Temperature-variable-stress-resistant self-feedback yarn anti-corrosion drying method

Abstract

The invention discloses a temperature-variable-stress-resistant self-feedback yarn anti-corrosion drying method, and relates to the technical field of intelligent control and material protection of a yarn drying process in the textile industry, and the method comprises the following steps: S1, establishing a digital twinning stress prediction model and a dynamic anti-corrosion performance evaluation model of yarns; the digital twinning stress prediction model is used for predicting transient thermal stress distribution in the yarn according to the drying process parameters. According to the temperature change resistant stress self-feedback yarn anti-corrosion drying method, synchronous and coordinated regulation and control of internal thermal stress, the surface anti-corrosion state and the moisture regain of the yarn in the drying process are achieved; on the premise of stabilizing the vehicle speed, the yarn structure damage risk caused by temperature fluctuation can be actively inhibited, continuous and effective corrosion protection is provided for the yarn in the drying process through intelligent management of the slow-release anti-corrosion medium, and the physical integrity and durability of the yarn are overall improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent control and material protection technology for yarn drying processes in the textile industry, specifically a temperature-resistant, variable stress self-feedback yarn anti-corrosion drying method. Background Technology

[0002] Yarn often requires drying during textile processing to control its moisture regain, enhance its physical properties, and prevent mildew. Temperature control in the drying process has a significant impact on yarn quality. Traditional methods typically control yarn moisture regain by adjusting the temperature or speed of the drying equipment. Publication number "CN104452147A" describes "a method for controlling yarn moisture regain by adjusting the temperature of the drying drum of a sizing machine." This method, while maintaining a stable sizing machine speed, rapidly adjusts the drying drum temperature to keep the yarn moisture regain within a set range, thereby avoiding yarn tension fluctuations caused by frequent speed changes and improving yarn quality and equipment efficiency. This method has the advantages of fast control response and stable moisture regain. However, the above methods still have the following shortcomings: First, the internal thermal stress of the yarn caused by temperature changes during the drying process is not effectively controlled, and long-term accumulation of temperature stress may lead to damage to the yarn structure and a decrease in strength; Second, the corrosive effect of humid and hot conditions in the drying environment on yarn materials is not considered, especially for some yarns that are susceptible to moisture, oxidation, or contain metal components; Third, there is a lack of an adaptive feedback mechanism for the yarn state during the drying process, making it impossible to adjust the drying strategy in real time according to the actual state of the yarn, and making it difficult to achieve intelligent and long-term corrosion prevention.

[0003] Therefore, there is an urgent need for a yarn drying method that can simultaneously regulate temperature stress during the drying process, has self-feedback capability, and has anti-corrosion function, in order to improve the overall performance and service life of the yarn. Summary of the Invention

[0004] The purpose of this invention is to provide a method for drying and protecting temperature-resistant, variable-stress self-feedback yarns to prevent corrosion, thereby solving the problems mentioned in the background art.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a method for drying and protecting temperature-resistant, variable-stress self-feedback yarns from corrosion, comprising the following steps: S1. Establish a digital twin stress prediction model and a dynamic anti-corrosion performance evaluation model for yarn; the digital twin stress prediction model is used to predict the transient thermal stress distribution inside the yarn based on drying process parameters; the dynamic anti-corrosion performance evaluation model is used to evaluate the anti-corrosion protection effect based on the release kinetics of the slow-release anti-corrosion medium and the state of the drying microenvironment. S2. Set the target moisture regain of the yarn and initialize the drying process parameters, including the initial temperature setting value of each zone of the drying cylinder and the initial speed of the yarn travel. S3. Based on the digital twin stress prediction model and the dynamic anti-corrosion performance evaluation model, a multi-objective collaborative optimization decision-making process is performed on the current drying process parameters to obtain the optimized drying process parameters; the multi-objective collaborative optimization decision-making process takes minimizing the internal thermal stress of the yarn, maximizing the anti-corrosion performance index, and minimizing the real-time moisture regain deviation as optimization objectives. S4. Send the optimized drying process parameters obtained in S3 to the actuator of the drying equipment to perform the drying operation on the yarn; S5. During the drying process, the microenvironmental parameters and actual moisture regain of the yarn in the drying oven are collected in real time, and the real-time stress prediction value calculated by the digital twin stress prediction model is fed back to the multi-objective collaborative optimization decision-making process for decision-making in the next control cycle.

[0006] Furthermore, in step S3, the multi-objective collaborative optimization decision-making process specifically includes: S31. Based on the real-time stress prediction value output by the digital twin stress prediction model and the real-time corrosion resistance index output by the dynamic corrosion resistance performance evaluation model, dynamically allocate the weight coefficients of the thermal stress minimization target, the corrosion resistance maximization target, and the moisture regain deviation minimization target. S32. Using the temperature setpoints and yarn travel speed of each zone of the drying cylinder as decision variables, and based on the weighting coefficients determined in step S31, use an optimization algorithm to solve for the Pareto optimal solution set that satisfies the above multiple objectives. S33. Cross-validate the candidate solutions in the Pareto optimal solution set: input the process parameters corresponding to the candidate solutions into the digital twin stress prediction model for stress secondary simulation verification, and input them into the dynamic anti-corrosion performance evaluation model for anti-corrosion performance change prediction verification. S34. From the candidate solutions that have passed all verifications in step S33, select the set of process parameters that are optimal in comprehensive evaluation as the output of the optimized drying process parameters.

[0007] Furthermore, the steps for establishing the digital twin stress prediction model include: acquiring the material property parameters, structural parameters, and sizing formula parameters of the yarn; and establishing a database of the relationship between the three-dimensional structural model of the yarn and the thermo-mechanical response under different drying process parameters based on the finite element analysis method. The drying process parameters include the temperature change rate and the temperature gradient inside the drying cylinder.

[0008] Furthermore, the establishment of the dynamic anti-corrosion performance evaluation model is based on the application of thermosensitive slow-release anti-corrosion microcapsules; the thermosensitive slow-release anti-corrosion microcapsules are incorporated into the sizing of the yarn, and their wall material can undergo phase change in a specific temperature range during the drying process, thereby controlling the release of gaseous corrosion inhibitors to the yarn surface and the surrounding microenvironment.

[0009] Furthermore, the microenvironmental parameters include temperature values, humidity values, and specific corrosive gas concentration values ​​at multiple locations within the oven; the dynamic anti-corrosion efficacy evaluation model calculates and outputs a dynamic anti-corrosion efficacy index characterizing the current adequacy of anti-corrosion protection based on the real-time collected microenvironmental parameters and the microcapsule release kinetic model under the current process parameters.

[0010] Furthermore, in step S31, the weighting coefficient allocation rule is as follows: when the real-time stress prediction value exceeds a preset first threshold, the weighting coefficient of the thermal stress minimization target is increased; when the real-time anti-corrosion efficiency index is lower than a preset second threshold, the weighting coefficient of the anti-corrosion efficiency maximization target is increased; when the real-time moisture regain deviation exceeds a preset allowable deviation range, the weighting coefficient of the moisture regain deviation minimization target is increased.

[0011] Furthermore, after step S5, step S6 is also included: model self-learning and correction process; this process compares the actual moisture regain rate collected in step S5 and the actual yarn state evaluated indirectly with the predicted values ​​output by the digital twin stress prediction model and the dynamic anti-corrosion performance evaluation model in the previous cycle. If the deviation continues to exceed the allowable range, the material response parameters in the digital twin stress prediction model or the release kinetic parameters in the dynamic anti-corrosion performance evaluation model are corrected based on the deviation data.

[0012] Furthermore, the real-time moisture regain deviation is calculated by continuously detecting the actual moisture regain of the yarn after drying, and calculating the difference between the actual moisture regain and the target moisture regain.

[0013] Furthermore, the actuator of the drying equipment includes a temperature control valve for independently adjusting the temperature of each drying drum zone, and a drive motor for adjusting the yarn travel speed.

[0014] A yarn drying system for implementing the temperature-resistant variable stress self-feedback yarn anti-corrosion drying method includes: The oven is equipped with a multi-zone independently temperature-controlled drying cylinder and a transmission mechanism for conveying yarn. A sensor array, arranged inside the oven, is used to collect microenvironmental parameters such as temperature, humidity, and specific gas concentrations in real time. A moisture regain detection device is installed at the outlet of the drying oven to detect the actual moisture regain of the yarn after drying. The model processing unit pre-stores the digital twin stress prediction model and the dynamic anti-corrosion performance evaluation model; The central decision control unit, connected to the sensor array, the moisture regain detection device, and the model processing unit, is configured to execute the multi-objective collaborative optimization decision-making process and generate control commands. The actuator drive unit is connected to the central decision control unit, the temperature control valve of the drying cylinder, and the drive motor of the transmission mechanism, and is used to adjust the process parameters according to the control command.

[0015] This invention provides a method for drying and protecting temperature-resistant, variable-stress self-feedback yarns for corrosion prevention. It offers the following advantages: This temperature-resistant, variable-stress self-feedback yarn anti-corrosion drying method constructs a digital twin stress prediction model and a dynamic anti-corrosion performance evaluation model. Based on these models, it implements multi-objective collaborative optimization decisions, achieving simultaneous and coordinated control of internal thermal stress, surface anti-corrosion status, and moisture regain during the drying process. This method overcomes the limitations of traditional technologies that only focus on a single moisture regain indicator. Under stable machine speeds, it actively suppresses the risk of yarn structural damage caused by temperature fluctuations. Furthermore, through intelligent management of the slow-release anti-corrosion medium, it provides continuous and effective corrosion protection for the yarn during the drying process, thereby improving the overall physical integrity and durability of the yarn.

[0016] This temperature-resistant, variable-stress self-feedback yarn anti-corrosion drying method introduces a closed-loop control architecture that includes cross-validation and model self-learning, ensuring the reliability and long-term adaptability of multi-objective decision-making. It can not only dynamically adjust the control strategy based on real-time process conditions, but also continuously correct internal model parameters based on historical production data, enabling the control accuracy and robustness of the entire system to continuously improve over time, ultimately achieving high-quality, high-consistency, and intelligent operation of the drying process. Attached Figure Description

[0017] Figure 1 This is a schematic flowchart of a temperature-resistant variable stress self-feedback yarn anti-corrosion drying method according to the present invention; Figure 2 This is a multi-objective optimization decision-making flowchart for a temperature-resistant variable stress self-feedback yarn anti-corrosion drying method according to the present invention; Figure 3 This is a process flow diagram of a temperature-resistant variable stress self-feedback yarn anti-corrosion drying method according to the present invention. Detailed Implementation

[0018] 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Please see Figures 1 to 3 This invention provides a technical solution: a method for drying and protecting temperature-resistant, variable-stress self-feedback yarn for corrosion prevention, comprising the following steps: S1. Establish a digital twin stress prediction model and a dynamic anti-corrosion performance evaluation model for yarn; the digital twin stress prediction model is used to predict the transient thermal stress distribution inside the yarn based on drying process parameters; the dynamic anti-corrosion performance evaluation model is used to evaluate the anti-corrosion protection effect based on the release kinetics of the slow-release anti-corrosion medium and the state of the drying microenvironment. S2. Set the target moisture regain of the yarn and initialize the drying process parameters, including the initial temperature setting value of each zone of the drying cylinder and the initial speed of the yarn. S3. Based on the digital twin stress prediction model and dynamic anti-corrosion performance evaluation model, a multi-objective collaborative optimization decision-making process is performed on the current drying process parameters to obtain the optimized drying process parameters. The multi-objective collaborative optimization decision-making process takes minimizing the internal thermal stress of the yarn, maximizing the anti-corrosion performance index, and minimizing the real-time moisture regain deviation as optimization objectives. S4. Send the optimized drying process parameters obtained in S3 to the actuator of the drying equipment to perform the drying operation on the yarn; S5. During the drying process, the microenvironment parameters inside the drying oven and the actual moisture regain of the yarn are collected in real time. The real-time stress prediction value calculated by the digital twin stress prediction model is fed back to the multi-objective collaborative optimization decision-making process to make decisions for the next control cycle.

[0020] It should be further explained that the specific implementation of this method first uses computer-aided engineering software to establish a three-dimensional geometric model of the yarn to be dried, based on its specific material type, linear density specification, sizing solution formula, and yarn twist structure parameters, and assigns corresponding thermophysical properties and mechanical performance parameters. Using this model, finite element analysis is used to simulate the transient thermal stress field generated inside the yarn due to non-uniform heating under different combinations of drying cylinder temperature distribution curves and yarn running speeds, forming a database of mapping relationships between process parameters and predicted stress peak values, which serves as the basis for the operation of the digital twin stress prediction model.

[0021] Meanwhile, when preparing the sizing solution, microcapsules with a wall material having a specific glass transition temperature are incorporated, and the core material contains a vapor-phase corrosion inhibitor. This allows the capsule wall to rupture in a controlled manner and release the preservative substance when the drying temperature reaches a specific range. Temperature and humidity sensors and corrosive gas detection probes are installed at multiple representative locations inside the oven. The real-time monitoring data is combined with the microcapsule release kinetic model to calculate and output a dynamic evaluation index that reflects the sufficiency of the preservative forming an effective protective film on the yarn surface.

[0022] When the system starts, the operator sets the target moisture regain value required for the yarn and inputs a set of initial heating temperatures for each zone of the drying cylinder and the yarn travel speed. The core multi-objective collaborative optimization decision-making process is executed by an embedded industrial computing module: in each control cycle, this module receives the predicted stress value calculated by the stress model based on the current parameters, the corrosion resistance index calculated by the corrosion resistance model, and the deviation between the actual moisture regain measured by the online moisture regain detector and the target value; the decision logic first dynamically adjusts and assigns weights to the three objectives of "reducing stress", "maintaining corrosion resistance" and "controlling moisture regain" based on a set of preset threshold rules.

[0023] Subsequently, using the temperature setpoints of each drying zone and yarn speed as optimization variables, a multi-objective optimization algorithm was employed for iterative search to find the Pareto optimal parameter combination that could simultaneously improve multiple objectives. To ensure the robustness of the decision, the initially selected optimal parameter combinations were re-substituted into a digital twin stress model for rapid secondary stress distribution simulation to verify whether they effectively controlled the theoretical stress value within the permissible range. Simultaneously, the expected impact of temperature changes on the microcapsule release rate and anti-corrosion efficacy index was evaluated. Only parameter combinations that passed this dual verification were ultimately adopted.

[0024] The optimized process parameters are transmitted via fieldbus to the electric regulating valves and traction motor frequency converters of each drying drum zone, enabling precise temperature and speed adjustments. Throughout the drying process, the system continuously collects oven environmental data and yarn status data, feeding them back to the decision-making module to initiate the next optimization cycle, forming a closed-loop control system based on real-time sensor information.

[0025] In addition, the system is designed with a self-correcting function. By comparing the actual yarn quality results data accumulated over a long period of operation with the model predictions, the system periodically calibrates the material constitutive parameters in the finite element model or the kinetic parameters in the microcapsule release model, making the model predictions more consistent with the physical process.

[0026] In step S3, the multi-objective collaborative optimization decision-making process specifically includes: S31. Based on the real-time stress prediction value output by the digital twin stress prediction model and the real-time corrosion resistance index output by the dynamic corrosion resistance performance evaluation model, dynamically allocate the weight coefficients of the thermal stress minimization target, the corrosion resistance maximization target, and the moisture regain deviation minimization target. S32. Using the temperature setpoints and yarn travel speed of each zone of the drying cylinder as decision variables, and based on the weighting coefficients determined in step S31, use an optimization algorithm to solve for the Pareto optimal solution set that satisfies the above multiple objectives. S33. Cross-validate candidate solutions in the Pareto optimal solution set: input the process parameters corresponding to the candidate solutions into the digital twin stress prediction model for stress secondary simulation verification, and input them into the dynamic anti-corrosion performance evaluation model for anti-corrosion performance change prediction verification. S34. From the candidate solutions that have passed all verifications in step S33, select the set of process parameters that are optimal in comprehensive evaluation as the output of the optimized drying process parameters.

[0027] It should be further explained that the multi-objective collaborative optimization decision-making process is implemented as follows: At the beginning of each control cycle, the system first receives the real-time predicted stress value output from the digital twin stress prediction model, the real-time anti-corrosion performance index calculated by the dynamic anti-corrosion performance evaluation model, and the real-time moisture regain deviation measured by the online moisture regain detection device.

[0028] The decision engine has a built-in weight allocator that dynamically adjusts the weight coefficients of each objective according to preset rules. For example, when the predicted stress value exceeds a certain set safety limit, the weight of the objective of reducing thermal stress will be automatically increased; when the corrosion resistance index is lower than the minimum limit required to maintain effective protection, the weight of the objective of improving corrosion resistance will be increased accordingly; when the moisture regain deviation exceeds the tolerance zone allowed by the process, the weight of the objective of reducing moisture regain deviation will be given priority.

[0029] After the weights are determined, the decision engine uses the set temperature values ​​of each independent temperature zone of the drying cylinder and the yarn travel speed as optimization variables, and calls the embedded optimization algorithm library (such as using a population-based iterative optimization algorithm) to solve the problem. The algorithm takes the current process parameters as the starting point and searches within the set variable range to minimize the multi-objective function after the above weighting, thereby generating a set of non-dominated solutions, i.e., the Pareto optimal solution set.

[0030] To ensure that the parameter combinations selected from the solution set are not only mathematically optimal but also physically safe and feasible, the system performs rigorous cross-validation on the candidate solutions: each set of candidate temperature and velocity parameters is re-inputted into the digital twin stress prediction model, and a rapid finite element simulation is initiated to verify whether the maximum predicted stress value inside the yarn has indeed been reduced to an acceptable level after the parameter adjustment; at the same time, the set of parameters (especially the temperature distribution) is input into the dynamic anti-corrosion performance evaluation model, and based on the microcapsule release kinetics formula, the change in the preservative release rate under this new temperature condition is deduced, and the expected anti-corrosion performance index is recalculated to confirm that it is not lower than the safety threshold or has been improved.

[0031] Only candidate solutions that pass both stress-based secondary simulation verification and corrosion resistance performance change prediction verification are considered valid solutions.

[0032] Ultimately, the decision engine selects the set of process parameters with the highest score from all valid solutions based on a predefined comprehensive evaluation function (e.g., a weighted score that weighs various indicators). This set is then used as the output of the optimized drying process parameters for the current cycle to control the actuators.

[0033] In step S32 of the multi-objective collaborative optimization decision-making process, the optimization algorithm used is the NSGA-II algorithm. The core parameters of this algorithm are set as follows: population size is set to 50-80, number of iterations is set to 30-50, crossover probability ranges from 0.7 to 0.9, and mutation probability ranges from 0.01 to 0.05. These parameters can be fine-tuned according to the actual specifications and production efficiency requirements of the dried yarn. In step S34, the comprehensive evaluation function used to screen the optimal process parameters has the following weighted scoring method: first, the predicted thermal stress value, corrosion resistance index, and real-time moisture regain deviation are converted into standardized scores of 0-100 points, where the lower the predicted thermal stress value, the higher the score; the higher the corrosion resistance index, the higher the score; and the smaller the real-time moisture regain deviation, the higher the score. Then, according to the weight coefficients of each objective determined in step S31, the three standardized scores are weighted and summed to obtain the comprehensive score of each candidate solution. The candidate solution with the highest comprehensive score is selected as the optimized drying process parameters.

[0034] This closed-loop decision-making process, which includes dynamic weight allocation, multi-objective optimization, and dual model verification, achieves synergistic protection of yarn structure reliability and long-term corrosion resistance while maintaining the basic process objectives of the drying process.

[0035] The steps to establish a digital twin stress prediction model include: obtaining the material property parameters, structural parameters, and sizing formula parameters of the yarn; establishing a database of the relationship between the three-dimensional structural model of the yarn and the thermo-mechanical response under different drying process parameters based on the finite element analysis method; and the drying process parameters including the temperature change rate and the temperature gradient inside the drying cylinder.

[0036] It should be further explained that the specific implementation of the digital twin stress prediction model is as follows: First, the basic parameters of the yarn to be dried are obtained through experiments or from a material database. These parameters include the density, specific heat capacity, thermal conductivity, elastic modulus, and coefficient of thermal expansion of the fiber material used in the yarn, as well as the actual diameter, twist, and ply structure information of the yarn. Simultaneously, the solid content, viscosity, and amount of the sizing solution adhering to the yarn surface are recorded. These parameters are then input into specialized computer-aided engineering software to construct a simplified three-dimensional geometric model of the yarn. This model reflects the basic outline and volumetric characteristics of the yarn.

[0037] Subsequently, the model was meshed using finite element methods in the software, and boundary conditions corresponding to the actual drying process were applied: the surfaces of the yarn in contact with the drying cylinder or exposed to thermal radiation were set as heat exchange boundaries, and corresponding convective heat transfer coefficients or heat flux densities were assigned according to the temperature settings of the drying cylinder zones; the axial displacement of the yarn ends was constrained to simulate the state under tension. Transient thermo-structural coupling analysis was performed by setting a series of different drying cylinder temperature distribution patterns (e.g., temperature gradient changes in each zone) and yarn running speeds.

[0038] During the calculation, the software first solves for the unsteady temperature field of the yarn under given thermal boundary conditions. Then, the calculated temperature distribution is applied as a load to the structural analysis module to solve for the stress field resulting from the coupling of thermal stress and mechanical tension. For each combination of process parameters, the maximum principal stress value, stress distribution uniformity index, and the time to reach the stress peak are recorded within the yarn model. The simulation calculation is repeated by systematically changing the process parameter inputs, associating all input parameter combinations (temperature, velocity) with the corresponding output stress results (peak stress, distribution contour map) and storing them in a structured database.

[0039] This database forms the core of the digital twin stress prediction model. During the actual drying process, the control system can quickly obtain the predicted stress values ​​corresponding to the current or to be adjusted process parameters by querying this database or calling the interpolation algorithm. To ensure the reliability of the model, in the initial stage, actual small-scale drying tests are conducted using a few typical process conditions, and the simulation prediction results are calibrated and corrected using micro-stress measurement or indirect mechanical property testing methods.

[0040] The database of thermo-mechanical response relationships for the digital twin stress prediction model has the following structure: Input parameters include yarn material properties (density, specific heat capacity, thermal conductivity, elastic modulus, coefficient of thermal expansion), structural parameters (diameter, twist), sizing agent formulation parameters (solid content, viscosity), and drying process parameters (temperature change rate, temperature gradient inside the drying cylinder, yarn travel speed). Output stress parameters include the maximum principal stress value inside the yarn, the stress distribution uniformity coefficient, and the stress peak occurrence time. The database must cover at least 50 typical combinations of process parameters, with each combination corresponding to the average of three repeated simulation calculations to ensure data reliability. In practical applications, the interpolation method for querying the stress prediction value corresponding to real-time process parameters using this database is linear interpolation. That is, the corresponding stress prediction value is calculated based on the ratio of the difference between the real-time process parameter and two adjacent parameter sets in the database.

[0041] The establishment of a dynamic anti-corrosion performance evaluation model is based on the application of thermosensitive slow-release anti-corrosion microcapsules. When thermosensitive slow-release anti-corrosion microcapsules are incorporated into the sizing of yarn, their wall material can undergo phase change in a specific temperature range during the drying process, thereby controlling the release of gaseous corrosion inhibitors to the yarn surface and the surrounding microenvironment.

[0042] It should be further explained that the establishment of the dynamic anti-corrosion performance evaluation model is based on the specific application of temperature-sensitive slow-release anti-corrosion microcapsules. The technical details are as follows: the microcapsules use a polymer as the wall material, and the glass transition temperature of the polymer is designed to be within the typical temperature range of the drying process, such as between 80 degrees Celsius and 120 degrees Celsius; the core material of the microcapsules contains a vapor-phase corrosion inhibitor, specifically a volatile corrosion inhibitor such as cyclohexylamine carbonate or benzotriazole derivatives.

[0043] In the sizing process, a certain mass ratio of these microcapsules is uniformly dispersed in the sizing solution, allowing them to adhere to the yarn surface and penetrate into the gaps within the yarn during the sizing process. When the drying process begins and the oven temperature rises above the glass transition temperature of the wall material polymer, the density of the wall material decreases or it softens and melts, allowing the vapor-phase corrosion inhibitor in the core material to be continuously released through diffusion or wall material rupture. The released corrosion inhibitor molecules diffuse and adsorb onto the yarn surface and the surface of surrounding metal parts under the convection of hot air in the oven, forming a monomolecular protective film.

[0044] To quantify the corrosion protection effect of this process, the dynamic corrosion protection performance evaluation model requires input of multiple real-time parameters, including temperature and relative humidity values ​​monitored by sensors placed at different locations within the oven, and optionally, the concentration of specific oxidizing gases such as sulfur dioxide.

[0045] The model integrates a kinetic equation describing the release rate of the specific microcapsule under the aforementioned temperature and humidity conditions. This equation can be obtained through prior experimental calibration. By combining real-time environmental data with the release kinetic equation, the model calculates the effective corrosion inhibitor molecular flux released per unit time from a unit surface area of ​​the yarn. This flux is then compared and calculated with a preset "critical protection flux" determined based on the yarn material and the intensity of the corrosion environment. Finally, a dimensionless value ranging from zero to one is output, namely the dynamic corrosion protection efficiency index. This index directly reflects the sufficiency of the protective film formed by the corrosion inhibitor under the current conditions and the expected corrosion protection capability.

[0046] Microenvironmental parameters include temperature, humidity, and specific corrosive gas concentrations at multiple locations within the oven. The dynamic corrosion protection performance evaluation model calculates and outputs a dynamic corrosion protection performance index that characterizes the current level of corrosion protection based on the real-time collected microenvironmental parameters and the microcapsule release kinetics model under the current process parameters.

[0047] Further explanation is needed regarding the specific implementation details of the dynamic anti-corrosion performance evaluation model: Multiple temperature and humidity sensors and specific gas sensors are distributed and installed at key locations along the yarn travel path and around the drying cylinder inside the oven; the temperature and humidity sensors use digital probes to monitor the dry-bulb temperature and relative humidity of the air in each area in real time; the specific gas sensors are selected according to the corrosive components that may be present in the process environment, for example, sensors based on electrochemical principles are used to monitor sulfur dioxide concentration, or metal oxide semiconductor sensors are used to monitor nitrogen oxide gas concentration.

[0048] These sensors continuously transmit monitoring data to the central processing unit at a certain sampling frequency. The model pre-stores experimentally calibrated release kinetic equations for the specific temperature-sensitive slow-release corrosion inhibitor microcapsules used, which describe the mass of vapor-phase corrosion inhibitor released per unit mass of microcapsules per unit time under given temperature and humidity conditions.

[0049] When the model is running, it first reads the micro-environmental parameters of each monitoring point at the current time and calculates their spatial average value or selects the values ​​of representative areas as model input; then, combined with the current temperature setting of the drying cylinder, since it directly affects the temperature of the yarn surface and the nearby air layer, it calls the release kinetic equation to calculate the theoretical release rate of the vapor phase corrosion inhibitor under the current process conditions.

[0050] To translate the release rate into an assessment of the actual protective effect on the yarn surface, the model introduces a "critical protection concentration" parameter. This parameter, determined through prior laboratory experiments, represents the minimum inhibitor molecular coverage density required on the yarn surface to prevent initiation of corrosion under specific humidity and contaminant concentration conditions. The model compares and calculates the theoretical release rate, the effective deposition rate of the inhibitor on the yarn surface estimated using an empirical model of airflow heat transfer within the oven, and the "critical protection concentration" requirement corresponding to the currently monitored environmental humidity and contaminant concentration in real time. The final output is a dynamic corrosion protection effectiveness index ranging from zero to one; an index of one indicates sufficient protection, while an index below one indicates insufficient protection. The specific value reflects the adequacy of the current corrosion protection measures relative to the critical requirement.

[0051] In the dynamic anti-corrosion efficacy evaluation model, the release kinetic model of the temperature-sensitive slow-release anti-corrosion microcapsules adopts a first-order kinetic model. The key coefficients of this model are calibrated through preliminary experiments: microcapsule specifications consistent with actual production are selected, and more than 10 different temperature and humidity combinations are set within the temperature range (80℃-120℃) and humidity range (30%-70%RH) commonly used in drying processes. The amount of gas phase corrosion inhibitor released by microcapsules at different time points under each condition is measured, and key coefficients such as reaction rate constant and activation energy are obtained through data fitting. The calculation logic of the dynamic corrosion resistance index is as follows: First, based on the real-time collected average temperature and humidity inside the oven and the current oven temperature setting, combined with the above-calibrated release kinetic model, the real-time release rate of the gas phase corrosion inhibitor is calculated; then, based on the critical protection concentration corresponding to the yarn material and the air flow in the oven, the effective deposition rate of the corrosion inhibitor on the yarn surface is estimated. If the effective deposition rate is not lower than the deposition rate requirement corresponding to the critical protection concentration, the corrosion resistance index is 1.0. If the effective deposition rate is lower than the requirement, the corrosion resistance index is determined according to the ratio of the effective deposition rate to the required rate, and finally a dimensionless value between 0 and 1 is output.

[0052] In step S31, the weighting coefficient allocation rule is as follows: when the real-time stress prediction value exceeds the preset first threshold, the weighting coefficient of the thermal stress minimization target is increased; when the real-time anti-corrosion efficiency index is lower than the preset second threshold, the weighting coefficient of the anti-corrosion efficiency maximization target is increased; when the real-time moisture regain deviation exceeds the preset allowable deviation range, the weighting coefficient of the moisture regain deviation minimization target is increased.

[0053] It should be further explained that the dynamic allocation of weighting coefficients is implemented as follows: Three independent threshold parameters are preset within the decision-making unit of the control system, corresponding to the stress safety limit, the minimum anti-corrosion performance limit, and the upper limit of the allowable deviation of moisture regain, respectively. The first threshold, the stress safety limit, is calculated and set as a specific stress value based on the yield strength or fatigue strength data of the yarn material and the stress concentration factor predicted by the digital twin model. The second threshold, the minimum anti-corrosion performance limit, is set as a specific performance index value, for example, 0.8, based on the dynamic anti-corrosion performance evaluation model and the results of previous accelerated corrosion tests.

[0054] The allowable deviation range is set according to the production process standards. At the beginning of each decision cycle, the decision unit compares the received real-time predicted stress value with the first threshold. If the predicted stress value exceeds the first threshold, the weight adjustment logic is triggered. At this time, the weight coefficient before the "minimize thermal stress" sub-item in the comprehensive optimization objective function will be increased according to the magnitude of the exceedance through a preset linear or nonlinear mapping relationship, so as to increase its proportion of influence on the final decision in the current cycle.

[0055] Similarly, if the real-time corrosion resistance index falls below the second threshold, the weight coefficient of the "maximizing corrosion resistance" sub-item will increase according to the extent that it falls below the threshold. If the absolute value of the real-time moisture regain deviation exceeds the allowable deviation range, the weight coefficient of the "minimizing moisture regain deviation" sub-item will also increase accordingly. When multiple conditions are triggered simultaneously, the weight coefficients of each sub-item are adjusted independently according to their respective rules. The decision-making unit will ultimately use these dynamically adjusted weight coefficients to construct the multi-objective optimization function for this control cycle, thereby guiding the subsequent optimization algorithm to prioritize improving those process indicators that are close to or exceed the safety and quality boundaries.

[0056] The calibration methods and numerical ranges for key parameters such as critical protection concentration, critical protection flux, first threshold, and second threshold are as follows: The first threshold is determined based on the yield strength or fatigue strength of the yarn material, specifically taking a value of 30%-50% of the yield strength of the yarn material. For example, the first threshold range for cotton fiber yarn is 20MPa-35MPa, and for composite yarn containing metal fibers, it is 40MPa-60MPa. The second threshold is calibrated through accelerated corrosion tests, measured under simulated industrial humid and hot corrosion conditions. The minimum corrosion resistance index required to maintain yarn without obvious corrosion marks is typically between 0.7 and 0.8. The critical protection concentration is determined based on the yarn material and the usage environment. For conventional textile yarns such as cotton and polyester, the critical protection concentration ranges from 5 μg / cm² to 15 μg / cm², while for yarns containing metal components, the critical protection concentration ranges from 10 μg / cm² to 25 μg / cm². The critical protection flux is the ratio of the critical protection concentration to the drying time, calculated by combining the actual drying line speed and the yarn surface area.

[0057] Following step S5, step S6 is also included: model self-learning and correction process; this process compares the actual moisture regain rate collected in step S5 and the actual yarn condition assessed indirectly with the predicted values ​​output by the digital twin stress prediction model and the dynamic anti-corrosion performance evaluation model in the previous cycle. If the deviation continues to exceed the allowable range, the material response parameters in the digital twin stress prediction model or the release kinetic parameters in the dynamic anti-corrosion performance evaluation model are corrected based on the deviation data.

[0058] It should be further explained that the model self-learning and correction process is implemented as follows: After the system completes the drying production of a batch or runs for a preset period of time, it starts the learning process. First, the system extracts the actual process parameters, sensor-monitored microenvironment data, and online moisture regain detection values ​​recorded in the database during that period, corresponding to the key decision points, and collects the actual quality data of the yarn samples of that batch obtained through offline laboratory testing; the actual quality data includes, but is not limited to, the test value of yarn breaking strength, the corrosion sign rating assessed by microscopic observation of the yarn surface, and the laboratory arbitration value of the actual moisture regain of the yarn.

[0059] These actual results data are defined as "actual yarn condition assessed indirectly". The system compares the stress prediction values ​​output by the digital twin stress prediction model, the corrosion resistance index prediction values ​​output by the dynamic corrosion resistance evaluation model, and the prediction baseline values ​​of the online moisture regain detector, under the same process parameter conditions during previous operation, with the corresponding actual condition data collected above one by one, and calculates the deviation between each prediction value and the actual value.

[0060] The system presets a deviation tolerance range, which can be determined through statistical process control methods or technological experience. If the system detects that the deviation between a certain type of predicted value, such as the predicted mechanical properties related to stress or the surface rating corresponding to corrosion resistance, and the actual value consistently exceeds this tolerance range across multiple production batches or time periods, the corresponding prediction model is deemed to have a systematic error, triggering a parameter correction procedure. For digital twin stress prediction models, the correction procedure focuses on the material constitutive parameters in the model, such as the coefficient of thermal expansion or elastic modulus of fibers. The program uses a parameter fitting algorithm to minimize the difference between historical actual stress-related data (derived from mechanical properties) and the model's predicted values, inverting to solve for a set of corrected constitutive parameters that better reflect the actual material behavior, and then updating the model.

[0061] For the dynamic anti-corrosion efficacy evaluation model, the correction procedure targets specific coefficients in the microcapsule release kinetic equation, such as activation energy or pre-exponential factor. The program utilizes historically recorded temperature and humidity sequences and the final yarn anti-corrosion status results to recalibrate the kinetic equation coefficients through an optimization algorithm, making the model's predicted efficacy index trend more closely match the actual anti-corrosion effect rating. After parameter correction, the updated model will be used for prediction and decision-making in subsequent production cycles, thus achieving a closed loop where the model's predictive ability gradually improves with the accumulation of production data.

[0062] The least squares method is used for correction during model self-learning and correction. The criteria for determining if the deviation continuously exceeds the allowable range are as follows: if, within three consecutive control periods, the deviation between the stress prediction value of the digital twin stress prediction model and the actual stress value derived from the yarn breaking strength exceeds 10%, or the deviation between the predicted index of the dynamic anti-corrosion performance evaluation model and the actual performance index corresponding to the yarn surface corrosion rating exceeds 15%, model correction is triggered. The correction process involves collecting historical deviation data from nearly 20 control periods. With the goal of minimizing the deviation, the least squares method is used to adjust the material response parameters (such as elastic modulus and coefficient of thermal expansion) in the digital twin stress prediction model or the release kinetic parameters (such as reaction rate constant) in the dynamic anti-corrosion performance evaluation model. The adjusted parameters are then substituted into the model for verification to ensure that the prediction deviation is below the allowable range for two consecutive control periods after correction.

[0063] The real-time moisture regain deviation is calculated as follows: the actual moisture regain of the yarn after drying is continuously monitored, and the difference between the actual moisture regain and the target moisture regain is calculated.

[0064] It should be further explained that the specific implementation method for calculating and obtaining the real-time moisture regain deviation is as follows: A non-contact online moisture regain detection device is installed at the oven outlet. This device is based on the principle of microwave or infrared absorption, and its detection probe is aimed at the yarn that is about to be wound after drying. The detection device operates continuously at a set sampling frequency, measuring and outputting the instantaneous moisture content signal of the yarn in real time. This signal is converted into a digital quantity representing the actual moisture regain by the built-in signal conditioning circuit. This actual moisture regain value is transmitted to the central decision control unit through an industrial communication network.

[0065] The control unit stores a target moisture regain value preset according to the production process requirements. In each control cycle, the control unit reads the latest received actual moisture regain measurement value, performs an algebraic subtraction operation between it and the stored target moisture regain value, and the difference is the real-time moisture regain deviation X at that moment.

[0066] To ensure the stability and reliability of the deviation value used for control, the system can perform digital filtering on the raw moisture regain data obtained from continuous sampling, such as using a moving average algorithm, to eliminate random fluctuations that may occur during the measurement process. This results in a smoother and more representative real-time moisture regain deviation for subsequent decision-making. This deviation value is directly input into the multi-objective collaborative optimization decision-making process as a quantitative input for the objective of "minimizing moisture regain deviation".

[0067] The actuators of the drying equipment include temperature control valves for independently adjusting the temperature of each drying drum zone, and drive motors for adjusting the yarn travel speed. Further details regarding the implementation of the drying equipment actuators are as follows: The temperature control valves are electrically adjustable valves, one for each drying drum zone, with the valve body connected in series to the steam or heat transfer medium pipeline leading to that zone's drying drum; the controller of the electrically adjustable valve receives a digital signal of the temperature setpoint from the central decision control unit, compares this setpoint with the measured value from the temperature sensor installed on the surface of the corresponding drying drum using a built-in proportional-integral control algorithm, and outputs a control current signal to drive the valve core, thereby adjusting the flow rate of the heat transfer medium entering that drying drum, achieving independent and precise control of the temperature of each zone.

[0068] The drive motor, equipped with a frequency converter, drives the traction rollers or winding device for yarn transport. The central decision control unit sends the optimized yarn travel speed setpoint to the frequency converter via digital communication. The frequency converter adjusts the frequency and voltage of the output power supply based on this setpoint, thereby changing the rotational speed of the drive motor and achieving continuous stepless adjustment of the yarn travel speed. The controller of the electric regulating valve and the frequency converter of the drive motor are both connected to the central decision control unit via industrial fieldbus or industrial Ethernet, forming a network capable of high-speed bidirectional data exchange. This allows optimized process parameters to be quickly and accurately transmitted, while the real-time status of the actuators, such as valve opening and actual motor speed, can also be fed back to the central unit for monitoring and closed-loop control.

[0069] A yarn drying system for implementing a temperature-resistant variable stress self-feedback yarn anti-corrosion drying method includes: The oven is equipped with a multi-zone independently temperature-controlled drying cylinder and a transmission mechanism for conveying yarn. A sensor array, arranged inside the oven, is used to collect microenvironmental parameters such as temperature, humidity, and specific gas concentrations in real time. A moisture regain detection device is installed at the outlet of the drying oven to detect the actual moisture regain of the yarn after drying. The model processing unit has a pre-stored digital twin stress prediction model and a dynamic corrosion protection performance evaluation model. The central decision control unit, which connects the sensor array, moisture regain detection device and model processing unit, is configured to execute a multi-objective collaborative optimization decision-making process and generate control commands. The actuator drive unit connects the central decision control unit, the temperature control valve of the drying cylinder, and the drive motor of the transmission mechanism, and is used to adjust process parameters according to control commands.

[0070] It should be further explained that the specific composition and cooperation mode of the yarn drying system are as follows: The main body of the system is a closed drying oven, in which multiple independent drying cylinders are arranged sequentially along the yarn travel path. Each drying cylinder is equipped with an independent heating element or steam flow channel, and each drying cylinder is equipped with an independent temperature sensor and temperature control valve, forming a multi-zone independent temperature control unit; the drying oven is also equipped with a transmission mechanism composed of guide rollers and traction rollers, which is used to guide and drive the yarn to continuously pass through the surface of each drying cylinder.

[0071] Sensor arrays are installed at key locations within the oven's interior. These arrays include multiple digital temperature and humidity sensors and specific gas concentration sensors. These sensors are distributed near the yarn, the surface of the drying cylinder, and the oven's circulating air duct to collect temperature, humidity, and specific corrosive gas concentration data at different locations. At the yarn outlet of the oven, a non-contact moisture regain detection device based on microwave or infrared absorption principles is installed, with its detection probe aimed at the output yarn.

[0072] The system's model processing unit is handled by an industrial computer or embedded server. It stores pre-built digital twin stress prediction models and dynamic corrosion resistance evaluation models for different yarn specifications, and is capable of receiving real-time data and performing model calculations. The central decision control unit is also implemented using a high-performance industrial controller. It connects to the sensor array, moisture regain detection device, and model processing unit via an industrial network bus, acquiring all sensor data, moisture regain data, and predicted values ​​from model calculations in real time. This unit internally runs control logic and algorithms, executes a multi-objective collaborative optimization decision-making process, and generates corresponding temperature and speed setpoint commands.

[0073] The actuator drive unit includes multiple digital input / output modules and a communication interface module. It receives control commands from the central decision control unit, distributes temperature setting commands to the corresponding electric regulating valve controllers of each drying cylinder, and sends speed setting commands to the frequency converter of the traction drive motor, thereby completing the closed-loop regulation of the entire drying process parameters. All units exchange data through standard industrial communication protocols to ensure information synchronization and real-time control.

[0074] This method constructs a digital twin stress prediction model and a dynamic anti-corrosion performance evaluation model, and implements multi-objective collaborative optimization decisions based on these models. This enables simultaneous and coordinated control of internal thermal stress, surface anti-corrosion status, and moisture regain during the drying process. This method overcomes the limitations of traditional technologies that only focus on a single moisture regain indicator. Under stable machine speeds, it actively suppresses the risk of yarn structural damage caused by temperature fluctuations. Furthermore, through intelligent management of the slow-release anti-corrosion medium, it provides continuous and effective corrosion protection for the yarn during the drying process, thereby improving the overall physical integrity and durability of the yarn.

[0075] This system ensures the reliability and long-term adaptability of multi-objective decision-making by introducing a closed-loop control architecture that includes cross-validation and model self-learning. It can not only dynamically adjust the control strategy based on real-time process conditions, but also continuously correct internal model parameters based on historical production data. This allows the control accuracy and robustness of the entire system to continuously improve over time, ultimately achieving high-quality, high-consistency, and intelligent operation of the drying process.

[0076] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0077] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for drying and protecting temperature-resistant, variable-stress self-feedback yarn for corrosion prevention, characterized in that, Includes the following steps: S1. Establish a digital twin stress prediction model and a dynamic anti-corrosion performance evaluation model for yarn; the digital twin stress prediction model is used to predict the transient thermal stress distribution inside the yarn based on drying process parameters; the dynamic anti-corrosion performance evaluation model is used to evaluate the anti-corrosion protection effect based on the release kinetics of the slow-release anti-corrosion medium and the state of the drying microenvironment. S2. Set the target moisture regain of the yarn and initialize the drying process parameters, including the initial temperature setting value of each zone of the drying cylinder and the initial speed of the yarn travel. S3. Based on the digital twin stress prediction model and the dynamic anti-corrosion performance evaluation model, a multi-objective collaborative optimization decision-making process is performed on the current drying process parameters to obtain the optimized drying process parameters; the multi-objective collaborative optimization decision-making process takes minimizing the internal thermal stress of the yarn, maximizing the anti-corrosion performance index, and minimizing the real-time moisture regain deviation as optimization objectives. S4. Send the optimized drying process parameters obtained in S3 to the actuator of the drying equipment to perform the drying operation on the yarn; S5. During the drying process, the microenvironmental parameters and actual moisture regain of the yarn in the drying oven are collected in real time, and the real-time stress prediction value calculated by the digital twin stress prediction model is fed back to the multi-objective collaborative optimization decision-making process for decision-making in the next control cycle.

2. The method for drying and protecting temperature-resistant, variable-stress self-feedback yarns according to claim 1, characterized in that: In step S3, the multi-objective collaborative optimization decision-making process specifically includes: S31. Based on the real-time stress prediction value output by the digital twin stress prediction model and the real-time corrosion resistance index output by the dynamic corrosion resistance performance evaluation model, dynamically allocate the weight coefficients of the thermal stress minimization target, the corrosion resistance maximization target, and the moisture regain deviation minimization target. S32. Using the temperature setpoints and yarn travel speed of each zone of the drying cylinder as decision variables, and based on the weighting coefficients determined in step S31, use an optimization algorithm to solve for the Pareto optimal solution set that satisfies the above multiple objectives. S33. Cross-validate the candidate solutions in the Pareto optimal solution set: input the process parameters corresponding to the candidate solutions into the digital twin stress prediction model for stress secondary simulation verification, and input them into the dynamic anti-corrosion performance evaluation model for anti-corrosion performance change prediction verification. S34. From the candidate solutions that have passed all verifications in step S33, select the set of process parameters that are optimal in comprehensive evaluation as the output of the optimized drying process parameters.

3. The method for drying and protecting temperature-resistant, variable-stress self-feedback yarns according to claim 2, characterized in that: The steps for establishing the digital twin stress prediction model include: obtaining the material property parameters, structural parameters, and sizing formula parameters of the yarn; establishing a database of the relationship between the three-dimensional structural model of the yarn and the thermo-mechanical response under different drying process parameters based on the finite element analysis method; the drying process parameters include the temperature change rate and the temperature gradient inside the drying cylinder.

4. The method for drying and protecting temperature-resistant, variable-stress self-feedback yarns according to claim 3, characterized in that: The establishment of the dynamic anti-corrosion performance evaluation model is based on the application of thermosensitive slow-release anti-corrosion microcapsules; the thermosensitive slow-release anti-corrosion microcapsules are incorporated into the slurry of the yarn, and their wall material can undergo phase change in a specific temperature range during the drying process, thereby controlling the release of gaseous corrosion inhibitors to the yarn surface and the surrounding microenvironment.

5. The method for drying and protecting temperature-resistant, variable-stress self-feedback yarns according to claim 4, characterized in that: The microenvironmental parameters include temperature, humidity, and specific corrosive gas concentrations at multiple locations within the oven. The dynamic anti-corrosion efficacy evaluation model calculates and outputs a dynamic anti-corrosion efficacy index characterizing the current level of anti-corrosion protection based on the real-time collected microenvironmental parameters and the microcapsule release kinetics model under the current process parameters.

6. The method for drying and protecting temperature-resistant, variable-stress self-feedback yarns according to claim 5, characterized in that: In step S31, the weighting coefficient allocation rule is as follows: when the real-time stress prediction value exceeds a preset first threshold, the weighting coefficient of the thermal stress minimization target is increased; when the real-time anti-corrosion efficiency index is lower than a preset second threshold, the weighting coefficient of the anti-corrosion efficiency maximization target is increased; when the real-time moisture regain deviation exceeds a preset allowable deviation range, the weighting coefficient of the moisture regain deviation minimization target is increased.

7. The method for drying and protecting temperature-resistant, variable-stress self-feedback yarns according to claim 6, characterized in that: Following step S5, step S6 is also included: model self-learning and correction process; this process compares the actual moisture regain rate collected in step S5 and the actual yarn condition evaluated indirectly with the predicted values ​​output by the digital twin stress prediction model and the dynamic anti-corrosion performance evaluation model in the previous cycle. If the deviation continues to exceed the allowable range, the material response parameters in the digital twin stress prediction model or the release kinetic parameters in the dynamic anti-corrosion performance evaluation model are corrected based on the deviation data.

8. The method for drying and protecting temperature-resistant, variable-stress self-feedback yarns according to claim 7, characterized in that: The real-time moisture regain deviation is calculated by continuously detecting the actual moisture regain of the yarn after drying, and calculating the difference between the actual moisture regain and the target moisture regain.

9. A method for drying and protecting temperature-resistant, variable-stress self-feedback yarns according to claim 8, characterized in that: The actuators of the drying equipment include temperature control valves for independently adjusting the temperature of each drying drum zone, and drive motors for adjusting the yarn travel speed.

10. A yarn drying system for implementing the temperature-resistant variable stress self-feedback yarn anti-corrosion drying method according to any one of claims 1 to 9, characterized in that, include: The oven is equipped with a multi-zone independently temperature-controlled drying cylinder and a transmission mechanism for conveying yarn. A sensor array, arranged inside the oven, is used to collect microenvironmental parameters such as temperature, humidity, and specific gas concentrations in real time. A moisture regain detection device is installed at the outlet of the drying oven to detect the actual moisture regain of the yarn after drying. The model processing unit pre-stores the digital twin stress prediction model and the dynamic anti-corrosion performance evaluation model; The central decision control unit, connected to the sensor array, the moisture regain detection device, and the model processing unit, is configured to execute the multi-objective collaborative optimization decision-making process and generate control commands. The actuator drive unit is connected to the central decision control unit, the temperature control valve of the drying cylinder, and the drive motor of the transmission mechanism, and is used to adjust the process parameters according to the control command.

Images