitored in real time by a thermocouple temperature sensor, the pressure data in the reaction kettle is tracked by a pressure transmitter, and the torque data obtained by a stirring motor torque sensor directly reflects the material viscosity data. It should be noted that the temperature data, pressure data and material viscosity data are collected synchronously, and the time interval between adjacent data collection is set to 1 minute in this embodiment. The implementer can set the time interval between adjacent data collection according to the actual situation, which is not limited herein. In addition, the initial material weight data of each polypropylene purification is obtained.

[0067] By collecting the above-mentioned temperature data, pressure data, material viscosity data and initial material weight data in real time, accurate and comprehensive data support can be provided for the subsequent temperature dynamic control of the whole polypropylene purification process, ensuring the scientificity and timeliness of the control strategy.

[0068] Step S2: based on the change of the temperature data of each purification, the degassing initial time of each purification is obtained; based on the similarity of the state data at the degassing initial time of the current purification and the historical purification, and the similarity of the initial material weight, the reference historical purification of the current purification is obtained.

[0069] Specifically, it is known that in the polypropylene purification process, the initial stage of the reaction kettle is in a dynamic unstable state, from the material entering the reaction kettle to being heated to the target temperature range, the temperature, pressure and material state are all changing sharply; at the same time, the initial conditions of different times of purification (such as ambient temperature, initial temperature of the material) may be different, resulting in different time points of reaching a stable state. Considering that when the polypropylene purification enters the vacuum degassing and impurity evaporation stage, the temperature data in the reaction kettle will remain stable. Therefore, based on the change of temperature data of each purification, the initial time of degassing of each purification, that is, the time when the temperature starts to stabilize, is obtained, which is essentially the starting time of the vacuum degassing and impurity evaporation stage.

[0070] In order to accurately predict the temperature data of the current purification for subsequent accurate control of the temperature in the reaction kettle during the current purification process, and to ensure that the polypropylene purification is stable and efficient, the reference historical purification of the current purification is obtained according to the similar state data at the initial time of degassing of the current purification and the historical purification, and the most similar historical purification to the current purification is accurately selected, so that personalized data generated under the closest conditions are used for prediction, effectively improving the pertinence and accuracy of subsequent prediction of the current purification.

[0071] Preferably, in one implementation manner of the present embodiment, the method for obtaining the initial time of degassing is: for any time of any purification, the difference between the standard deviations of the temperature data of the purification in a first preset time period and a second preset time period at the time is obtained as the degassing reference value at the time; the larger the degassing reference value, the more likely it is that the time is the initial time of degassing of the purification. Wherein, the lengths of the first preset time period and the second preset time period are the same, the end time of the first preset time period is the time, and the start time of the second preset time period is the time; the present embodiment sets the lengths of the first preset time period and the second preset time period as 10 minutes, and the implementer can set the lengths of the first preset time period and the second preset time period according to the actual situation, which is not limited herein. Further, the degassing reference value of each time of the purification is obtained, and the time corresponding to the maximum degassing reference value is taken as the initial time of degassing of the purification.

[0072] At this point, the initial time of degassing of each purification is obtained.

[0073] Preferably, in one implementation manner of the present embodiment, the reference historical purification acquisition method is as follows: for each historical purification and each state data, the absolute value of the difference between the degassing initial time of the current purification and the degassing initial time of the historical purification is normalized to obtain the first difference of the state data; the absolute value of the difference between the initial material weight data of the current purification and the historical purification is normalized to obtain the initial weight difference; the above absolute values are normalized by the norm normalization function in the present embodiment. The smaller the first difference and the initial weight difference, the more similar the current purification and the historical purification. Then, the negative correlation and normalization result of the sum of the first difference and the initial weight difference of all state data is taken as the similarity degree between the current purification and the historical purification; the sum of the first difference and the initial weight difference is processed by the negative correlation and normalization function in the present embodiment, where x represents the sum of the first difference and the initial weight difference of all state data; norm is a normalization function. The greater the similarity degree, the more similar the current purification and the historical purification. Therefore, the present embodiment sets the preset similarity degree threshold value to 0.6, and the implementer can set the size of the preset similarity degree threshold value according to the actual situation, which is not limited herein. When the similarity degree is greater than the preset similarity degree threshold value, the corresponding historical purification is the reference historical purification of the current purification. The sum of the first difference and the initial weight difference is processed by the negative correlation and normalization function, where x represents the sum of the first difference and the initial weight difference of all state data; norm is a normalization function. The greater the similarity degree, the more similar the current purification and the historical purification. Therefore, the present embodiment sets the preset similarity degree threshold value to 0.6, and the implementer can set the size of the preset similarity degree threshold value according to the actual situation, which is not limited herein. When the similarity degree is greater than the preset similarity degree threshold value, the corresponding historical purification is the reference historical purification of the current purification.

[0074] At this point, the reference historical purification of the current purification is accurately selected. It should be noted that the number of historical purifications in the present embodiment is set to 600, and the implementer can set the number of historical purifications according to the actual situation, which is not limited herein.

[0075] Step S3: According to the material viscosity data change of each reference historical purification in a specified time period after the degassing initial time, and the material viscosity data of the current purification at the current time, the predicted material viscosity data of the current purification at the future time is obtained.

[0076] Specifically, the temperature data and the pressure data during the degassing process in the reactor are directly controlled in real time. This control behavior itself introduces frequent and short-period correction actions, resulting in significant short-term fluctuations and strong intervention traces in the temperature data and the pressure data in the historical data. Therefore, if the continuous prediction model of the temperature data or the pressure data in the purification process is directly established based on these historical data that are strongly disturbed by external control, the reliability is low, and the prediction result is easily distorted. Unlike the temperature data and the pressure data, the change of the material viscosity data is mainly dominated by the change of the internal state, i.e., the impurity content, that is, a relatively continuous and smooth physical and chemical process determined by the inherent law of the reaction. Therefore, the material viscosity data has higher predictability and stability, and the evolution process of the material state in the reactor can be more stably and truly reflected by inferring the change trend of the material viscosity data.

[0077] It is known that the impurities such as residual solvents and unreacted monomers contained in the material have short molecular chains and usually exhibit lower viscosity than the polypropylene body. With the progress of the degassing process, these low-molecular-weight impurities are continuously removed, resulting in a relatively increasing proportion of the high-molecular-weight components in the material system, which macroscopically exhibits that the viscosity of the entire molten material gradually increases with the progress of the degassing process. It should be noted that the change of the material viscosity data is not uniform and linear. Due to the difference in the internal impurity content and composition at different degassing stages, the change rate of the material viscosity data is not the same, which further affects the heat transfer efficiency and the gas escape behavior in the reactor, and directly drives the fluctuation of the temperature and the pressure at the subsequent time. Therefore, the change of the material viscosity data is essentially an indirect representation of the dynamic change of the impurity content in the reactor.

[0078] In order to accurately predict the predicted material viscosity data at the future time of the current purification, so as to accurately predict the evolution process of the material state at the subsequent time of the current purification, the embodiment obtains the predicted material viscosity data at the future time of the current purification according to the change of the material viscosity data in a specified time period after the initial time of the degassing of each reference historical purification and the material viscosity data at the current time of the current purification, and lays a foundation for the subsequent feedforward control of the temperature and the pressure.

[0079] Preferably, in one implementation mode of the present embodiment, the method for obtaining the predicted material viscosity data is: obtaining the reference viscosity unit change value at the current time of the current purification according to the unit change of the material viscosity data in a specified time period after the degassing initial time of each reference historical purification, which accurately reflects the trend of the unit change of the subsequent material viscosity data after the current time of the current purification; wherein the current time is after the degassing initial time of the current purification, and the current time is the real-time state of the vacuum degassing and impurity evaporation stage of the current purification, the initial time of all specified time periods is equal to the time length from the corresponding degassing initial time, and the time length from the corresponding degassing initial time to the current time is equal, which essentially aligns the degassing initial time of each reference historical purification with the current purification, and then determines the time point in each reference historical purification which is equal in time length to the degassing initial time, i.e. the initial time of the specified time period in each reference historical purification;

[0080] The method for obtaining the reference viscosity unit change value is: for any one reference historical purification, the difference between the material viscosity data at each time point in the specified time period of the reference historical purification and the previous adjacent time point is taken as the second difference; it should be noted that the initial time in the specified time period of the reference historical purification is not analyzed because it does not have a previous adjacent time point in the specified time period; the average of the ratio of all second differences to the time length between the corresponding time points is taken as the unit viscosity change rate of the specified time period of the reference historical purification; then the average of the unit viscosity change rates of the specified time period of all reference historical purifications is taken as the reference viscosity unit change value at the current time of the current purification;

[0081] It should be noted that the length of the specified time period needs to be set in combination with process requirements, data characteristics and control objectives to avoid the length of the specified time period being too short to identify trends in advance or the length of the specified time period being too long to cause poor data timeliness and lead to prediction failure; therefore, the length of the specified time period should be greater than or equal to the response time required for the reactor temperature control system to perform a control action (such as adjusting the heating power) to the time required for observing a significant temperature change in the reactor, to ensure that the prediction can cover the system delay and make the feedforward control meaningful; the length of the specified time period should also be based on the typical duration of the continuous change of the material viscosity data in the vacuum degassing and impurity evaporation stage; for example, the length of the specified time period can be set to 10% to 30% of the total length of the vacuum degassing and impurity evaporation stage to ensure that meaningful trend changes can be captured and large errors can be avoided due to predicting too far into the future; the length of the specified time period should also be an integer multiple of the system control period, for example, if the control system calculates and outputs a control instruction once every 5 seconds, the length of the specified time period can be set to 30 seconds and 60 seconds, etc., to ensure that the prediction and control are synchronized; in addition, the length of the specified time period should also be set such that the correlation coefficient of the predicted sequence of the material viscosity data and the corresponding historical sequence in the reference historical purification is higher than a preset threshold; in this embodiment, the preset threshold is set to 0.7, and the implementer can set the size of the preset threshold according to the actual situation, which is not limited herein; the method for obtaining the correlation coefficient is a known technology, such as Pearson correlation coefficient and Kendall rank correlation coefficient, which will not be described herein. In a specific embodiment, by analyzing the data of the historical vacuum degassing and impurity evaporation stage, it is determined that the typical length of this stage is 20 minutes, and considering the response delay of about 1-2 minutes caused by the system thermal inertia, to ensure the effectiveness of the prediction and take into account the calculation efficiency, the length of the specified time period is set to 3 to 5 minutes, which can both anticipate the response delay of the system and be within a short-term range in which the trend of the change of the material viscosity data can be reasonably predicted. The implementer can set the length of the specified time period according to the actual situation, which is not limited herein.

[0082] The time period formed by the length of the specified time period is taken as the first prediction time period of the current purification with the current time as the starting point; the time points in the first prediction time period are all taken as the first future time points; for any first future time point, the length of the first future time point from the current time is taken as the first length; the product of the reference viscosity unit change value and the first length is taken as the viscosity reference change value; and then the sum of the material viscosity data at the current time of the current purification and the viscosity reference change value is taken as the predicted material viscosity data at the first future time point.

[0083] Up to now, the predicted material viscosity data at each first future time point of the current purification is obtained.

[0084] Step S4: obtaining the predicted pressure data at the future time of the current purification based on the predicted material viscosity data and the hysteresis of the change of the material viscosity data and the change of the pressure data in the historical purifications.

[0085] Specifically, when the material viscosity data gradually increases due to the removal of impurities, the gas diffusion and overflow resistance in the melt increases, resulting in a slowdown of the internal gas release rate. This change will cause the pressure in the reactor to rise hysteresis, and the change of the pressure will directly affect the boiling point of the material and the heat transfer efficiency, thereby feeding back to the heat balance of the system and ultimately causing the temperature to change. Therefore, the pressure data can be used as an intermediate bridge connecting the material viscosity data and the temperature data, so as to first predict the pressure data based on the material viscosity data, that is, in this embodiment, the predicted pressure data at the future time of the current purification is obtained based on the predicted material viscosity data and the hysteresis of the change of the material viscosity data and the change of the pressure data in the historical purifications, which provides a key and reliable intermediate variable for subsequent temperature feedforward control, and indirectly realizes reliable inference of the change of the temperature data.

[0086] Preferably, in one implementation manner of the present embodiment, the method for obtaining the predicted pressure data is: first, according to the hysteresis of the change of the material viscosity data and the change of the pressure data in the historical purifications, the change hysteresis time length of the pressure data relative to the material viscosity data is obtained, so as to accurately determine the time corresponding to the pressure data predicted according to the material viscosity data, and improve the stability and accuracy of the predicted pressure data.

[0087] The method for obtaining the change hysteresis time length is: for each reference historical purification, the material viscosity data of the reference historical purification is arranged in time sequence to obtain a viscosity data sequence; the pressure data of the reference historical purification is arranged in time sequence to obtain a pressure data sequence; the cross-correlation function of the viscosity data sequence and the pressure data sequence is calculated, and the time shift amount that makes the cross-correlation function reach the maximum value is taken as the reference hysteresis time length corresponding to the reference historical purification; finally, the mean value of the reference hysteresis time lengths corresponding to all reference historical purifications is taken as the change hysteresis time length of the pressure data relative to the material viscosity data. The cross-correlation function is a known content and will not be described in detail;

[0088] The time point after the current time and at a distance of the change hysteresis time length is taken as the initial second future time, that is, , wherein s represents the current time, , and the change hysteresis time length; the time period formed by the initial second future time as the starting point and the time length of the specified time period is taken as the second predicted time period of the current purification, that is, ; wherein S is the length of the specified time period; the time points in the second prediction time period are all taken as second future time points; wherein one second future time point corresponds to one first future time point, and the interval length between each second future time point and the first future time point corresponding thereto is ; the time points corresponding to each first future time point in each reference historical purification are all taken as first historical reference time points; wherein each first future time point and the first historical reference time point corresponding thereto are the same distance from the corresponding degassing initial time point; the time points corresponding to each second future time point in each reference historical purification are all taken as second historical reference time points; wherein each second future time point and the second historical reference time point corresponding thereto are the same distance from the corresponding degassing initial time point; and it can be further inferred that each first historical reference time point corresponds to a second historical reference time point, and the length of time between the first historical reference time point and the corresponding second historical reference time point is also the change lag length ;

[0089] The material viscosity data and the vacuum valve position set value at each first historical reference time point in the reference historical purification, and the initial material weight data of the reference historical purification are taken as independent variables; the pressure data at the second historical reference time point corresponding to each first historical reference time point in the reference historical purification is taken as the dependent variable; a set of stable reference regression coefficients is obtained by using the least square method for multiple linear regression analysis: ; wherein is a basic pressure compensation term, which is the initial pressure data of the reaction kettle without material and without air extraction; is a material viscosity coefficient, which represents the influence weight of the material viscosity data on the predicted pressure data; is a valve position control coefficient, which represents the influence weight of the vacuum valve position on the predicted pressure data; is a material weight coefficient, which represents the influence weight of the initial material weight data on the predicted pressure data;

[0090] and further determines the trained regression equation: ; wherein is the predicted pressure data at the tth time point; is the change lag length; is the material viscosity data at the tth time point; is the vacuum valve position set value at the tth time point; and B is the initial material weight data;

[0091] ​Finally, the predicted material viscosity data and vacuum valve position setting value at each first future time and the initial material weight data of the current purification are input into the trained regression equation to obtain the predicted pressure data at the corresponding second future time. The vacuum valve position setting value at each first future time is set in advance and can be directly called.

[0092] It should be noted that for the predicted pressure data at each time within the time period constituted by the current time and the initial second future time, the corresponding regression equation at this time can be obtained according to the real material viscosity data obtained at the corresponding time before the current time of the current purification by the above method of obtaining the regression equation, and then the predicted pressure data at each time within the time period constituted by the current time and the initial second future time is obtained. The time length between each time within the time period constituted by the current time and the initial second future time and the corresponding time before it is the change lag time.

[0093] At this point, the predicted pressure data at the future time of the current purification is obtained.

[0094] Step S5: based on the predicted material viscosity data and the predicted pressure data, the predicted temperature data at the future time of the current purification is obtained through the temperature prediction model.

[0095] Specifically, in order to accurately obtain the predicted temperature data at the future time and timely and accurately regulate the temperature data in the reaction kettle, the embodiment obtains the predicted temperature data at the future time of the current purification through the temperature prediction model based on the predicted material viscosity data and the predicted pressure data, that is, the predicted material viscosity data and the predicted pressure data in the predicted reference time period are sequentially input into the trained temperature prediction model, and the predicted temperature data at each future time in the reference time period is output, which clearly reflects the future evolution trend of the temperature data in the reaction kettle without intervention. The length of the reference time period in the embodiment is set to 5 minutes, and the implementer can set the length of the reference time period according to the actual situation, which is not limited herein, but the initial time of the reference time period must be the current time.

[0096] The temperature prediction model is a multi-layer feedforward neural network with ReLU activation function, including an input layer, a hidden layer and an output layer. The input layer contains two nodes, which respectively receive the normalized predicted material viscosity data and predicted pressure data; the hidden layer can be set to one or more layers, each layer contains a plurality of neurons, and ReLU activation function is used to introduce nonlinear transformation, so that the model can learn and express the complex coupling relationship between the material viscosity data, pressure data and temperature data; the output layer is a single neuron, which uses a linear activation function to directly output the predicted temperature data, which is suitable for regression prediction tasks. The loss function of the temperature prediction model is mean square error, so that the mean square error between the temperature data predicted by the neural network and the actual temperature data recorded in the historical database is minimized. The multi-layer feedforward neural network with ReLU activation function, linear activation function and mean square error are all known contents, and will not be described in detail.

[0097] In the training process of the temperature prediction model, a large amount of "aligned" material viscosity data-pressure data-temperature data collected in the historical purification process are used as the training set, and all weight parameters and bias terms in the network are optimized through the back propagation algorithm until the model converges, i.e. the loss function decreases to a stable interval and there is no overfitting. The back propagation algorithm is a known content and will not be described in detail.

[0098] Step S6: controlling the temperature of the reaction kettle in the current purification process based on the predicted temperature data.

[0099] Specifically, based on the predicted temperature data, potential temperature control problems in the reaction kettle can be identified in advance, and then the temperature of the reaction kettle in the current purification process is controlled based on the predicted temperature data, effectively improving the quality of polypropylene purification.

[0100] When the predicted temperature data indicates that the future temperature will exceed the preset upper temperature limit, it indicates that the exothermic reaction intensity in the reaction kettle may exceed the heat dissipation or suppression capacity of the current control system, at which time the heating power of the reaction kettle needs to be reduced in advance to guide the temperature rise momentum; when the predicted temperature data indicates that the future temperature will be lower than the preset lower temperature limit, it may indicate that the heating system efficiency is declining, at which time the heating power of the reaction kettle needs to be increased in advance to actively make up for the expected heat gap; the preset upper temperature limit and the preset lower temperature limit in the embodiment are set by professionals according to the actual situation, which is not limited here.

[0101] By controlling the temperature of the reaction kettle in the current purification process based on the predicted temperature data, a leap from post-correction to pre-prevention is effectively realized, so that control intervention can be completed before the measurable temperature deviation actually occurs; effectively avoiding the quality problems such as overheating degradation or incomplete condensation of the product, while significantly improving the stability, accuracy and product consistency of the temperature control in the entire polypropylene purification process.

[0102] In summary, the embodiment obtains state data of a polypropylene purification process reactor; obtains a degassing initial time based on changes in temperature data of each purification; obtains a reference historical purification of the current purification based on similar conditions of the state data; obtains predicted material viscosity data according to changes in material viscosity data of the reference historical purification within a specified time period after the degassing initial time, material viscosity data of the current purification at the current time, and obtains predicted pressure data in combination with a lag condition of changes in material viscosity data and pressure data in the reference historical purification; and controls the temperature of the current purification reactor based on the predicted material viscosity data and the predicted pressure data. The present application accurately obtains predicted temperature data, which is conducive to early control of the temperature of the reactor, and effectively reduces the hysteresis and inaccuracy of temperature control.

[0103] Embodiment 2:

[0104] The present application also provides a polypropylene purification reactor temperature control system, please refer to Figure 2 , which shows a structure diagram of a polypropylene purification reactor temperature control system provided by an embodiment of the present application. The system comprises a data acquisition module 10, a reference historical purification acquisition module 20, a predicted material viscosity data acquisition module 30, a predicted pressure data acquisition module 40, a predicted temperature data acquisition module 50, and a temperature control module 60.

[0105] The data acquisition module 10 is used to acquire state data in the polypropylene purification process reactor in real time; the state data includes temperature data, pressure data and material viscosity data;

[0106] The reference historical purification acquisition module 20 is used to obtain the degassing initial time of each purification based on the change condition of the temperature data of each purification; and obtain the reference historical purification of the current purification according to the similar conditions of the state data at the degassing initial time of the current purification and historical purification, and the similar conditions of the initial material weight;

[0107] The predicted material viscosity data acquisition module 30 is used to obtain predicted material viscosity data at a future time of the current purification according to the change condition of the material viscosity data within a specified time period after the degassing initial time of each reference historical purification, and the material viscosity data at the current time of the current purification;

[0108] The predicted pressure data acquisition module 40 is used to obtain predicted pressure data at a future time of the current purification based on the predicted material viscosity data, and the lag condition of changes in material viscosity data and pressure data in the reference historical purification;

[0109] The prediction temperature data acquisition module 50 is configured to acquire, based on the predicted material viscosity data and the predicted pressure data, prediction temperature data of a future time point of the current purification process by using a temperature prediction model.

[0110] The temperature control module 60 is configured to control the temperature of the reaction kettle in the current purification process based on the prediction temperature data.

[0111] It should be noted that the system provided in the above embodiment is only used as an example for the division of the above functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the above described functions. In addition, the reaction kettle temperature control system for polypropylene purification and the reaction kettle temperature control method for polypropylene purification provided in the above embodiment belong to the same concept, and the specific implementation process is described in the method embodiment, which will not be repeated here.

[0112] Embodiment 3:

[0113] The application further provides a reaction kettle temperature control device for polypropylene purification, which comprises a memory and a processor, wherein the memory stores executable program codes, and the processor is configured to call and execute the executable program codes to execute the reaction kettle temperature control method for polypropylene purification provided in the embodiments. The device can be a chip, an assembly or a module, and the chip can comprise a processor and a memory connected thereto. The memory is configured to store instructions, and when the processor calls and executes the instructions, the chip can execute the reaction kettle temperature control method for polypropylene purification provided in the above embodiments.

[0114] In addition, the embodiments of the present application also protect a computer device, please refer to Figure 3 The computer device comprises a memory 401, a processor 402 and a computer program 403 stored in the memory 401 and running on the processor 402, wherein when the processor 402 executes the computer program 403, the computer device can execute any of the above-mentioned reaction kettle temperature control methods for polypropylene purification.

[0115] Embodiment 4:

[0116] The embodiments also provide a computer readable storage medium, which stores computer program codes, and when the computer program codes run on a computer, the computer executes the above-mentioned related method steps to implement the reaction kettle temperature control method for polypropylene purification provided in the above embodiments.

[0117] Embodiment 5:

[0118] The embodiment also provides a computer program product, which, when running on a computer, enables the computer to execute the above related steps to realize the polypropylene purification reaction kettle temperature control method provided by the above embodiment.

[0119] Wherein, the device, computer readable storage medium, computer program product or chip provided by the embodiment are used to execute the corresponding method provided above, thus the beneficial effects achieved thereby can refer to the beneficial effects in the corresponding method provided above, which will not be described here again.

[0120] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0121] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments.

Claims

1. A method for controlling the temperature of a reactor for purifying polypropylene, characterized by, The method comprises the following steps: Real-time acquisition of state data in a polypropylene purification process reactor; the state data comprises temperature data, pressure data and material viscosity data; Based on the change of the temperature data of each purification, the initial degassing time of each purification is obtained; based on the similarity of the state data at the initial degassing time of the current purification and the historical purification, and the similarity of the initial material weight, the reference historical purification of the current purification is obtained; Based on the change of the material viscosity data of each reference historical purification within a specified time period after the initial degassing time, and the material viscosity data at the current time of the current purification, the predicted material viscosity data at the future time of the current purification is obtained; Based on the predicted material viscosity data, and the lag of the change of the material viscosity data and the change of the pressure data in the reference historical purification, the predicted pressure data at the future time of the current purification is obtained; The method for obtaining the predicted pressure data is: based on the lag of the change of the material viscosity data and the change of the pressure data in the reference historical purification, the change lag length of the pressure data relative to the material viscosity data is obtained; Based on the predicted material viscosity data and the predicted pressure data, the predicted temperature data at the future time of the current purification is obtained through a temperature prediction model; Based on the predicted temperature data, the temperature of the reactor in the current purification process is controlled; The method for obtaining the change lag length is: For any reference historical purification, the material viscosity data of the reference historical purification is arranged in time sequence to obtain a viscosity data sequence; The pressure data of the reference historical purification is arranged in time sequence to obtain a pressure data sequence; The cross-correlation function of the viscosity data sequence and the pressure data sequence is calculated, and the time shift amount that makes the cross-correlation function reach the maximum value is taken as the reference lag length corresponding to the reference historical purification; The mean value of the reference lag lengths corresponding to all reference historical purifications is taken as the change lag length of the pressure data relative to the material viscosity data.

2. The method for controlling the temperature of a reactor for purifying polypropylene according to claim 1, wherein The method for obtaining the initial degassing time is: For any time of any purification, the difference between the standard deviations of the temperature data of the purification in a first preset time period and a second preset time period is taken as the degassing reference value of the time; the first preset time period and the second preset time period have the same length, and the end time of the first preset time period is the time, and the start time of the second preset time period is the time; The degassing reference value of each time of the purification is obtained, and the time corresponding to the maximum degassing reference value is taken as the initial degassing time of the purification.

3. The method of claim 1, wherein the temperature of the reactor is controlled by a temperature controller. The method for obtaining the reference historical purification is: For any historical purification and any state data, the difference between the state data of the current purification and the state data of the historical purification at the initial degassing time is normalized to obtain the first difference of the state data; The difference between the initial material weight data of the current purification and the initial material weight data of the historical purification is normalized to obtain the initial weight difference; The sum of the first differences of all state data and the initial weight difference is negatively correlated and normalized to obtain the similarity degree of the current purification and the historical purification. When the similarity degree is greater than the preset similarity degree threshold, the corresponding historical purification is a reference historical purification for the current purification.

4. The method for controlling the temperature of a reactor for purifying polypropylene according to claim 1, wherein The method for obtaining the predicted material viscosity data is: According to the unit change of the material viscosity data of each reference historical purification in a specified time period after the initial degassing time point of the reference historical purification, a reference unit viscosity change value at the current time point of the current purification is obtained; the current time point is after the initial degassing time point of the current purification, and the initial time point of the specified time period and the current time point are both equal in length to the corresponding initial degassing time point; A time period formed by taking the current time point as the starting point and the length of the specified time period as the length of the time period is taken as a first prediction time period of the current purification; Each time point in the first prediction time period is taken as a first future time point; For any first future time point, the length of the first future time point from the current time point is taken as a first length; The product of the reference unit viscosity change value and the first length is taken as a viscosity reference change value; The addition result of the material viscosity data at the current time point of the current purification and the viscosity reference change value is taken as the predicted material viscosity data at the first future time point.

5. The method of claim 4, wherein the temperature of the reactor is controlled by the temperature of the cooling water. The method for obtaining the reference unit viscosity change value is: For any reference historical purification, the difference between the material viscosity data at each time point in the specified time period of the reference historical purification and the material viscosity data at the previous adjacent time point is taken as a second difference; The average of the ratio of all second differences to the length of the corresponding time point is taken as the unit viscosity change rate of the specified time period of the reference historical purification; The average of the unit viscosity change rates of the specified time periods of all reference historical purifications is taken as the reference unit viscosity change value at the current time point of the current purification.

6. The method of claim 4, wherein the temperature of the reactor is controlled by a temperature controller. The method for obtaining the predicted pressure data further includes: A time point after the current time point and having a length of a change lag length is taken as an initial second future time point; A time period formed by taking the initial second future time point as the starting point and the length of the specified time period as the length of the time period is taken as a second prediction time period of the current purification; each time point in the second prediction time period is taken as a second future time point; wherein one second future time point corresponds to one first future time point, and the interval length between each second future time point and the corresponding first future time point is the change lag length; The time point corresponding to each first future time point in each reference historical purification is taken as a first historical reference time point; wherein each first future time point and the corresponding first historical reference time point are the same in length from the corresponding initial degassing time point; The time point corresponding to each second future time point in each reference historical purification is taken as a second historical reference time point; wherein each second future time point and the corresponding second historical reference time point are the same in length from the corresponding initial degassing time point; The material viscosity data and the vacuum valve position setting value at each first historical reference time in the reference historical purification, and the initial material weight data of the reference historical purification are taken as independent variables; the pressure data at the second historical reference time corresponding to each first historical reference time in the reference historical purification is taken as dependent variable; a set of stable reference regression coefficients is obtained by using the least square method for multiple linear regression analysis: ; wherein, is a basic pressure compensation term, which is the initial pressure data of the reaction kettle without material and without pumping; is a material viscosity coefficient, which represents the influence weight of the material viscosity data on the predicted pressure data; is a valve position control coefficient, which represents the influence weight of the vacuum valve position on the predicted pressure data; is a material weight coefficient, which represents the influence weight of the initial material weight data on the predicted pressure data; Further determine the trained regression equation: ; in the formula, is the first The predicted pressure data at the corresponding moment; is the change lag length; is the material viscosity data at the tthmoment; is the vacuum valve position set value at the tthmoment; B is the initial material weight data; The predicted material viscosity data at each first future time point and the vacuum valve position setting value, and the initial material weight data of the current purification are input into the trained regression equation to obtain the predicted pressure data at the corresponding second future time point.

7. The method of claim 1, wherein the temperature of the reactor is controlled by a temperature controller. The method for obtaining the predicted temperature data is: The predicted material viscosity data and the predicted pressure data in the reference time period are sequentially input into the trained temperature prediction model, and predicted temperature data at each future time in the reference time period is output.

8. The method of claim 1, wherein the temperature of the reactor is controlled by a temperature controller. 5 The method for controlling the temperature of the reaction kettle in the current purification process is: When the predicted temperature data indicates that the future temperature will exceed the preset upper temperature limit, the heating power of the reaction kettle is reduced in advance; When the predicted temperature data indicates that the future temperature will be lower than the preset lower temperature limit, the heating power of the reaction kettle is increased in advance.

9. The method of claim 7, wherein the temperature of the reactor is controlled by a temperature controller. The temperature prediction model is a multi-layer feedforward neural network with a ReLU activation function, which is trained by minimizing the mean square error between the predicted temperature and the actual temperature.

Images