A Multivariable Collaborative Optimization Control System and Method for a Viscose Staple Fiber Dryer Based on Digital Twin

By using digital twin technology to achieve multi-variable collaborative optimization control of the viscose staple fiber dryer, the problems of finished product moisture regain fluctuation and high steam consumption in the existing system have been solved, achieving high efficiency, stable quality and optimized energy consumption, and adapting to complex working conditions.

CN123113316APending Publication Date: 2026-11-17TANGSHAN SANYOU YUANDA FIBER CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611144175.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-07-30
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

The existing control system of viscose staple fiber dryer cannot effectively take into account the coupling relationship between multiple variables such as drying temperature, chain speed, and dehumidification air volume, resulting in large fluctuations in finished product moisture regain, high steam consumption, and reliance on manual parameter adjustment, making it difficult to adapt to production fluctuations and environmental changes.

Method used

A multivariate collaborative optimization control system based on digital twins is adopted, including data acquisition, digital twin simulation, multivariate prediction, intelligent control and field execution units, to achieve real-time synchronous simulation and multi-process parameter coupled calculation. The intelligent control unit outputs collaborative control commands to drive the field execution units to adjust in a coordinated manner.

Benefits of technology

It significantly improves the uniformity of finished product quality, reduces steam consumption, reduces the workload of manual parameter adjustment, has strong system adaptability, can cope with production fluctuations and environmental changes, and has good industrial promotion value.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123113316A_ABST
    Figure CN123113316A_ABST
Patent Text Reader

Abstract

This invention relates to a multivariate collaborative optimization control system for a viscose staple fiber dryer based on digital twins, comprising a data acquisition unit, a digital twin simulation unit, a multivariate prediction unit, an intelligent control unit, and a field execution unit. The data acquisition unit collects raw data from the physical dryer equipment and uploads it to the digital twin simulation unit. The digital twin simulation unit receives the raw dryer data, enables synchronous simulation between the physical dryer equipment and the digital virtual model, and performs coupled calculations of process parameters. The multivariate prediction unit, integrated within the digital twin simulation unit, performs quality and energy consumption predictions and fault warnings based on process parameters. The intelligent control unit outputs multi-device collaborative control commands based on the prediction results. The field execution unit receives the control commands, adjusts the drying process variables, and provides feedback on the equipment's operating status.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of automatic control technology for viscose fiber production, specifically to a multivariable collaborative optimization control system and method for a viscose staple fiber dryer based on digital twins. Background Technology

[0002] In the viscose staple fiber drying process, the dryer directly determines the finished product's moisture regain quality and steam consumption cost. Existing production lines generally use DCS combined with single-loop PID to independently control various process parameters. This method cannot take into account the coupled relationship between multiple variables such as drying temperature, chain speed, exhaust air volume, and ambient temperature and humidity. When faced with external disturbances such as production fluctuations and seasonal temperature and humidity changes, the adjustment lag is serious. Actual production data shows that the finished product moisture regain can fluctuate between 5% and 19% under traditional control schemes, with poor moisture content stability. In addition, to ensure product quality, a high steam supply must be maintained continuously, resulting in high steam consumption per ton of product. When the operating conditions deviate from the optimal range, manual on-site parameter adjustments are necessary, which involves a large amount of manual intervention and high production costs. Currently, there is a lack of mature control schemes in the industry that integrate digital twins, online prediction, and multivariate model prediction for collaborative optimization of viscose staple fiber dryers. Conventional simulation and control methods are difficult to achieve real-time synchronous simulation of virtual and physical equipment and adaptive linkage control of multiple parameters. There is an urgent need for an intelligent control technology that can balance product quality stability and energy consumption reduction. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a multivariable collaborative optimization control system and method for viscose staple fiber dryer based on digital twin, which addresses the shortcomings of the prior art.

[0004] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: a multivariable collaborative optimization control system for a viscose staple fiber dryer based on digital twin, including a data acquisition unit, a digital twin simulation unit, a multivariable prediction unit, an intelligent control unit, and a field execution unit; The data acquisition unit is used to collect raw data of the dryer physical equipment and upload it to the digital twin simulation unit; The digital twin simulation unit is used to receive the original data of the dryer physical equipment, realize the synchronous simulation of the dryer physical equipment and the digital virtual model, and perform coupled calculations of process parameters; The multivariate prediction unit is integrated into the digital twin simulation unit and performs quality and energy consumption prediction and fault early warning based on process parameters. The intelligent control unit outputs multi-device collaborative control commands based on the prediction results; The field execution unit receives control commands, adjusts the drying process variables, and provides feedback on the equipment's operating status.

[0005] The beneficial effects of adopting the technical solution of this invention are as follows: This invention comprehensively collects all-dimensional process data of the dryer through the data acquisition unit, realizes real-time synchronous simulation of physical equipment and virtual model and coupling calculation of multiple process parameters through the digital twin simulation unit, and predicts finished product moisture regain, steam energy consumption fluctuations and abnormal equipment conditions in advance with the help of the built-in multivariate prediction unit. Then, the intelligent control unit outputs multivariate collaborative control commands to drive the field execution unit to adjust each drying equipment in a coordinated manner. It can stably control the finished product moisture regain rate, significantly improve the uniformity of product quality, and optimize the steam supply under the condition of meeting quality constraints, reduce steam consumption per ton of product, reduce the workload of manual on-site parameter adjustment, and the system can adapt to various disturbance conditions such as production fluctuations and changes in environmental temperature and humidity. The overall intelligence level and adaptability to working conditions are strong, and it has good industrial promotion value.

[0006] Furthermore, the data acquisition unit includes a temperature and humidity sensor, a medium flow collector, and a transmission and fan operating parameter collector, used to collect raw process data such as drying temperature, steam flow, equipment operating conditions, environmental parameters, and finished product quality.

[0007] The beneficial effect of adopting the above-mentioned further solution is that by combining multiple types of sensing devices such as temperature and humidity sensors, medium flow collectors, and transmission and fan operation parameter collectors, it can completely cover the full-dimensional process information of drying temperature, steam flow, equipment operation, environmental conditions, and finished product quality. It can comprehensively acquire various coupled and related parameters during the operation of the dryer, providing complete and reliable underlying raw data support for the digital twin simulation unit to carry out parameter coupling calculations and for the multivariate prediction unit to achieve accurate prediction of quality and energy consumption. This avoids simulation distortion and prediction deviation caused by missing data acquisition dimensions, and ensures that the subsequent collaborative control command output is accurate and effective.

[0008] Furthermore, the digital twin simulation unit is an industrial simulation computing carrier, consisting of industrial computing hardware and a digital twin simulation software platform, integrating equipment 3D models, process mechanism models, energy consumption models, and finished product moisture regain quality prediction models.

[0009] The beneficial effects of adopting the above-mentioned further scheme are that it can integrate the physical structure of the equipment, the drying reaction mechanism, the energy consumption change law and the correlation with the quality of the finished product to carry out high-fidelity coupled calculations, fully reproduce the real production conditions of the dryer, provide a basis for accurate simulation and deduction for the multivariate prediction unit, improve the prediction accuracy of finished product rehydration and steam energy consumption, and facilitate subsequent iterative calibration of model parameters based on measured data, ensuring the synchronization of virtual and real equipment simulation and the accuracy of process parameter matching.

[0010] Furthermore, the multivariate prediction unit uses process parameters as model inputs and finished product quality indicators and unit product energy consumption indicators as model prediction outputs.

[0011] The beneficial effect of adopting the above-mentioned further scheme is that it can establish a quantitative mapping relationship between drying process parameters and core production indicators, and can predict the fluctuation of finished product moisture regain and the trend of steam consumption changes in real time and identify abnormal operating conditions. This provides accurate predictive basis for intelligent control unit to carry out multi-variable collaborative optimization and control, making it easier for the control system to correct process operation parameters in advance, reduce finished product quality fluctuations, avoid energy waste, and improve the foresight and accuracy of drying process control from the source.

[0012] Furthermore, the intelligent control unit is a multivariable optimization control hardware platform that integrates an RTO real-time optimization module, an MPC predictive control module, a network switch, and a human-machine interaction terminal, with a finished product moisture regain rate of 12% ± 0.5% as the system regulation constraint threshold.

[0013] The beneficial effects of adopting the above-mentioned further solutions are that, under the premise of ensuring stable and qualified finished product quality, the optimal process operation parameters can be solved, data communication between units can be realized by relying on network switches, and human-machine interaction terminals can be used to facilitate operators to view the operating conditions and adjust control parameters. Compared with traditional single-loop PID control, it can realize the coordinated adjustment of multiple process variables, effectively offset the impact of operating condition disturbances such as output, ambient temperature and humidity, and balance product quality consistency and steam energy consumption optimization, and significantly reduce the frequency of manual on-site adjustment.

[0014] Furthermore, the field execution unit includes a steam regulating valve, a dryer chain speed inverter, an exhaust fan inverter, and supporting communication cards and electrical protection accessories, which synchronously execute multi-variable linkage adjustment commands.

[0015] The beneficial effects of adopting the above-mentioned further solution are that the steam regulating valve, the dryer chain speed inverter, and the exhaust fan inverter respectively regulate the steam supply, material conveying speed, and exhaust air volume. With the communication card to ensure high-speed transmission of control commands, and electrical protection accessories to ensure safe operation of the equipment, it can synchronously receive multi-variable linkage adjustment commands issued by the intelligent control unit and synchronously complete the coordinated adjustment of multiple process parameters. This achieves synchronous linkage response of operation variables throughout the drying process, eliminates the parameter matching imbalance problem caused by independent adjustment of a single device, and ensures that the optimal process parameters formed by digital twin simulation and predictive optimization can be accurately implemented.

[0016] A multivariable collaborative optimization control method for a viscose staple fiber dryer based on digital twins, applied to the control system described above, includes the following steps: Collect and preprocess raw data from the dryer's physical equipment; Analysis of the coupling between raw data of the dryer's physical equipment and calibration of multiple parameters; Construct a digital twin model and conduct drying condition simulation and process parameter trend prediction; Build a multivariate online prediction model; Establish an integrated collaborative architecture for real-time RTO optimization and model predictive control (MPC), and correct the control commands of each actuator in real time based on twin prediction results; The collaborative control strategy is sent to the field control system, and the parameters of the digital twin model and the coefficients of the MPC control algorithm are calibrated in reverse based on the measured production data.

[0017] The beneficial effects of adopting the technical solution of this invention are as follows: First, complete and standardized processing of all-dimensional original process data of the dryer is collected. Then, the coupling relationship of each process parameter is calibrated based on the dataset. Relying on the digital twin model integrating multiple sub-models, virtual and real synchronous simulation and parameter trend prediction are realized. Combined with the multivariate online prediction model, the quality and energy consumption prediction results are output in real time. Through the integrated collaborative architecture of RTO and MPC, the control commands of each actuator are dynamically corrected according to the prediction. Finally, the model and control algorithm are continuously iteratively calibrated using on-site measured data, forming a closed-loop control process of data acquisition, simulation prediction, collaborative regulation, and iterative optimization. This improves the uniformity of product quality and reduces steam consumption per unit while meeting quality constraints, reducing the workload of manual on-site parameter adjustment. The whole method can adapt to various disturbance conditions such as production fluctuations and sudden changes in environmental temperature and humidity. It has strong adaptability to operating conditions and effectively balances product quality improvement and production energy consumption reduction, and has high industrial application value.

[0018] Furthermore, the acquisition and preprocessing of the original data of the dryer physical equipment includes the deployment of temperature and humidity sensors in each drying zone of the dryer, the air inlet, the air outlet and the surrounding environment, and the remote acquisition and control of the fan speed by a variable frequency exhaust fan.

[0019] The beneficial effect of adopting the above-mentioned further scheme is that it can collect temperature and humidity information and fan operation data of the drying area, air intake and exhaust and production environment in an all-round and comprehensive manner, and fully cover the key disturbance parameters that affect the finished product moisture regain and steam consumption. This provides comprehensive and detailed on-site basic data for subsequent data preprocessing, process coupling calibration and digital twin modeling, avoids the data being one-sided and the simulation and prediction results being distorted due to the lack of local measurement points, and ensures the data integrity and accuracy of the subsequent simulation, prediction and coordinated control links of the whole control method.

[0020] Furthermore, the data transmission delay between the physical dryer and the digital virtual model does not exceed 200ms.

[0021] The beneficial effects of adopting the above-mentioned further solutions are that they can realize real-time synchronization between the on-site equipment operating parameters, operating conditions and digital twin models, eliminate simulation deviations caused by the lag between virtual and real data, ensure the real-time performance and accuracy of the digital twin model in performing operating condition simulation and process parameter trend prediction, and enable the multivariate prediction unit to capture disturbances such as output and environmental temperature and humidity in a timely manner, providing reliable real-time simulation support for the intelligent control unit to quickly output the optimal collaborative control commands, and improving the system's response speed and anti-interference ability to cope with operating condition fluctuations.

[0022] Furthermore, the reverse calibration of the digital twin model parameters and MPC control algorithm coefficients includes three stages: no-load debugging, material-loaded trial operation, and full-load disturbance test. It simulates production output and environmental temperature and humidity fluctuations, collects measured data, and iteratively updates the digital twin coupling parameters and MPC control algorithm coefficients.

[0023] The beneficial effects of adopting the above-mentioned further solutions are that they can cover all real production scenarios, such as equipment no-load, normal production, and severe operating conditions, and verify the digital twin coupling parameters and MPC adjustment coefficients in a multi-level and all-round way. Through multiple rounds of data iteration and updates, the model and algorithm deviations are continuously corrected, which effectively improves the simulation accuracy of the digital twin model and the dynamic adaptation capability of the MPC controller. This enables the system to accurately complete multi-variable collaborative control under various complex disturbances, and the finished product moisture regain rate is more stable and the steam energy saving effect is more lasting and stable under long-term operation. Attached Figure Description

[0024] Figure 1 This is a system schematic diagram of a multivariable collaborative optimization control system for a viscose staple fiber dryer based on digital twin, provided for an embodiment of the present invention.

[0025] Figure 2 This is a flowchart illustrating a multivariate collaborative optimization control method for a viscose staple fiber dryer based on digital twins, provided as an embodiment of the present invention. Detailed Implementation

[0026] The principles and features of the present invention are described below. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0028] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0029] It should be noted that similar reference numerals and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In the description of the embodiments of the present invention, it should be noted that if terms such as "upper," "lower," "horizontal," "inner," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the figures, or the orientation or positional relationship in which the product of the invention is usually placed, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0030] In the description of the embodiments of the present invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention according to the specific circumstances.

[0031] like Figure 1 As shown, this embodiment of the invention provides a multivariate collaborative optimization control system for a viscose staple fiber dryer based on digital twins, including a data acquisition unit, a digital twin simulation unit, a multivariate prediction unit, an intelligent control unit, and a field execution unit; the units achieve bidirectional data transmission and signal interaction through an industrial communication network.

[0032] The data acquisition unit is used to collect raw data of the dryer physical equipment and upload it to the digital twin simulation unit.

[0033] The digital twin simulation unit is used to receive the original data of the dryer physical equipment, realize synchronous simulation of the dryer physical equipment and the digital virtual model, and perform coupled calculations of process parameters.

[0034] The multivariate prediction unit is integrated within the digital twin simulation unit and performs quality and energy consumption prediction and fault early warning based on process parameters.

[0035] The intelligent control unit outputs multi-device collaborative control commands based on the prediction results.

[0036] The field execution unit receives control commands, adjusts the drying process variables, and provides feedback on the equipment's operating status.

[0037] The beneficial effects of adopting the technical solution of this invention are as follows: This invention comprehensively collects all-dimensional process data of the dryer through the data acquisition unit, realizes real-time synchronous simulation of physical equipment and virtual model and coupling calculation of multiple process parameters through the digital twin simulation unit, and predicts finished product moisture regain, steam energy consumption fluctuations and abnormal equipment conditions in advance with the help of the built-in multivariate prediction unit. Then, the intelligent control unit outputs multivariate collaborative control commands to drive the field execution unit to adjust each drying equipment in a coordinated manner. It can stably control the finished product moisture regain rate, significantly improve the uniformity of product quality, and optimize the steam supply under the condition of meeting quality constraints, reduce steam consumption per ton of product, reduce the workload of manual on-site parameter adjustment, and the system can adapt to various disturbance conditions such as production fluctuations and changes in environmental temperature and humidity. The overall intelligence level and adaptability to working conditions are strong, and it has good industrial promotion value.

[0038] Furthermore, the data acquisition unit includes a temperature and humidity sensor, a medium flow rate collector, and a transmission and fan operating parameter collector, used to collect raw process data such as drying temperature, steam flow rate, equipment operating conditions, environmental parameters, and finished product quality. The data acquisition unit also includes a DCS analog input card and instrument cables. The instrument cables serve as signal transmission channels, stably transmitting various continuous analog signals to the DCS analog input card. The DCS analog input card performs analog-to-digital signal conversion, signal isolation and buffering, and uniformly outputs standardized raw process data, which is then uploaded to the digital twin simulation unit.

[0039] The beneficial effect of adopting the above-mentioned further solution is that by combining multiple types of sensing devices such as temperature and humidity sensors, medium flow collectors, and transmission and fan operation parameter collectors, it can completely cover the full-dimensional process information of drying temperature, steam flow, equipment operation, environmental conditions, and finished product quality. It can comprehensively acquire various coupled and related parameters during the operation of the dryer, providing complete and reliable underlying raw data support for the digital twin simulation unit to carry out parameter coupling calculations and for the multivariate prediction unit to achieve accurate prediction of quality and energy consumption. This avoids simulation distortion and prediction deviation caused by missing data acquisition dimensions, and ensures that the subsequent collaborative control command output is accurate and effective.

[0040] Furthermore, the digital twin simulation unit is an industrial simulation computing carrier, consisting of industrial computing hardware and a digital twin simulation software platform, integrating equipment 3D models, process mechanism models, energy consumption models, and finished product moisture regain quality prediction models.

[0041] The beneficial effects of adopting the above-mentioned further scheme are that it can integrate the physical structure of the equipment, the drying reaction mechanism, the energy consumption change law and the correlation with the quality of the finished product to carry out high-fidelity coupled calculations, fully reproduce the real production conditions of the dryer, provide a basis for accurate simulation and deduction for the multivariate prediction unit, improve the prediction accuracy of finished product rehydration and steam energy consumption, and facilitate subsequent iterative calibration of model parameters based on measured data, ensuring the synchronization of virtual and real equipment simulation and the accuracy of process parameter matching.

[0042] Furthermore, the multivariate prediction unit uses process parameters as model inputs and finished product quality indicators and unit product energy consumption indicators as model prediction outputs.

[0043] The beneficial effect of adopting the above-mentioned further scheme is that it can establish a quantitative mapping relationship between drying process parameters and core production indicators, and can predict the fluctuation of finished product moisture regain and the trend of steam consumption changes in real time and identify abnormal operating conditions. This provides accurate predictive basis for intelligent control unit to carry out multi-variable collaborative optimization and control, making it easier for the control system to correct process operation parameters in advance, reduce finished product quality fluctuations, avoid energy waste, and improve the foresight and accuracy of drying process control from the source.

[0044] Furthermore, the intelligent control unit is a multivariate optimization control hardware platform, integrating an RTO real-time optimization module, an MPC predictive control module, a network switch, and a human-machine interface terminal. The system uses a finished product moisture regain of 12% ± 0.5% as the system's control constraint threshold. The network switch enables data exchange with the upper-level digital twin simulation unit and the lower-level field execution unit. The human-machine interface terminal allows maintenance personnel to view process data online, monitor equipment operating status, and manually intervene in control parameters. The system sets the finished product moisture regain of 12% ± 0.5% as a hard control constraint threshold. During operation, the RTO module uses this quality range as the boundary and minimum steam consumption as the optimization objective. It combines the moisture regain and energy consumption prediction values ​​output by the multivariate prediction unit to solve for optimal operating variables such as steam flow rate, chain speed, and fan frequency. The optimal process parameters are then sent to the MPC predictive control module, which continuously corrects the control output commands based on real-time operating condition deviations, achieving coordinated adjustment of multiple process variables.

[0045] The beneficial effects of adopting the above-mentioned further solutions are that, under the premise of ensuring stable and qualified finished product quality, the optimal process operation parameters can be solved, data communication between units can be realized by relying on network switches, and human-machine interaction terminals can be used to facilitate operators to view the operating conditions and adjust control parameters. Compared with traditional single-loop PID control, it can realize the coordinated adjustment of multiple process variables, effectively offset the impact of operating condition disturbances such as output, ambient temperature and humidity, and balance product quality consistency and steam energy consumption optimization, and significantly reduce the frequency of manual on-site adjustment.

[0046] Furthermore, the field execution unit includes a steam regulating valve, a dryer chain speed inverter, an exhaust fan inverter, and supporting communication cards and electrical protection accessories, which synchronously execute multi-variable linkage adjustment commands. The steam regulating valve, dryer chain speed inverter, and exhaust fan inverter respectively control the drying steam supply, material conveying speed, and drying exhaust air volume. The supporting communication card establishes an industrial communication channel to achieve high-speed and stable transmission of multi-variable collaborative commands issued by the intelligent control unit. The electrical protection accessories can cut off the circuit in case of overload, short circuit, or signal abnormality, ensuring the safe and stable operation of various actuators.

[0047] The beneficial effects of adopting the above-mentioned further solution are that the steam regulating valve, the dryer chain speed inverter, and the exhaust fan inverter respectively regulate the steam supply, material conveying speed, and exhaust air volume. With the communication card to ensure high-speed transmission of control commands, and electrical protection accessories to ensure safe operation of the equipment, it can synchronously receive multi-variable linkage adjustment commands issued by the intelligent control unit and synchronously complete the coordinated adjustment of multiple process parameters. This achieves synchronous linkage response of operation variables throughout the drying process, eliminates the parameter matching imbalance problem caused by independent adjustment of a single device, and ensures that the optimal process parameters formed by digital twin simulation and predictive optimization can be accurately implemented.

[0048] like Figure 2 As shown, another embodiment of the present invention provides a multivariable collaborative optimization control method for a viscose staple fiber dryer based on digital twins, applied to the control system described above, including the following steps: Collect and preprocess the raw data of the dryer equipment.

[0049] The analysis focuses on the original data of the dryer and the calibration of multiple parameters. Based on a standardized process dataset, the study analyzes the variation patterns of wind speed, chain speed, moisture removal rate, steam flow rate, ambient temperature and humidity, finished product moisture regain, and steam consumption. The coupling relationships of various process parameters are calibrated, and optimal operating ranges for each parameter are defined. Within the drying process, process parameters such as wind speed, chain speed, steam supply, and ambient temperature and humidity do not act independently but are strongly coupled. Adjusting a single parameter will simultaneously change the finished product moisture content and steam consumption. Traditional single-variable control ignores this coupling relationship, easily leading to control imbalances. This step relies on a standardized dataset after interference removal to eliminate invalid data interference. Through multi-gradient operating condition tests, the influence weight of each parameter on the finished product moisture regain rate and steam consumption is quantified. A mathematical correlation model between parameters is established, distinguishing between the reasonable adjustment range of each parameter and the optimal range that balances quality and energy consumption. The complex interaction relationship between multiple variables is quantified and solidified, providing a quantitative process basis for building a high-precision process mechanism model for the digital twin simulation unit, conducting index prediction for the multivariate prediction module, and solving the optimal collaborative control parameters for the intelligent control unit. This solves the problem of difficulty in quantifying and matching multivariate coupling, ensuring the accuracy of subsequent simulation prediction and optimization control from the process bottom layer.

[0050] A digital twin model was constructed to simulate drying conditions and predict process parameter trends. The digital twin model was built by combining the process mechanism and parameter coupling relationship, and real-time field data was integrated to synchronize the virtual model with the physical equipment status. The model was then used to complete operating condition simulation and parameter trend prediction.

[0051] A multivariate online prediction model was built. Using steam flow rate, chain speed, moisture removal rate, and ambient temperature and humidity as inputs, and finished product moisture regain rate and steam consumption per unit as outputs, the model predicted moisture regain rate, energy consumption, and abnormal operating conditions and output early warning signals.

[0052] An integrated collaborative architecture for real-time optimization (RTO) and model predictive control (MPC) is established, which corrects the control commands of each actuator in real time based on twin prediction results. A collaborative control strategy is constructed by combining model predictive control algorithms, incorporating the drying zone temperature, steam flow rate, chain speed, and dehumidification fan frequency into a unified control system, and automatically correcting control parameters based on prediction results and real-time operating conditions.

[0053] The collaborative control strategy is distributed to the field control system, and the parameters of the digital twin model and the coefficients of the MPC control algorithm are calibrated in reverse based on the measured production data. The control strategy is then deployed to the field, and tests are conducted under disturbance conditions to further calibrate the digital twin model and the control algorithm.

[0054] The beneficial effects of adopting the technical solution of this invention are as follows: First, complete and standardized processing of all-dimensional original process data of the dryer is collected. Then, the coupling relationship of each process parameter is calibrated based on the dataset. Relying on the digital twin model integrating multiple sub-models, virtual and real synchronous simulation and parameter trend prediction are realized. Combined with the multivariate online prediction model, the quality and energy consumption prediction results are output in real time. Through the integrated collaborative architecture of RTO and MPC, the control commands of each actuator are dynamically corrected according to the prediction. Finally, the model and control algorithm are continuously iteratively calibrated using on-site measured data, forming a closed-loop control process of data acquisition, simulation prediction, collaborative regulation, and iterative optimization. This improves the uniformity of product quality and reduces steam consumption per unit while meeting quality constraints, reducing the workload of manual on-site parameter adjustment. The whole method can adapt to various disturbance conditions such as production fluctuations and sudden changes in environmental temperature and humidity. It has strong adaptability to operating conditions and effectively balances product quality improvement and production energy consumption reduction, and has high industrial application value.

[0055] Furthermore, the acquisition and preprocessing of raw data from the dryer's physical equipment includes deploying temperature and humidity sensors in each drying zone, air inlet, air outlet, and surrounding environment of the dryer, and using variable frequency exhaust fans to remotely acquire and control fan speeds. Parameters such as dryer drying zone temperature, steam flow rate, chain speed, exhaust fan speed, ambient temperature and humidity, and finished product moisture regain are collected. The raw data undergoes noise reduction, outlier removal, and time-series alignment processing to obtain a standardized process dataset.

[0056] The beneficial effect of adopting the above-mentioned further scheme is that it can collect temperature and humidity information and fan operation data of the drying area, air intake and exhaust and production environment in an all-round and comprehensive manner, and fully cover the key disturbance parameters that affect the finished product moisture regain and steam consumption. This provides comprehensive and detailed on-site basic data for subsequent data preprocessing, process coupling calibration and digital twin modeling, avoids the data being one-sided and the simulation and prediction results being distorted due to the lack of local measurement points, and ensures the data integrity and accuracy of the subsequent simulation, prediction and coordinated control links of the whole control method.

[0057] Furthermore, the data transmission delay between the physical dryer and the digital virtual model shall not exceed 200ms. If the data transmission delay between the physical dryer and the digital virtual model is too large, the internal state of the virtual model will have a time difference with the actual working conditions on site, resulting in asynchrony between the virtual and real systems. This will cause distortion in the process parameter coupling simulation and the prediction results of quality and energy consumption trends. Subsequently, the adjustment commands output by the RTO and MPC collaborative control will be delayed and unable to offset disturbances in time, resulting in increased fluctuations in finished product moisture regain and a decrease in energy consumption optimization effect.

[0058] The beneficial effects of adopting the above-mentioned further solutions are that they can realize real-time synchronization between the on-site equipment operating parameters, operating conditions and digital twin models, eliminate simulation deviations caused by the lag between virtual and real data, ensure the real-time performance and accuracy of the digital twin model in performing operating condition simulation and process parameter trend prediction, and enable the multivariate prediction unit to capture disturbances such as output and environmental temperature and humidity in a timely manner, providing reliable real-time simulation support for the intelligent control unit to quickly output the optimal collaborative control commands, and improving the system's response speed and anti-interference ability to cope with operating condition fluctuations.

[0059] Furthermore, the reverse calibration of the digital twin model parameters and MPC control algorithm coefficients includes three stages: no-load debugging, material-loaded trial operation, and full-load disturbance test. It simulates production output and environmental temperature and humidity fluctuations, collects measured data, and iteratively updates the digital twin coupling parameters and MPC control algorithm coefficients.

[0060] The beneficial effects of adopting the above-mentioned further solutions are that they can cover all real production scenarios, such as equipment no-load, normal production, and severe operating conditions, and verify the digital twin coupling parameters and MPC adjustment coefficients in a multi-level and all-round way. Through multiple rounds of data iteration and updates, the model and algorithm deviations are continuously corrected, which effectively improves the simulation accuracy of the digital twin model and the dynamic adaptation capability of the MPC controller. This enables the system to accurately complete multi-variable collaborative control under various complex disturbances, and the finished product moisture regain rate is more stable and the steam energy saving effect is more lasting and stable under long-term operation.

[0061] The present invention will be further described in detail below with reference to specific embodiments: The data acquisition unit continuously collects parameters such as drying zone temperature, steam flow rate, dryer chain speed, fan speed, ambient temperature and humidity, and finished product moisture regain rate. The raw data is denoised using a filtering algorithm to remove abnormal data caused by shutdown, equipment maintenance, and signal failure, resulting in a standardized process dataset.

[0062] Multiple sets of comparative calibration experiments were conducted based on standardized datasets, identifying three core variables: perturbation variable DV (ambient temperature and humidity, incoming material moisture content, and production line output); operation variable MV (steam flow rate, dryer chain speed, exhaust fan frequency, and drying zone temperature); and controlled variable CV (finished product moisture regain and steam consumption per ton of product). By adjusting the chain speed, steam flow rate, fan frequency, and drying temperature using gradients, the moisture content of the finished product and steam consumption corresponding to different parameter combinations were recorded. A linear correlation model between moisture content and steam consumption was fitted, clarifying that for every 1% increase in moisture content, steam consumption decreases by 0.0486 t / t. The coupling effect of all process parameters was calibrated, and the normal operating range and optimal operating range of each parameter were defined. A material drying curve was constructed to characterize the correspondence between moisture, temperature, humidity, and time.

[0063] A digital twin system integrating four types of sub-models was built within the industrial server digital application platform: a 3D physical model of the equipment, a drying process mechanism model, an energy consumption prediction model, and a finished product moisture regain quality prediction model. A real-time communication link was established to ensure that the data transmission latency between the model and the on-site physical equipment is ≤200ms, achieving synchronization of the virtual and physical equipment's operating conditions, parameters, and running status. The accuracy of the twin model was verified using historical production data from the field. After successful verification, full-condition simulation was performed based on the model, simulating moisture regain and energy consumption indicators under different MV and DV combinations in batches, selecting the optimal process parameter combination, and providing a model foundation for the subsequent MPC controller.

[0064] Based on a digital twin model with a built-in multivariate online prediction module, using MV and DV as inputs, it outputs real-time predicted values ​​for finished product moisture regain and steam consumption per unit area, simultaneously identifying abnormal operating conditions such as sudden changes in production volume and drastic fluctuations in temperature and humidity, and triggering early warnings. A real-time RTO optimization module is built, with constraints set: a finished product moisture regain control target of 12% ± 0.5%, equipment rated operating limits, and a safe steam supply threshold; the optimization objective is to minimize steam consumption while meeting quality constraints. The RTO optimization output is used as the setpoint for the Model Predictive Controller (MPC), constructing a multivariate collaborative control logic that incorporates drying temperature, steam flow rate, chain speed, and fan frequency into a unified control system, automatically and dynamically correcting operating parameters based on real-time prediction deviations.

[0065] The entire collaborative control strategy was implemented in the field intelligent control system, and disturbance condition tests were conducted in three phases to continuously calibrate the twin model and control algorithm in reverse. (1) No-load commissioning: Verify the stability of data transmission from sensors, frequency converters, and communication links; (2) Trial operation with materials: low-load stable production, fine-tuning of model coupling coefficient, and initial stabilization of the rehydration range; (3) Full-load disturbance test: Simulate typical disturbances such as production fluctuations, sudden changes in ambient temperature and humidity, and equipment start-up and shutdown switching, and compare the energy consumption performance of different target humidity ranges: Controlling the moisture content to 14%: theoretical steam consumption per ton is 1.191 t / t, resulting in energy savings of 12.15%. Controlling the moisture content to 13%: theoretical steam consumption per ton is 1.239 t / t, resulting in energy savings of 8.6%; The target moisture content is 12.5%; the theoretical steam consumption is 1.263 t / t. Controlling the target moisture content to 12%: theoretical steam consumption per ton is 1.288t / t, resulting in energy savings of approximately 5%.

[0066] Taking into account the risk of secondary moisture absorption during finished product storage, the optimal control target was determined to be a finished product moisture regain rate of 12% ± 0.5%, which was used as the benchmark for system priority control. After multiple rounds of disturbance testing and iterative optimization, the system's adaptive adjustment capability and anti-interference performance were significantly improved.

[0067] After the entire digital twin multivariate collaborative control system was put into continuous and stable operation, the moisture regain of the finished product remained stable within the range of 12%±0.5% for a long period of time, and the standard deviation of moisture content decreased from 1.15% before the transformation to 0.5%. The steam consumption per ton of product decreased steadily from 1.344t / t before the transformation to 1.288t / t, a decrease of 0.056t / t, and a reduction in steam consumption of approximately 4.2%. The drying process no longer requires frequent manual adjustment of valves and fans, significantly reducing the frequency of manual intervention, and the equipment operates smoothly throughout the entire process.

[0068] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A viscose staple dryer multivariate collaborative optimization control system based on digital twinning, characterized in that, It includes a data acquisition unit, a digital twin simulation unit, a multivariate prediction unit, an intelligent control unit, and a field execution unit; The data acquisition unit is used to collect raw data of the dryer physical equipment and upload it to the digital twin simulation unit; The digital twin simulation unit is used to receive the original data of the dryer physical equipment, realize the synchronous simulation of the dryer physical equipment and the digital virtual model, and perform coupled calculations of process parameters; The multivariate prediction unit is integrated into the digital twin simulation unit and performs quality and energy consumption prediction and fault early warning based on process parameters. The intelligent control unit outputs multi-device collaborative control commands based on the prediction results; The field execution unit receives control commands, adjusts the drying process variables, and provides feedback on the equipment's operating status.

2. The digital-twin-based viscose staple dryer multivariate collaborative optimization control system according to claim 1, characterized in that, The data acquisition unit includes a temperature and humidity sensor, a medium flow collector, and a transmission and fan operating parameter collector, which are used to collect raw process data such as drying temperature, steam flow, equipment operating conditions, environmental parameters, and finished product quality.

3. The digital-twin-based spun-bond dryer multivariate collaborative optimization control system according to claim 1, wherein, The digital twin simulation unit is an industrial simulation computing carrier, consisting of industrial computing hardware and a digital twin simulation software platform, integrating equipment 3D models, process mechanism models, energy consumption models, and finished product moisture regain quality prediction models.

4. The digital-twin-based spun-bond dryer multivariate collaborative optimization control system of claim 1, wherein, The multivariate prediction unit uses process parameters as model inputs and finished product quality indicators and unit product energy consumption indicators as model prediction outputs.

5. The digital-twin-based spun-bond dryer multivariate collaborative optimization control system according to claim 1, wherein, The intelligent control unit is a multivariable optimization control hardware platform that integrates an RTO real-time optimization module, an MPC predictive control module, a network switch, and a human-machine interaction terminal, with a finished product moisture regain rate of 12% ± 0.5% as the system regulation constraint threshold.

6. The digital-twin-based spun-bond dryer multivariate collaborative optimization control system of claim 1, wherein, The field execution unit includes a steam regulating valve, a dryer chain speed inverter, a dehumidifying fan inverter, and supporting communication cards and electrical protection accessories, which synchronously execute multi-variable linkage adjustment commands.

7. A kind of based on digital twin viscose staple dryer multivariate collaborative optimization control method, it is applied to the control system in any one of claims 1-6, it is characterized in that, Includes the following steps: Collect and preprocess raw data from the dryer's physical equipment; Analysis of the coupling between raw data of the dryer's physical equipment and calibration of multiple parameters; Construct a digital twin model and conduct drying condition simulation and process parameter trend prediction; Build a multivariate online prediction model; Establish an integrated collaborative architecture for real-time RTO optimization and MPC model predictive control, and correct the control commands of each actuator in real time based on twin prediction results; The collaborative control strategy is sent to the field control system, and the parameters of the digital twin model and the coefficients of the MPC control algorithm are calibrated in reverse based on the measured production data.

8. The digital-twin-based viscose staple dryer multivariate collaborative optimization control method according to claim 7, characterized in that, The acquisition and preprocessing of the original data of the dryer physical equipment includes the deployment of temperature and humidity sensors in each drying zone of the dryer, the air inlet and outlet, and the surrounding environment, as well as the remote acquisition and control of the fan speed by a variable frequency exhaust fan.

9. The digital-twin-based viscose staple dryer multivariate collaborative optimization control method according to claim 7, characterized in that, The data transmission delay between the physical dryer and the digital virtual model does not exceed 200ms.

10. The digital-twin-based cohesive staple dryer multivariate collaborative optimization control method according to claim 7, characterized in that, The reverse calibration of digital twin model parameters and MPC control algorithm coefficients includes three stages: no-load debugging, material-loaded trial operation, and full-load disturbance test. It simulates production output and environmental temperature and humidity fluctuations, collects measured data, and iteratively updates digital twin coupling parameters and MPC control algorithm coefficients.