Paper machine operation parameter optimization adjustment method and system based on adaptive algorithm

Abstract

The invention discloses a papermaking machine operation parameter optimization adjustment method and system based on a self-adaptive algorithm, and relates to the technical field of equipment control. The parameter optimization adjustment method comprises the following steps: basic data collection: collecting historical production data of the paper machine; and establishing associated data: quantitatively expressing the association degree among parameters in the associated data through a data driving model according to historical production data. According to the method, effective theoretical support can be provided for subsequent data prediction by utilizing comprehensive production data, the prediction model realizes prediction of subsequent data by combining real-time detection data and theoretical detection data, equipment parameters are adjusted based on a prediction result, the paper production quality can be ensured by adjusting equipment, and the paper production efficiency is improved. Meanwhile, after the equipment parameters are adjusted, support can be provided for subsequent production, the stability of the equipment during production is guaranteed, and the situation that detection data exceed an allowable range is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment control, and in particular to a method and system for optimizing and adjusting operating parameters of a papermaking machine based on an adaptive algorithm. Background Art

[0002] In the papermaking industry, papermaking machines are one of the key equipment for producing paper. Their performance and stability have a decisive impact on paper quality and production efficiency. As an advanced control method, adaptive algorithms can automatically adjust control parameters according to the real-time status and operating data of the system to keep the system in the best working state. Applying adaptive algorithms to the optimization and adjustment of the operating parameters of papermaking machines can achieve precise control of the papermaking process, thereby ensuring the stability of the production quality of papermaking machines.

[0003] For example, the patent publication number is "CN118311871A", and the patent name is "Speed ​​Governor Control Method and System Based on Adaptive Model Predictive Control Algorithm". Step 1: Start the simulation environment module, simulate the actual operating status of the turbine, and monitor the status data in real time; Step 2: Input the monitored data into the adaptive model predictive control algorithm; The present invention introduces an adaptive model predictive control algorithm, which can update the model parameters in real time according to changes in the operating conditions of the turbine, thereby improving the robustness and accuracy of the speed control.

[0004] When the above method is applied to a papermaking machine, there will be a problem that the optimization and adjustment method of the papermaking machine's operating parameters is highly targeted but lacks flexibility, especially when it is necessary to produce paper of different thicknesses (or qualities). When producing paper of a single thickness (or quality), the adjustment method often shows good practicality due to the support of rich historical production data. Once it is necessary to produce paper of different thicknesses (or qualities), the adjustment method has to be changed. Taking toilet paper as an example, its thickness standard needs to be controlled between 0.06 and 0.18 mm, and other types of paper also have their own different thickness requirements. This means that even toilet paper, with different thickness specifications such as 0.06 mm, 0.07 mm and 0.08 mm, requires corresponding adjustment algorithms to ensure the thickness after production.

[0005] In the actual production process, multiple dimensions of product quality (such as the allowable range of thickness, allowable range of roughness, tensile strength, etc.) are combined to form a wide range of production requirements. For some ordinary paper, the allowable range of production is particularly wide. This may lead to a lack of corresponding historical production data as a reference in some cases. When faced with such paper production tasks without historical data to rely on, the adjustment work becomes particularly difficult because there is a lack of experience to guide the setting of the operating parameters of the papermaking machine.

[0006] Therefore, the diversity of paper quality production requirements directly leads to the continuous changes in paper machine operating parameters, and the optimization adjustment method for different paper qualities becomes complicated and there is no historical data to rely on. For this reason, a paper machine operating parameter optimization adjustment method and system based on an adaptive algorithm is invented. Summary of the invention

[0007] The object of the present invention is to provide a method and system for optimizing and adjusting the operating parameters of a papermaking machine based on an adaptive algorithm, so as to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solution: the parameter optimization and adjustment method comprises:

[0009] Basic data collection: Collect historical production data of papermaking machines;

[0010] Establishing associated data: Based on historical production data, a data-driven model is used to quantitatively express the degree of association between parameters in the associated data. Based on the historical production data and the degree of association, an association diagram is established between the equipment, the equipment's operating parameters, the paper parameters in the paper production process, and the quality parameters of the final product;

[0011] Establish and apply simulation models: establish simulation models, simulate blank production data through simulation models, obtain simulated production data, and combine simulated production data with historical production data to obtain a complete collection of simulated production data;

[0012] Input requirements: The user inputs the target theoretical final product quality data, and obtains the theoretical operating parameter data of the paper machine and the theoretical paper parameter data by searching from the complete collection;

[0013] Establishing an allowable range: establishing an allowable range based on the quality parameters in the input requirements, wherein the allowable range includes the allowable range of equipment operation parameters, the allowable range of paper parameters and the allowable range of quality parameters;

[0014] Real-time detection data: Real-time detection of papermaking machine production data, obtaining real-time equipment operation parameters, real-time parameter data, real-time paper parameter data and real-time quality parameter data;

[0015] Establish and apply prediction model: establish prediction model, the prediction model combines real-time parameter data and theoretical parameter data, predicts future paper parameter data and future quality parameter data of paper production, and obtains predicted paper parameters and predicted quality parameters;

[0016] Adaptive adjustment: Establish parameter adjustment method and parameter fine-tuning method based on correlation degree, correlation diagram and allowable range. When the predicted paper parameter exceeds the allowable range of paper parameter, the parameter fine-tuning method is adopted. When the predicted quality parameter exceeds the allowable range of quality parameter, the parameter adjustment method is adopted.

[0017] Adaptive overall control: Establish hierarchical control for adjusting equipment operating parameters, and adopt hierarchical control based on the comparison between real-time paper parameter data and the allowable range of paper parameters. The hierarchical control includes short feedback adjustment for fine-tuning the parameters of the equipment in front of the assembly line and long feedback adjustment for overall optimization;

[0018] Repeated continuous correction: Continuously monitor real-time data and continuously apply predictive models, adjustments and overall control based on real-time data until paper production is completed.

[0019] Furthermore, the simulation method of the simulation model includes: taking historical production data as a reference, realizing the simulation between equipment parameters, paper parameters in the production process and final quality parameters of the product through the degree of association, inputting the final quality parameters, setting the theoretical product final quality data in the simulation model, and using the simulation model and associated data to simulate the process of producing the theoretical product final quality data. The simulation model obtains process data during the simulation process, and the process data includes simulated equipment parameter data and simulated paper parameter data. The theoretical product final quality data, process data and historical production data are combined to obtain a complete collection of simulated production data.

[0020] Furthermore, the prediction method of the prediction model includes: combining a complete collection of simulated production data, using real-time paper parameter data as input to the prediction model, and inputting real-time paper parameters and theoretical paper parameters into the correlation degree to obtain corresponding predicted quality parameter data.

[0021] Furthermore, the parameter adjustment method includes: obtaining predicted quality parameter data based on actual device parameter data and real-time paper parameter data in combination with a prediction model, obtaining a first difference between the predicted quality parameter data and an allowable range of quality parameters, controlling specific values ​​of device operating parameters according to the degree of association, and ensuring that the paper parameter data is within the allowable range of paper parameters in combination with the prediction model, so that the adjusted predicted quality parameters are within the allowable range of quality parameters.

[0022] Furthermore, the parameter fine-tuning method includes: obtaining a second difference between the real-time paper parameter and the allowable range of the paper parameter, controlling the specific value of the corresponding device operating parameter according to the degree of association, and controlling the paper parameter data to be within the allowable range of the paper parameter in combination with the prediction model.

[0023] Furthermore, the comparison result includes: obtaining the middle value of the allowable range of paper parameters, obtaining the No. 3 difference between the real-time paper parameter data and the middle value, and judging the positive and negative situation of the No. 3 difference. When the actual paper parameter data exceeds the allowable range of paper parameters, long feedback adjustment is triggered. When the actual paper parameter data does not exceed the allowable range of paper parameters and the No. 3 difference ensures that the positive and negative values ​​remain unchanged, short feedback adjustment is triggered.

[0024] Furthermore, the long feedback adjustment includes: adjusting the device parameter data sorted in the front position according to the sorting order in the pipeline, obtaining the corresponding device based on the degree of association and the comparison result, adjusting the operating parameters of the corresponding device, obtaining the adjusted device operating parameters, predicting the paper parameters through the prediction model, obtaining the adjusted predicted paper parameter data, and the adjusted predicted paper parameter data is within the allowable range of the paper parameters.

[0025] Furthermore, the short feedback adjustment method includes: adjusting the parameter data of the device before the assembly line, adjusting the parameter of the previous device based on the degree of association and the comparison result, and combining the prediction model to obtain the adjusted predicted paper parameter data, obtain the predicted number three difference between the predicted paper parameter data and the intermediate value, and control the specific value of the predicted number three difference to be at the minimum value.

[0026] A papermaking machine operating parameter optimization and adjustment system based on an adaptive algorithm adopts the above-mentioned papermaking machine operating parameter optimization and adjustment method based on an adaptive algorithm.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] The papermaking machine operating parameter optimization and adjustment method and system based on the adaptive algorithm obtains simulated production data by simulating the production process, so as to obtain comprehensive production data. The comprehensive production data can provide effective theoretical support for subsequent data prediction. The prediction model combines real-time detection data with theoretical detection data to realize the prediction of subsequent data. Based on the prediction results, the equipment parameters are adjusted. The quality of paper production can be guaranteed by adjusting the equipment. At the same time, after the equipment parameters are adjusted, support can be provided for subsequent production, the stability of the equipment during production can be guaranteed, and the situation where the detection data exceeds the allowable range can be reduced.

[0029] At the same time, through the settings of adjustment and overall control, the parameter fine-tuning method and the parameter adjustment method are based on the paper parameters at the detection point to adjust the operating parameters of the subsequent equipment. By adjusting the operating parameters of the subsequent equipment, the quality parameters of the paper at this point can meet the needs. The overall control is based on the paper parameters at the detection point to adjust the equipment at the front of the assembly line. By adjusting the operating parameters of the front equipment, the difference between the subsequent paper parameters at this point and the middle value of the allowable range of the paper parameters is reduced, or the paper parameters at this point are avoided from exceeding the allowable range of the paper parameters, thereby achieving comprehensive adjustment of the operating parameters of the papermaking machine while ensuring production quality.

[0030] Through the design of correlation degree and simulation model, the simulation model can simulate blank production data through correlation degree to supplement production data. By simulating the complete collection of production data, it can provide assistance for the prediction of subsequent prediction model. At the same time, the use of the complete collection can provide effective theoretical support for the subsequent adjustment process of equipment parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A schematic diagram of the parameter optimization and adjustment method of the present invention;

[0032] Figure 2 It is a schematic diagram of the association diagram of the present invention and the association diagram of No. 1;

[0033] Figure 3 A schematic diagram of adjusting the operating parameters of subsequent equipment according to the present invention;

[0034] Figure 4 This is a schematic diagram of adjusting the operating parameters of the previous equipment according to the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] like Figure 1 - Figure 4 As shown, the present invention provides a technical solution: the parameter optimization adjustment method includes:

[0037] Basic data collection: Collect historical production data of papermaking machines;

[0038] Establishing associated data: Based on historical production data, a data-driven model is used to quantitatively express the degree of association between parameters in the associated data. Based on the historical production data and the degree of association, an association diagram is established between the equipment, the equipment's operating parameters, the paper parameters in the paper production process, and the quality parameters of the final product;

[0039] Establish and apply simulation models: establish simulation models, simulate blank production data through simulation models, obtain simulated production data, and combine simulated production data with historical production data to obtain a complete collection of simulated production data;

[0040] Input requirements: The user inputs the target theoretical final product quality data, and obtains the theoretical operating parameter data of the paper machine and the theoretical paper parameter data by searching from the complete collection;

[0041] Establishing the allowable range: Establishing the allowable range based on the quality parameters in the input requirements. The allowable range includes the allowable range of equipment operation parameters, the allowable range of paper parameters and the allowable range of quality parameters.

[0042] Real-time detection data: Real-time detection of papermaking machine production data, obtaining real-time equipment operation parameters, real-time parameter data, real-time paper parameter data and real-time quality parameter data;

[0043] Establish and apply prediction model: establish prediction model, the prediction model combines real-time parameter data and theoretical parameter data, predicts future paper parameter data and future quality parameter data of paper production, and obtains predicted paper parameters and predicted quality parameters;

[0044] Adaptive adjustment: Establish parameter adjustment method and parameter fine-tuning method based on correlation degree, correlation diagram and allowable range. When the predicted paper parameter exceeds the allowable range of paper parameter, the parameter fine-tuning method is adopted. When the predicted quality parameter exceeds the allowable range of quality parameter, the parameter adjustment method is adopted.

[0045] Adaptive overall control: Establish hierarchical control for adjusting equipment operating parameters. Hierarchical control is adopted based on the comparison between real-time paper parameter data and the allowable range of paper parameters. Hierarchical control includes short feedback adjustment for fine-tuning the parameters of the equipment arranged at the front of the assembly line and long feedback adjustment for overall optimization.

[0046] Repeated continuous correction: Continuously monitor real-time data and continuously apply predictive models, adjustments and overall control based on real-time data until paper production is completed.

[0047] The simulation method of the simulation model includes: taking historical production data as a reference, realizing the simulation between equipment parameters, paper parameters in the production process and final quality parameters of the product through the degree of association, inputting the final quality parameters, setting the theoretical product final quality data in the simulation model, simulating the process of producing the theoretical product final quality data by using the simulation model and the associated data, the simulation model obtains process data during the simulation process, the process data includes simulated equipment parameter data and simulated paper parameter data, the theoretical product final quality data, process data and historical production data are combined to obtain a complete collection of simulated production data.

[0048] The prediction method of the prediction model includes: combining a complete collection of simulated production data, using real-time paper parameter data as input to the prediction model, and inputting real-time paper parameters and theoretical paper parameters into the correlation degree to obtain corresponding prediction quality parameter data.

[0049] The parameter adjustment method includes: obtaining predicted quality parameter data based on actual equipment parameter data and real-time paper parameter data in combination with a prediction model, obtaining a first difference between the predicted quality parameter data and an allowable range of quality parameters, controlling specific values ​​of equipment operating parameters according to the degree of association, and ensuring that the paper parameter data is within the allowable range of paper parameters in combination with the prediction model, so that the adjusted predicted quality parameters are within the allowable range of quality parameters.

[0050] The parameter fine-tuning method includes: obtaining a second difference between the real-time paper parameter and the allowable range of the paper parameter, controlling the specific value of the corresponding equipment operating parameter according to the degree of association, and controlling the paper parameter data to be within the allowable range of the paper parameter in combination with the prediction model.

[0051] The comparison results include: obtaining the middle value of the allowable range of paper parameters, obtaining the No. 3 difference between the real-time paper parameter data and the middle value, and judging the positive and negative situation of the No. 3 difference. When the actual paper parameter data exceeds the allowable range of paper parameters, long feedback adjustment is triggered. When the actual paper parameter data does not exceed the allowable range of paper parameters and the No. 3 difference ensures that the positive and negative values ​​remain unchanged, short feedback adjustment is triggered.

[0052] Long feedback adjustment includes: adjusting the device parameter data in the front position according to the sorting order in the assembly line, obtaining the corresponding device based on the degree of association and the comparison result, adjusting the operating parameters of the corresponding device, obtaining the adjusted device operating parameters, predicting the paper parameters through the prediction model, obtaining the adjusted predicted paper parameter data, and the adjusted predicted paper parameter data is within the allowable range of the paper parameters.

[0053] The short feedback adjustment method includes: adjusting the parameter data of the device before the assembly line, adjusting the parameters of the previous device based on the degree of association and the comparison result, and combining the prediction model to obtain the adjusted predicted paper parameter data, obtain the predicted No. 3 difference between the predicted paper parameter data and the intermediate value, and control the specific value of the predicted No. 3 difference to be at the minimum value.

[0054] A papermaking machine operating parameter optimization and adjustment system based on an adaptive algorithm adopts the above-mentioned papermaking machine operating parameter optimization and adjustment method based on an adaptive algorithm.

[0055] Although historical production data may not cover the production range of paper quality, the parameters, quality and other related data are numerically represented for subsequent processing and use. After obtaining the historical production data, the historical production data is processed, and data cleaning and deduplication are performed to improve the reliability of the historical production data. The production data includes equipment operating parameters, paper parameters in the paper production process and quality parameters of the final product. Equipment operating parameters are equipment parameters in the equipment operation process, paper parameters. During the production process, a detection device is used to detect the paper to obtain paper parameter data in the production process and final quality parameters. After the paper production is completed, the paper quality is detected by a detection device. The paper quality includes thickness and surface roughness, etc. Since the papermaking machine operates in an assembly line manner, the subsequent equipment and the previous equipment mentioned in this application refer to the relative positions on the assembly line.

[0056] There will be a device for detecting the same parameter at the discharge end of the equipment. For example, equipment for detecting the moisture content of paper is installed at the discharge end of the pressing and drying process equipment. However, since the two process positions are different, their properties are also different. Therefore, the two obtained paper parameters cannot be regarded as the same paper parameters.

[0057] Real-time detection of paper machine operating parameters and paper parameter data during the paper machine production process, obtaining real-time parameter data of the paper machine and real-time paper parameter data, combining real-time equipment parameters with subsequent theoretical equipment parameters, and obtaining predicted paper parameter data through a prediction model, combining real-time paper parameter data with subsequent predicted paper parameter data, and obtaining predicted quality parameter data through a prediction model. This process is a continuous process, with the continuous process of production, continuous collection of real-time parameter data and real-time paper parameter data, and then continuous correction.

[0058] There are two types of problems regarding the same batch. The first type is that the unformed products are moved as a whole from one process to the next process, and the current process and the next process do not process the same batch of products when working at the same time. The second type is that the unformed products are moved continuously from one process to the next process, and the current process and the next process process the same batch of products when working at the same time. For example, the process flow of a papermaking machine includes pulp, loose pulp, high-concentration deslagging, refining, pulping, forming, pressing, drying, corrugating, paper rolling, and base paper, among which pulp, loose pulp, high-concentration deslagging, refining, and pulping can be regarded as the first type of batch, and forming, pressing, drying, corrugating, paper rolling, and base paper can be regarded as the second type of batch. The specific parameter adjustment methods used in the two will be significantly different. Since the first type moves the product as a whole in the process, the detected paper parameters can be detected in real time by the detection device. However, the paper parameters can be changed by changing the operating parameters of the equipment or the content of raw materials inside the equipment so that the paper parameters reach the allowable range, or even the optimal data point within the allowable range. When the paper parameters reach the optimal data point or the allowable range, the product can be moved to the next process. The present application is for the second type. In this process, when detecting the paper parameters at the discharge end of the equipment, if the paper parameters exceed the corresponding allowable range, the paper parameters cannot be corrected at this time. Even when adjusting the equipment parameters, the paper parameters at the discharge end cannot be modified and adjusted, and the adjustment of the equipment parameters can only adjust the subsequent paper parameters. Therefore, if the paper parameters need to be corrected to ensure the quality parameters of the paper at this location, the subsequent equipment parameters need to be adjusted in order to correct the quality parameters of the paper at this location.

[0059] The production of papermaking machines is a continuous process, from pulp forming to product production. For example, there are processes of pulping, pulping, forming, pressing, drying, and rewinding in papermaking machines, and equipment to implement the above processes. The equipment is arranged according to the assembly line, and a detection device for detecting product paper parameter data is installed at the discharge end of the equipment. The detection device includes an online near-infrared moisture detector, which is mainly used for moisture content detection in the papermaking process. It can provide real-time and rapid moisture data of the paper, so as to timely adjust the production process parameters (such as pressing pressure, drying temperature and speed, etc.) to ensure that the moisture content of the paper meets the production standards. It also includes optical performance detection equipment, which realizes There will be other detection devices for the whiteness and opacity of paper. The existence of detection devices requires specific types of data based on the final quality parameters. The data-driven model is a statistical-based model that relies on the data itself to find parameters and achieve preset goals. Through correlation analysis, it can be found that there is a significant linear relationship between pulp concentration and paper thickness, strength and other indicators. Through regression analysis, a mathematical relationship between pulp concentration and paper quality can be established to predict and control paper quality. Using machine learning models, the impact of multiple parameters on paper quality can be comprehensively considered, and predicted values ​​or classification results can be output to provide support for decision-making in the production process.

[0060] There are existing technologies for both simulation models and prediction models. Historical production data are used in the simulation model. According to the association diagram and the historical production data, a data-driven model is used to quantitatively express the degree of association between parameters in the association data, which is represented by numerical values, and to simulate blank and missing production parameters, such as operating parameter a, paper parameter p and quality parameter q, where a, p and q all represent positive integers.

[0061] Calculation method of paper parameter p:

[0062] K11 operating parameter 1+K12 operating parameter 2+…K1a operating parameter a=paper parameter 1;

[0063] K21 operating parameter 1+K22 operating parameter 2+…K2a operating parameter a=paper parameter 2;

[0064] …

[0065] Kp1 operating parameter 1+Kp2 operating parameter 2+…Kpa operating parameter a=paper parameter p;

[0066] Calculation method of quality parameter q:

[0067] H11 paper parameter 1+H12 paper parameter 2+…H1p paper parameter p=quality parameter 1;

[0068] H21 paper parameter 1 + H22 paper parameter 2 + ... H2p paper parameter p = quality parameter 2;

[0069] …

[0070] Hq1 paper parameter 1+Hq2 paper parameter 2+…Hqp paper parameter p=quality parameter q;

[0071] Among them, K11, K12...Kpa are coefficients, H11, H12...Hqp are coefficients, and the K coefficient and H coefficient are calculated through historical production data. The remaining blank production data are supplemented by the obtained K coefficient and H coefficient and the calculation method of paper parameter p and the calculation method of paper parameter p. The K coefficient and H coefficient may have a value of zero. The input needs include the required quality parameter q. At the same time, based on the principle of similarity, similar paper parameters in the historical production data are selected as references and substituted. At this time, although there is a deviation between the obtained quality parameters and the required quality parameters, according to the arbitrary change of one or more paper parameters, the paper parameters with the least number are modified first. The principle of similarity is to find parameters with similar values ​​to the quality parameters from the historical production data based on the quality parameters in the input requirements. In fact, the calculation method of paper parameter p and the calculation method of quality parameter q do not all use linear parameters for calculation, and other calculation methods can also be used for calculation, using nonlinear regression models, such as polynomial regression, exponential regression, logarithmic regression, etc. These models can capture more complex nonlinear relationships and improve the accuracy of calculation.

[0072] Through numerical simulation, calculations are performed to obtain the final quality data and process data of the simulated theoretical product. A complete collection of simulated production data is obtained, and the simulation process of the data in the simulation model can be used as a reference for the establishment of a prediction model. The simulation process is based on historical production data to generate blank production data, and the prediction model simulates the changes in quality parameters based on parameter changes. The simulation model combines historical production data to simulate the simulated equipment parameter data and simulated paper parameter data under the theoretical final quality data. The simulation data is combined with historical production data to obtain a comprehensive and complete production data collection. The simulation model can be used to simulate production data. First, the theoretical product final quality data is input into the simulation model. The simulation model simulates production based on the theoretical product final quality data to obtain process data. The process data includes simulated equipment parameter data and simulated paper parameter data. After that, the data is integrated to obtain a complete collection of production data. The complete collection can achieve correspondence and full coverage of the production range of quality parameters for subsequent predictions. At the same time, in actual production, the actual paper parameters, actual paper parameters and actual quality parameters are obtained, and the simulation data in the complete production data collection can be corrected.

[0073] There is a natural correlation between the equipment and its operating parameters. A No. 1 correlation is obtained between the equipment and its operating parameters. The establishment of the No. 1 correlation is mainly to obtain the sequence of the equipment and combine the sequence of sequence with the equipment operating parameters, so that the sequence of sequence can be used as a reference for paper parameters.

[0074] In the long feedback adjustment, therefore, in actual production, when the equipment operating parameters, paper parameters and final quality parameters are all within the allowable range, the system will not automatically apply the operating parameter optimization adjustment method. Only when the paper parameters exceed the allowable range of the intermediate value, long feedback adjustment will be performed. A detection device for detecting paper parameter data is provided at the discharge end of each device. The detection device detects the paper parameter data in real time to obtain paper parameter data about the discharge end of the device. The paper parameter data is compared with the allowable range of the paper parameters. When it exceeds the range, the optimization adjustment system runs and long feedback adjustment is applied to adjust the operating parameters of the equipment. At the same time, the prediction model is used to predict the paper parameter data of the paper at this location, and the subsequent paper parameter data and final quality parameters are predicted. When the final quality parameter data exceeds the allowable range of the final quality parameter, a series of subsequent equipment operating parameters will be adjusted.

[0075] In short feedback adjustment, the real-time detected paper parameter data will change, but because it is still within the allowable range, long feedback adjustment will not be triggered. However, with the increase of usage time, the change of real-time paper parameter data will reach the point of triggering long feedback adjustment. Due to the complexity of adjustment and the large adjustment degree in long feedback adjustment, short feedback adjustment will be used to correct the real-time detected paper parameter data to ensure that the real-time detected paper parameter data can be within the allowable range. When the real-time paper parameter data are all normal, but the final quality parameter data detected still exceeds its operating range, the short feedback adjustment is applied to adjust the equipment parameter data in real time so that the paper parameters at the discharge end of the equipment can be better within the corresponding operating range. The short feedback adjustment adjusts the paper parameters by correcting the equipment parameters at the previous position, thereby adjusting the quality parameters of the final product. Through short feedback adjustment, the specific data of the simulated quality parameters or simulated paper parameters will fluctuate on the intermediate value. By controlling the specific values ​​to fluctuate on the intermediate value, this method can ensure the stability of the papermaking machine operation and thus ensure the stability of papermaking machine production.

[0076] like Figure 3As shown, the actual paper parameter 1 is obtained through the real-time detection method, and the actual paper parameter 1 is combined with the subsequent theoretical paper parameter 3 to obtain the prediction of the quality parameter through the prediction model. When it is judged that the specific value of the predicted quality parameter 1 exceeds the allowable range of the corresponding quality parameter, it will be adjusted. According to the association diagram and the degree of association, the device parameter 4 is controlled to be adjusted so that the paper parameter 3 is modified, and then the modified final quality 1 is obtained, and it is ensured that the modified final quality 1 is within the allowable range of the corresponding quality parameter, wherein the modified paper parameter 3 and the modified final quality 1 are both obtained through prediction by the prediction model.

[0077] like Figure 4 As shown, when it is detected that the actual paper parameter 3 exceeds the allowable range of the corresponding paper parameter, long feedback adjustment and short feedback adjustment will be used to adjust the equipment parameters at the front of the assembly line, and combined with the prediction model, the predicted adjusted paper parameter 3 can be within the allowable range of the corresponding paper parameter. At the same time, when the prediction model is making a prediction, it needs to ensure that the predicted final quality 1 is within the allowable range of the corresponding quality parameter.

[0078] Before production, the user inputs the demand. The target theoretical product final quality data refers to the paper data that the user wants to produce. According to the demand, the corresponding theoretical equipment operating parameters and theoretical paper parameters are obtained from the simulated production data in the complete collection. Ideally, the required paper can be obtained by following the operating parameters of the theoretical equipment. The operating parameters of the equipment can be directly controlled, and the control of paper parameters and theoretical quality parameters can only be achieved through the operating parameters. When the detection device detects the actual paper parameters, the actual paper parameters are combined with the theoretical paper parameters, and the simulation between the quality parameters is realized through the prediction model to obtain the simulated quality parameters. The simulated quality parameters are compared with the allowable range of the quality parameters. The middle value in the allowable range of the quality parameters is used as a reference. When the simulated quality parameters exceed the allowable range of the quality parameters, long feedback adjustment is applied. If the specific data of the simulated quality parameters will continue to deviate from the middle value in the allowable range, short feedback adjustment is applied. The short feedback adjustment adjusts the equipment parameters, so that the specific data of the simulated quality parameters fluctuate at the middle value of the allowable range. The use of parameter fine-tuning method, parameter adjustment method, short feedback adjustment and long feedback adjustment is essentially the application of adaptive algorithm.

[0079] The parameter fine-tuning method and the parameter adjustment method are to adjust the operating parameters of subsequent equipment based on the paper parameters at the detection point, and by adjusting the operating parameters of subsequent equipment, the quality parameters of the paper at this point can meet the needs. The overall control is to adjust the equipment at the front of the assembly line based on the paper parameters at the detection point, and by adjusting the operating parameters of the front equipment, the difference between the subsequent paper parameters at this point and the middle value of the allowable range of the paper parameters can be reduced, or the paper parameters at this point can be avoided from exceeding the allowable range of the paper parameters, thereby achieving comprehensive adjustment of the operating parameters of the papermaking machine while ensuring production quality.

[0080] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is limited by the attached embodiments and their equivalents.

Claims

1. A method for optimizing and adjusting operating parameters of a papermaking machine based on an adaptive algorithm, characterized in that: The parameter optimization and adjustment method comprises: Basic data collection: Collect historical production data of papermaking machines; Establishing associated data: Based on historical production data, a data-driven model is used to quantitatively express the degree of association between parameters in the associated data. Based on the historical production data and the degree of association, an association diagram is established between the equipment, the equipment's operating parameters, the paper parameters in the paper production process, and the quality parameters of the final product; Establish and apply simulation models: establish simulation models, simulate blank production data through simulation models, obtain simulated production data, and combine simulated production data with historical production data to obtain a complete collection of simulated production data; Input requirements: The user inputs the target theoretical final product quality data, and obtains the theoretical operating parameter data of the paper machine and the theoretical paper parameter data by searching from the complete collection; Establishing an allowable range: establishing an allowable range based on the quality parameters in the input requirements, wherein the allowable range includes the allowable range of equipment operation parameters, the allowable range of paper parameters and the allowable range of quality parameters; Real-time detection data: Real-time detection of papermaking machine production data, obtaining real-time equipment operation parameters, real-time parameter data, real-time paper parameter data and real-time quality parameter data; Establish and apply prediction model: establish prediction model, the prediction model combines real-time parameter data and theoretical parameter data, predicts future paper parameter data and future quality parameter data of paper production, and obtains prediction parameters and predicted quality parameters; Adaptive adjustment: Establish parameter adjustment method and parameter fine-tuning method based on correlation degree, correlation diagram and allowable range. When the predicted paper parameter exceeds the allowable range of paper parameter, the parameter fine-tuning method is adopted. When the predicted quality parameter exceeds the allowable range of quality parameter, the parameter adjustment method is adopted. Adaptive overall control: Establish hierarchical control for adjusting equipment operating parameters, and adopt hierarchical control based on the comparison between real-time paper parameter data and the allowable range of paper parameters. The hierarchical control includes short feedback adjustment for fine-tuning the parameters of the equipment in front of the assembly line and long feedback adjustment for overall optimization; Repeated continuous correction: Continuously monitor real-time data and continuously apply predictive models, adjustments and overall control based on real-time data until paper production is completed.

2. The method for optimizing and adjusting the operating parameters of a papermaking machine based on an adaptive algorithm according to claim 1, characterized in that: The simulation method of the simulation model includes: taking historical production data as a reference, realizing the simulation between equipment parameters, paper parameters in the production process and final quality parameters of the product through the degree of association, inputting the final quality parameters, setting the theoretical product final quality data in the simulation model, simulating the process of producing the theoretical product final quality data by using the simulation model and the associated data, the simulation model obtains process data during the simulation process, the process data includes simulated equipment parameter data and simulated paper parameter data, the theoretical product final quality data, process data and historical production data are combined to obtain a complete collection of simulated production data.

3. The method for optimizing and adjusting the operating parameters of a papermaking machine based on an adaptive algorithm according to claim 1, characterized in that: The prediction method of the prediction model includes: combining a complete collection of simulated production data, using real-time paper parameter data as input to the prediction model, and inputting real-time paper parameters and theoretical paper parameters into the correlation degree to obtain corresponding prediction quality parameter data.

4. The method for optimizing and adjusting operating parameters of a papermaking machine based on an adaptive algorithm according to claim 1, characterized in that: The parameter adjustment method includes: obtaining predicted quality parameter data based on actual equipment parameter data and real-time paper parameter data in combination with a prediction model, obtaining a first difference between the predicted quality parameter data and an allowable range of quality parameters, controlling specific values ​​of equipment operating parameters according to the degree of association, and ensuring that the paper parameter data is within the allowable range of paper parameters in combination with the prediction model, so that the adjusted predicted quality parameters are within the allowable range of quality parameters.

5. The method for optimizing and adjusting operating parameters of a papermaking machine based on an adaptive algorithm according to claim 1, characterized in that: The parameter fine-tuning method includes: obtaining a second difference between the real-time paper parameter and the allowable range of the paper parameter, controlling the specific value of the corresponding device operating parameter according to the degree of association, and controlling the paper parameter data to be within the allowable range of the paper parameter in combination with the prediction model.

6. The method for optimizing and adjusting operating parameters of a papermaking machine based on an adaptive algorithm according to claim 1, characterized in that: The comparison result includes: obtaining the middle value of the allowable range of paper parameters, obtaining the No. 3 difference between the real-time paper parameter data and the middle value, and judging the positive and negative situation of the No. 3 difference. When the actual paper parameter data exceeds the allowable range of paper parameters, long feedback adjustment is triggered. When the actual paper parameter data does not exceed the allowable range of paper parameters and the No. 3 difference ensures that the positive and negative values ​​remain unchanged, short feedback adjustment is triggered.

7. The method for optimizing and adjusting operating parameters of a papermaking machine based on an adaptive algorithm according to claim 1, characterized in that: The long feedback adjustment includes: adjusting the device parameter data in the front position according to the sorting order in the pipeline, obtaining the corresponding device based on the degree of association and the comparison result, adjusting the operating parameters of the corresponding device, obtaining the adjusted device operating parameters, predicting the paper parameters through the prediction model, obtaining the adjusted predicted paper parameter data, and the adjusted predicted paper parameter data is within the allowable range of the paper parameters.

8. The method for optimizing and adjusting the operating parameters of a papermaking machine based on an adaptive algorithm according to claim 1, characterized in that: The short feedback adjustment method includes: adjusting the parameter data of the previous device sorted in the assembly line, adjusting the previous device parameter based on the correlation degree and the comparison result, and combining the prediction model to obtain the adjusted predicted paper parameter data, obtain the predicted No. 3 difference between the predicted paper parameter data and the intermediate value, and control the specific value of the predicted No. 3 difference to be at the minimum value.

9. A paper machine operating parameter optimization and adjustment system based on an adaptive algorithm, characterized in that: A method for optimizing and adjusting the operating parameters of a papermaking machine based on an adaptive algorithm as described in any one of claims 1 to 8 is adopted.

Images