PVA production process control system based on key process parameter identification

Abstract

The invention discloses a PVA production process control system based on key process parameter identification. The method comprises the following steps: acquiring expected control signal information and feedback control signal information; the feedback control signal information comprises first feedback control signal information and second feedback control signal information; the first feedback control signal information represents the temperature of the middle position of the reaction kettle; the second feedback control signal represents the temperature of the bottom of the reaction kettle; performing signal generation processing on the expected control signal information and the feedback control signal information to obtain first target control signal information; performing signal generation processing on the feedback control signal information and the first target control signal information to obtain second target control signal information; the second target control signal information is used for controlling the temperature of the bottom of the reaction kettle.

Description

Technical Field

[0001] This invention relates to the field of control technology, and in particular to a PVA production process control system based on the identification of key process parameters. Background Technology

[0002] PVA is a precursor to PVB in chemical synthesis and is also a type of polymer, serving as an irreplaceable raw material in PVB production. The PVA production process control typically exhibits complex dynamic characteristics and is prone to nonlinearity and disturbances. Specifically, the dynamic characteristics are complex because the heat transfer coefficients and exothermic reaction rates differ significantly at different reaction stages, leading to time-varying model parameters. The limitations of PID control in handling nonlinear and time-varying conditions are becoming increasingly apparent. Therefore, this paper proposes a PVA production process control system based on the identification of key process parameters to improve the control accuracy and dynamic response performance of the PVA production process. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a PVA production process control system based on the identification of key process parameters, which is beneficial to improving the control accuracy and dynamic response efficiency of the PVA production process.

[0004] To address the aforementioned technical problems, a first aspect of the present invention discloses a control method, the method comprising: Acquire desired control signal information and feedback control signal information; the feedback control signal information includes first feedback control signal information and second feedback control signal information; the first feedback control signal information represents the temperature at the middle position of the reactor; the second feedback control signal information represents the temperature at the bottom of the reactor. The desired control signal information and the feedback control signal information are processed to generate a first target control signal information. The feedback control signal information and the first target control signal information are processed to generate a second target control signal information; the second target control signal information is used to control the temperature at the bottom of the reactor.

[0005] A second aspect of this invention discloses a control system, the system comprising: The acquisition module is used to acquire desired control signal information and feedback control signal information; the feedback control signal information includes first feedback control signal information and second feedback control signal information; the first feedback control signal information represents the temperature at the middle position of the reactor; the second feedback control signal information represents the temperature at the bottom of the reactor. The first processing module is used to perform signal generation processing on the desired control signal information and the feedback control signal information to obtain the first target control signal information; The second processing module is used to perform signal generation processing on the feedback control signal information and the first target control signal information to obtain the second target control signal information; the second target control signal information is used to control the temperature of the bottom of the reactor.

[0006] A third aspect of the present invention discloses another control system, the system comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in the control method disclosed in the first aspect of the present invention.

[0007] The fourth aspect of the present invention discloses a computer-readable storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the control method disclosed in the first aspect of the present invention. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a schematic diagram of a scenario for the control system provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating a control method disclosed in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a control system disclosed in an embodiment of the present invention; Figure 4 This is a schematic diagram of another control system disclosed in an embodiment of the present invention; Figure 5 These are effect diagrams of an embodiment of the present invention. Detailed Implementation

[0010] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. 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.

[0011] It should be noted that the terminology used in the embodiments of this application is for the purpose of describing specific embodiments only and is not intended to limit the application. The singular forms "a," "the," and "the" used in the embodiments of this application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0012] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0013] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0014] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0015] It should be noted that the term "and / or" used in this application is merely a description of the same field in the related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0016] It should be noted that, depending on the context, the word "if" as used herein can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0017] It should be noted that in the description of this application, the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", and "outer" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the system or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0018] It should be noted that the phrase "within the range" used in this application, unless otherwise specified, includes both endpoints of the range by default. For example, in the range of 1 to 5, it includes the values ​​1 and 5.

[0019] It should be noted that since the method in this application embodiment is executed in a computer device, the processing objects of each computer device exist in the form of data or information, such as time, which is essentially time information. It is understood that if size, quantity, position, etc. are mentioned in subsequent embodiments, they are all corresponding data that exist so that the computer device can process them. Specific details will not be elaborated here.

[0020] It should be noted that the artificial intelligence-related technologies that may be involved in this application will be briefly described. Artificial intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. Artificial intelligence is the study of the design principles and implementation methods of various intelligent machines, enabling machines to have the functions of perception, reasoning, and decision-making.

[0021] Artificial intelligence (AI) is a comprehensive discipline encompassing a wide range of fields, including both hardware and software technologies. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies primarily include computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0022] Computer vision (CV) is a science that studies how to enable machines to "see." More specifically, it refers to machine vision, which uses cameras and computers to replace human eyes in recognizing and measuring targets, and then performs image processing to create images more suitable for human observation or transmission to instruments. As a scientific discipline, computer vision studies related theories and technologies, attempting to build artificial intelligence systems capable of extracting information from images or multidimensional data. Computer vision technologies typically include image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content / behavior recognition, 3D object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping (SLAM), and common biometric recognition technologies such as facial recognition and fingerprint recognition.

[0023] Monomodal information refers to data of only one type, such as text, images, audio, video, or electromagnetic signals. Multimodal information refers to data that includes at least two types of monomodal information. Furthermore, multimodal information is suitable for complex tasks that require the integration of multiple information sources, such as sentiment analysis, robot interaction, and autonomous driving. By integrating information from multiple modalities, higher performance and accuracy can usually be achieved in these tasks.

[0024] Large models refer to artificial neural network models with a very large number of parameters. In the field of artificial intelligence, large models typically refer to models with hundreds of millions to trillions of parameters. These models usually need to be trained on large-scale datasets and require a significant amount of computing resources for optimization and tuning. Large models are commonly used to solve complex tasks such as natural language processing, computer vision, and speech recognition. Generative AI is a type of AI that can create new content and ideas, including dialogues, stories, images, videos, and music. In this embodiment, the large model can be a large-scale pre-trained model such as the ChatGPT series, BERT, XLNet, Zhipu model, Claude, Moonshot AI model, ChatGLM model, Gemini series, Qianyitongwen model, MiniMax model, Xinghuo model, Llama model, 360GPT model, Qwen model, Baichuan model, Yunque model, vivoLM model, deepseek, Tencent Yuanbao, and Wenxin Yiyan, etc. This embodiment does not limit the scope of the large model.

[0025] This application provides a control method, system, computer device, and computer-readable storage medium, which will be described in detail below.

[0026] Please see Figure 1 , Figure 1 This is a schematic diagram of a scenario for the control system provided in an embodiment of this application. The control system may include a computer device 100, which integrates the control system, such as... Figure 1 Computer equipment in the country.

[0027] In this embodiment of the application, the computer device 100 is mainly used to acquire desired control signal information and feedback control signal information; the feedback control signal information includes first feedback control signal information and second feedback control signal information; the first feedback control signal information represents the temperature at the middle position of the reactor; the second feedback control signal represents the temperature at the bottom of the reactor. The desired control signal information and the feedback control signal information are processed to generate the first target control signal information. The feedback control signal information and the first target control signal information are processed to generate the second target control signal information; the second target control signal information is used to control the temperature at the bottom of the reactor.

[0028] It can improve the control precision and dynamic response efficiency of the PVA production process.

[0029] In this embodiment, the computer device 100 can be a standalone server, a server network, or a server cluster. For example, the computer device 100 described in this embodiment includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. The cloud server is composed of a large number of computers or network servers based on cloud computing.

[0030] It is understood that the computer device 100 used in the embodiments of this application can be a device that includes both receiving and transmitting hardware, that is, a device having receiving and transmitting hardware capable of performing bidirectional communication on a bidirectional communication link. Such a device may include: cellular or other communication devices having a single-line display, a multi-line display, or a cellular or other communication device without a multi-line display. Specifically, the computer device 100 may be a desktop terminal or a mobile terminal, and may also be one of a mobile phone, tablet computer, laptop computer, etc.

[0031] Those skilled in the art will understand that Figure 1 The application environment shown is merely one application scenario of the solution in this application and does not constitute a limitation on the application scenario of the solution in this application. Other application environments may include those that are more specific to this application. Figure 1 The number of computer devices shown is more or less, for example Figure 1 Only one computer device is shown in the diagram. It is understood that the control system may also include one or more other services, which are not limited here.

[0032] In addition, such as Figure 1 As shown, the control system may also include a memory 200 for storing data, such as image data and location information.

[0033] It should be noted that, Figure 1 The schematic diagram of the control system shown is merely an example. The control system and scenario described in this application are intended to more clearly illustrate the technical solutions of this application and do not constitute a limitation on the technical solutions provided in this application. As those skilled in the art will know, with the evolution of control systems and the emergence of new business scenarios, the technical solutions provided in this application are also applicable to similar technical problems.

[0034] This invention discloses a PVA production process control system based on key process parameter identification, which is beneficial to improving the control accuracy and dynamic response efficiency of the PVA production process. Detailed descriptions follow.

[0035] Example 1 Please see Figure 2 , Figure 2 This is a flowchart illustrating a control method disclosed in an embodiment of the present invention. Wherein, Figure 2 The described control method is applied in a management system, such as a local server or cloud server for management, and the embodiments of the present invention are not limited thereto. Figure 2 As shown, the control method may include the following operations: 101. Obtain the desired control signal information and the feedback control signal information.

[0036] In this embodiment of the invention, the feedback control signal information includes first feedback control signal information and second feedback control signal information.

[0037] In this embodiment of the invention, the first feedback control signal information represents the temperature at the middle position of the reactor.

[0038] In this embodiment of the invention, the second feedback control signal characterizes the temperature at the bottom of the reactor.

[0039] 102. Perform signal generation processing on the desired control signal information and the feedback control signal information to obtain the first target control signal information.

[0040] 103. Perform signal generation processing on the feedback control signal information and the first target control signal information to obtain the second target control signal information.

[0041] In this embodiment of the invention, the second target control signal information is used to control the temperature at the bottom of the reactor.

[0042] It should be noted that the control method of this application adopts a dual closed-loop cascade control architecture, clearly distinguishing between the outer loop with feedback of "temperature at the middle position of the reactor" and the inner loop with feedback of "temperature at the bottom of the reactor". This solves the problem of poor control quality caused by the non-uniform temperature field and complex dynamic characteristics (non-linear and time-varying) of the reactor in PVA production, thereby achieving coordinated control of the non-uniform temperature field inside the reactor and improving accuracy, response speed and stability. The embodiments of this invention are not limited.

[0043] Furthermore, step 102 focuses on the long-term stability of the core process parameter (middle temperature), eliminating the problem that while the bottom temperature may be stable under single-loop control, the middle temperature may have deviated from the process requirements. Step 103 specifically suppresses local and rapid disturbances occurring at the bottom of the vessel, preventing their propagation and impact on the outer loop, significantly accelerating the system response speed. It is evident that the cascade structure compensates for some nonlinear and time-varying characteristics of the inner loop process by the inner loop controller, thereby purifying the process characteristics of the outer loop and reducing the sensitivity of the entire system to parameter changes and disturbances. This benefits the control system by improving control accuracy, accelerating dynamic response, and enhancing system robustness. The embodiments of this invention are not limited to these specific examples.

[0044] like Figure 5 As shown, the method of this application has better performance than Ground Truth and fuzzy PID control. That is, this application can better balance control accuracy and dynamic response, and has better robustness. The embodiments of this invention are not limited.

[0045] It should be noted that the key process parameters in the above control method may include first weight parameter information, second weight parameter information, etc., which can be identified based on a large model, and this embodiment of the invention does not limit this. Furthermore, before identifying the key process parameters, the data is standardized as follows to eliminate the differences in the dimensions of each parameter:

[0046] Where x represents the original data; μ represents the mean; σ represents the standard deviation; and z represents the standard data value.

[0047] Pearson correlation coefficient:

[0048] r is the Pearson correlation coefficient; , It is the i-th sample point; y and y are the means of x and y, respectively; n is the sample size.

[0049] Furthermore, the identification of key process parameters can be based on an improved Adabosst algorithm, which includes: The formula used by weak learning machine A is:

[0050] in, This involves concatenating vectors. The input vector is normalized. This is the output vector of the MLP network.

[0051] Weak learning machine B:

[0052] in, This represents the output vector of the SVR.

[0053] Weak learning machine C:

[0054]

[0055] in, This represents the regression target vector of the regression function.

[0056] Furthermore, Adaboost regression theory is applied to update the dataset weights and weak learning machine weights, and the regression theory for synthesizing strong learning machines from weak learning machines is optimized to improve the performance of the regression model. Assume the... Weak learning machine Its error on the training set:

[0057] in, The maximum absolute error across all samples; m is the total number of samples in the training set; and For the first One regression input vector and one regression target vector; For the first Each sample relative to The squared relative error.

[0058] Then, the sample data weight set for the t-th weak learning machine is initialized. :

[0059] During initialization, the weight value of each sample is 0. . No. The relative loss of each weak learning machine and the ensemble weight of the weak learning machines are expressed as follows:

[0060] in, Let be the total relative loss of the t-th weak learning machine.

[0061] application This represents the importance of the relative error, and is also the ensemble weight of the weak learning machine; the smaller the error, the higher the importance. The weights for each sample are then updated:

[0062] in, As a normalization factor, it can guarantee The value does not increase or decrease infinitely with training iterations; Let be the sample weight value of the i-th sample in the next round of update.

[0063] Finally, after iterative training, AdaBoost typically selects only the weak learning machine with the largest weight value as the weak learning machine output:

[0064] in, This is the output of the Adaboost algorithm, and its output is the weights. The largest The output of this method is shown. However, this method completely ignores the role of other weak learning machines. An improved approach is to use the softmax function for optimization.

[0065] in, The i-th parameter in the vector of parameters to be identified that the regression function regresses; This represents the i-th output in the regression function vector, corresponding to the weak learning machine. ; Index for weak learning machines.

[0066] Furthermore, the immune ant colony algorithm can be used in the identification of key process parameters. The artificial immune algorithm introduces antibody concentration, which represents the proportion of similar optimal solutions in the entire population, and is used to measure whether the population is trapped in local overfitting.

[0067] in, Antibody affinity, i.e., the affinity between two antibodies. The degree of similarity. The similarity of hyperparameter combinations. Here, L is the setpoint, representing the antibody length, i.e., the number of hyperparameters. When the number of similar parameters exceeds... If the two numbers are similar, they are defined as similar; otherwise, they are not similar. This is a relatively simple parameter similarity measure function, which uses parameters that are completely identical as the measure of parameter similarity. The antibody concentration is the average antibody affinity of t with all antibodies in the population. Subsequently, the artificial immune algorithm calculates the Excellence operator. Excellence is an operator that combines antibody concentration with a fitness function; it can be considered as a fitness function with regularization based on antibody concentration. This operator is inspired by the immune system, where an increase in the number of identical immune cells can enhance the immune effect. It is a means to maintain the continuous evolution of immune cells to form new antibodies. To maintain the search range of the artificial immune algorithm, the Excellence operator is:

[0068] Where J is the Excellence operator, The coefficient is used to balance the antibody concentration-based regularization and the fitness function, and is generally taken to be close to 1. This represents the ratio of the current individual's fitness function to that of all individuals in the population. Due to the mean squared error property, the fitness function must be positive. Additionally, it uses... To assess antibody concentration, more genes of superior antibodies can be selected and utilized.

[0069] Crossover and mutation operators are important operators for antibody modification and recombination, enabling antibody coding updates and obtaining new hyperparameter combinations.

[0070] This represents the probability of selection via a roulette wheel, also known as the crossover probability. When an individual j has a relatively high Excellence value, it has a higher probability of being selected as a parent sample. Two parent samples form a new hyperparameter set by exchanging some hyperparameter values. Adaptive mutation is then incorporated so that some values ​​are not entirely dependent on the parent parameter combination, thus expanding the search range. To propose a novel adaptive method for calculating mutation probability, t is a constant coefficient controlling the overall probability upper limit. This represents the individual with the optimal fitness function in the current generation H. The dot (.) represents the optimal fitness function for the HRth generation. R is the interval between generations. N represents the top N individuals of the current population (sorted by fitness). Let i represent the fitness value of the i-th individual in the population, and the fitness values ​​of the current N individuals. Part Two Calculations and The average absolute difference between them. Part 1 The coefficients are used to control intergenerational exploration interest. The greater the change in the optimal fitness function, the higher the mutation probability will be, creating positive feedback. Part Two: Applications This is used to control the exploration speed within the current generation of the population. When there are large differences in the population, it further encourages searching, forming a positive feedback loop. The combination of these two parts constitutes the adaptive mutation operator. .

[0071] Furthermore, an ant colony immunity algorithm is constructed based on the aforementioned artificial immunity algorithm: First, construct the initial pheromone tensor, treating a set of hyperparameter combinations as a single coordinate. Then, the complete pheromone tensor is:

[0072] This represents a 16-dimensional tensor. Typically, during initialization... The matrix takes the value 1. Because... If the dimensions are too large, the program will struggle to run due to memory limitations. In actual program execution... The matrix sampling only retains the coordinates and pheromone values ​​of the individuals traversed; paths not yet traversed are automatically assigned a pheromone concentration of 1. This simplification does not affect the results or formula representation.

[0073]

[0074] This method represents a significant improvement over ordinary ant colony movement operators. Ordinary movement operators rely solely on pheromone concentration and distance, leading to instances of individual ants repeatedly exploring the same area. Furthermore, it is difficult to apply to non-pathfinding problems. Equation (2-19) demonstrates a significant improvement in this approach. Let A be the probability of the desired parameter combination being selected. If we denote this coordinate as A, then the pheromone density at that point is... and the fitness function of the current point. The value, and the reciprocal of the average distance to other individuals in the current population. The reciprocal of the distance term can have a similar effect to pheromones, causing the group to converge towards the optimal individual. Another optimization point is... tensor, The tensor is a repeated exploration weakening operator, related to the pheromone concentration tensor. Consistent dimensions. By using matrix dot product, the selection probability is reduced by multiplying the coordinates of historical fitness calculations by a fixed coefficient, thereby reducing the calculation of coordinates that have already undergone fitness calculations, preventing wasted computing power, and accelerating the iteration to the optimum.

[0075] Pheromone tensor update operator:

[0076] Specifically, when the fitness function decreases (i.e., when the improved Adaboost regression MSE value decreases), the parameters are fixed. This increases the information velocity concentration at that coordinate point. Then, using... Constant coefficients are used in the early pheromone dissipation process during iteration, and new coefficients are introduced. The value allows the pheromone concentration to continuously change during iterations to adapt to the current population movement process.

[0077] Finally, in the proposed artificial immune ant colony algorithm, the migration operator is:

[0078] By using the migration operator, the artificial immune algorithm population is... The three best individuals are determined by using a roulette wheel probability algorithm instead of an ant colony. Similarly, the three best individuals from the improved ant colony algorithm are replaced with the three worst individuals from the artificial immune algorithm using a roulette wheel probability test. This completes the migration operator operation.

[0079] It is evident that implementing the control method described in the embodiments of the present invention is beneficial to improving the control accuracy and dynamic response efficiency of the PVA production process.

[0080] In an optional embodiment, the above-described signal generation processing of the feedback control signal information and the first target control signal information to obtain the second target control signal information includes: The first target control signal information and the second feedback control signal information in the feedback control signal information are analyzed and processed to obtain the first process control signal information; the first process control signal information includes the first sub-control signal information and the second sub-control signal information. The first process control signal information is processed to generate the second target control signal information.

[0081] It should be noted that the above-mentioned signal generation processing of feedback control signal information and first target control signal information to obtain second target control signal information decomposes complex calculations into two steps: analysis and processing and signal generation, which reduces the complexity of system design. This embodiment of the present invention does not limit this.

[0082] It should be noted that the above analysis and processing of the second feedback control signal in the first target control signal information and the feedback control signal information involves first subtracting the first target control signal corresponding to the first target control signal information and the second feedback control signal in the feedback control signal information to obtain the first sub-control signal information. Then, combining the historical first sub-control signal information and the currently calculated first sub-control signal information, differential processing is performed to obtain the second sub-control signal information. In other words, using the first target control signal and the bottom temperature feedback as inputs, a first process control signal containing two components is parsed out, namely, the first sub-control signal information representing the comprehensive deviation between the outer loop command and the inner loop state, and the second sub-control signal information representing the dynamic change trend of the inner loop state. This embodiment of the invention is not limited to this.

[0083] It is evident that implementing the control method described in the embodiments of the present invention is beneficial to improving the control accuracy and dynamic response efficiency of the PVA production process.

[0084] In another optional embodiment, the first process control signal information is subjected to signal generation processing to obtain the first target control signal information, including: Based on the first process control signal information, control parameter information is determined; the control parameter information includes a first control parameter value, a second control parameter value, and a third control parameter value; Based on the control parameter information and the first process control signal information, the second target control signal information is determined.

[0085] It should be noted that the control parameter information determined based on the first process control signal information is to determine the dynamic parameters of the control system. That is, it is no longer preset and fixed, but is dynamically determined online according to the "first process control signal information" that reflects the real-time state of the system, so as to adapt to the time-varying and nonlinear characteristics of the PVA production process and maintain excellent control performance and stability. This embodiment of the invention does not limit this.

[0086] It is evident that implementing the control method described in the embodiments of the present invention is beneficial to improving the control accuracy and dynamic response efficiency of the PVA production process.

[0087] In yet another optional embodiment, control parameter information is determined based on the first process control signal information, including: The first process control signal information is processed by nonlinear calculation to obtain the first calculation parameter information; The first signal generation model is used to calculate and process the first weight parameter information and the first calculation parameter information to obtain the control parameter information.

[0088] It should be noted that the above-mentioned determination of control parameter information based on the first process control signal information is achieved by performing a deeper, nonlinear analysis of the process signal to capture its complex inherent laws, and by using "nonlinear calculation processing" to drive the adaptive adjustment of parameters, thereby more efficiently matching the current control state and improving control accuracy and dynamic response. This embodiment of the invention does not limit this.

[0089] It should be noted that the above-mentioned first signal generation model is as follows: ; In the formula, The first character in the characterization of control parameter information One control parameter value; The first calculated parameter information represents the first The first calculated parameter value; The coordinates in the first weight parameter information are The weight parameter values.

[0090] It should be noted that the aforementioned first weight parameter information can be determined by user input or based on historical weight parameter values; this embodiment of the invention does not impose any limitations.

[0091] It is evident that implementing the control method described in the embodiments of the present invention is beneficial to improving the control accuracy and dynamic response efficiency of the PVA production process.

[0092] In another optional embodiment, the first process control signal information is subjected to nonlinear analysis and calculation to obtain first calculation parameter information, including: The first sub-control signal information and the second sub-control signal information in the first process control signal information are calculated and processed using the first nonlinear coupling model and the second nonlinear coupling model respectively to obtain the first coupling factor information and the second coupling factor information; the first coupling factor information includes 3 first coupling factors; the second coupling factor information includes 3 second coupling factors. The first nonlinear coupling model is as follows: ; The second nonlinear coupling model is: ; In the formula, Characterizing the first coupling factor information The first coupling factor; and These respectively characterize the first sub-process control signal information and the second sub-process control signal information in the first process control signal information; Characterizing the second coupling factor information A second coupling factor; and These respectively characterize the first strength coefficient and the second strength coefficient; and The first shape factor and the second shape factor are respectively characterized; Characterizing the first The first characteristic center value corresponding to a typical macroscopic working condition; Characterizing the first The second characteristic center value corresponding to a typical bottom temperature dynamic; The first coupling factor information and the second coupling factor information are synthesized by corresponding elements using a signal synthesis model, and the first calculation parameter information is obtained by normalization. The signal synthesis model is as follows: ; In the formula, The first calculated parameter information represents the first The first calculated parameter value; Characterized by the normalization coefficient; and Representing the first coupling factor information respectively The first coupling factor and the second The first coupling factor; and The second coupling factor information is characterized respectively. The second coupling factor and the first A second coupling factor.

[0093] It should be noted that the first strength coefficient and the second strength coefficient, the first shape factor and the second shape factor mentioned above are pre-calibrated based on the nonlinear heat transfer characteristics and the exothermic reaction rate of the reactor in the PVA production process, and are not limited in the embodiments of the present invention.

[0094] It should be noted that the above-mentioned... The first characteristic center value and the second characteristic center value corresponding to a typical macroscopic working condition The second characteristic center value corresponding to a typical bottom temperature dynamic can be obtained by analyzing historical data, and this embodiment of the invention does not limit it.

[0095] It should be noted that the above normalization coefficients are positive numbers not greater than 1 and not less than 0, such as 0.1, 0.2, etc., and are not limited in the embodiments of the present invention.

[0096] It should be noted that the above-mentioned nonlinear analysis and calculation of the first process control signal information to obtain the first calculation parameter information is achieved by using two nonlinear coupling models to calculate the matching degree (i.e., coupling strength) between the first and second subprocess control signal information and a series of preset typical operating condition center values. Then, the coupling factors are multiplied by a signal synthesis model to obtain the comprehensive weight of each typical operating condition. After normalization, this weight represents the current control strategy that should be adopted. The confidence level of preset parameters is used, that is, the controller parameters are dynamically determined as a weighted average of preset parameters under various typical operating conditions by calculating the similarity between the current state and a set of typical states. Therefore, this weighted switching mechanism can approximate complex nonlinear processes with high accuracy, achieving smooth, disturbance-free controller parameter adaptation. This parameter determination method not only provides a clear logical interpretation of the entire calculation process, superior to "black box" neural networks, but also enables the controller to maintain optimal performance throughout the entire production cycle by preset multiple sets of parameters optimized for different typical operating conditions. This embodiment of the invention is not limited in its scope. Furthermore, the first and second nonlinear coupling models are based on the fusion results of multiple typical operating conditions, rather than decisions based on a single operating condition. This makes the system more adaptable to intermediate states or unknown disturbances that are not precisely defined as typical operating conditions, thereby improving the stability and accuracy of control. This embodiment of the invention is not limited in its scope.

[0097] It is evident that implementing the control method described in the embodiments of the present invention is beneficial to improving the control accuracy and dynamic response efficiency of the PVA production process.

[0098] In an optional embodiment, the determination of the second target control signal information based on the control parameter information and the first process control signal information includes: Acquire historical system control information; historical system control information includes historical first target control signal information, historical target control signal information, and historical control target object information; The historical system control information, the second weight parameter information set, and the first calculation parameter information are parsed and processed to obtain the corrected weight information; the corrected weight information includes the first corrected weight value, the second weight value, and the third weight value; The target signal generation model is used to process historical system control information, control parameter information, and correction weight information to generate the second target control signal information. The target signal generation model is as follows: ; In the formula, Characterizes the control signal information of the second target; , and These respectively represent the first control parameter value, the second control parameter value, and the third control parameter value in the control parameter information; , and These respectively represent the first, second, and third corrected weight values ​​in the corrected weight information; Characterizes the control signal information of the first target in history.

[0099] It should be noted that the production control of PVA process under continuous operating conditions should not only be based on the parameter adaptation of the current state, but can also be further optimized by drawing on historical experience. Therefore, after determining the control parameter information, historical control data can be used to predict trends, suppress overshoot, and achieve more stable control. The approach in this application is to determine the second target control signal information based on the control parameter information and the first process control signal information. The second target control signal information uses the temperature at the middle position of the reactor as the main controlled variable. Its function is to ensure that the temperature in the core reaction area can accurately track the expected value. Moreover, it integrates the signals from the current moment and the previous moment, which improves the perception capability of the outer loop controller, making its decision based on trends rather than just instantaneous values, and ensuring that the set signal sent to the inner loop is more stable and reasonable. The embodiments of this invention are not limited.

[0100] It should be noted that the aforementioned historical first target control signal information represents the first target control signal information calculated at multiple past moments. The historical target control signal information represents the second target control signal information calculated at multiple past moments. The historical control target object information represents the actual temperature of the reactor bottom at multiple past moments, which is not limited in this embodiment of the invention.

[0101] It should be noted that the above-described signal generation process, which utilizes the target signal generation model to process historical system control information, control parameter information, and correction weight information to obtain the second target control signal, comprehensively leverages historical control experience, real-time adaptively adjusted controller parameters, and correction weights learned from historical data to generate an optimal control command generation method capable of achieving "fast, stable, precise, and overshoot-free" control effects. The historical system control information, representing the second target control signal output from the previous control cycle, serves to provide the basic control quantity in the model, ensuring control continuity and avoiding significant jumps. The correction weight information and control parameter information can be further improved by using proportional, integral, and derivative actions to better correct errors and more effectively enhance control accuracy; however, this embodiment of the invention does not impose limitations on these methods.

[0102] It should be noted that the above-mentioned second weight parameter information set includes the second weight parameter information at the current time, the second weight parameter information at the previous time, and the second weight parameter information at the time before that. This embodiment of the invention does not limit this.

[0103] In this optional embodiment, as an optional implementation method, the above-described parsing and processing of historical system control information, second weight parameter information set, and first calculation parameter information to obtain corrected weight information includes: The process weight information is obtained by parsing the historical system control information, the second weight parameter information set, and the first calculation parameter information using the first weight correction model. The first weight correction model is as follows: ; In the formula, The first weight information in the representation process Each process weight parameter value; The first calculated parameter information represents the first The first calculated parameter value; The second weight parameter information representing the current time moment The second weight parameter value; The second weight parameter information representing the previous time step The second weight parameter value; The second weight parameter information representing the previous time step. The second weight parameter value; Characterizes the historical first target control signal information in the historical system control information; Information representing historical control target objects in historical system control information; Characterizes historical target control signal information in historical system control information; The process weight information is analyzed and processed using the second weight correction model to obtain the corrected weight information; The second modified model is as follows: ; In the formula, , and These represent the first, second, and third corrected weight values ​​in the corrected weight information, respectively.

[0104] It should be noted that tt represents the current time, tt-1 represents the previous time, and tt-2 represents the time before that. This embodiment of the invention does not limit the time.

[0105] It should be noted that the above-mentioned parsing and processing of historical system control information, the second weight parameter information set, and the first calculation parameter information to obtain corrected weight information includes two stages. The first stage uses a first weight correction model to parse the input data and obtain process weight information, which updates the second weight parameter values ​​using an adaptive learning method based on gradient descent. Then, in the second stage, a linear transformation is performed on the process weight information to solve for the corrected weight information. The two processes of parsing and processing historical system control information, the second weight parameter information set, and the first calculation parameter information in this application can adjust the weights online through historical errors and system gradients, enabling the controller to automatically optimize parameters and adapt to system changes. Simultaneously, the linear transformation of the second model ensures the continuity of the control signal and avoids jumps. Therefore, the method of this application has significant improvements in accuracy, stability, and anti-interference capabilities compared to static control methods. The embodiments of this invention are not limited to these specific methods.

[0106] It is evident that implementing the control method described in the embodiments of the present invention is beneficial to improving the control accuracy and dynamic response efficiency of the PVA production process.

[0107] In another optional embodiment, the desired control signal information and the feedback control signal information are processed to generate a first target control signal information, including: The desired control signal information and the feedback control signal information are fused to obtain fused control signal information. The desired control signal information includes the first desired control signal at the current time and the second desired control signal at the previous time. The first feedback control signal information includes the first feedback control signal at the current time and the second feedback control signal at the previous time. The fusion processing characterizes the signals at the current time and the previous time to be rearranged in chronological order and in the order of desired control signal and feedback control signal to form a signal vector. The fused control signal information is processed to generate the first target control signal information.

[0108] It should be noted that the above-mentioned signal generation processing of the desired control signal information and feedback control signal information to obtain the first target control signal information is mainly to improve the decision quality of the outer loop controller, so that the inner loop setpoint (first target control signal) it gives is not only accurate but also changes smoothly, avoiding unnecessary impact on the inner loop. This embodiment of the invention does not limit this.

[0109] It should be noted that the above-mentioned signal fusion processing of the first feedback control signal information in the desired control signal information and feedback control signal information is to fuse the desired signal and the feedback signal at the current time and the previous time in chronological order to form a signal vector, which not only contains the current error information, but also implies the error change trend. This makes the outer loop controller's decision based on richer information and has predictive ability, enabling the outer loop controller to perceive the change trend earlier, which is more conducive to improving the dynamic quality of the entire cascade system. The embodiments of the present invention are not limited thereto.

[0110] In this optional embodiment, as an optional implementation, the above-described signal generation processing of the fused control signal information to obtain the first target control signal information includes: Obtain the second weight parameter information; The second weight parameter information and the fused control signal information are weighted and summed to obtain the weighted control signal information. The weighted control signal information is processed using a target control signal generation model to obtain the first target control signal information. The target control signal generation model is as follows: ; In the formula, Characterizes the control signal information of the first target; It represents the weighted control signal information.

[0111] It should be noted that the aforementioned second weight parameter information can be determined by user input or obtained based on the analysis of historical weights; this embodiment of the invention does not impose any limitations. Furthermore, the second weight parameter information changes over time; that is, the system contains several second weight parameter information, and each moment has a new second weight parameter information, which may be the same as or different from the second weight parameter information of the previous moment; this embodiment of the invention does not impose any limitations.

[0112] It should be noted that the above-mentioned signal generation processing of the fused control signal information to obtain the first target control signal information, followed by weighted summation of the second weight information and the fused control signal, can adjust the influence of each signal component in the overall control signal, making the control signal more in line with the current dynamic requirements of the system. The weighted control signal information is then input into the target control signal generation module, i.e., a nonlinear transformation is performed on the input weighted control signal information to limit and normalize the amplitude of the control signal, ensuring that the output first target control signal varies within a reasonable range, avoiding system shocks caused by signal abrupt changes, and making the control output more continuous and stable. This embodiment of the invention does not impose limitations.

[0113] Furthermore, compared to traditional controllers that often rely solely on a single signal at the current moment when generating target control signals, ignoring historical errors and their changing trends, which can lead to abrupt changes or over-response in the control signal and cause severe impacts or instability in the inner-loop controlled object, this application performs signal generation processing on the desired control signal information and feedback control signal information to obtain the first target control signal information. By fusing the desired and feedback signals from the current and previous moments, a comprehensive analysis of error information and its changing trends is achieved. This enables the generated target control signal to reference historical dynamics, more accurately reflecting the current state and changing trends of the system, thereby improving the smoothness and continuity of the control signal. Furthermore, if an unsmoothed or nonlinearly processed fused signal is directly used in the PVA process control, it may cause severe fluctuations in the control signal, affecting the stable operation of the overall system. By introducing a target control signal generation model, appropriate soft constraints can be applied to the weighted fused signal, effectively suppressing excessive control amplitude changes, avoiding unnecessary impacts on the inner loop, and ensuring the stability and reliability of the control system. Furthermore, since signal fusion encompasses the time-series information of the error, the first target control signal generated after weighting and nonlinear transformation of the fused signal can detect error changes and trends in advance, improving the predictability and decision-making quality of the controller, thereby improving the dynamic performance of the cascade control system and achieving faster response speed and lower overshoot. This embodiment of the invention is not limited to this. Therefore, the above-described signal generation processing of the desired control signal information and feedback control signal information effectively solves the problems of abrupt control signal changes, unsmooth response, and insufficient dynamic performance in traditional control systems. It improves the accuracy, smoothness, and predictability of the first target control signal output by the outer loop controller, thereby optimizing the dynamic quality and stability of the overall cascade control system.

[0114] It is evident that implementing the control method described in the embodiments of the present invention is beneficial to improving the control accuracy and dynamic response efficiency of the PVA production process.

[0115] Example 2 Please see Figure 3, Figure 3 This is a schematic diagram of the structure of a control system disclosed in an embodiment of the present invention. Figure 3 The described system can be applied to management systems, such as managing local servers or cloud servers, and the embodiments of this invention are not limited thereto. Figure 3 As shown, the system may include: The acquisition module 201 is used to acquire desired control signal information and feedback control signal information; the feedback control signal information includes first feedback control signal information and second feedback control signal information; the first feedback control signal information represents the temperature at the middle position of the reactor; the second feedback control signal represents the temperature at the bottom of the reactor. The first processing module 202 is used to perform signal generation processing on the desired control signal information and the feedback control signal information to obtain the first target control signal information; The second processing module 203 is used to perform signal generation processing on the feedback control signal information and the first target control signal information to obtain the second target control signal information; the second target control signal information is used to control the temperature of the bottom of the reactor.

[0116] It is evident that implementation Figure 3 The described control system is beneficial for improving the control accuracy and dynamic response efficiency of the PVA production process.

[0117] In another alternative embodiment, such as Figure 3 As shown, the feedback control signal information and the first target control signal information are processed to generate the second target control signal information, including: The first target control signal information and the second feedback control signal information in the feedback control signal information are analyzed and processed to obtain the first process control signal information; the first process control signal information includes the first sub-control signal information and the second sub-control signal information. The first process control signal information is processed to generate the second target control signal information.

[0118] It is evident that implementation Figure 3 The described control system is beneficial for improving the control accuracy and dynamic response efficiency of the PVA production process.

[0119] In yet another alternative embodiment, such as Figure 3 As shown, the first process control signal information is processed to generate the second target control signal information, including: Based on the first process control signal information, control parameter information is determined; the control parameter information includes a first control parameter value, a second control parameter value, and a third control parameter value; Based on the control parameter information and the first process control signal information, the first target control signal information is determined.

[0120] It is evident that implementation Figure 3 The described control system is beneficial for improving the control accuracy and dynamic response efficiency of the PVA production process.

[0121] In yet another alternative embodiment, such as Figure 3 As shown, based on the first process control signal information, the control parameter information is determined, including: The first process control signal information is processed by nonlinear calculation to obtain the first calculation parameter information; The first signal generation model is used to calculate and process the first weight parameter information and the first calculation parameter information to obtain the control parameter information.

[0122] It is evident that implementation Figure 3 The described control system is beneficial for improving the control accuracy and dynamic response efficiency of the PVA production process.

[0123] In yet another alternative embodiment, such as Figure 3 As shown, nonlinear analysis and calculation are performed on the first process control signal information to obtain the first calculation parameter information, including: The first sub-control signal information and the second sub-control signal information in the first process control signal information are calculated and processed using the first nonlinear coupling model and the second nonlinear coupling model respectively to obtain the first coupling factor information and the second coupling factor information; the first coupling factor information includes 3 first coupling factors; the second coupling factor information includes 3 second coupling factors. The first nonlinear coupling model is as follows: ; The second nonlinear coupling model is: ; In the formula, Characterizing the first coupling factor information The first coupling factor; and These respectively characterize the first sub-process control signal information and the second sub-process control signal information in the first process control signal information; Characterizing the second coupling factor information A second coupling factor; and These respectively characterize the first strength coefficient and the second strength coefficient; and The first shape factor and the second shape factor are respectively characterized; Characterizing the first The first characteristic center value corresponding to a typical macroscopic working condition; Characterizing the first The second characteristic center value corresponding to a typical bottom temperature dynamic; The first coupling factor information and the second coupling factor information are synthesized by corresponding elements using a signal synthesis model, and the first calculation parameter information is obtained by normalization. The signal synthesis model is as follows: ; In the formula, The first calculated parameter information represents the first The first calculated parameter value; Characterized by the normalization coefficient; and Representing the first coupling factor information respectively The first coupling factor and the second The first coupling factor; and The second coupling factor information is characterized respectively. The second coupling factor and the first A second coupling factor.

[0124] It is evident that implementation Figure 3 The described control system is beneficial for improving the control accuracy and dynamic response efficiency of the PVA production process.

[0125] In yet another alternative embodiment, such as Figure 3 As shown, based on the control parameter information and the first process control signal information, the second target control signal information is determined, including: Acquire historical system control information; historical system control information includes historical first target control signal information, historical target control signal information, and historical control target object information; The historical system control information, first weight parameter information, and first calculation parameter information are parsed and processed to obtain the corrected weight information; the corrected weight information includes the first corrected weight value, the second corrected weight value, and the third corrected weight value; The target signal generation model is used to process historical system control information, control parameter information, and correction weight information to generate the second target control signal information. The target signal generation model is as follows: ; In the formula, Characterizes the control signal information of the second target; , and These respectively represent the first control parameter value, the second control parameter value, and the third control parameter value in the control parameter information; , and These respectively represent the first, second, and third corrected weight values ​​in the corrected weight information; Characterizes the control signal information of the first target in history.

[0126] It is evident that implementation Figure 3 The described control system is beneficial for improving the control accuracy and dynamic response efficiency of the PVA production process.

[0127] In yet another alternative embodiment, such as Figure 3 As shown, the desired control signal information and feedback control signal information are processed to generate the first target control signal information, including: The desired control signal information and the feedback control signal information are fused to obtain fused control signal information. The desired control signal information includes the first desired control signal at the current time and the second desired control signal at the previous time. The first feedback control signal information includes the first feedback control signal at the current time and the second feedback control signal at the previous time. The fusion processing characterizes the signals at the current time and the previous time to be rearranged in chronological order and in the order of desired control signal and feedback control signal to form a signal vector. The fused control signal information is processed to generate the first target control signal information.

[0128] It is evident that implementation Figure 3 The described control system is beneficial for improving the control accuracy and dynamic response efficiency of the PVA production process.

[0129] Example 3 Please see Figure 4 , Figure 4 This is a schematic diagram of another control system disclosed in an embodiment of the present invention. Wherein, Figure 4 The described system can be applied to management systems, such as local servers or cloud servers, and this invention does not limit its application. Figure 4 As shown, the system may include: Memory 301 storing executable program code; Processor 302 coupled to memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps in the control method described in Embodiment 1.

[0130] Example 4 This invention discloses a computer-readable storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to perform the steps of the control method described in Embodiment 1.

[0131] Example 5 This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the control method described in Embodiment 1.

[0132] The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0133] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0134] Finally, it should be noted that the PVA production process control system based on key process parameter identification disclosed in the embodiments of the present invention is only a preferred embodiment of the present invention and is only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A control method, characterized in that, The method includes: Acquire desired control signal information and feedback control signal information; the feedback control signal information includes first feedback control signal information and second feedback control signal information; the first feedback control signal information represents the temperature at the middle position of the reactor; the second feedback control signal information represents the temperature at the bottom of the reactor. The desired control signal information and the feedback control signal information are processed to generate a first target control signal information. The feedback control signal information and the first target control signal information are processed to generate a second target control signal information; the second target control signal information is used to control the temperature at the bottom of the reactor.

2. The control method according to claim 1, characterized in that, The step of generating and processing the feedback control signal information and the first target control signal information to obtain the second target control signal information includes: The first target control signal information and the second feedback control signal in the feedback control signal information are analyzed and processed to obtain the first process control signal information; the first process control signal information includes the first sub-control signal information and the second sub-control signal information. The first process control signal information is processed to generate the second target control signal information.

3. The control method according to claim 2, characterized in that, The step of performing signal generation processing on the first process control signal information to obtain the second target control signal information includes: Based on the first process control signal information, control parameter information is determined; the control parameter information includes a first control parameter value, a second control parameter value, and a third control parameter value. Based on the control parameter information and the first process control signal information, the second target control signal information is determined.

4. The control method according to claim 3, characterized in that, The step of determining control parameter information based on the first process control signal information includes: The first process control signal information is subjected to nonlinear calculation processing to obtain the first calculation parameter information; The first signal generation model is used to calculate and process the first weight parameter information and the first calculation parameter information to obtain the control parameter information.

5. The control method according to claim 4, characterized in that, The step of performing nonlinear analysis and calculation on the first process control signal information to obtain the first calculation parameter information includes: The first sub-control signal information and the second sub-control signal information in the first process control signal information are calculated and processed using the first nonlinear coupling model and the second nonlinear coupling model respectively to obtain the first coupling factor information and the second coupling factor information; the first coupling factor information includes three first coupling factors; the second coupling factor information includes three second coupling factors. The first nonlinear coupling model is as follows: ； The second nonlinear coupling model is: ； In the formula, Characterizing the first coupling factor information in the first coupling factor information The first coupling factor; and The first sub-process control signal information and the second sub-process control signal information in the first process control signal information are respectively represented; Characterizing the second coupling factor information in the first A second coupling factor; and These respectively characterize the first strength coefficient and the second strength coefficient; and The first shape factor and the second shape factor are respectively characterized; Characterizing the first The first characteristic center value corresponding to a typical macroscopic working condition; Characterizing the first The second characteristic center value corresponding to a typical bottom temperature dynamic; The first coupling factor information and the second coupling factor information are synthesized by corresponding elements using a signal synthesis model, and the first calculation parameter information is obtained by normalization. The signal synthesis model is as follows: ； In the formula, Characterizing the first calculation parameter information The first calculated parameter value; Characterized by the normalization coefficient; and Each characterizes the first coupling factor information in the first coupling factor information. The first coupling factor and the first The first coupling factor; and Each characterizes the second coupling factor information in the first... The second coupling factor and the first A second coupling factor.

6. The control method according to claim 3, characterized in that, The step of determining the second target control signal information based on the control parameter information and the first process control signal information includes: Acquire historical system control information; the historical system control information includes historical first target control signal information, historical target control signal information, and historical control target object information; The historical system control information, the second weight parameter information set, and the first calculation parameter information are parsed and processed to obtain corrected weight information; the corrected weight information includes a first corrected weight value, a second corrected weight value, and a third corrected weight value. The target signal generation model is used to process the historical system control information, the control parameter information, and the correction weight information to generate a second target control signal information. The target signal generation model is as follows: ； In the formula, Characterizes the control signal information of the second target; , and The first control parameter value, the second control parameter value, and the third control parameter value in the control parameter information are respectively represented; , and The first modified weight value, the second modified weight value, and the third modified weight value in the modified weight information are respectively represented; This represents the historical first target control signal information.

7. The control method according to claim 1, characterized in that, The step of generating and processing the desired control signal information and the feedback control signal information to obtain the first target control signal information includes: The desired control signal information and the first feedback control signal information in the feedback control signal information are subjected to signal fusion processing to obtain fused control signal information; the desired control signal information includes the first desired control signal corresponding to the current time and the second desired control signal at the previous time; the first feedback control signal information includes the first feedback control signal corresponding to the current time and the second feedback control signal at the previous time; the fusion processing represents reorganizing the signals of the current time and the previous time in chronological order and in the order of the desired control signal and the feedback control signal to form a signal vector; The fused control signal information is processed to generate the first target control signal information.

8. A control system, characterized in that, The system includes: The acquisition module is used to acquire desired control signal information and feedback control signal information; the feedback control signal information includes first feedback control signal information and second feedback control signal information; the first feedback control signal information represents the temperature at the middle position of the reactor; the second feedback control signal information represents the temperature at the bottom of the reactor. The first processing module is used to perform signal generation processing on the desired control signal information and the feedback control signal information to obtain the first target control signal information; The second processing module is used to perform signal generation processing on the feedback control signal information and the first target control signal information to obtain the second target control signal information; the second target control signal information is used to control the temperature of the bottom of the reactor.

9. A control system, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the control method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which, when invoked, are used to execute the control method as described in any one of claims 1-7.

Images