Rotary valve control method, device and equipment for polyvinyl chloride feeding and conveying production line

Abstract

This invention belongs to the field of industrial control technology and discloses a rotary valve control method, device, and equipment for a polyvinyl chloride (PVC) feeding and conveying production line. The method includes: real-time acquisition of sensor data to obtain material characteristic data, which at least includes flow rate data; calculating a flow rate deviation based on the flow rate data and a target flow rate; when the flow rate deviation is less than a preset threshold, adjusting the PID parameters of an adaptive PID controller based on the flow rate deviation, calculating a first opening value based on the adjusted PID parameters, and adjusting the opening of the rotary valve based on the first opening value; otherwise, inputting the material characteristic data into a pre-constructed nonlinear model to obtain a second opening value, and adjusting the opening of the rotary valve based on the second opening value. The nonlinear model characterizes the nonlinear relationship between the material characteristic data and the opening of the rotary valve. This method enables timely and precise control of material flow rate, adapting to complex production requirements.

Description

Technical Field

[0001] This invention belongs to the field of industrial control technology, specifically relating to a rotary valve control method, device, and equipment for a polyvinyl chloride feeding and conveying production line. Background Technology

[0002] In polyvinyl chloride (PVC) feeding and conveying systems, the main methods for controlling rotary valves include manual adjustment, timed control, and simple on / off control. Manual adjustment refers to the operator manually adjusting the opening degree of the rotary valve based on actual feeding conditions and production experience, thereby controlling the material feeding speed. A larger opening degree means the valve is open more fully, allowing for a greater material flow rate; a smaller opening degree means a correspondingly smaller material flow rate. Manual adjustment relies on human operation, has low precision, is easily limited by operator experience, and struggles to respond promptly to changes in production capacity demands. Timed control automatically adjusts the rotary valve opening at preset time intervals to ensure a certain amount of material is fed within a specified time. Because of the fixed time intervals, it is difficult to flexibly respond to rapid changes in production capacity demands, especially when demand fluctuates significantly, leading to a delayed response. Simple on / off control directly controls the opening and closing state of the rotary valve through a switch signal, meaning the rotary valve is either fully open or fully closed. While simple to operate, it lacks precise control over material flow and cannot adapt to complex production requirements. Summary of the Invention

[0003] The purpose of this invention is to provide a rotary valve control method, device, equipment, and storage medium for a polyvinyl chloride (PVC) feeding and conveying production line, which can solve the problem of not being able to control the material flow in a timely and precise manner and being unable to adapt to complex production requirements.

[0004] The first aspect of this invention discloses a rotary valve control method for a polyvinyl chloride (PVC) feeding and conveying production line, comprising:

[0005] Real-time acquisition of sensor data to obtain material characteristic data, which includes at least flow rate data;

[0006] Calculate the flow deviation based on the flow data and the target flow;

[0007] When the flow deviation is less than a preset threshold, the PID parameters of the adaptive PID controller are adjusted according to the flow deviation, a first opening value is calculated according to the adjusted PID parameters, and the opening of the rotary valve is adjusted according to the first opening value.

[0008] Otherwise, the material characteristic data is input into a pre-built nonlinear model to obtain a second opening value, and the opening of the rotary valve is adjusted according to the second opening value. The nonlinear model is used to characterize the nonlinear relationship between the material characteristic data and the opening of the rotary valve.

[0009] In some embodiments, the material property data further includes viscosity data, pressure data, and temperature data, and a pre-built nonlinear model includes:

[0010] For the nonlinear input of the Hammerstein-Wiener model, first models are constructed for material viscosity, pipeline pressure, and material temperature, respectively.

[0011] For the linear dynamic part of the Hammerstein-Wiener model, a second model is constructed based on all the first model and transfer functions;

[0012] For the nonlinear part of the output of the Hammerstein-Wiener model, a third model is constructed based on the second model;

[0013] Construct the loss function for the Hammerstein-Wiener model based on the third model;

[0014] The nonlinear model is obtained by iteratively training the Hammerstein-Wiener model based on historical material property data.

[0015] In some embodiments, before inputting historical material property data into the Hammerstein-Wiener model, a moving average filter is used to smooth the viscosity data, the pressure data, and the temperature data.

[0016] In some embodiments, constructing the first models corresponding to material viscosity, pipeline pressure, and material temperature respectively includes:

[0017] A first model corresponding to the material viscosity is constructed using linear, quadratic, and exponential terms.

[0018] A first model corresponding to pipeline pressure is constructed using linear and quadratic terms;

[0019] A first model corresponding to the material temperature is constructed using logarithmic and linear terms.

[0020] In some embodiments, after acquiring sensor data in real time, the method further includes:

[0021] The material property data is input into a pre-built nonlinear model to obtain the initial opening value of the rotary valve;

[0022] Adjust the opening degree of the rotary valve according to the initial opening degree value.

[0023] In some embodiments, adjusting the PID parameters of the adaptive PID controller according to the flow deviation to obtain the first opening value includes:

[0024] Based on the flow deviation, calculate the proportional, integral, and derivative parameters of the adaptive PID controller.

[0025] The first opening value is calculated based on the proportional parameter, the integral parameter, and the differential parameter.

[0026] A second aspect of this invention discloses a rotary valve control device for a polyvinyl chloride (PVC) feeding and conveying production line, comprising:

[0027] The data acquisition module is used to acquire sensor data in real time to obtain material characteristic data, which includes at least flow rate data.

[0028] The flow deviation module is used to calculate the flow deviation based on the flow data and the target flow.

[0029] The fine-tuning module is used to adjust the PID parameters of the adaptive PID controller according to the flow deviation when the flow deviation is less than a preset threshold, calculate a first opening value according to the adjusted PID parameters, and adjust the opening of the rotary valve according to the first opening value.

[0030] The global optimization module is used to input the material characteristic data into a pre-built nonlinear model to obtain a second opening value when the flow deviation is greater than or equal to a preset threshold, and adjust the opening of the rotary valve according to the second opening value. The nonlinear model is used to characterize the nonlinear relationship between the material characteristic data and the opening of the rotary valve.

[0031] In some embodiments, the fine-tuning module further includes a PID parameter unit, which is used to calculate the proportional parameter, integral parameter, and derivative parameter of the adaptive PID controller according to the flow deviation; and to calculate the first opening value according to the proportional parameter, the integral parameter, and the derivative parameter.

[0032] A third aspect of the present invention discloses an electronic device, including a memory storing executable program code and a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the rotary valve control method for a polyvinyl chloride feeding and conveying production line disclosed in the first aspect.

[0033] The fourth aspect of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute the rotary valve control method for a polyvinyl chloride feeding and conveying production line disclosed in the first aspect.

[0034] The beneficial effects of this invention lie in its pre-construction of a nonlinear model to accurately capture the complex relationship between material characteristics and the rotary valve opening. It calculates the deviation between the actual flow rate and the target flow rate. When the flow rate fluctuates slightly, the PID parameters of the adaptive PID controller are dynamically adjusted to calculate the rotary valve opening, keeping the material flow rate stable near the target value, thus improving the system's response speed and control stability. When the material flow rate changes significantly, i.e., when the material characteristics change significantly, directly using the PID controller cannot adequately handle the complex nonlinear dynamics. The nonlinear model is then invoked again to predict the rotary valve opening, ensuring the accuracy of flow control. This invention provides precise control under complex material characteristic variations while possessing rapid response capabilities, ensuring stable and efficient operation and control of the system under different operating conditions. Attached Figure Description

[0035] The accompanying drawings illustrate specific examples of the technical solutions described in this invention and, together with the detailed embodiments, form part of the specification, serving to explain the technical solutions, principles, and effects of this invention.

[0036] Unless otherwise specified or defined, the same reference numerals in different figures represent the same or similar technical features, and different reference numerals may be used to represent the same or similar technical features.

[0037] Figure 1 This is a flowchart of a rotary valve control method for a polyvinyl chloride feeding and conveying production line disclosed in an embodiment of the present invention;

[0038] Figure 2 This is a flowchart illustrating the pre-constructed nonlinear model in an embodiment of the present invention;

[0039] Figure 3 This is a flowchart of constructing the first model in an embodiment of the present invention;

[0040] Figure 4 This is a schematic diagram of the rotary valve control device of the polyvinyl chloride feeding and conveying production line according to an embodiment of the present invention;

[0041] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0042] Unless otherwise specified or defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. When combined with the technical solutions of the invention in a real-world scenario, all technical and scientific terms used herein may also have meanings corresponding to the purpose of achieving the technical solutions of the invention. The terms "first," "second," etc., used herein are merely for distinguishing names and do not represent a specific number or order. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0043] It should be noted that when a component is considered "fixed" to another component, it can be directly fixed to the other component or there can be an intervening component; when a component is considered "connected" to another component, it can be directly connected to the other component or there can be an intervening component; when a component is considered "mounted" on another component, it can be directly mounted on the other component or there can be an intervening component; when a component is considered "placed" on another component, it can be directly placed on the other component or there can be an intervening component.

[0044] Unless otherwise specified or defined, the terms "described" or "the" as used herein refer to the technical features or technical content mentioned or described prior to the relevant section, which may be the same as or similar to the technical features or technical content mentioned herein. Furthermore, the terms "comprising" and "having," and any variations thereof, as used herein, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such processes, methods, products, or apparatus.

[0045] The process flow of the polyvinyl chloride (PVC) feeding and conveying production line is as follows: Materials are packaged in ton bags and transported by overhead crane to designated ton bag unpacking equipment. The ton bag unpacking machine unpacks and discharges the material, controlling the discharge switch via a butterfly valve and the discharge amount via a rotary valve to the accelerator. Next, the material passes through the accelerator and is conveyed under dilute phase positive pressure by a Roots blower into the powder tank. Then, it passes through the accelerator again and is drawn under negative pressure by the Roots blower to a vacuum feeder, subsequently being conveyed to the adhesive metering tank. In the adhesive metering tank, the material is preheated and stirred before being transported through pipelines to the next process, completing the entire feeding and conveying process.

[0046] In polyvinyl chloride (PVC) feeding and conveying production lines, current methods for controlling rotary valves cannot respond promptly or provide precise control under complex material characteristic changes. To address these issues, this invention combines nonlinear modeling with an adaptive PID (Proportional Integral Differential) controller. When material flow changes are small, the adaptive PID controller performs real-time dynamic fine-tuning. When material flow changes significantly, nonlinear modeling is used for global optimization and adjustment, ensuring that the system can adapt to complex operating conditions and achieve optimal control and efficient operation.

[0047] This invention discloses a rotary valve control method for a polyvinyl chloride (PVC) feeding and conveying production line. This method controls the opening degree of the rotary valve in the PVC feeding and conveying production line, providing precise control under complex material characteristic changes and exhibiting rapid response capabilities. The method can be implemented via computer programming, either as an independent control system or as part of the PVC feeding and conveying production line's control system. The execution entity of this method can be an electronic device such as a computer, laptop, or tablet, or a control chip embedded in an electronic device; this invention does not limit this. To facilitate understanding of this invention, specific embodiments will be described in more detail below with reference to the accompanying drawings.

[0048] like Figure 1 As shown, the method includes the following steps:

[0049] Step S100: Collect sensor data in real time to obtain material characteristic data, wherein the material characteristic data includes at least flow rate data;

[0050] The sensor is installed downstream of the rotary valve. The type of sensor is not limited, as long as it can collect data related to material properties. These material properties must be related to the opening degree of the rotary valve. Since material flow rate is the most directly related factor to the opening degree of the rotary valve, the material properties must at least include material flow rate. Other parameters are not limited, such as material viscosity, pipeline pressure, material temperature, material velocity, and material particle size. In this embodiment, material viscosity, pipeline pressure, material temperature, and material flow rate are selected as the material properties.

[0051] Material characteristic data is collected in real time by sensors, and the material characteristic data includes at least flow rate data. In this embodiment, the material characteristic data includes viscosity data, pressure data, temperature data, and flow rate data. Specifically, the viscosity data at time t is denoted as V(t), the pressure data as P(t), the temperature data as T(t), and the flow rate data as F(t).

[0052] Step S200: Calculate the flow deviation based on the flow data and the target flow;

[0053] The real-time collected flow data F(t) is compared with the target flow F. target Subtracting (t) from the flow rate, we obtain the flow deviation e(t). The specific expression is: e(t) = F target (t)-F(t).

[0054] Step S300: When the flow deviation is less than the preset threshold, adjust the PID parameters of the adaptive PID controller according to the flow deviation, calculate the first opening value according to the adjusted PID parameters, and adjust the opening of the rotary valve according to the first opening value.

[0055] When the flow deviation is less than a preset threshold (e.g., within 5%), it indicates that the material flow rate has only changed slightly. In this case, using an adaptive PID controller to fine-tune the rotary valve can both maintain the material flow rate stable near the target value and improve the system's response speed and control stability. The adaptive PID controller is a control algorithm that can automatically adjust its control parameters (proportional, integral, and derivative gain) according to dynamic changes in the system.

[0056] Specifically, firstly, based on the flow deviation, the proportional, integral, and derivative parameters of the adaptive PID controller are calculated respectively; then, based on the proportional, integral, and derivative parameters, the first opening value is calculated, and the opening of the rotary valve is adjusted according to the first opening value.

[0057] In this embodiment, the PID parameter K of the adaptive PID controller is first dynamically adjusted. p K i K d The specific formula is as follows:

[0058] K p =K p +α×|e(t)|,

[0059] K i =K i +β×∫e(t)dt,

[0060]

[0061] Where α, β, and γ are the adjustment coefficients for proportional gain, integral gain, and derivative gain, respectively, and are usually taken as small values ​​(such as 0.01 to 0.1), and e(t) is the flow deviation.

[0062] Then, calculate the output y of the adaptive PID controller. c (t), which is the first opening value, is used to fine-tune the opening of the rotary valve. The specific formula for calculating the first opening value is:

[0063]

[0064] Where τ is the value between time 0 and t.

[0065] Otherwise, when the flow deviation is greater than or equal to the preset threshold, the following step S400 is executed.

[0066] Step S400: Input the material property data into the pre-built nonlinear model to obtain the second opening value, and adjust the opening of the rotary valve according to the second opening value. The nonlinear model is used to characterize the nonlinear relationship between the material property data and the opening of the rotary valve.

[0067] When the flow deviation is greater than or equal to a preset threshold, it indicates a significant fluctuation in material characteristics, leading to a corresponding significant change in material flow. Although the adaptive PID controller has a fast response speed, in this situation, fine-tuning the rotary valve opening using the adaptive PID controller is no longer sufficient to adapt to the latest material characteristics. Therefore, it is necessary to input the material characteristic data into a pre-built nonlinear model. This pre-built nonlinear model has learned the complex nonlinear dynamic relationship between the material characteristic data and the rotary valve opening, and can re-produce a matching rotary valve opening based on the latest material characteristics, i.e., obtain a second opening value. The rotary valve opening is then adjusted according to this second opening value to adapt to the new operating conditions. This global adjustment method can better cope with large fluctuations in material characteristics, ensuring efficient system operation under different conditions.

[0068] By combining nonlinear modeling and an adaptive PID controller, precise control of the rotary valve opening under complex nonlinear conditions was achieved in a PVC feeding and conveying production line. This system accurately captures the relationship between material characteristics and the rotary valve opening under complex nonlinear conditions. When material flow changes are small, the adaptive PID controller fine-tunes the PID parameters in real time based on the real-time flow deviation, automatically adjusting the rotary valve opening to achieve rapid fine-tuning and stable operation of the production line. When material flow changes significantly, the nonlinear model is invoked again for global optimization and the control strategy is adjusted to ensure precise material flow control and ensure the production line adapts to complex conditions. This system achieves real-time adjustment of the rotary valve opening based on material characteristics or operating conditions, and continuously optimizes the control strategy during operation.

[0069] Specifically, this embodiment constructs a nonlinear model based on the Hammerstein-Wiener model. The Hammerstein-Wiener model is a mathematical tool for modeling nonlinear systems, combining the characteristics of the Hammerstein and Wiener models. It is commonly used to describe systems with nonlinear dynamic characteristics and is widely applied in fields such as control engineering, signal processing, and system identification. The Hammerstein-Wiener model consists of an input nonlinear part, a linear dynamic part, and an output nonlinear part.

[0070] like Figure 2 As shown, the steps for pre-constructing a nonlinear model include:

[0071] Step P100: For the nonlinear input of the Hammerstein-Wiener model, construct the first model corresponding to the material viscosity, pipeline pressure and material temperature respectively;

[0072] Based on the application scenario of a PVC feeding and conveying production line, the nonlinear input mainly performs nonlinear transformations on the material's viscosity V(t), pressure P(t), and temperature T(t) to generate an intermediate signal z. v (t), z p (t), z t (t) is used to capture the nonlinear relationship between input variables and system dynamic behavior, and first models are constructed for material viscosity, pipeline pressure and material temperature respectively.

[0073] like Figure 3 As shown, the specific steps for constructing the first model include:

[0074] Step P110: Construct the first model corresponding to the material viscosity using linear, quadratic, and exponential terms;

[0075] Step P120: Construct the first model corresponding to the pipeline pressure using linear and quadratic terms;

[0076] Step P130: Construct the first model corresponding to the material temperature using logarithmic and linear terms.

[0077] The viscosity of the material is expressed through the linear term V(t) and the quadratic term V(t). 2 Nonlinear modeling is performed using the exponential term exp(a4V(t)) to obtain the first model corresponding to the material viscosity. The specific expression is:

[0078] z v (t)=f1(V(t))=a1V(t)+a2V(t) 2 +a3exp(a4V(t)),

[0079] Where a1, a2, a3, and a4 represent the coefficients of the nonlinear influence of viscosity data V(t) on the production line.

[0080] The pipeline pressure passes through the linear term P(t) and the quadratic term P(t). 2 This describes the direct and nonlinear effects of pipeline pressure on the system, obtaining the first model corresponding to the pipeline pressure. The specific expression is:

[0081] z p (t)=f2(P(t))=b1P(t)+b2P(t)2 ,

[0082] Where b1 and b2 represent the linear and nonlinear coefficients of the pressure data P(t), respectively.

[0083] The material temperature is described using a logarithmic term log(T(t)+1) combined with a linear term T(t) to represent the slow, gradual effect of material temperature on the production line, thus obtaining the first model corresponding to the material temperature. The specific expression is:

[0084] z t (t)=f3(T(t))=c1T(t)+c2log(T(t)+1),

[0085] Where c1 and c2 are the nonlinear and linear coefficients of the temperature data, respectively.

[0086] Step P200: For the linear dynamic part of the Hammerstein-Wiener model, construct the second model based on all the first model and transfer functions;

[0087] The linear dynamic component describes the time response of the production line, and is usually represented by the transfer function G(s):

[0088]

[0089] Where k is the gain, representing the degree to which the system amplifies or reduces the input; τ is the time constant, describing the dynamic response of the system to the input signal; and s is the frequency domain variable in the Laplace transform, obtained by performing a Laplace transform on the time-domain signal of the input data. By transforming the differential equations in the time domain into algebraic equations in the frequency domain, frequency domain analysis simplifies complex dynamic behaviors, making the analysis of system response more intuitive and efficient.

[0090] In this embodiment, after nonlinear transformations are performed on material viscosity, pipeline pressure, and material temperature to obtain their respective first models, these are used as input signals for the linear dynamic system. Together with the transfer function, they construct the second model, the specific expression of which is as follows:

[0091] z(t)=G(s·(z) v (t)+z p (t)+z t (t)).

[0092] Step P300: For the nonlinear part of the output of the Hammerstein-Wiener model, construct the third model based on the second model;

[0093] The output nonlinear component is used to convert the output z(t) of the second model in the linear dynamic system into the opening of the rotary valve. The specific expression for the nonlinear function is as follows:

[0094]

[0095] Where d1 and d2 represent the linear and quadratic coefficients of z(t), respectively, and tanh is a nonlinear activation function. d3 represents the amplification factor of the tanh function, which is used to control the effect of tanh(d4z(t)) on the output of the linear dynamic system; d4 represents the sensitivity factor of the tanh function, which controls the speed and sensitivity of the linear dynamic system to the nonlinear response of z(t).

[0096] Step P400: Construct the loss function for the Hammerstein-Wiener model based on the third model;

[0097] The loss function is used to measure the difference between the output of the Hammerstein-Wiener model and the experimental data. For the Hammerstein-Wiener model, this is achieved by minimizing the model output. The loss function is constructed by the sum of squared errors between the experimental output y(t) and the experimental output y(t).

[0098]

[0099] Where θ is the set of parameters to be estimated, θ={a1,a2,a3,a4,b1,b2,c1,c2,d1,d2,d3,d4}; t=1 indicates that the error is calculated from the first time point, and T is the total number of time steps.

[0100] Step P500: Iteratively train the Hammerstein-Wiener model based on historical material property data to obtain a nonlinear model.

[0101] The Hammerstein-Wiener model is optimized by minimizing the loss function (minE(θ)) to solve for the parameters θ, ultimately yielding a nonlinear model. This embodiment uses gradient descent for optimization. First, the parameters are initialized; these parameters can be set empirically or randomly. Then, the loss function is calculated for each parameter θ. i partial derivatives This is the rate of change of the loss function with respect to each parameter. The gradient indicates how to adjust the parameters to reduce the error given the current parameter values. Update each parameter value based on the gradient direction:

[0102]

[0103] Here, α is the learning rate, which controls the step size of each parameter update. The parameters are updated incrementally until the loss function converges to a small value.

[0104] When training the Hammerstein-Wiener model, you can use pre-collected historical data from the PVC feeding and conveying production line (including material characteristic data and rotary valve opening data at historical moments) as the training dataset, or you can use both the real-time data and the historical data as the training dataset.

[0105] In some embodiments, before inputting historical material property data into the Hammerstein-Wiener model, the collected data is preprocessed to ensure accuracy and stability by filtering out noise. This embodiment uses moving average filtering to smooth viscosity, pressure, and temperature data. Specifically, let... Representing viscosity data stress data Temperature data Traffic data and real-time rotary valve opening For any variable in the data, the smoothed data X(t) after being processed by the moving average filter is expressed as:

[0106]

[0107] Where X(t) is the smoothed data (viscosity V(t), pressure P(t), temperature T(t), flow rate F(t), and real-time rotary valve opening y(t)). This is the original material property data, and N is the window size for the moving average.

[0108] The smoothing process described above can be a separate module or integrated into a module of a nonlinear model.

[0109] In practical use, to ensure that the initial opening of the rotary valve matches the current material characteristics, after real-time acquisition of sensor data, the process includes: inputting the material characteristic data into a pre-built nonlinear model to obtain the initial opening value of the rotary valve; and adjusting the opening of the rotary valve based on the initial opening value. Clearly, when the nonlinear model does not integrate a smoothing module, the aforementioned material characteristic data can be smoothed before being input into the pre-built nonlinear model. Outputting the initial opening value of the rotary valve through the nonlinear model ensures that the material flow rate of the PVC feeding and conveying production line reaches the target value in the initial state.

[0110] In summary, this embodiment pre-models the complex nonlinear dynamic relationship between material properties and the opening degree of the rotary valve, constructing a nonlinear model to accurately capture this complex relationship. Then, sensor data (including material viscosity, pressure, temperature, and flow rate) is collected in real time. When the flow rate fluctuates slightly, the PID parameter K of the adaptive PID controller is dynamically adjusted by calculating the deviation between the actual flow rate and the target flow rate. p K i K d To maintain a stable material flow rate near the target value, the system's response speed and control stability are improved. When the material flow rate changes significantly, indicating a significant change in material characteristics, the nonlinear model is invoked again to predict the rotary valve opening, ensuring the accuracy of flow control.

[0111] By effectively combining nonlinear modeling with real-time feedback adjustment, precise control can be provided under complex material property changes, while also having rapid response capabilities, ensuring stable and efficient operation and control of the system under different working conditions.

[0112] like Figure 4 As shown, based on the above-mentioned rotary valve control method for a polyvinyl chloride (PVC) feeding and conveying production line, this embodiment of the invention discloses a rotary valve control device for a PVC feeding and conveying production line, comprising:

[0113] The data acquisition module 600 is used to acquire sensor data in real time and obtain material characteristic data, wherein the material characteristic data includes at least flow rate data.

[0114] The flow deviation module 610 is used to calculate the flow deviation based on the flow data and the target flow.

[0115] The fine-tuning module 620 is used to adjust the PID parameters of the adaptive PID controller according to the flow deviation when the flow deviation is less than a preset threshold, calculate a first opening value according to the adjusted PID parameters, and adjust the opening of the rotary valve according to the first opening value.

[0116] The global optimization module 630 is used to input the material characteristic data into a pre-built nonlinear model to obtain a second opening value when the flow deviation is greater than or equal to a preset threshold, and adjust the opening of the rotary valve according to the second opening value. The nonlinear model is used to characterize the nonlinear relationship between the material characteristic data and the opening of the rotary valve.

[0117] In some embodiments, the opening fine-tuning module further includes a PID parameter unit, which is used to calculate the proportional parameter, integral parameter, and derivative parameter of the adaptive PID controller according to the flow deviation; and to calculate the first opening value according to the proportional parameter, the integral parameter, and the derivative parameter.

[0118] like Figure 5 As shown, an embodiment of the present invention discloses an electronic device, including a memory 401 storing executable program code and a processor 402 coupled to the memory 401;

[0119] The processor 402 calls the executable program code stored in the memory 401 to execute the rotary valve control method for the polyvinyl chloride feeding and conveying production line described in the above embodiments.

[0120] This invention also discloses a computer-readable storage medium storing a computer program that causes a computer to execute the rotary valve control method for the polyvinyl chloride feeding and conveying production line described in the above embodiments.

[0121] The purpose of the above embodiments is to reproduce and derive the technical solution of the present invention by way of example, and to fully describe the technical solution, purpose and effect of the present invention. The purpose is to enable the public to have a more thorough and comprehensive understanding of the disclosure of the present invention, and not to limit the scope of protection of the present invention.

[0122] The above embodiments are not an exhaustive list based on the present invention, and there may be many other embodiments not listed. Any substitutions and improvements made without departing from the concept of the present invention are within the protection scope of the present invention.

Claims

1. A rotary valve control method for a polyvinyl chloride (PVC) feeding and conveying production line, characterized in that, include: Real-time acquisition of sensor data to obtain material characteristic data, which includes at least flow rate data; Calculate the flow deviation based on the flow data and the target flow; When the flow deviation is less than a preset threshold, the PID parameters of the adaptive PID controller are adjusted according to the flow deviation, a first opening value is calculated according to the adjusted PID parameters, and the opening of the rotary valve is adjusted according to the first opening value. Otherwise, the material characteristic data is input into a pre-built nonlinear model to obtain a second opening value, and the opening of the rotary valve is adjusted according to the second opening value. The nonlinear model is used to characterize the nonlinear relationship between the material characteristic data and the opening of the rotary valve. The material property data also includes viscosity data, pressure data, and temperature data, and a pre-built nonlinear model includes: For the nonlinear input of the Hammerstein-Wiener model, first models are constructed for material viscosity, pipeline pressure, and material temperature, respectively. For the linear dynamic part of the Hammerstein-Wiener model, a second model is constructed based on all the first model and transfer functions; For the nonlinear part of the output of the Hammerstein-Wiener model, a third model is constructed based on the second model; Construct the loss function for the Hammerstein-Wiener model based on the third model; The nonlinear model is obtained by iteratively training the Hammerstein-Wiener model based on historical material property data. The step of adjusting the PID parameters of the adaptive PID controller according to the flow deviation, and calculating the first opening value based on the adjusted PID parameters, includes: Based on the flow deviation, calculate the proportional, integral, and derivative parameters of the adaptive PID controller. The first opening value is calculated based on the proportional parameter, the integral parameter, and the differential parameter.

2. The rotary valve control method for a polyvinyl chloride (PVC) feeding and conveying production line as described in claim 1, characterized in that, Before inputting historical material property data into the Hammerstein-Wiener model, a moving average filter is used to smooth the viscosity data, pressure data, and temperature data.

3. The rotary valve control method for a polyvinyl chloride (PVC) feeding and conveying production line as described in claim 1, characterized in that, The construction of the first models corresponding to material viscosity, pipeline pressure, and material temperature respectively includes: A first model corresponding to the material viscosity is constructed using linear, quadratic, and exponential terms. A first model corresponding to pipeline pressure is constructed using linear and quadratic terms; A first model corresponding to the material temperature is constructed using logarithmic and linear terms.

4. The rotary valve control method for a polyvinyl chloride (PVC) feeding and conveying production line as described in claim 1, characterized in that, After real-time acquisition of sensor data, the following is also included: The material property data is input into a pre-built nonlinear model to obtain the initial opening value of the rotary valve; Adjust the opening degree of the rotary valve according to the initial opening degree value.

5. A rotary valve control device for a polyvinyl chloride (PVC) feeding and conveying production line, used to execute the rotary valve control method for a PVC feeding and conveying production line as described in claim 1, characterized in that, include: The data acquisition module is used to acquire sensor data in real time to obtain material characteristic data, which includes at least flow rate data. The flow deviation module is used to calculate the flow deviation based on the flow data and the target flow. The fine-tuning module is used to adjust the PID parameters of the adaptive PID controller according to the flow deviation when the flow deviation is less than a preset threshold, calculate a first opening value according to the adjusted PID parameters, and adjust the opening of the rotary valve according to the first opening value. The global optimization module is used to input the material characteristic data into a pre-built nonlinear model to obtain a second opening value when the flow deviation is greater than or equal to a preset threshold, and adjust the opening of the rotary valve according to the second opening value. The nonlinear model is used to characterize the nonlinear relationship between the material characteristic data and the opening of the rotary valve.

6. The rotary valve control device for the polyvinyl chloride feeding and conveying production line as described in claim 5, characterized in that, The fine-tuning module further includes a PID parameter unit, which is used to calculate the proportional parameter, integral parameter, and derivative parameter of the adaptive PID controller according to the flow deviation; and to calculate the first opening value according to the proportional parameter, integral parameter, and derivative parameter.

7. An electronic device, characterized in that, It includes a memory storing executable program code and a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the rotary valve control method for the polyvinyl chloride feeding and conveying production line according to any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program causes a computer to execute the rotary valve control method for a polyvinyl chloride feeding and conveying production line according to any one of claims 1 to 4.

Images