Production process and circulating flow rate cooperative control method of high molecular weight bisphenol A polycarbonate polyether polyol

Abstract

The invention relates to the technical field of chemistry and chemical engineering, and particularly discloses a high-molecular-weight bisphenol A type polycarbonate polyether polyol production process and a circulating flow rate cooperative control method, raw materials are premixed and then fed into a reaction pipeline at one time, gas-liquid circulation in opposite directions is performed in the reaction pipeline, and the high-molecular-weight bisphenol A type polycarbonate polyether polyol is obtained. Meanwhile, an intelligent industrial control technology is adopted for conducting time sequence collaborative analysis on the liquid circulation flow speed and the gas circulation flow speed, then characteristic screening optimization is conducted on gas-liquid circulation flow speed time sequence collaborative correlation characteristics based on the time sequence correlation change rule of the liquid circulation flow speed, and the optimal collaborative matching relation between the gas-liquid circulation flow speeds is captured; therefore, the self-adaptive adjustment of the liquid circulation flow velocity is carried out. Through the mode, cooperative work of the liquid circulating pump and the gas circulating pump can be realized, so that heat is conveniently dispersed in time, the temperature uniformity of a reaction system is maintained, and the problem that the reaction time is prolonged due to yellowing of a product caused by overhigh local temperature is avoided.

Description

Technical Field

[0001] The present application relates to the field of chemical engineering technology, and more specifically, to a production process of high molecular weight bisphenol A type polycarbonate polyether polyol and a method for coordinated control of circulation flow rate. Background Art

[0002] Polycarbonate polyether polyols are a type of polyols with carbonate groups in the molecule and hydroxyl groups at the ends of the molecular chain, which can be obtained by copolymerization of carbon dioxide and epoxy compounds. Carbon dioxide, as one of the raw materials, is cheap and easy to obtain, non-toxic and non-flammable, has a clear carbon dioxide chemical fixation effect, and requires low temperature and low energy consumption during the reaction, making the carbon dioxide and epoxy compound regulation copolymerization method have broad application prospects and high industrial value.

[0003] High molecular weight bisphenol A type polycarbonate polyether polyol is a polycarbonate polyether polyol with a molecular weight greater than 3000 synthesized by using bisphenol A as a small molecule initiator. The process of synthesizing polycarbonate polyether polyol is mainly synthesized by using carbon dioxide and epoxy compounds through a bimetallic complex (abbreviated as DMC) catalyst. The reaction of polycarbonate polyether polyol catalyzed by DMC has the characteristics of temperature fluctuation. Specifically, the DMC catalytic process includes an induction activation period and a segment growth period. Before the polyether chain growth reaction stage, it is necessary to go through the induction activation stage. During the induction activation period, the epoxy compound activates DMC to produce a large number of active centers. Because the epoxy compound releases a lot of heat during polymerization, it is necessary to pay attention to the temperature peak and control the initial activation temperature to avoid overheating, thereby affecting the pressure resistance of the equipment and the activity of the catalyst. During the segment growth period, after DMC is fully activated, the active center combines with the initiator, the epoxy compound inserts the polymerization, and the initiator undergoes a replacement reaction with the active structure of DMC and the epoxy compound. This stage requires external heat to promote chain growth.

[0004] At present, in the process of synthesizing bisphenol A polycarbonate polyether polyol, on the one hand, the DMC activation catalytic process has two different thermal characteristics, and the drastic temperature fluctuation has a negative impact on the synthesis of bisphenol A polycarbonate polyether polyol, causing the initiator decomposition products to turn yellow, affecting the product quality; on the other hand, in order to solve the problem of drastic temperature fluctuations in the polymerization reaction and the problem of reduced carbonate chain segments in the synthesis of high molecular weight bisphenol A polycarbonate polyether polyol, the process adopted in the prior art is to add the reactants in batches, thereby reducing the concentrated release of heat in the polymerization process, which reduces the efficiency of the production process.

[0005] In addition, in polymerization reactions, the circulation of materials in the reactor has an important influence on temperature distribution, CO2 solubility and overall reaction efficiency. However, in traditional processes, the material circulation flow rate is mainly regulated based on manual experience, which is not only prone to untimely and inaccurate regulation, but also difficult to cope with dynamically changing reaction environments and process conditions, thus affecting product quality and production efficiency.

[0006] Therefore, an optimized production process and a method for coordinated control of circulation flow rate of high molecular weight bisphenol A polycarbonate polyether polyol are desired. Summary of the invention

[0007] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a novel production process and a circulation flow rate coordinated control method for high molecular weight bisphenol A type polycarbonate polyether polyol, which premixes the raw materials and feeds them into the reaction pipe at one time, performs gas-liquid circulation in opposite directions in the reaction pipe, and uses intelligent industrial control technology to perform time-series coordinated analysis on the liquid circulation flow rate and the gas circulation flow rate, digs out the time-series coordinated correlation mode between the two, and then based on the time-series correlation change law of the liquid circulation flow rate itself, the gas-liquid circulation flow rate timing coordinated correlation characteristics are screened and optimized, and the best coordinated matching relationship between the gas-liquid circulation flow rates is captured, so as to perform adaptive adjustment of the liquid circulation flow rate. In this way, the coordinated work of the liquid circulation pump and the gas circulation pump can be achieved, so as to disperse the heat in time, maintain the temperature uniformity of the reaction system, and avoid the yellowing problem of the product caused by local temperature overheating.

[0008] Accordingly, according to one aspect of the present application, a production process of high molecular weight bisphenol A type polycarbonate polyether polyol is provided, and the production process of high molecular weight bisphenol A type polycarbonate polyether polyol is carried out in a tube-in-tube reaction device, the reaction device comprises a premixing unit and a reaction zone, the reaction zone comprises a reaction pipeline, a liquid circulation pump and a gas circulation pump, a heating jacket is provided on the outside of the reaction pipeline, the liquid circulation pump and the gas circulation pump are both connected to the reaction pipeline, the liquid circulation pump is used to make the material in the reaction pipeline circulate in the reaction pipeline along a first direction, and the gas circulation pump is used to make the gas in the reaction pipeline circulate in the reaction pipeline along a second direction, wherein the first direction and the second direction are opposite directions; the production process comprises: a premixing step: after mixing the epoxy compound, CO2, bisphenol A and the catalyst in the premixing unit, a premix is ​​obtained; a feeding step: the premix is ​​fed into the reaction zone at one time; a CO2 pressure maintaining step: after the feeding is completed, CO2 is introduced into the reaction zone, and the pressure of the introduced CO2 is 3~4MPa; Reaction step: start the liquid circulation pump and the gas circulation pump, adjust the temperature of the medium in the heating jacket to heat the reaction pipeline to 75°C~85°C; after the heating is completed, monitor the temperature in the reaction pipeline, and maintain the temperature of the reaction pipeline at 75°C~85°C by adjusting the temperature of the medium in the heating jacket; wherein, the reaction step also includes: obtaining the time queue of the circulation flow rate of the liquid circulation pump and the time queue of the circulation flow rate of the gas circulation pump; extracting the timing coordination mode characteristics of the time queue of the circulation flow rate of the gas circulation pump and the time queue of the circulation flow rate of the liquid circulation pump to obtain a liquid-gas circulation flow rate timing coordination feature diagram; based on the timing correlation characteristics of the circulation flow rate of the liquid circulation pump, the liquid-gas circulation flow rate timing coordination feature diagram is coordinated modulated and optimized to obtain a liquid circulation flow rate coordinated modulation vector; based on the liquid circulation flow rate coordinated modulation vector, determine the circulation flow rate adjustment strategy of the liquid circulation pump, the adjustment strategy is used to indicate that the circulation flow rate of the liquid circulation pump at the next time point should increase, decrease or remain unchanged.

[0009] In the production process of the above-mentioned high molecular weight bisphenol A polycarbonate polyether polyol, the timing coordination pattern characteristics of the time queue of the circulation flow rate of the gas circulation pump and the time queue of the circulation flow rate of the liquid circulation pump are extracted to obtain a liquid-gas circulation flow rate timing coordination feature diagram, including: performing full timing circulation flow rate association on the time queue of the circulation flow rate of the gas circulation pump and the time queue of the circulation flow rate of the liquid circulation pump to obtain a liquid-gas circulation flow rate timing association matrix; inputting the liquid-gas circulation flow rate timing association matrix into a liquid-gas circulation flow rate timing coordination pattern feature extractor based on a void convolutional neural network model to obtain the liquid-gas circulation flow rate timing coordination feature diagram.

[0010] In the production process of the above-mentioned high molecular weight bisphenol A polycarbonate polyether polyol, based on the timing correlation characteristics of the circulation flow rate of the liquid circulation pump, the liquid-gas circulation flow rate timing collaborative characteristic diagram is collaboratively modulated and optimized to obtain the liquid circulation flow rate collaborative modulation vector, including: extracting the liquid circulation flow rate timing correlation characteristic vector from the time queue of the circulation flow rate of the liquid circulation pump; inputting the liquid circulation flow rate timing correlation characteristic vector and the liquid-gas circulation flow rate timing collaborative characteristic diagram into a collaborative optimization analysis module to obtain the liquid circulation flow rate collaborative modulation vector.

[0011] In the production process of the above-mentioned high molecular weight bisphenol A polycarbonate polyether polyol, a liquid circulation flow rate time series correlation feature vector is extracted from the time queue of the circulation flow rate of the liquid circulation pump, including: inputting the time queue of the circulation flow rate of the liquid circulation pump into a time series feature extractor based on a one-dimensional convolutional neural network model to obtain the liquid circulation flow rate time series correlation feature vector.

[0012] In the production process of the high molecular weight bisphenol A polycarbonate polyether polyol, the liquid circulation flow rate timing correlation feature vector and the liquid-gas circulation flow rate timing synergistic feature map are input into a synergistic optimization analysis module to obtain the liquid circulation flow rate synergistic modulation vector, including: performing a linear transformation on the liquid circulation flow rate timing correlation feature vector based on a first weight modifier matrix and a second weight modifier matrix to obtain a first liquid circulation flow rate timing correlation feature mapping pattern representation vector and a second liquid circulation flow rate timing correlation feature mapping pattern representation vector; based on the gradient amplitude of each position in the first liquid circulation flow rate timing correlation feature mapping pattern representation vector, performing a masking process on the first liquid circulation flow rate timing correlation feature mapping pattern representation vector based on the gradient amplitude to obtain a masked first liquid circulation flow rate timing correlation feature mapping pattern representation vector. formula representation vector; based on the gradient amplitude of each position in the second liquid circulation flow rate timing association feature mapping pattern representation vector, the second liquid circulation flow rate timing association feature mapping pattern representation vector is subjected to gradient amplitude-based masking processing to obtain a masked second liquid circulation flow rate timing association feature mapping pattern representation vector; based on the masked first liquid circulation flow rate timing association feature mapping pattern representation vector and the hyperbolic tangent function, the liquid-gas circulation flow rate timing collaborative feature map is subjected to preliminary feature screening to obtain a preliminary screened liquid-gas circulation flow rate timing collaborative feature map; based on the masked second liquid circulation flow rate timing association feature mapping pattern representation vector and the Sigmoid function, the preliminary screened liquid-gas circulation flow rate timing collaborative feature map is subjected to feature screening again to obtain the liquid circulation flow rate collaborative modulation vector.

[0013] In the above-mentioned production process of high molecular weight bisphenol A type polycarbonate polyether polyol, based on the gradient amplitude of each position in the first liquid circulation flow rate timing correlation feature mapping pattern representation vector, the first liquid circulation flow rate timing correlation feature mapping pattern representation vector is subjected to gradient amplitude-based masking processing to obtain a masked first liquid circulation flow rate timing correlation feature mapping pattern representation vector, including: for each position in the first liquid circulation flow rate timing correlation feature mapping pattern representation vector, the absolute value of the difference between the eigenvalue of the previous position and the eigenvalue of the next position adjacent to it is calculated to obtain the gradient amplitude of each position in the first liquid circulation flow rate timing correlation feature mapping pattern representation vector; the gradient amplitude of each position in the first liquid circulation flow rate timing correlation feature mapping pattern representation vector is compared with a preset mask threshold, and the position greater than the preset mask threshold is marked as 1, and the position less than or equal to the preset mask threshold is marked as 0, so as to obtain the masked first liquid circulation flow rate timing correlation feature mapping pattern representation vector.

[0014] In the production process of the above-mentioned high molecular weight bisphenol A polycarbonate polyether polyol, the liquid-gas circulation flow rate timing series collaborative feature map after the preliminary screening is subjected to a second feature screening based on the masked second liquid circulation flow rate timing association feature mapping pattern representation vector and the Sigmoid function to obtain the liquid circulation flow rate collaborative modulation vector, including: using the eigenvalues ​​of each position in the masked second liquid circulation flow rate timing association feature mapping pattern representation vector as weights, weighting each channel feature matrix of the liquid-gas circulation flow rate timing series collaborative feature map after the preliminary screening to obtain the screened liquid-gas circulation flow rate timing collaborative feature map; activating the screened liquid-gas circulation flow rate timing series collaborative feature map through a Sigmoid function and then performing global pooling along the channel dimension to obtain the liquid circulation flow rate collaborative modulation vector.

[0015] In the production process of the above-mentioned high molecular weight bisphenol A polycarbonate polyether polyol, based on the liquid circulation flow rate cooperative modulation vector, the adjustment strategy of the circulation flow rate of the liquid circulation pump is determined, and the adjustment strategy is used to indicate whether the circulation flow rate of the liquid circulation pump at the next time point should increase, decrease or remain unchanged, including: inputting the liquid circulation flow rate cooperative modulation vector into a liquid circulation flow rate control module based on a classifier to obtain the adjustment strategy.

[0016] In the above-mentioned production process of high molecular weight bisphenol A polycarbonate polyether polyol, the reaction zone is provided with a plurality of reaction pipes arranged in parallel, each of the reaction pipes is provided with the gas circulation pump to realize gas circulation in the reaction pipe; the feed ends of the plurality of reaction pipes are converged to the liquid distributor through connecting pipes, and the discharge ends of the plurality of reaction pipes are converged to the liquid circulation pump through connecting pipes, and the liquid circulation pump is connected to the liquid distributor through connecting pipes; the number of the reaction pipes is 2 to 20.

[0017] According to another aspect of the present application, a method for coordinated control of circulation flow rates is provided, which includes: obtaining a time queue of the circulation flow rate of a liquid circulation pump and a time queue of the circulation flow rate of a gas circulation pump; extracting the timing coordinated mode characteristics of the time queue of the circulation flow rate of the gas circulation pump and the time queue of the circulation flow rate of the liquid circulation pump to obtain a liquid-gas circulation flow rate timing coordinated characteristic diagram; based on the timing correlation characteristics of the circulation flow rate of the liquid circulation pump, performing coordinated modulation optimization on the liquid-gas circulation flow rate timing coordinated characteristic diagram to obtain a liquid circulation flow rate coordinated modulation vector; based on the liquid circulation flow rate coordinated modulation vector, determining an adjustment strategy for the circulation flow rate of the liquid circulation pump, the adjustment strategy being used to indicate whether the circulation flow rate of the liquid circulation pump at the next time point should increase, decrease or remain unchanged.

[0018] Compared with the prior art, the production process and the circulation flow rate coordinated control method of the high molecular weight bisphenol A type polycarbonate polyether polyol described in the present application are that the raw materials are pre-mixed and then fed into the reaction pipeline at one time, and gas-liquid circulation in opposite directions is performed in the reaction pipeline, and intelligent industrial control technology is used to perform time-series coordinated analysis on the liquid circulation flow rate and the gas circulation flow rate, and the time-series coordinated correlation mode between the two is excavated, and then the gas-liquid circulation flow rate time-series coordinated correlation characteristics are screened and optimized based on the time-series correlation change law of the liquid circulation flow rate itself, and the best coordinated matching relationship between the gas-liquid circulation flow rates is captured, so as to perform adaptive adjustment of the liquid circulation flow rate. In this way, the coordinated work of the liquid circulation pump and the gas circulation pump can be achieved, so as to disperse the heat in time, maintain the temperature uniformity of the reaction system, and avoid the problem of yellowing of the product caused by local temperature overheating. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0020] Figure 1 This is an overall schematic diagram of a tube-in-tube reaction device for producing high molecular weight bisphenol A polycarbonate polyether polyols according to an embodiment of the present application, wherein the black arrow represents the flow direction of the raw material mixture, the green arrow represents the gas circulation direction, the pink arrow represents the circulation direction of the raw material and product mixture, and the red arrow represents the product flow direction.

[0021] Figure 2 The flowchart is a production process of high molecular weight bisphenol A polycarbonate polyether polyol according to an embodiment of the present application.

[0022] Figure 3 The flowchart is a reaction step in the production process of high molecular weight bisphenol A polycarbonate polyether polyol according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0024] The present application proposes a production process of a high molecular weight bisphenol A type polycarbonate polyether polyol. Specifically, the high molecular weight bisphenol A type polycarbonate polyether polyol is synthesized by using bisphenol A as an initiator, propylene oxide and CO2 under the action of a DMC catalyst, and the molecular weight of the product is greater than 3000. Among them, the small molecule initiator containing an active H-functional group is added to the reaction system to obtain a polycarbonate polyether polyol with a molecular weight of several thousand, so that the polymer structure contains both polycarbonate chain segments and polyether chain segments generated by homopolymerization of epoxy compounds, and has high Young's modulus and flexibility. The initiator usually participates in the initial stage of the polymerization reaction to generate active centers, such as free radicals, cations or anions, which further promote the connection of monomer molecules to form polymer chains. In some polymerization reactions, a portion of the initiator (for example, the free radical portion in the free radical initiator) may be integrated into the end of the polymer chain. Ideally, the initiator will be completely consumed during the reaction without significant residue. However, in actual applications, a small amount of initiator may remain in the final product. When bisphenol A is exposed to a temperature higher than 80°C for a long time, it is easy to generate small molecular substances dimethyl phthalate, which not only cannot form a reactive active center, but also will remain and make the product yellow. Therefore, during the synthesis process in the reaction zone, the local uniformity of the temperature field in the reactor needs to be strictly controlled to prevent explosion and local high temperature from occurring, so as to reduce the decomposition of bisphenol A into small molecular substances.

[0025] Based on this, the present application proposes a production process for high molecular weight bisphenol A type polycarbonate polyether polyol, which is carried out in a tube-in-tube reaction device. Figure 1 Schematic diagram of the overall structure of the tube-in-tube reaction device for producing high molecular weight bisphenol A type polycarbonate polyether polyol according to the embodiment of the present application. Figure 1 As shown, the reaction device includes a reaction pipeline 101, a liquid distributor 102, a liquid circulation pump 103, and a gas circulation pump 104. The raw materials are premixed in the premixing unit, and are introduced into the reaction device after the premixing is completed. After the feeding is completed, the materials are liquid circulated, and the CO2 gas is gas circulated. The liquid circulation pump 103 and the gas circulation pump 104 are both connected to the reaction pipeline 101. The liquid circulation pump 103 is used to circulate the materials in the reaction pipeline 101 in the first direction in the reaction pipeline 101, and the gas circulation pump 104 is used to circulate the gas in the reaction pipeline 101 in the second direction in the reaction pipeline 101, wherein the first direction and the second direction are opposite directions. Preferably, the number of the reaction pipelines 101 is 2 to 20.

[0026] Further preferably, the reaction pipe 101 is provided with an upper dispersion sheet and a lower dispersion sheet from top to bottom, and the upper dispersion sheet, the lower dispersion sheet, the gas circulation pump 104 and the liquid circulation pump 103 together constitute a gas-liquid mixed heat conduction system, so that the material and CO2 are subjected to mass and heat transfer, so that the mixed material with a low CO2 content in the reaction zone is redissolved in CO2, and heat is exchanged in the gas-liquid mixed heat conduction system at the same time, and the catalyst can be evenly dispersed, and the reaction heat in the reaction pipe can be dispersed, and the temperature difference between the center temperature in the reaction pipe and the pipe wall can be reduced to avoid the generation of an explosion point. Wherein, a static mixer or a dynamic mixer is provided in the reaction pipe 101. Preferably, in this embodiment, a static mixer is provided in the reaction pipe 101, and the static mixer can be, for example, a DSR static mixer, a Kenics mixer, etc., but is not limited thereto.

[0027] Further preferably, the first direction is the direction from the feed end to the discharge end of the reaction pipe 101, and the second direction is the direction from the discharge end to the feed end of the reaction pipe 101; the reaction mixture product flowing through the discharge end of the reaction pipe 101 is circulated to the feed end of the reaction pipe 101 via the liquid circulation pump 103.

[0028] Further preferably, a temperature sensor is provided inside the reaction pipe 101, and a density detector is provided at the outlet, and the jacket temperature is adjusted according to the material density and the temperature inside the reactor to control the reaction rate. Specifically, in one embodiment, the reaction pipe 101 is provided with at least three temperature sensors in the area where the material reacts, for example, temperature sensors are provided in the upper part, the middle part and the lower part, so as to more comprehensively monitor the temperature inside the reaction pipe 101.

[0029] Figure 2 Flow chart of the production process of high molecular weight bisphenol A type polycarbonate polyether polyol according to the embodiment of the present application. Figure 2 As shown, the production process of the high molecular weight bisphenol A type polycarbonate polyether polyol comprises the following steps: premixing step S1: after mixing the epoxy compound, CO2, bisphenol A and the catalyst in the premixing unit, a premix is ​​obtained; feeding step S2: the premix is ​​fed into the reaction zone at one time; CO2 pressure maintaining step S3: after the feeding is completed, CO2 is introduced into the reaction zone, and the pressure of the introduced CO2 is 3~4MPa; reaction step S4: start the liquid circulation pump and the gas circulation pump, adjust the temperature of the medium in the heating jacket, so as to heat the reaction pipe to 79℃~81℃; after the heating is completed, monitor the temperature in the reaction pipe, and maintain the temperature of the reaction pipe at 75℃~85℃ by adjusting the temperature of the medium in the heating jacket.

[0030] The following will be combined Figures 1 to 3The production process of the high molecular weight bisphenol A polycarbonate polyether polyol is described in detail.

[0031] Specifically, the premixing step S1: in the premixing unit, carbon dioxide is provided by a carbon dioxide storage tank and passed into the premixing unit, and the propylene oxide raw material enters the premixing unit in the carbon dioxide atmosphere through a metering pump. A fixed amount of bisphenol A and a catalyst are added to the premixing unit using a weighing bucket. Wherein, the catalyst is a DMC catalyst; the feed molar ratio of the epoxy compound and the bisphenol A is 60:1~100:1, and preferably, the feed molar ratio is 70:1. After the raw materials are mixed in the premixing unit, a premix is ​​obtained. Preferably, the temperature of the premixing unit is 0~40°C, the pressure is 0.1~2MPa, and the premixing time is 1~2h. More preferably, the premixing time is 1h.

[0032] Specifically, the feeding step S2: feed the premix into the reaction zone through the feed port at one time. When the raw materials enter the reaction pipe 101, the reaction unit is controlled to meet the following conditions: the temperature of the reaction pipe 101 is 35-45°C, and the CO2 pressure is 0.1-2MPa. More preferably, during the feeding process, the temperature is low to prevent the initiator from decomposing into small molecules.

[0033] Specifically, the CO2 pressure maintenance step S3: when the raw materials are completely fed in, the feeding is completed. Carbon dioxide is supplemented through the carbon dioxide gas inlet 105 to make the pressure in the reaction pipeline 101 3-4 MPa, and more preferably, the pressure value is 3 MPa. When the pressure is too low, carbon dioxide is introduced from the carbon dioxide gas inlet 105 to supplement the pressure. Specifically, the supplementation of CO2 in the reaction pipeline 101 is automatically controlled by a pressure regulating valve.

[0034] Specifically, the reaction step S4: start the liquid circulation pump 103 and the gas circulation pump 104, adjust the temperature of the medium in the jacket, so as to heat the reaction pipe 101 to 79-81°C (for example, to 80°C), and during the heating process of the reaction pipe 101, control the temperature difference between the medium temperature in the jacket and the temperature of the reaction pipe 101 to not exceed 5°C. Preferably, the temperature difference between the medium temperature in the jacket and the temperature of the reaction pipe 101 is controlled to be 5°C, and the temperature of the reaction pipe 101 is slowly increased until the temperature of the reaction pipe 101 reaches 79-81°C. More preferably, during the heating process, the temperature value of the temperature sensor installed in the middle of the reaction pipe 101 is used as the temperature of the reaction pipe 101.

[0035] After the temperature is raised to 79-81° C., the liquid circulation pump 103 and the gas circulation pump 104 are kept turned on, and the temperature in the reaction pipe 101 is monitored. When the temperature of the reaction pipe 101 increases or decreases, the temperature of the medium in the jacket is correspondingly reduced or increased, and the reduced or increased temperature of the jacket medium is roughly equal to the increased or decreased temperature of the reaction pipe 101, so that the material temperature is maintained at 79-81° C. Specifically, in the above process, when the temperature of any temperature sensor in the reaction pipe 101 increases, the temperature of the medium in the jacket is correspondingly reduced, so that the temperatures of the upper, middle and lower regions of the reaction pipe 101 are kept relatively constant.

[0036] Meanwhile, in the above-mentioned cyclic reaction process, the circulation flow rate of the liquid circulation pump and the gas circulation pump is one of the key factors affecting the solubility of CO2 gas in the material and the overall temperature uniformity in the reaction system. As the reaction proceeds, the viscosity and density of the material will gradually increase, thereby affecting the flow of the gas, causing the gas circulation flow rate to change. At this point, if the circulation flow rate of the liquid circulation pump is too fast or too slow relative to the circulation flow rate of the gas circulation pump, the solubility of CO2 gas in the reaction system will be uneven, which may cause local area heat accumulation and increase the risk of implosion. Therefore, in order to ensure that CO2 gas can be evenly dissolved in the reaction solution, so as to achieve efficient gas-liquid mass transfer and heat exchange, in the technical solution of the present application, the circulation flow rate of the liquid circulation pump and the circulation flow rate of the gas circulation pump are further coordinated and controlled. Specifically, the present application uses deep learning technology to perform time-series collaborative analysis on the circulation flow rate data of the liquid circulation pump and the gas circulation pump to explore the time-series collaborative correlation pattern between the liquid circulation flow rate and the gas circulation flow rate, and then screens and optimizes the gas-liquid circulation flow rate timing collaborative correlation characteristics based on the time-series correlation change law of the liquid circulation flow rate itself, so as to capture the best collaborative matching relationship between the liquid circulation flow rate and the gas circulation flow rate, and use this to adaptively adjust the circulation flow rate of the liquid circulation pump to make it compatible with the circulation flow rate of the gas circulation pump, thereby realizing the collaborative work of the liquid circulation pump and the gas circulation pump, so as to timely disperse heat and reactants and reduce the risk of explosion.

[0037] Figure 3 Flow chart of the reaction steps in the production process of high molecular weight bisphenol A polycarbonate polyether polyol according to the embodiment of the present application. Figure 3As shown, the reaction step S4 also includes: S410, obtaining the time queue of the circulation flow rate of the liquid circulation pump and the time queue of the circulation flow rate of the gas circulation pump; S420, extracting the timing coordination mode characteristics of the time queue of the circulation flow rate of the gas circulation pump and the time queue of the circulation flow rate of the liquid circulation pump to obtain a liquid-gas circulation flow rate timing coordination feature diagram; S430, based on the timing correlation characteristics of the circulation flow rate of the liquid circulation pump, performing coordinated modulation optimization on the liquid-gas circulation flow rate timing coordination feature diagram to obtain a liquid circulation flow rate coordinated modulation vector; S440, based on the liquid circulation flow rate coordinated modulation vector, determining an adjustment strategy for the circulation flow rate of the liquid circulation pump, the adjustment strategy being used to indicate whether the circulation flow rate of the liquid circulation pump at the next time point should increase, decrease or remain unchanged.

[0038] Specifically, after obtaining the time queue of the circulation flow rate of the liquid circulation pump and the time queue of the circulation flow rate of the gas circulation pump through the step S410, in order to fully understand the correlation and influence between the liquid circulation flow rate and the gas circulation flow rate, first, the time queue of the circulation flow rate of the gas circulation pump and the time queue of the circulation flow rate of the liquid circulation pump are subjected to a timing coordination mode analysis.

[0039] In a specific example of the present application, the step S420 includes: performing full-time circulation flow rate association on the time queue of the circulation flow rate of the gas circulation pump and the time queue of the circulation flow rate of the liquid circulation pump to obtain a liquid-gas circulation flow rate timing association matrix; inputting the liquid-gas circulation flow rate timing association matrix into a liquid-gas circulation flow rate timing collaborative pattern feature extractor based on a void convolutional neural network model to obtain the liquid-gas circulation flow rate timing collaborative feature graph.

[0040] That is, first, by performing full-time circulation flow rate association coding on the time queue of the circulation flow rate of the gas circulation pump and the time queue of the circulation flow rate of the liquid circulation pump, a correlation model between the liquid and gas circulation flow rates is established, the dynamic change law between the two is revealed, and a liquid-gas circulation flow rate time series association matrix is ​​generated. In a specific example of the present application, the time queue of the circulation flow rate of the gas circulation pump and the time queue of the circulation flow rate of the liquid circulation pump are arranged in time order in the form of a one-dimensional time series input vector, and the outer product between the two vectors is calculated to reveal the interaction strength between the liquid circulation flow rate and the gas circulation flow rate at different time points, thereby obtaining the liquid-gas circulation flow rate time series association matrix.

[0041] Next, since the correlation pattern between the liquid and gas circulation flow rates has complex time dependence. Therefore, in order to further identify the time series synergistic correlation pattern between the liquid circulation flow rate and the gas circulation flow rate, the present application uses a hole convolutional neural network model as a feature extractor to process the liquid-gas circulation flow rate time series correlation matrix, and uses the characteristics of the hole convolutional neural network model, that is, introducing holes (i.e., intervals) in the convolution kernel to effectively expand the feature receptive field to capture longer-distance time series dependencies, thereby extracting the complex time series correlation features between the liquid circulation flow rate and the gas circulation flow rate, so as to obtain a liquid-gas circulation flow rate time series synergistic feature map.

[0042] Then, in order to further enhance the discrimination capability of the liquid-gas circulation flow rate timing collaborative characteristic diagram, the present application optimizes the liquid-gas circulation flow rate timing collaborative characteristic diagram by considering the timing correlation change characteristics of the liquid circulation flow rate itself, so as to eliminate the redundant or noise characteristics therein, retain the relevant characteristics, and thus focus on the parts with important correlation between the liquid circulation flow rate and the gas circulation flow rate. Accordingly, the step S430 includes: extracting the liquid circulation flow rate timing correlation characteristic vector from the time queue of the circulation flow rate of the liquid circulation pump; inputting the liquid circulation flow rate timing correlation characteristic vector and the liquid-gas circulation flow rate timing collaborative characteristic diagram into the collaborative optimization analysis module to obtain the liquid circulation flow rate collaborative modulation vector.

[0043] Specifically, first, in order to capture the temporal correlation change law of the liquid circulation flow rate itself, the present application adopts a temporal analysis method to process the time queue of the circulation flow rate of the liquid circulation pump, and extracts the temporal correlation feature vector of the liquid circulation flow rate from it, so as to reveal the dynamic change characteristics of the liquid circulation flow rate in the time dimension. In a specific example of the present application, the implementation method of extracting the temporal correlation feature vector of the liquid circulation flow rate from the time queue of the circulation flow rate of the liquid circulation pump is to input the time queue of the circulation flow rate of the liquid circulation pump into a temporal feature extractor based on a one-dimensional convolutional neural network model to obtain the temporal correlation feature vector of the liquid circulation flow rate. It should be understood that by using a one-dimensional convolution kernel to perform a sliding convolution operation along the time dimension on the time queue of the circulation flow rate of the liquid circulation pump, the temporal correlation dependency between the liquid circulation flow rates at each time point can be effectively captured, thereby generating the temporal correlation feature vector of the liquid circulation flow rate, and providing strong support for subsequent feature collaborative optimization.

[0044] Next, in order to utilize the liquid circulation flow rate timing-related feature vector to strengthen the important feature interaction in the liquid-gas circulation flow rate timing collaborative feature map, in the step S430, the present application designs a collaborative optimization analysis module to perform cross-modal feature interaction and screening on the liquid circulation flow rate timing-related feature vector and the liquid-gas circulation flow rate timing collaborative feature map. Specifically, the collaborative optimization analysis module first linearly transforms the liquid circulation flow rate timing-related feature vector through two different weight modifier matrices to expand the expression range of the feature, so as to capture the correlation between the liquid circulation flow rate timing-related features and the liquid-gas circulation flow rate timing collaborative feature map from different angles. Then, feature masking is performed based on the gradient amplitude of each position in the two feature vectors after linear transformation to highlight the important liquid circulation flow rate timing-related features, so as to enhance the focus on important features in the subsequent feature screening process. Furthermore, the two masked feature vectors are used to perform two feature screenings on the liquid-gas circulation flow rate timing collaborative feature map, and the weighted operation along the channel dimension is performed to extract the part closely related to the liquid circulation flow rate timing correlation feature. In addition, in order to improve the nonlinear expression ability of the feature, the hyperbolic tangent function and the Sigmoid function are introduced in the two feature screenings for feature activation processing. Among them, the output range of the hyperbolic tangent function is between -1 and +1, which is used to preliminarily screen out features that are highly correlated with the liquid circulation flow rate timing correlation feature; and the output range of the Sigmoid function is between 0 and 1, which is suitable for probability estimation and binary decision-making, and it is used for the final feature screening. Finally, the pooling operation is performed on the filtered feature map to further reduce the feature dimension and extract key information, thereby obtaining the liquid circulation flow rate collaborative modulation vector.

[0045] In a specific example of the present application, the liquid circulation flow rate timing association feature vector and the liquid-gas circulation flow rate timing cooperative feature map are input into a cooperative optimization analysis module to obtain the liquid circulation flow rate cooperative modulation vector, including: performing a linear transformation on the liquid circulation flow rate timing association feature vector based on a first weight modifier matrix and a second weight modifier matrix to obtain a first liquid circulation flow rate timing association feature mapping pattern representation vector and a second liquid circulation flow rate timing association feature mapping pattern representation vector; based on the gradient amplitude of each position in the first liquid circulation flow rate timing association feature mapping pattern representation vector, performing a masking process on the first liquid circulation flow rate timing association feature mapping pattern representation vector based on the gradient amplitude to obtain a masked first liquid circulation flow rate timing association feature mapping pattern representation vector; based on The gradient amplitude at each position in the second liquid circulation flow rate timing association feature mapping pattern representation vector is subjected to a masking process based on the gradient amplitude to obtain a masked second liquid circulation flow rate timing association feature mapping pattern representation vector; based on the masked first liquid circulation flow rate timing association feature mapping pattern representation vector and the hyperbolic tangent function, the liquid-gas circulation flow rate timing collaborative feature map is subjected to a preliminary feature screening to obtain a preliminary screened liquid-gas circulation flow rate timing collaborative feature map; based on the masked second liquid circulation flow rate timing association feature mapping pattern representation vector and the Sigmoid function, the preliminary screened liquid-gas circulation flow rate timing collaborative feature map is subjected to a further feature screening to obtain the liquid circulation flow rate collaborative modulation vector.

[0046] More specifically, based on the gradient amplitude of each position in the first liquid circulation flow rate timing association feature mapping pattern representation vector, the first liquid circulation flow rate timing association feature mapping pattern representation vector is subjected to gradient amplitude-based masking processing to obtain a masked first liquid circulation flow rate timing association feature mapping pattern representation vector, including: for each position in the first liquid circulation flow rate timing association feature mapping pattern representation vector, calculating the absolute value of the difference between the eigenvalue of the previous position and the eigenvalue of the next position adjacent to it to obtain the gradient amplitude of each position in the first liquid circulation flow rate timing association feature mapping pattern representation vector; comparing the gradient amplitude of each position in the first liquid circulation flow rate timing association feature mapping pattern representation vector with a preset mask threshold, marking the position greater than the preset mask threshold as 1, and marking the position less than or equal to the preset mask threshold as 0, to obtain the masked first liquid circulation flow rate timing association feature mapping pattern representation vector.

[0047] More specifically, based on the masked second liquid circulation flow rate timing associated feature mapping pattern representation vector and the Sigmoid function, the liquid-gas circulation flow rate timing series collaborative feature map after the preliminary screening is subjected to feature screening again to obtain the liquid circulation flow rate collaborative modulation vector, including: using the eigenvalues ​​of each position in the masked second liquid circulation flow rate timing associated feature mapping pattern representation vector as weights, weighting each channel feature matrix of the liquid-gas circulation flow rate timing series collaborative feature map after the preliminary screening to obtain the screened liquid-gas circulation flow rate timing series collaborative feature map; activating the screened liquid-gas circulation flow rate timing series collaborative feature map through a Sigmoid function and then performing global pooling along the channel dimension to obtain the liquid circulation flow rate collaborative modulation vector.

[0048] That is, the liquid circulation flow rate timing correlation feature vector and the liquid-gas circulation flow rate timing cooperative feature map are processed by the following cooperative optimization analysis formula to obtain the liquid circulation flow rate cooperative modulation vector, wherein the cooperative optimization analysis formula is:

[0049]

[0050]

[0051]

[0052]

[0053]

[0054]

[0055] in, represents the time series correlation feature vector of the liquid circulation flow rate, represents a linear transformation based on the first weight modifier matrix, represents a linear transformation based on the second weight modifier matrix, represents the first weight modifier matrix, represents the second weight modifier matrix, and Represent different bias terms, represents the first liquid circulation flow rate time series correlation feature mapping mode representation vector, represents the second liquid circulation flow rate time series correlation feature mapping mode representation vector, and respectively represent the first liquid circulation flow rate time series correlation feature mapping mode representation vector Location and The eigenvalues ​​of the positions, and respectively represent the second liquid circulation flow rate time series correlation feature mapping mode representation vector Location and The eigenvalues ​​of the positions, Indicates mask processing, is the preset mask threshold, The first one represents the masked first liquid circulation flow rate time series correlation feature mapping pattern representation vector The eigenvalues ​​of the positions, represents the masked first liquid circulation flow rate time series correlation feature mapping pattern representation vector, The first one represents the masked second liquid circulation flow rate time series correlation feature mapping pattern representation vector The eigenvalues ​​of the positions, represents the masked second liquid circulation flow rate time series correlation feature mapping pattern representation vector, represents matrix multiplication, represents the liquid-gas circulation flow rate time series synergy characteristic diagram, is the hyperbolic tangent function, It represents the time series synergistic characteristic diagram of liquid-gas circulation flow rate after preliminary screening, is the sigmoid activation function, represents the pooling operation, represents the liquid circulation flow rate coordinated modulation vector.

[0056] Furthermore, based on the liquid circulation flow rate collaborative modulation vector, the adjustment strategy of the circulation flow rate of the liquid circulation pump is determined, and the adjustment strategy is used to indicate whether the circulation flow rate of the liquid circulation pump at the next time point should be increased, decreased or kept unchanged. In a specific example of the present application, the step S440 includes: inputting the liquid circulation flow rate collaborative modulation vector into the liquid circulation flow rate control module based on the classifier to obtain the adjustment strategy. That is, the liquid circulation flow rate collaborative modulation vector is classified and processed using a classification algorithm to determine the adjustment direction of the circulation flow rate of the liquid circulation pump. Specifically, the classifier can accurately judge the adjustment direction of the circulation flow rate of the liquid circulation pump in the current state by learning the time series collaborative association information between the liquid and gas circulation flow rates contained in the liquid circulation flow rate collaborative modulation vector, and combining the decision boundary obtained by training, thereby mapping the liquid circulation flow rate collaborative modulation vector to the corresponding adjustment strategy category, such as increase, decrease and remain unchanged. In this way, by real-time monitoring and adjusting the circulation flow rate of the liquid circulation pump, the dynamic balance between the liquid and gas circulation flow rates can be ensured, thereby improving the overall reaction efficiency and stability.

[0057] Preferably, inputting the liquid circulation flow rate coordinated modulation vector into a classifier-based liquid circulation flow rate control module to obtain an adjustment strategy comprises: Determine the number of zero eigenvalues ​​in the liquid circulation flow rate cooperative modulation vector, and respectively calculate the reciprocal of the logarithm of the number of zero eigenvalues ​​with base two and the exponential value of the reciprocal of the number of zero eigenvalues ​​with base natural constant to obtain a first liquid circulation flow rate cooperative modulation representative value and a second liquid circulation flow rate cooperative modulation representative value; Calculate a power function of each eigenvalue of the liquid circulation flow rate cooperative modulation vector with the inverse of the number of zero eigenvalues ​​as an exponent to obtain a liquid circulation flow rate cooperative modulation structure state vector; Performing a dot multiplication of the liquid circulation flow rate cooperative modulation structure state vector and the first liquid circulation flow rate cooperative modulation representation value to obtain a liquid circulation flow rate cooperative modulation information representation vector; Performing dot multiplication of the autocorrelation matrix of the liquid circulation flow rate cooperative modulation structure state vector with the second liquid circulation flow rate cooperative modulation representation value and weight hyperparameter respectively to obtain a liquid circulation flow rate cooperative modulation regression understanding matrix; Performing matrix multiplication of the liquid circulation flow rate cooperative modulation information representation vector and the liquid circulation flow rate cooperative modulation regression understanding matrix to obtain an optimized liquid circulation flow rate cooperative modulation vector; The optimized liquid circulation flow rate cooperative modulation vector is input into a classifier-based liquid circulation flow rate control module to obtain an adjustment strategy.

[0058] That is, the first liquid circulation flow rate coordinated modulation representation value and the second liquid circulation flow rate coordinated modulation representation value are expressed as:

[0059]

[0060] in, is the number of zero eigenvalues ​​in the liquid circulation velocity coordinated modulation vector, is the cooperative modulation value of the first liquid circulation flow rate, is the cooperative modulation value of the second liquid circulation flow rate, It is an exponential function with a natural constant as base; And the optimized liquid circulation flow rate coordinated modulation vector is expressed as:

[0061]

[0062]

[0063] in, is the liquid circulation flow rate coordinated modulation vector, is the weight hyperparameter, is the liquid circulation flow rate co-modulation regression matrix, is the liquid circulation flow rate coordinated modulation information representation vector, is the number of zero eigenvalues ​​in the liquid circulation velocity coordinated modulation vector, is the cooperative modulation value of the first liquid circulation flow rate, is the cooperative modulation value of the second liquid circulation flow rate, represents a power function that calculates each eigenvalue of the liquid circulation flow rate coordinated modulation vector with the inverse of the number of zero eigenvalues ​​as the exponent, represents the transpose of a vector, It is the point multiplication by position. is matrix multiplication, is the optimized liquid circulation flow rate coordinated modulation vector.

[0064] Here, in the case where the liquid circulation flow rate timing association feature vector and the liquid-gas circulation flow rate timing collaborative feature diagram respectively represent the liquid circulation flow rate timing association feature and the liquid-gas circulation flow rate timing collaborative association, when performing collaborative optimization analysis on them, the feature dimension difference and feature hidden association between the liquid circulation flow rate timing association feature vector and the liquid-gas circulation flow rate timing collaborative feature diagram will result in the existence of selective state space during the collaborative optimization analysis, causing the liquid circulation flow rate collaborative modulation vector to have a long-range class regression understanding representation imbalance, thereby deviating from the source time series distribution feature representation class understanding, affecting the accuracy of the classification results.

[0065] Based on this, the present application realizes effective long-range modeling of the liquid circulation flow rate cooperative modulation vector under the field linear complexity by modeling the vector field zero dimension of the liquid circulation flow rate cooperative modulation vector as a global field redundant dependency, so as to perform structured correlation self-distillation between information representation and class understanding based on the selective state space of feature distribution in the feature regression process of the liquid circulation flow rate cooperative modulation vector, thereby maintaining the overall information complexity of the feature distribution of the liquid circulation flow rate cooperative modulation vector while promoting the long-range dynamic class understanding balance of its feature convergence, so as to improve the class understanding consistency between the classification regression and feature extraction processes, and improve the accuracy of the adjustment strategy obtained by inputting the liquid circulation flow rate cooperative modulation vector into the liquid circulation flow rate control module based on the classifier.

[0066] Further preferably, in the above reaction process, the density is taken as the reaction end point, and when the density reaches 1.1-1.3 g / cm 3More preferably, the reaction is terminated when the density reaches 1.12 g / cm 3 The reaction is terminated.

[0067] Further preferably, in the above reaction process, the reaction mixture product at the discharge end of the reaction pipeline converges to the liquid circulation pump 103 via a connecting pipeline at one end, and converges to the liquid distributor 102 at the top of the reaction pipeline 101 through the liquid circulation pump 103 and the connecting pipeline at the other end, and then flows to the lower end through the upper end of the reaction pipeline 101 to complete a cycle. The circulation flow rate of the liquid circulation pump 103 is 1 to 20 minutes to complete a cycle. Further preferably, the circulation flow rate of the liquid circulation pump is 10 to 15 minutes to complete a cycle. More preferably, the circulation fluidity of the liquid circulation pump is 10 minutes to complete a cycle. By adjusting the circulation flow rate of the liquid control circulation pump 103, it is ensured that the reaction process is fully carried out in heat conduction, gas-liquid mass transfer, and solid-liquid mixing processes, and the reaction process is ensured to be stable, and the quality and production efficiency of the product are improved.

[0068] After the reaction is completed, the reaction product (the reaction product is a mixture containing polycarbonate polyether polyol, cyclic carbonate and unreacted raw material propylene oxide) flows out from the discharge port. The single discharge of the discharge port is not more than 80% of the volume of the reaction pipeline. The reaction product is then passed into the separation unit in the post-processing area, and the separation unit separates the propylene oxide and dissolved CO2 in the mixture to obtain a crude product, and adjusts the viscosity of the crude product at the same time. The crude product is passed into the refining unit, and the refining agent is added for adsorption treatment. After filtering, a crude product with a catalyst metal content of less than 5ppm is obtained. The refined crude product is passed into the distillation unit to separate the main product polycarbonate polyether polyol and the by-product cyclic carbonate, that is, the polycarbonate polyether polyol product is obtained, and enters the filling unit for filling.

[0069] It should be noted that the above-mentioned premixing unit, separation unit, refining unit, distillation unit, filling unit, etc. can all refer to the existing structure and will not be described in detail here.

[0070] Correspondingly, the present application also provides a method for coordinated control of circulation flow rate, which includes: obtaining a time queue of the circulation flow rate of a liquid circulation pump, and a time queue of the circulation flow rate of a gas circulation pump; extracting the timing coordinated mode characteristics of the time queue of the circulation flow rate of the gas circulation pump and the time queue of the circulation flow rate of the liquid circulation pump to obtain a liquid-gas circulation flow rate timing coordinated characteristic diagram; based on the timing correlation characteristics of the circulation flow rate of the liquid circulation pump, performing coordinated modulation optimization on the liquid-gas circulation flow rate timing coordinated characteristic diagram to obtain a liquid circulation flow rate coordinated modulation vector; based on the liquid circulation flow rate coordinated modulation vector, determining an adjustment strategy for the circulation flow rate of the liquid circulation pump, the adjustment strategy being used to indicate whether the circulation flow rate of the liquid circulation pump at the next time point should increase, decrease or remain unchanged.

[0071] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned circulation flow rate coordinated control method have been described in detail in the description of the production process of the above-mentioned high molecular weight bisphenol A polycarbonate polyether polyol, and therefore, its repeated description will be omitted.

[0072] In summary, the production process of high molecular weight bisphenol A type polycarbonate polyether polyol according to the embodiment of the present application is explained, which pre-mixes the raw materials and feeds them into the reaction pipe at one time, performs gas-liquid circulation in opposite directions in the reaction pipe, and uses intelligent industrial control technology to perform time-series collaborative analysis on the liquid circulation flow rate and the gas circulation flow rate, digs out the time-series collaborative correlation mode between the two, and then based on the time-series correlation change law of the liquid circulation flow rate itself, performs feature screening and optimization on the gas-liquid circulation flow rate time-series collaborative correlation characteristics, captures the best collaborative matching relationship between the gas-liquid circulation flow rates, and performs adaptive adjustment of the liquid circulation flow rate. In this way, the coordinated work of the liquid circulation pump and the gas circulation pump can be achieved, so as to disperse the heat in time, maintain the temperature uniformity of the reaction system, and avoid the problem of yellowing of the product caused by local temperature overheating.

[0073] The characteristics and performance of this production process are further described in detail below in conjunction with specific embodiments.

[0074] Example 1 This embodiment provides a high molecular weight bisphenol A type polycarbonate polyether polyol, using the reaction device mentioned above, the reaction process is as follows: 8 L of propylene oxide, 4 g of DMC catalyst, and 373 g of bisphenol A were added to the premixing kettle at a molar ratio of 70:1 of epoxide to bisphenol A, and 0.4 MPa of carbon dioxide was introduced to mix and stir at a temperature of 40°C. After stirring for 1 hour, the mixture was pressed into an 8L×2 tubular reactor, with a single reaction pipe having a diameter of 100 mm and a length of 1000 mm. After all the mixture was pressed in, carbon dioxide was introduced into the reaction pipe to 3 MPa and the pressure was maintained. The liquid circulation pump and the gas circulation pump were turned on, and the liquid circulation flow rate control strategy was a fixed flow rate, that is, the liquid flow rate was controlled at 600 g / min. The temperature difference between the medium temperature in the heating jacket of the reaction pipe and the temperature in the reactor was controlled to be 3°C, and the temperature in the reactor was slowly increased until the temperature of the raw materials in the reaction unit was increased to 80°C. During the cyclic reaction, when the temperature of the raw material rises due to the exothermic reaction, the jacket temperature is reduced, and the reduced temperature is equal to the difference of 80°C of the temperature sensor in the middle of the reaction pipeline, so that the material temperature is kept balanced at 80°C. In this process, when the temperature in the reaction pipeline is greater than 85°C, CO2 is introduced from the CO2 purification system, the gas temperature is 40°C, and the pressure is supplemented to 4MPa until the temperature in the reaction pipeline drops to 80°C. After reacting at 80°C for 3 hours, the density is uniformly increased to 1.12g / cm 3 The reaction is complete and the temperature is lowered to remove the product. After the catalyst is removed by the catalyst filter, the main and by-products are separated by a scraper evaporator.

[0075] The DMC catalyst is a zinc-cobalt double metal cyanide complex catalyst obtained by reacting water-soluble metal salts of zinc and cobalt in a water-soluble solvent. The specific preparation method is as follows: potassium hexacyanocobaltate and zinc bromide in a molar ratio of 1:4 are weighed, dissolved in an aqueous solvent containing water and tert-butyl alcohol, and stirred continuously, and the total mass of the metal salt (i.e., cobalt salt and zinc salt) and the mass ratio of the aqueous solvent are 1:5. Inorganic acid and organic acid are added, the inorganic acid is dilute hydrochloric acid, the pH value is 2, the organic acid is glutaric acid, the molar ratio of the inorganic acid to the organic acid is 5:1, and the total molar number of the metal salt to the molar number of the acid is 4:1. Stir for several hours at a temperature of 10-100°C, and precipitate is continuously generated. The above precipitate is filtered and dried to obtain a filter cake. The filter cake is re-slurried and washed with an aqueous solvent at a temperature of 10-100°C, specifically, the washing temperature is 100°C, washing for 3 minutes, stirring for several hours, and then filtered and dried to obtain a filter cake, and the above slurrying, washing, and drying steps are repeated for multiple times at a temperature of 10-100°C until the system liquid pH is 6-7, specifically, the temperature is 60°C, and each time for 6 minutes. The solid product is further dried under vacuum conditions at 80-100°C to obtain the final catalyst, and the catalyst is processed into powder particles by mechanical grinding under anhydrous drying conditions before use.

[0076] Example 2 In Example 2, the liquid circulation flow rate control strategy is an intelligent collaborative control strategy, which is: using intelligent industrial control technology to perform time-series collaborative analysis on the liquid circulation flow rate and the gas circulation flow rate, digging out the time-series collaborative correlation mode between the two, and then based on the time-series correlation change law of the liquid circulation flow rate itself, the gas-liquid circulation flow rate time-series collaborative correlation characteristics are screened and optimized, and the best collaborative matching relationship between the gas-liquid circulation flow rates is captured, so as to perform adaptive adjustment of the liquid circulation flow rate. Other conditions are the same as those in Example 1.

[0077] The purified product is sampled and analyzed, specifically, the polymerization product (polycarbonate-polyether polyol and cyclic propylene carbonate and unreacted propylene oxide) is sampled and collected in a container, and the polymerization product logistics sample is characterized by nuclear magnetic hydrogen spectrum to calculate the ratio of polymer to cyclic small molecules in the crude product. After the polymer is purified, the nuclear magnetic hydrogen spectrum test is performed to calculate the ratio of polycarbonate chain segments to polyether chain segments on the polymer main chain. There are only two structures of polycarbonate chain segments and polyether chain segments on the polymer main chain, and the sum of the percentages of the two is 100%. The final product with a carbonate connection ratio of 50-65% is a qualified product, and 55-60% is a superior product.

[0078] With the help of 1 The amount of carbon dioxide introduced in the obtained polycarbonate polyether polyol (carbonate segment content) and the ratio of propylene carbonate (cyclic carbonate) to polycarbonate polyether polyol were determined by H-NMR (Bruker, DPX400, 400 MHz; pulse program zg30, waiting time d1:10 s, 64 scans). In each case, the sample was dissolved in deuterated chloroform. 1 The relevant resonant proton peaks in H-NMR (based on TMS=0ppm) are as follows: Among them, 5.0ppm and 4.2ppm belong to the proton peaks of the methine and methylene on the polycarbonate chain, 4.9ppm, 4.5ppm and 4.1ppm belong to the proton peaks of the methine and methylene in the five-membered ring carbonate, and 3.5-3.8ppm belong to the proton peak of the ether chain. The capital letter A plus a numerical subscript represents the integrated area of ​​the peak at a certain ppm on the nuclear magnetic resonance hydrogen spectrum, for example, A 5.0 represents the integrated area of ​​the peak at 5.0 ppm. 1 The integral area of ​​the H-NMR spectrum and its related proton peaks is used to calculate the carbonate chain ratio (molar ratio) F in the copolymerization reaction. CO2 and cyclic carbonate content mass fraction W PC , the amount of carbon dioxide embedded M CO2 , the specific calculation method is as follows: F CO2 =(A 5.0+A 4.2 -2×A 4.6 ) / [(A 5.0 +A 4.2 -2×A 4.6 )+A 3.5 ]×100%; W PC =102×A 1.5 / [102×(A 5.0 +A 4.2 -2×A 4.6 +A1.5)+58×A 3.5 ]×100%; M CO2 =44×F CO2 / [102×F CO2 +58×(1-F CO2 )]×100%.

[0079] The coefficient 44 is the molar mass of carbon dioxide, the coefficient 58 is the molar mass of PO (propylene oxide), and the coefficient 102 is the sum of the molar masses of carbon dioxide (molar mass 44 g / mol) and PO (molar mass 58 g / mol).

[0080] The formula for calculating the product conversion rate n is n=m×(1-M CO2 ) / (Mm×M CO2 ); wherein m is the mass of the product after removing propylene oxide, and M is the total sample mass containing propylene oxide.

[0081] The polymer number average molecular weight (Mn) and polymer molecular weight polydispersity index (PDI) are determined by gel permeation chromatography (GPC). The smaller the PDI of the final product, the better the quality. A PDI below 2 is a qualified product, and a PDI below 1.5 is a superior product.

[0082] The final product was tested for colorimetry. 5g of the test object was placed in a cuvette and the cuvette was placed in a dark environment to reduce the influence of the light source on the test and cause errors. The NR10QC colorimeter was used for the test, and the test data included three basic indicators: L*, a*, and b*.

[0083] The L* value represents the color brightness, L*=0 indicates black, and L*=100 indicates white.

[0084] The a* value represents the position between red / magenta and green, with negative a* values ​​indicating green and positive a* values ​​indicating magenta.

[0085] The b* value represents the position between yellow and blue, with a negative b* value indicating blue and a positive b* value indicating yellow.

[0086] The smaller the absolute values ​​of a* and b*, the better; the smaller they are, the closer they are to colorless.

[0087] The test results are shown in Table 1 below: Table 1

[0088] As can be seen from Table 1, the reaction time of the cyclic flow rate coordinated control strategy provided by the present application is optimized relative to the fixed cyclic flow rate control strategy. It should be noted that in Example 1, the reaction end time is 3 hours, while in Example 2, the reaction end time is 2.4 hours, and the reaction efficiency is improved by 20%; while increasing the reaction rate, the quality of the reactants is not reduced. The reaction products are tested and the molecular weight distribution, catalyst residue and chromaticity between the two are comparable, and the carbonate chain content is further optimized and improved, from 52% to 60%. Therefore, the gas intelligent control method provided by the present application can improve the reaction efficiency and ensure the quality of the reaction products.

[0089] Finally, it should be noted that the embodiments described above are only some embodiments of the present invention, rather than all embodiments. The detailed description of the embodiments of the present invention is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

Claims

1. A production process for high molecular weight bisphenol A polycarbonate polyether polyol, characterized in that: The production process of the high molecular weight bisphenol A type polycarbonate polyether polyol is carried out in a tubular reaction device, the reaction device comprises a premixing unit and a reaction zone, the reaction zone comprises a reaction pipeline, a liquid circulation pump and a gas circulation pump, a heating jacket is arranged outside the reaction pipeline, the liquid circulation pump and the gas circulation pump are both connected to the reaction pipeline, the liquid circulation pump is used to make the material in the reaction pipeline circulate in the reaction pipeline along a first direction, and the gas circulation pump is used to make the gas in the reaction pipeline circulate in the reaction pipeline along a second direction, wherein the first direction and the second direction are opposite directions; The production process comprises: Premixing step: mixing the epoxy compound, CO2, bisphenol A and the catalyst in the premixing unit to obtain a premix; Feeding step: feeding the premixture into the reaction zone at one time; CO2 pressure maintenance step: after the feeding is completed, CO2 is introduced into the reaction zone, and the pressure of the introduced CO2 is 3-4 MPa; Reaction step: starting the liquid circulation pump and the gas circulation pump, adjusting the temperature of the medium in the heating jacket to raise the temperature of the reaction pipeline to 75° C. to 85° C.; after the temperature is raised, monitoring the temperature in the reaction pipeline, and maintaining the temperature of the reaction pipeline at 75° C. to 85° C. by adjusting the temperature of the medium in the heating jacket; Wherein, the reaction step further comprises: Acquire a time queue of the circulation flow rate of the liquid circulation pump and a time queue of the circulation flow rate of the gas circulation pump; Extracting the timing coordination mode characteristics of the time queue of the circulation flow rate of the gas circulation pump and the time queue of the circulation flow rate of the liquid circulation pump to obtain a liquid-gas circulation flow rate timing coordination characteristic diagram; Based on the time series correlation characteristics of the circulation flow rate of the liquid circulation pump, the liquid-gas circulation flow rate time series cooperative characteristic diagram is cooperatively modulated and optimized to obtain a liquid circulation flow rate cooperative modulation vector; Based on the liquid circulation flow rate coordinated modulation vector, an adjustment strategy for the circulation flow rate of the liquid circulation pump is determined, wherein the adjustment strategy is used to indicate whether the circulation flow rate of the liquid circulation pump at the next time point should increase, decrease or remain unchanged.

2. The production process of high molecular weight bisphenol A polycarbonate polyether polyol according to claim 1, characterized in that: Extracting the timing coordination mode characteristics of the time queue of the circulation flow rate of the gas circulation pump and the time queue of the circulation flow rate of the liquid circulation pump to obtain a liquid-gas circulation flow rate timing coordination characteristic diagram, including: Performing full-time circulation flow rate correlation on the time queue of the circulation flow rate of the gas circulation pump and the time queue of the circulation flow rate of the liquid circulation pump to obtain a liquid-gas circulation flow rate time series correlation matrix; The liquid-gas circulation flow rate timing association matrix is ​​input into a liquid-gas circulation flow rate timing coordination pattern feature extractor based on a void convolutional neural network model to obtain the liquid-gas circulation flow rate timing coordination feature graph.

3. The production process of high molecular weight bisphenol A polycarbonate polyether polyol according to claim 2, characterized in that: Based on the time series correlation characteristics of the circulation flow rate of the liquid circulation pump, the liquid-gas circulation flow rate time series cooperative characteristic diagram is cooperatively modulated and optimized to obtain a liquid circulation flow rate cooperative modulation vector, including: Extracting a liquid circulation flow rate time series correlation feature vector from a time queue of the circulation flow rate of the liquid circulation pump; The liquid circulation flow rate timing correlation feature vector and the liquid-gas circulation flow rate timing cooperative feature diagram are input into a cooperative optimization analysis module to obtain the liquid circulation flow rate cooperative modulation vector.

4. The production process of high molecular weight bisphenol A polycarbonate polyether polyol according to claim 3, characterized in that: Extracting a liquid circulation flow rate time series correlation feature vector from the time queue of the circulation flow rate of the liquid circulation pump includes: The time queue of the circulation flow rate of the liquid circulation pump is input into a time series feature extractor based on a one-dimensional convolutional neural network model to obtain a time series correlation feature vector of the liquid circulation flow rate.

5. The production process of high molecular weight bisphenol A polycarbonate polyether polyol according to claim 4, characterized in that: Inputting the liquid circulation flow rate time series correlation feature vector and the liquid-gas circulation flow rate time series cooperative feature diagram into a cooperative optimization analysis module to obtain the liquid circulation flow rate cooperative modulation vector, including: Performing a linear transformation based on a first weight modifier matrix and a second weight modifier matrix on the liquid circulation flow rate time series associated feature vector to obtain a first liquid circulation flow rate time series associated feature mapping mode representation vector and a second liquid circulation flow rate time series associated feature mapping mode representation vector; Based on the gradient amplitude of each position in the first liquid circulation flow rate time series correlation feature mapping pattern representation vector, performing gradient amplitude-based mask processing on the first liquid circulation flow rate time series correlation feature mapping pattern representation vector to obtain a masked first liquid circulation flow rate time series correlation feature mapping pattern representation vector; Based on the gradient amplitude of each position in the second liquid circulation flow rate time series correlation feature mapping pattern representation vector, performing a masking process based on the gradient amplitude on the second liquid circulation flow rate time series correlation feature mapping pattern representation vector to obtain a masked second liquid circulation flow rate time series correlation feature mapping pattern representation vector; Based on the masked first liquid circulation flow rate time series associated feature mapping pattern representation vector and the hyperbolic tangent function, the liquid-gas circulation flow rate time series collaborative feature diagram is preliminarily screened to obtain a preliminarily screened liquid-gas circulation flow rate time series collaborative feature diagram; Based on the masked second liquid circulation flow rate timing associated feature mapping pattern representation vector and Sigmoid function, the liquid-gas circulation flow rate timing collaborative feature map after the preliminary screening is subjected to feature screening again to obtain the liquid circulation flow rate collaborative modulation vector.

6. The production process of high molecular weight bisphenol A polycarbonate polyether polyol according to claim 5, characterized in that: Based on the gradient amplitude of each position in the first liquid circulation flow rate time series association feature mapping pattern representation vector, performing a masking process based on the gradient amplitude on the first liquid circulation flow rate time series association feature mapping pattern representation vector to obtain a masked first liquid circulation flow rate time series association feature mapping pattern representation vector, including: For each position in the first liquid circulation flow rate time series associated characteristic mapping pattern representation vector, calculate the absolute value of the difference between the characteristic value of the previous position and the characteristic value of the next position adjacent thereto to obtain the gradient amplitude of each position in the first liquid circulation flow rate time series associated characteristic mapping pattern representation vector; The gradient amplitude of each position in the first liquid circulation flow rate timing association feature mapping pattern representation vector is compared with a preset mask threshold, and the positions greater than the preset mask threshold are marked as 1, and the positions less than or equal to the preset mask threshold are marked as 0, so as to obtain the masked first liquid circulation flow rate timing association feature mapping pattern representation vector.

7. The production process of high molecular weight bisphenol A polycarbonate polyether polyol according to claim 6, characterized in that: The liquid-gas circulation flow rate time series collaborative feature map after the preliminary screening is subjected to feature screening again based on the masked second liquid circulation flow rate time series associated feature mapping pattern representation vector and the Sigmoid function to obtain the liquid circulation flow rate collaborative modulation vector, including: Using the eigenvalues ​​of each position in the masked second liquid circulation flow rate timing association feature mapping pattern representation vector as weights, weighting each channel feature matrix of the preliminary screened liquid-gas circulation flow rate timing synergistic feature map to obtain the screened liquid-gas circulation flow rate timing synergistic feature map; The screened liquid-gas circulation flow rate time series collaborative feature map is activated by a Sigmoid function and then globally pooled along the channel dimension to obtain the liquid circulation flow rate collaborative modulation vector.

8. The production process of high molecular weight bisphenol A polycarbonate polyether polyol according to claim 7, characterized in that: Based on the liquid circulation flow rate coordinated modulation vector, determining an adjustment strategy for the circulation flow rate of the liquid circulation pump, wherein the adjustment strategy is used to indicate whether the circulation flow rate of the liquid circulation pump at a next time point should be increased, decreased, or kept unchanged, including: The liquid circulation flow rate cooperative modulation vector is input into a classifier-based liquid circulation flow rate control module to obtain the adjustment strategy.

9. The production process of high molecular weight bisphenol A polycarbonate polyether polyol according to claim 1, characterized in that: The reaction zone is provided with a plurality of reaction pipes arranged in parallel, each of the reaction pipes is provided with the gas circulation pump to realize gas circulation in the reaction pipe; the feed ends of the plurality of reaction pipes are converged to the liquid distributor through connecting pipes, and the discharge ends of the plurality of reaction pipes are converged to the liquid circulation pump through connecting pipes, and the liquid circulation pump is connected to the liquid distributor through connecting pipes; the number of the reaction pipes is 2 to 20.

Images