Intelligent control system and self-adaptive adjusting method of large-scale devolatilizer

Abstract

The application discloses an intelligent control system and a self-adaptive adjusting method of a large-scale devolatilizer, and relates to the technical field of devolatilizer control.The system comprises a multi-source data sensing module, a volatile component concentration prediction module, an optimal set value solving module and a set value executing module.The multi-source data sensing module is used for collecting process variable data in the operation of the devolatilizer in real time through a sensor group.The volatile component concentration prediction module is used for dynamically estimating and outputting the real-time average volatile component concentration of the melt in the current cavity according to the process variable data.The optimal set value solving module is used for solving the optimal set value combination in the next control cycle by using a collaborative optimization function.The set value executing module is used for driving the actuating mechanism to act with the optimal set value combination, so as to complete the self-adaptive adjustment of the devolatilization process.The application can effectively overcome the disadvantages of traditional control, such as dependence on manual operation and adjustment lag, significantly improve the consistency and stability of product quality, and improve the production automation level and overall energy efficiency.

Description

Technical Field

[0001] This invention relates to the field of wavemaker control technology, and in particular to an intelligent control system and adaptive adjustment method for a large wavemaker. Background Technology

[0002] Deviation is a key process in polymer production, used to remove residual monomers, solvents, and other volatile components from the melt, directly affecting the purity, quality, and performance of the final product. Large-scale devolatilizers, as the core equipment for this process, are widely used in chemical, rubber and plastics, and new materials industries.

[0003] In existing technologies, the control systems of large-scale devourers mainly rely on traditional PLC (Programmable Logic Controller) and PID (Proportional-Integral-Derivative) control loops, operating through preset fixed process parameters (such as temperature, pressure, speed, and liquid level). However, with the increasing demands from industry for consistent product quality, production efficiency, and "smart manufacturing," these traditional control systems have gradually revealed the following key bottlenecks and pain points in practice:

[0004] 1. Relying on human experience and delayed adjustments makes it difficult to guarantee the stability of product quality.

[0005] Large-scale devolatilization processes are complex nonlinear systems involving mass and heat transfer. Their performance is significantly affected by various time-varying factors, such as raw material batch characteristics (e.g., initial volatile content and viscosity), operating condition fluctuations (e.g., unstable steam pressure), and equipment status (e.g., fouling on heat exchange surfaces). Traditional control systems lack the ability to perceive and intelligently decide on these disturbances. When production conditions change, the system cannot proactively predict and adjust in a timely manner, often requiring manual intervention by operators based on their personal experience. This lag-dependent adjustment mode not only demands extremely high operator skills but also results in highly uncertain and accidental adjustments, easily leading to fluctuations in product quality between different production batches, and even the production of substandard products, severely restricting the stable production of high-end polymer products.

[0006] 2. Rigid and inflexible control parameters lead to persistently high energy and material consumption.

[0007] In traditional control modes, to cope with the worst operating conditions and ensure safety, the system typically sets control parameters according to the most conservative conditions (e.g., setting a high heating temperature or a low vacuum). While this "one-size-fits-all" strategy can guarantee basic operation, it lacks the ability to fine-tune and adaptively adjust to the actual needs of the current process. The direct consequence is that under most non-full-load or favorable conditions, the system remains in an "over-processing" state, resulting in significant waste of energy such as steam, electricity, and cooling water. Furthermore, overheating may lead to material degradation, increasing production costs and affecting the long-term stable operation of the equipment.

[0008] Therefore, developing a control system and method for large-scale devourers that can sense the process status in real time, make intelligent decisions, and adaptively adjust operating parameters has become a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0009] This invention provides an intelligent control system for a large-scale volatile matter degassing machine, comprising: a multi-source data sensing module, a volatile matter concentration prediction module, an optimal setpoint solution module, and a setpoint execution module;

[0010] The multi-source data sensing module is used to collect process variable data during the operation of the devolatilizer in real time through a sensor group. The process variable data includes the temperature, pressure, stirring shaft power, and inlet and outlet melt flow rate of each chamber.

[0011] The volatile matter concentration prediction module is used to input the collected process variable data into the volatile matter concentration predictor, dynamically estimate and output the real-time average volatile matter concentration of the melt in the current cavity;

[0012] The optimal setpoint solution module is used to use the real-time average volatile concentration as feedback input, and the heating power and vacuum degree setpoints as optimization variables, and to use the collaborative optimization function to solve for the optimal setpoint combination in the next control cycle.

[0013] The setpoint execution module is used to drive the actuator to move with the optimal setpoint combination, thereby completing the adaptive adjustment of the release process.

[0014] The intelligent control system for a large-scale winch generator as described above includes a multi-source data sensing module comprising: a multi-source data acquisition submodule, a multi-source data alignment submodule, and a multi-source data push submodule.

[0015] The multi-source data acquisition submodule is used to synchronously acquire process variable data read by the sensor group at a preset sampling frequency;

[0016] The multi-source data alignment submodule is used to add timestamps and location identifiers to process variable data, forming standardized data frames with spatiotemporal labels;

[0017] The multi-source data push submodule is used to package standardized data frames in time sequence and push them to the volatile concentration prediction module.

[0018] The intelligent control system for a large-scale devolatizer as described above includes a volatile matter concentration prediction module that specifically comprises: a predictor initialization submodule, a prediction result output submodule, and a prediction result push submodule.

[0019] The predictor initialization submodule is used to initialize various parameters within the volatile concentration predictor;

[0020] The prediction result output submodule is used to control the predictor to output real-time prediction results based on the received process variable data;

[0021] The prediction result push submodule is used to package and push real-time prediction results to the optimal setting value solution module.

[0022] The intelligent control system for a large-scale winch generator as described above includes an optimal setpoint solution module that specifically comprises: a collaborative optimization function initialization submodule, a rolling solution submodule, and a setpoint combination push submodule.

[0023] The collaborative optimization function initialization submodule is used to initialize the various parameters in the collaborative optimization function.

[0024] The rolling solver submodule is used to solve for the optimal setpoint combination that minimizes the co-optimization function and satisfies all process constraints.

[0025] The setpoint combination push submodule is used to encapsulate the solved optimal setpoint combination and push it to the setpoint execution module in real time.

[0026] The present invention also provides an adaptive adjustment method for a large-scale devourer, comprising:

[0027] Step S210: Collect process variable data of the devolatilizer in real time through the sensor group. The process variable data includes the temperature, pressure, stirring shaft power and inlet and outlet melt flow rate of each chamber.

[0028] Step S220: Input the collected process variable data into the volatile concentration predictor to dynamically estimate and output the real-time average volatile concentration of the melt in the current cavity;

[0029] Step S230: Using the real-time average volatile concentration as the feedback input, and the heating power and vacuum degree setpoints as optimization variables, the optimal setpoint combination in the next control cycle is solved using the co-optimization function;

[0030] Step S240: Drive the actuator to move with the optimal set value combination to complete the adaptive adjustment of the detachment process.

[0031] The beneficial effects achieved by this invention are as follows: Through real-time sensing, intelligent prediction, and rolling optimization, adaptive and precise control of key parameters (heating power, vacuum degree) in the devolatilization process is realized. This effectively overcomes the drawbacks of traditional control methods that rely on manual intervention and suffer from lag in adjustment, significantly improving the consistency and stability of product quality, and enhancing the level of production automation and overall energy efficiency. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0033] Figure 1 This is a schematic diagram of an intelligent control system for a large-scale devourer provided in Embodiment 1 of this application;

[0034] Figure 2 This is a flowchart of an adaptive adjustment method for a large-scale devourer provided in Embodiment 2 of this application. Detailed Implementation

[0035] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0036] Example 1

[0037] like Figure 1 As shown, Embodiment 1 of this application provides an intelligent control system for a large-scale volatile matter generator, including: a multi-source data sensing module 11, a volatile matter concentration prediction module 12, an optimal setpoint solution module 13, and a setpoint execution module 14.

[0038] The multi-source data sensing module 11 is used to collect process variable data during the operation of the devolatilizer in real time through a sensor group. The process variable data includes the temperature, pressure, stirring shaft power, and inlet and outlet melt flow rate of each stage of the chamber. Specifically, it includes: a multi-source data acquisition submodule, a multi-source data alignment submodule, and a multi-source data push submodule.

[0039] 1. Multi-source data acquisition submodule, used to synchronously acquire process variable data read by the sensor group at a preset sampling frequency;

[0040] This submodule is directly connected to the physical sensor group (including thermocouples, pressure transmitters, power meters, and electromagnetic flow meters) deployed in various key parts of the devolatilizer (including each stage of the chamber, heating jacket, vacuum pipeline, stirring motor, and inlet and outlet pipelines). It can acquire process variable data read by each sensor in real time, including the temperature, pressure, stirring shaft power, and inlet and outlet melt flow rate (kg / h) of each stage of the chamber.

[0041] 2. Multi-source data alignment submodule, used to add timestamps and location identifiers to process variable data to form standardized data frames with spatiotemporal labels;

[0042] To assign a unified, high-precision system timestamp to the collected process variable data, and to address time series misalignments caused by minor differences in sampling time or loss of individual data, a linear interpolation method is used to align all data to a series of standard time nodes. Each data point is then assigned a clear location identifier (such as "first-stage devolatilization chamber - temperature" or "second-stage vacuum pump inlet - pressure") to form a standardized data frame with complete spatiotemporal labels.

[0043] 3. Multi-source data push submodule, used to package standardized data frames in time sequence and push them to the volatile concentration prediction module.

[0044] The volatile matter concentration prediction module 12 is used to input the collected process variable data into the volatile matter concentration predictor, dynamically estimate and output the real-time average volatile matter concentration of the melt in the current cavity; specifically, it includes: a predictor initialization submodule, a prediction result output submodule, and a prediction result push submodule.

[0045] 1. Predictor initialization submodule, used to initialize various parameters within the volatile matter concentration predictor;

[0046] Each chamber stage is equipped with a separate instance of a volatile matter concentration predictor, whose core equation is expressed as:

[0047]

[0048] Where k represents the current time. This represents the concentration of volatiles at time k-1. At that time, the predictor's predicted value for the volatile concentration at time k is... The initial value at the start of the predictor is set to the same as... The values ​​are consistent. This indicates the volatile content concentration of the imported melt, which is the mass percentage of volatiles in the melt raw material entering the current chamber. For the first-stage (initial) devolatilization chamber, its value comes from real-time data provided by the online analyzer in the upstream process. For the second-stage and subsequent chambers, its value is extracted from the predicted volatile content concentration output by the predictor corresponding to the upper-stage chamber at the previous moment. , This represents the melt flow rate at the inlet and outlet of the cavity at time k-1, M is the average melt holdup in the cavity, and A represents the effective mass transfer area of ​​the devolatilization interface (obtained from the equipment documentation). The pressure value inside the cavity at time k-1 is... This represents the temperature value inside the cavity at time k-1. Indicates in Stress and The equilibrium volatile concentration at a given temperature is calculated based on the thermodynamic properties of the specific polymer-solvent system using well-known thermodynamic models (such as Henry's law, the Flory-Huggins equation, etc.) or experimental correlations. Specific model parameters can be obtained by consulting property databases or through experimental determination. The time interval for the predictor to make predictions and update. The overall mass transfer coefficient is the coefficient that characterizes the combined rate of diffusion of volatiles from the bulk melt to the devolatilization interface.

[0049]

[0050] The reference mass transfer constant is determined by nonlinear regression fitting of historical production data or calibration experimental data designed specifically for pilot-scale equipment. The goal of the fitting is to minimize the concentration prediction error of the predictor throughout the entire operating range. The apparent activation energy reflects the temperature sensitivity of the devolatilization process. It is obtained by fitting laboratory devolatilization experimental data of the same material at different temperatures using the Arrhenius equation, where R is the ideal gas constant. This is a viscosity influence factor used to quantify the impact of melt viscosity on mass transfer resistance. It is determined through regression analysis on historical datasets containing different viscosity conditions (such as different concentrations and temperatures). The apparent viscosity of the melt characterizes the melt's properties. Temperature and The flow resistance at a given concentration is determined by the net power W of the stirring shaft, the rotational speed N, and the geometric constants of the stirrer. Online back-calculation using hybrid power metric relationships We obtain, where D is the diameter of the stirrer. For reference viscosity, the typical viscosity value of the material under standard process conditions (such as target temperature and target concentration) is used. It is the saturated vapor pressure of the volatile components at the melt temperature.

[0051] 2. Prediction result output submodule, used to control the predictor to output real-time prediction results based on the received process variable data;

[0052] The submodule sequentially calls the predictors of each cavity and inputs the real-time process variable data of each cavity into the predictor to obtain the real-time volatile concentration in each cavity, and outputs it as the prediction result.

[0053] 3. Prediction result push submodule, which is used to package and push real-time prediction results to the optimal setpoint solution module;

[0054] The output results of each cavity predictor and the real-time process variable data are uniformly structured and packaged (the packaged data packet must be tagged with a timestamp and cavity identifier), and then the packaged data packet is pushed to the optimal setpoint solving module.

[0055] The optimal setpoint solution module 13 is used to use the real-time average volatile concentration as feedback input, and the heating power and vacuum degree setpoints as optimization variables, and to use the collaborative optimization function to solve for the optimal setpoint combination in the next control cycle; specifically, it includes: a collaborative optimization function initialization submodule, a rolling solution submodule, and a setpoint combination push submodule.

[0056] 1. The collaborative optimization function initialization submodule is used to initialize the various parameters in the collaborative optimization function;

[0057] Note that the parameters to be initialized in the co-optimization function are determined based on the real-time average volatile concentration and process variable data within the cavity. However, the average volatile concentration and process variable data are different for different levels of cavities. Therefore, the co-optimization process for each level of cavity should be executed independently and in parallel. That is, for each level of cavity, a co-optimization function needs to be initialized using its own data, and then the function should be solved in a rolling manner to obtain an independent combination of setpoints for each level of cavity.

[0058] The collaborative optimization function Represented as:

[0059]

[0060] in To optimize variables, This is the heating power setting value. Set the vacuum level. The parameter to be initialized represents the combination of given set values. The predicted volatile concentration is calculated by calling a lightweight process prediction model. This model is based on the current real-time state, namely the current real-time average volatile concentration in the cavity, process variable data, and set value. It quickly simulates the evolution of the volatile concentration in the future optimization time domain and extracts the predicted final value (initialization step, which is actually to make the prediction effect meet the production requirements, such as an error of less than 5%). To achieve the target volatile concentration required by the process, The comprehensive heating efficiency coefficient, used to convert electrical power consumption into standard energy consumption units, is obtained from the equipment manual. Characterizing the maintenance of vacuum The required power consumption was obtained by fitting the measured power-vacuum curve of the vacuum pump. , For custom weighting coefficients, and + =1, , The value can be adjusted according to actual needs; if the current production stage prioritizes quality, then increase it appropriately. If energy efficiency is a greater priority, then the capacity should be increased appropriately. .

[0061] 2. The rolling solver submodule is used to solve for the optimal setpoint combination that minimizes the co-optimization function and satisfies all process constraints;

[0062] The process constraints can be customized according to the needs of the actual application scenario. For example, the heating power setting value and vacuum degree setting value should be within the equipment's capacity range, and the heating temperature should be within the safe range allowed by the process (to prevent material degradation or solidification).

[0063] Since the current optimization problem is relatively small (2 variables) but may be nonlinear and nonconvex, it is preferable to use a constrained global optimization algorithm (sequential quadratic programming or particle swarm optimization). The algorithm starts with a preset initial value and iteratively optimizes the optimization variables within the feasible region defined by the process constraints. In each iteration, the co-optimization function needs to be evaluated until the function curve no longer shows a significant downward trend. The iteration stops when the set value combination at this time is output as the optimal solution.

[0064] 3. The setpoint combination push submodule is used to encapsulate the solved optimal setpoint combination and push it to the setpoint execution module in real time;

[0065] To avoid the impact of setpoint jumps on the actuator, a first-order filter is applied to the optimal value obtained in this solution and the actual setpoint used in the previous cycle to generate a smoothed final setpoint. Then, the final setpoint, the current timestamp, and the cavity identifier are encapsulated into a data packet and pushed to the setpoint execution module in real time.

[0066] The setpoint execution module 14 is used to drive the actuator to move with the optimal setpoint combination, so as to complete the adaptive adjustment of the release process;

[0067] First, the system receives data packets pushed by the setpoint combination push submodule and converts the heating power setpoint into heater control commands and the vacuum setpoint into vacuum valve adjustment commands. Then, based on the cavity identifier in the data packet, the system maps the heater control commands and vacuum valve adjustment commands to the corresponding cavity's heater and vacuum regulation system. Finally, through the industrial bus, the system sends the final heating control commands and vacuum valve adjustment commands to the corresponding field actuators (i.e., power adjustment devices, frequency converters, regulating valve positioners, etc.) in real time to complete the adaptive adjustment of the devolatilization process.

[0068] Example 2

[0069] like Figure 2 As shown, Embodiment 2 of this application provides an adaptive adjustment method for a large-scale devourer, comprising:

[0070] Step S210: Collect process variable data of the devolatilizer in real time through the sensor group. The process variable data includes the temperature, pressure, stirring shaft power and inlet and outlet melt flow rate of each chamber.

[0071] Step S220: Input the collected process variable data into the volatile concentration predictor to dynamically estimate and output the real-time average volatile concentration of the melt in the current cavity;

[0072] Step S230: Using the real-time average volatile concentration as the feedback input, and the heating power and vacuum degree setpoints as optimization variables, the optimal setpoint combination in the next control cycle is solved using the co-optimization function;

[0073] Step S240: Drive the actuator to move with the optimal set value combination to complete the adaptive adjustment of the detachment process.

[0074] Corresponding to the above embodiments, the present invention provides a computer storage medium, including: at least one memory and at least one processor;

[0075] The memory is used to store one or more program instructions;

[0076] A processor is used to run one or more program instructions to execute an adaptive adjustment method for a large-scale de-energizer.

[0077] Corresponding to the above embodiments, the present invention provides a computer-readable storage medium containing one or more program instructions, which are used by a processor to provide an adaptive adjustment method for a large-scale decoupling machine.

[0078] The embodiments disclosed in this invention provide a computer-readable storage medium storing computer program instructions that, when executed on a computer, cause the computer to perform the aforementioned adaptive adjustment method for a large-scale de-rotator.

[0079] In this embodiment of the invention, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0080] The various methods, steps, and logic diagrams disclosed in the embodiments of this invention can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor reads information from the storage medium and, in conjunction with its hardware, completes the steps of the above methods.

[0081] The storage medium can be memory, such as volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0082] Among them, non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0083] Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0084] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0085] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this invention can be implemented using a combination of hardware and software. When applied as software, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. Storage media can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0086] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solution of the present invention should be included within the scope of protection of the present invention.

Claims

1. An intelligent control system for a large scale devolatilizer, characterized by, The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. where k represents the current time, represents the volatile concentration at k-1 time , the predictor predicts the volatile concentration at k time, The initial value at the start of the predictor is set to be consistent with value, represents the volatile concentration of the inlet melt, that is, the mass percentage of volatile in the melt raw material entering the current chamber. For the first-stage devolatilization chamber, the value is derived from the real-time data provided by the online analyzer of the upstream process. For the second-stage and subsequent chambers, the value is extracted from the volatile concentration prediction value output by the corresponding predictor of the upper chamber at the last time, , represents the melt flow at the inlet and outlet of the current chamber at k-1 time, M is the average holding amount of the melt in the current chamber, and A represents the effective mass transfer area of the devolatilization interface, which is obtained by querying the equipment documents, is the pressure value in the current chamber at k-1 time, represents the temperature value in the current chamber at k-1 time, represents the equilibrium volatile concentration at pressure and temperature, is the time interval for the predictor to make predictions and updates, is the total mass transfer coefficient, which represents the comprehensive rate coefficient of the diffusion of volatile from the melt body to the devolatilization interface; Kref is the reference mass transfer constant, Ea is the apparent activation energy, R is the ideal gas constant, visc is the viscosity impact factor, used to quantify the degree of influence of melt viscosity on mass transfer resistance, visc is the melt apparent viscosity, characterizing the flow resistance of the melt at temperature and concentration, visc is the reference viscosity, taking the typical viscosity value of the material at standard process conditions, Pv is the saturated vapor pressure of the volatile fraction at the melt temperature; The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine.

2. The intelligent control system for large scale devolatilizers of claim 1, wherein, The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine.

3. The intelligent control system for large scale devolatilizers of claim 2, wherein, The application relates to a self-adaptive control system for a devolatilization machine.

4. The intelligent control system for large scale devolatilizers of claim 1, wherein, The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine.

5. The intelligent control system for large scale devolatilizers of claim 1, wherein, The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine.

6. The intelligent control system for large scale devolatilizers of claim 1, wherein, The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolatilization machine. The application relates to a self-adaptive control system for a devolat 7. A method of adaptive regulation of a large scale devolatilizer, characterized by, The application is applied to the intelligent control system of a large-scale devolatilization machine as claimed in any one of claims 1-6, and comprises the following steps: Step S210: collecting process variable data in the operation of the devolatilization machine in real time through a sensor group, wherein the process variable data comprises the temperature, pressure, stirring shaft power of each stage cavity, and melt flow rate at the inlet and outlet; Step S220: inputting the collected process variable data into a volatile component concentration predictor, dynamically estimating and outputting the real-time average volatile component concentration of the melt in the current cavity; Step S230: taking the real-time average volatile component concentration as feedback input, taking the heating power and vacuum degree set value as optimization variables, and solving the optimal set value combination in the next control cycle by using a collaborative optimization function; Step S240: driving the actuator to act with the optimal set value combination, and completing the adaptive adjustment of the devolatilization process.

Images