A parameter configuration method for bio-based nylon fabric digital jet printing sizing

Abstract

The present application relates to the field of dyeing and printing of textiles, and particularly relates to a parameter configuration method for bio-based nylon fabric digital jet printing sizing, which comprises the following steps: obtaining the moisture absorption, spreading, thermal response, safety threshold and equipment limit data of the bio-based nylon fabric and constructing an initial data set; constructing a material sensitivity index through multi-physical characteristic coupling calculation, combining a safety margin to construct a boundary risk index, and then coupling with the equipment parameters to obtain a safety correction coefficient; using the coefficient to smooth and dampen the correction of the output parameters of the conventional model, obtaining the safety parameters for execution, and completing the critical region configuration. The present application constructs a material sensitivity index through multi-physical field coupling to accurately predict the risk of material critical mutation, and combines the equipment operation parameters to form a safety correction coefficient to continuously correct the theoretical parameters, which overcomes the boundary distortion problem of the traditional model from the mechanism, effectively avoids the process fluctuation and fabric deformation, and significantly improves the printing quality stability.

Description

Technical Field

[0001] This invention relates to the fields of dyeing and printing textiles. In particular, it relates to a parameter configuration method for digital inkjet printing sizing of bio-based nylon fabrics. Background Technology

[0002] In the actual digital inkjet printing production of bio-based nylon fabrics, sizing, as a key pre-process to ensure printing quality, faces severe technical challenges. Due to the significant differences in molecular structure and physical properties between bio-based nylon and traditional fibers, it is highly susceptible to abrupt changes in its physical state within specific temperature and concentration ranges near its glass transition or thermal shrinkage initiation point. Currently, the conventional parameter mapping models or empirical trial-and-error methods commonly used in the industry are mostly based on fixed process variables and historical data, making it difficult to accurately identify such critical abrupt change regions. This leads to existing technologies often outputting theoretical extreme values ​​that deviate from the material's actual withstand capabilities when approaching safety limits, easily causing uneven sizing distribution, ink edge diffusion, or localized thermal deformation of the fabric, resulting in a serious disconnect between process configuration and equipment execution capabilities. Summary of the Invention

[0003] To address the problem that the configuration of sizing parameters for digital inkjet printing on bio-based nylon fabrics often uses a fixed process variable mapping model, which makes it difficult to accurately identify the critical change region of the material. When the parameters approach the safety threshold, it is easy to cause uneven sizing distribution, ink edge diffusion, or local thermal deformation of the fabric, resulting in unstable printing quality. The present invention provides a solution in the following aspects.

[0004] A parameter configuration method for digital inkjet printing and sizing of bio-based nylon fabrics includes: obtaining the fiber moisture absorption tendency value, surface spreading characteristic value, basic reference value of thermal response of bio-based nylon fabrics, as well as process safety critical threshold and equipment operation limit value, and constructing an initial dataset; Based on the fiber moisture absorption tendency value, surface spreading characteristic value and thermal response basic reference value, multi-physical feature coupling calculation is performed to construct a material sensitivity index for identifying the material's critical abrupt change tendency. Based on the safety margin between the material sensitivity index and the process safety critical threshold, a boundary risk index is constructed to quantify the risk of approaching the critical region. By dynamically coupling the boundary risk index with the equipment operating parameters, a safety correction coefficient for suppressing overshoot of critical zone parameters is obtained. The safety correction coefficient is used to smooth and damp the sizing parameters output by the conventional model to obtain safe sizing parameters, which are then sent out for execution to complete the configuration of critical region parameters.

[0005] Preferably, the material sensitivity index is calculated as follows: Based on the fiber moisture absorption tendency value, surface spreading characteristic value, and thermal response baseline reference value, the results are obtained through coupling calculation of fluid characteristic terms and thermal characteristic terms. The fluid characteristic term is the ratio of the fiber moisture absorption tendency value to the surface spreading characteristic value, and the thermal characteristic term is the difference between the actual drying temperature and the thermal response baseline reference value.

[0006] Preferably, the boundary risk index is calculated as follows: The ratio of the material sensitivity index to the process safety critical threshold and the current parameter trial value is calculated; The calculation results are smoothed using the hyperbolic tangent function to obtain the boundary risk index, which is used to quantify the risk level of parameters approaching the critical region.

[0007] Preferably, the safety correction factor is calculated as follows: The actual dwell time of the fabric is calculated based on the effective length of the drying zone and the linear speed of the fabric movement. The actual dwell time is then normalized to the reference time to obtain the relative dwell multiple. The relative dwell time multiple is coupled and weighted with the boundary risk index, and then mapped using an exponential decay function to obtain the safety correction coefficient.

[0008] Preferably, the step of applying the safety correction coefficient to smooth and damp the sizing parameters output by the conventional model includes: Set process safety benchmark values ​​as safety boundaries for parameter correction to ensure that the corrected parameters do not exceed the physical tolerance limits of bio-based nylon fabrics; The safety correction coefficient is used as the parameter adjustment weight to perform damped interpolation calculation on the sizing parameters output by the conventional process model. During the correction process, parameter step changes are eliminated, taking into account both the safety and continuity of parameter adjustment, and outputting safe sizing parameters that meet the process requirements and material properties.

[0009] Preferably, the process of sending the safety sizing parameters to the equipment for execution also includes: real-time online monitoring of the actual operating conditions of the digital inkjet printing sizing equipment, and comparing the degree of deviation between the actual operating conditions and the current safety sizing parameters; When the actual operating conditions are detected to deviate from the preset allowable operating conditions range, the material sensitivity index, boundary risk index and safety correction coefficient are recalculated and updated in real time, and the safety sizing parameters are refreshed simultaneously, so that the process parameters can be dynamically adapted to the fluctuations of the on-site operating conditions.

[0010] Preferably, the construction of the initial dataset specifically includes: The fiber moisture absorption tendency value and surface spreading characteristic value were normalized to eliminate absolute value deviation; the normalized data were checked for range and outliers were removed, and out-of-range data were replaced with stable verification data of the same batch. Using the production batch index as the time axis benchmark, the effective physical property data, critical thresholds and equipment limits are combined to form an initial dataset that binds material status and process constraints by batch; among them, the effective physical property data are the fiber moisture absorption tendency value, surface spreading characteristic value and thermal response basic reference value after normalization and outlier removal processing.

[0011] Preferably, after the safety sizing parameters are issued and executed, a closed-loop feedback control step is also included: Obtain the sizing uniformity, adhesion strength, and printing color reproduction index of the actual fabric, and compare the deviation with the preset quality target. If the deviation is within the allowable tolerance, the current configuration is confirmed to be effective and archived as historical stable data. If the deviation exceeds the limit, extract the abnormal feature parameters, reverse the response curve of the boundary threshold and safety correction coefficient of the initial dataset, and complete the cross-batch process adaptive iterative optimization.

[0012] The present invention has the following effects: 1. This invention constructs a material sensitivity index to characterize the fiber's moisture absorption, surface spreading, and thermal response characteristics through multi-physics coupling. This allows for the early identification of material state transition trends before process parameters approach the glass transition and thermal shrinkage initiation points. It addresses the technical shortcomings of conventional mapping models, such as their inability to capture nonlinear changes in the critical region and their tendency to output distorted extreme values, at the mechanistic level. This reduces the probability of uneven slurry distribution, ink diffusion, and fabric thermal deformation from the source.

[0013] 2. This invention generates a safety correction coefficient by coupling the boundary risk index with the equipment operating parameters. It uses an exponential decay and interpolation smoothing structure to continuously correct the theoretical recommended value, replacing the traditional hard cut-off method. This avoids equipment shocks and process fluctuations caused by parameter jumps, ensuring that the sizing parameters are always within a safe process window that the material can withstand and the equipment can execute stably, significantly improving the clarity of the printed pattern and the consistency of color reproduction.

[0014] 3. This invention relies on real-time operating condition monitoring and cross-batch data feedback to achieve online iterative updates of material sensitivity, boundary risk and safety correction coefficients, so that configuration parameters can adapt to material batch fluctuations, equipment cycle changes and on-site environmental disturbances. At the same time, qualified process data is used for benchmark optimization to continuously improve the stability, repeatability and adaptability to large-scale production of bio-based nylon digital inkjet printing sizing. Attached Figure Description

[0015] Figure 1 This is a flowchart of steps S1-S5 in a parameter configuration method for digital inkjet printing and sizing of bio-based nylon fabric according to an embodiment of the present invention. Detailed Implementation

[0016] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments.

[0017] Reference Figure 1 A parameter configuration method for digital inkjet printing and sizing of bio-based nylon fabric includes steps S1-S5, as detailed below: S1: Obtain the fiber moisture absorption tendency value, surface spreading characteristic value, basic reference value of thermal response, process safety critical threshold and equipment operation limit value of bio-based nylon fabric, and construct the initial dataset.

[0018] Using standard moisture regain testing equipment or online moisture monitoring terminals, data on the moisture absorption of the bio-based nylon fabrics to be treated were collected batch by batch to obtain the fiber moisture absorption tendency value. This parameter is defined as the fiber's ability to adsorb liquid under standard conditions. For example, the standard environment is: temperature 23±2℃, relative humidity 65±5%. It characterizes the ability of the internal pores of the bio-based nylon fiber to capture slurry and moisture, and the unit is %, the higher the value, the stronger the fiber's adsorption capacity for slurry.

[0019] The spreading characteristics of the slurry on the fabric surface are obtained through offline sampling with a static contact angle meter or real-time monitoring with an online wetting rate detection module. This parameter reflects the slurry's diffusion and uniform coverage capabilities on the fabric surface, and is measured in units of... The higher the value, the faster the slurry spreads on the fabric surface and the more evenly it covers it.

[0020] Thermal response data of bio-based nylon fabrics are collected using a differential scanning calorimeter (DSC) or an online temperature monitoring module to obtain the baseline thermal response value. This parameter is an inherent property of the material itself and corresponds to the critical temperature at which the fabric undergoes significant thermal deformation. The unit is °C, and it is the core benchmark for judging whether the subsequent processing temperature exceeds the limit. Its value is determined by the material composition and fiber structure of the fabric and remains constant within the same batch of fabrics.

[0021] The system reads the current production line's critical safety thresholds through the equipment control system terminal. These thresholds include the safety upper limits of process parameters, equipment operating limits such as the upper limit of drying temperature and slurry concentration, and equipment operating status parameters such as drying fan speed and slurry delivery pump power. These parameters collectively constitute the safety boundary of process operation, ensuring that subsequent parameter configurations do not exceed the equipment hardware's capacity and material tolerance limits, and that the units remain consistent with the corresponding process variables.

[0022] It should be noted that the acquisition and preprocessing of all parameters follow the principle of batch correspondence and real-time synchronization to ensure that each batch of datasets is independent and traceable, and to avoid parameter configuration deviations caused by data confusion between different batches. By normalizing the acquired fiber moisture absorption tendency value, surface spreading characteristic value, and thermal response basic reference value, the magnitude difference of different physical quantities is eliminated. The normalization follows a common standardized formula to ensure that the converted data retains the original physical meaning.

[0023] Based on preset process safety standards, a data filtering threshold is constructed to verify the range of the collected raw data. Abnormal data exceeding the tolerance range of the bio-based nylon fabric and the safe operating range of the equipment are automatically intercepted and marked. Simultaneously, a moving average filtering algorithm is used to eliminate abnormal fluctuations caused by random detection noise, preventing abnormal data from affecting the accuracy of subsequent indicator calculations. For intercepted abnormal data, the average of normal data from the same batch is used as a replacement to ensure the integrity and validity of the dataset.

[0024] After normalization, outlier removal, and replacement of out-of-bounds data, the fiber moisture absorption tendency values, surface spreading characteristics values, thermal response baseline reference values, critical thresholds, and equipment limits are classified and organized according to production batches and process nodes to construct a standardized initial dataset.

[0025] Bio-based nylon fabrics are high-molecular composite fiber materials. During sizing and drying processes, they exhibit both fluid behavior (slurry penetration and spreading) and thermal response behavior (thermal deformation). Traditional fixed process parameter configuration methods only match single process variables in production, failing to comprehensively characterize the fabric's inherent property differences, slurry wetting competition, and abrupt changes near the thermal critical state, making it difficult to identify critical abrupt change regions in advance. Therefore, a sensitivity index that quantifies the material's critical abrupt change tendency is constructed by coupling the fabric's moisture absorption and spreading properties with its thermal response characteristics. The specific operation steps are as follows: S2: Based on the fiber moisture absorption tendency value, surface spreading characteristic value and thermal response basic reference value, multi-physical feature coupling calculation is performed to construct a material sensitivity index for identifying the material's critical abrupt change tendency.

[0026] The fiber hygroscopic tendency value, surface spreading characteristic value, and thermal response baseline reference value were selected. These three parameters are directly related to the adaptability of the sizing process of bio-based nylon fabrics and are the core physical basis for constructing the index. Among them, the fiber hygroscopic tendency value is used to characterize the adsorption and penetration capacity of bio-based nylon fibers for sizing liquid. The larger the value, the stronger the fiber's internal adsorption capacity for sizing liquid. The surface spreading characteristic value is used to characterize the diffusion and spreading capacity of sizing liquid on the surface of bio-based nylon fabric. The larger the value, the faster the diffusion rate of sizing liquid on the fabric surface and the wider the spreading range. The thermal response baseline reference value is an inherent thermal characteristic parameter of bio-based nylon fabric, corresponding to the critical temperature benchmark for the fabric to undergo thermal deformation and thermal shrinkage. It is the core basis for judging whether the actual drying temperature is close to the critical state of the material. Its value is determined by the material composition and fiber structure of bio-based nylon fabric and is a fixed constant.

[0027] On the one hand, fluid characteristic terms are constructed, which are obtained by calculating the ratio of fiber hygroscopic tendency value to surface spreading characteristic value. The core physical meaning of this ratio is to accurately characterize the dual movement law of the slurry on the surface and inside of the bio-based nylon fabric. The wetting process of the slurry on the fabric is essentially a competitive process of inward penetration and outward spreading. When the fiber hygroscopic tendency value is greater than the surface spreading characteristic value, the slurry tends to penetrate into the fabric more, while the surface spreading ability is weak. At this time, small fluctuations in process parameters (such as slurry concentration and coating speed) will be amplified by this characteristic of strong inward absorption and weak outward spreading, which can easily lead to defects such as uneven slurry layer thickness and local slurry leakage. When the fiber hygroscopic tendency value is less than the surface spreading characteristic value, the slurry tends to spread on the fabric surface more, the inward absorption ability is weak, and the impact of process parameter fluctuations on the uniformity of the slurry layer is relatively small. Therefore, by constructing fluid characteristic terms by the ratio of fiber hygroscopic tendency value to surface spreading characteristic value, the competitive relationship of the slurry wetting process can be accurately quantified, thereby reflecting the sensitivity of the fabric to fluctuations in fluid-related process parameters.

[0028] On the other hand, a thermal characteristic term is constructed, which is calculated by the difference between the actual drying temperature and the baseline reference value of the thermal response. The core physical meaning of this difference is to characterize the degree of deviation between the actual drying conditions and the critical state of the thermal response of the bio-based nylon fabric: the baseline reference value corresponds to the critical thermal response temperature of the fabric. When the actual drying temperature is lower than the baseline reference value, the thermal characteristic term is negative. At this time, the fabric's thermal deformation is small and shows a gradual trend with temperature change, indicating low sensitivity to temperature parameter fluctuations. When the actual drying temperature is close to or higher than the baseline reference value, the thermal characteristic term approaches zero or is positive. At this time, as a polymer material, the degree of thermal deformation of bio-based nylon will accelerate with increasing temperature, and its sensitivity to temperature parameter fluctuations will increase sharply, making it prone to defects such as local thermal shrinkage and wrinkles. Therefore, constructing a thermal characteristic term by the difference between the actual drying temperature and the baseline reference value of the thermal response can accurately capture the distance between the fabric's heating state and the critical thermal response state, quantifying the fabric's sensitivity to temperature parameter fluctuations.

[0029] By coupling and correlating the constructed fluid and thermal characteristic terms, and comprehensively integrating the fluid wetting behavior of the slurry with the thermal response behavior of the material, a material sensitivity index is obtained. In other words, in actual sizing processes, the wetting process of the slurry and the heating process of the fabric do not occur independently, but rather simultaneously and interact: the internal absorption and spreading of the slurry affect the thermal conductivity of the fabric, thus altering its thermal response characteristics; while the heating state of the fabric changes the surface tension of the fibers, thus affecting the wetting effect of the slurry. Therefore, coupling the fluid and thermal characteristic terms allows for a comprehensive and accurate reflection of the overall sensitivity of bio-based nylon fabrics to fluctuations in overall sizing process parameters under the combined effects of multiple physical processes. This provides accurate and reliable basic data for the construction of subsequent boundary risk indicators and the calculation of safety correction coefficients, ensuring that subsequent parameter corrections can specifically avoid risks in critical abrupt change regions and guarantee stable sizing quality.

[0030] Specifically, the material sensitivity index satisfies the following relationship: ; In the formula, This indicates the material sensitivity index for the current production batch, representing the overall sensitivity of the current batch of fabric to process fluctuations such as concentration, coating amount, and drying temperature. This value represents the fiber's hygroscopic tendency, characterizing the fiber's ability to hold onto slurry. A higher value indicates that the slurry is more easily absorbed into the fiber. This value represents the surface spreading characteristics, characterizing the ability of the slurry to spread laterally on the fabric surface. A higher value indicates that the slurry is easier to spread evenly. It represents the difference between the current drying process setting temperature and the standard ambient reference temperature, characterizing the net heat input intensity applied to the fabric; This represents the baseline reference value for the thermal response of bio-based nylon, indicating the temperature at which the fiber begins to undergo significant thermal deformation.

[0031] It should be noted that a high-precision temperature sensor is installed at the entrance of the drying area. This sensor collects the target drying temperature set by the current process in real time. The standard ambient temperature of the production site is obtained in real time using a workshop environmental monitoring terminal. The difference between the target drying temperature and the ambient temperature is calculated to obtain the difference in drying heat driving force. Under normal mass production drying conditions, to ensure the drying, dehydration, and slurry solidification effects, the target drying temperature set by the process is always higher than the workshop ambient temperature. However, if special conditions such as abnormal equipment temperature control or extreme seasonal temperature fluctuations occur, leading to… When the control system determines that the current heat input conditions do not meet the normal process control conditions, it will automatically trigger the constant temperature protection control strategy and suspend the current process parameter iteration update process, and will no longer enter the subsequent multi-feature coupling and index calculation stage.

[0032] The material sensitivity index is used to quantify the sensitivity of bio-based nylon fabrics to parameter fluctuations during sizing processes. Its core construction lies in combining the competitive mechanism of sizing agent penetration within the fabric and its surface spreading, as well as the thermal response characteristics of polymer materials under heat deformation, to achieve standardized characterization and measurement of fabric sizing sensitivity. In other words, it selects the ratio of fiber hygroscopic tendency value to surface spreading characteristic value. As a fluid characteristic, it can directly reflect the relative strength of the slurry's penetration into the fabric and its diffusion to the surface. When the slurry's penetration into the fabric is strong while its surface spreading is weak, small fluctuations in process parameters are easily amplified, ultimately resulting in uneven coating thickness.

[0033] Bio-based nylon is a polymer material whose thermal deformation does not change linearly with temperature, but rather accelerates as the temperature approaches the material's critical response value. A logarithmic structure is employed. It can both conform to the actual thermal response law of polymer materials and reflect the sensitive acceleration characteristics when the temperature is close to the critical value, and at the same time avoid the sharp amplification of the calculated values, thus ensuring the stability and rationality of the exponent.

[0034] Material sensitivity indices alone can only characterize the fabric's sensitivity to process fluctuations, but cannot quantify the proximity of current process parameters to the safety threshold and the associated risk. Traditional fixed threshold judgment methods only make simple out-of-bounds checks, failing to perform continuous risk grading based on material sensitivity and remaining safety margins. This leads to misjudgments, delayed corrections, and difficulty in proactively intervening in parameter out-of-bounds issues in the critical region. Therefore, it is necessary to establish a continuous and quantifiable risk assessment mechanism that combines material sensitivity indices with the remaining safety margin of the process safety threshold. This mechanism accurately characterizes the degree to which process parameters approach the critical region, providing a quantitative risk basis for subsequent parameter adjustments. The specific steps are as follows: S3: Based on the safety margin between the material sensitivity index and the critical threshold for process safety, construct a boundary risk index to quantify the risk of approaching the critical zone.

[0035] The critical threshold for process safety is a preset upper limit benchmark value for the process, which is calibrated in advance based on the thermal deformation and slurry coating limit characteristics of bio-based nylon fabrics. The basis for setting it is the material temperature resistance limit, the maximum coating tolerance of the slurry, and the mass production process safety boundary test data, which serve as the benchmark red line for judging whether the process parameters have entered the danger zone.

[0036] The difference between the current process trial parameters and the process safety critical threshold is calculated to obtain the safety margin. Using the material sensitivity index as the risk amplification factor and the safety margin as the distance constraint factor, a correlation ratio between the two is constructed to reflect the inherent logic that the higher the sensitivity, the stronger the risk, and the larger the safety margin, the lower the risk. A smoothing mapping function is introduced to normalize the correlation ratio, and finally a boundary risk index that can be continuously quantified and evaluated is generated, realizing a refined hierarchical characterization of the approach risk of the critical region.

[0037] Specifically, the boundary risk index satisfies the following relationship: ; In the formula, The boundary risk index represents the degree to which the current parameter trial value approaches the material's critical safety state; This represents the current trial configuration value (such as drying temperature, candidate slurry concentration, etc.) during the parameter optimization iteration process; it is strictly constrained within the search space of the optimization algorithm. Ensure that the test value is always inside the safety red line; This represents the critical threshold for process safety, with units consistent with the corresponding process variables. It indicates the safety boundary for bio-based nylon to undergo thermal shrinkage or slurry adsorption saturation. Indicates the material sensitivity index; Represents a minimal zero-preserving constant, exemplified by... , This represents the tangent function of a hyperbola.

[0038] It should be noted that the current trial configuration value is not set manually, but is dynamically and autonomously generated by the parameter optimization algorithm built into the system. The optimization algorithm constructs an objective function based on a preset process quality target, and continuously generates new candidate process parameter values ​​within a predefined process safety allowable range based on the gradient change direction of the objective function or a predetermined iteration step size constraint; the candidate parameter value generated in each round of this iteration is the current trial configuration value.

[0039] The boundary risk index is used to continuously quantify the risk level of the current sizing parameters approaching the safety critical threshold and to provide a risk basis for subsequent parameter correction. Its core construction lies in: using the ratio of the material sensitivity index to the remaining safe distance of the parameters, combined with a smooth mapping function, to achieve a standardized and continuous characterization of the critical approach risk.

[0040] In other words, the difference between the process safety critical threshold and the current parameter trial value is used as the safety margin. This difference directly reflects the remaining space between the current parameter configuration and the safety critical value. The smaller the safety margin, the closer the current parameters are to the material's critical limit, and the higher the risk of parameters exceeding the limit.

[0041] Using the material sensitivity index as the numerator and the safety margin as the denominator to construct the ratio input, this setting can fully reflect the amplifying effect of the material's own characteristics on the degree of risk. Under the same safety margin condition, the higher the material sensitivity, the more significant the impact of small fluctuations in process parameters on the final sizing effect, the lower the system's tolerance for parameter fluctuations, and the higher the corresponding risk level. This forms an objective calculation logic that the higher the sensitivity, the higher the risk, and the larger the safety margin, the lower the risk.

[0042] By inputting the ratio input term into the hyperbolic tangent function for smooth mapping, the input value can be constrained to... The standardized range avoids numerical anomalies caused by the infinite increase of calculation results, and ensures a continuous and smooth transition of risk levels with parameter changes, without abrupt changes, making the risk signal more consistent with the actual process variation.

[0043] The value of the boundary risk index directly represents the safety intervention priority of the current parameter configuration path: when the index value approaches 1, it indicates that the current parameter is extremely close to the safety critical threshold and the material sensitivity is high, the parameter overshoot risk is high, and the parameter constraint correction logic needs to be activated; when the index value approaches 0, it indicates that the current parameter is far from the safety critical threshold or the material is in a low sensitivity state, the parameter overshoot risk is extremely low, and the normal parameter configuration strategy can be maintained.

[0044] The boundary risk index only reflects the critical risk of process parameters exceeding limits, without considering the actual operating conditions of the drying equipment. Different residence times of the fabric in the drying zone result in significant differences in heat accumulation and slurry wetting accumulation effects. Under the same risk level, longer residence times increase the probability of parameter overshoot leading to thermal deformation and uneven coating. Fixed adjustments based solely on the risk index cannot match the actual operating cycle of the equipment and the material residence characteristics, resulting in a mismatch between the adjustment strength and the actual operating conditions. Therefore, it is necessary to dynamically couple the boundary risk index with the equipment operating parameters to construct an adaptive suppression weight that can adapt to changes in operating conditions. The specific steps are as follows: S4: Dynamically couple the boundary risk index with the equipment operating parameters to obtain a safety correction coefficient for suppressing overshoot of critical region parameters.

[0045] Based on the effective length of the drying zone and the linear velocity of the fabric, the actual physical residence time of the fabric in the drying zone is calculated in real time. A preset reference time is introduced to normalize the actual residence time, resulting in a dimensionless relative residence multiple, eliminating the influence of differences in equipment size and linear velocity. The relative residence multiple is dynamically coupled and weighted with the boundary risk index, integrating the equipment operating time factor and the critical risk factor. An exponential decay function is used to map the coupled value to generate a safety correction coefficient.

[0046] Specifically, the safety correction factor satisfies the following relationship: ; in, This represents the safety correction coefficient, which characterizes the degree of suppression on the output amplitude of the parametric model. The smaller the value, the stronger the suppression. Indicates the boundary risk index; Indicates the effective working length of the drying zone, in units of This information is obtained from the equipment's mechanical structure drawings or control system. This indicates the linear speed of the fabric in the current batch, in units of... The data is collected in real time by the encoder on the production line. This represents the standard process reference time, in units of... , is a preset constant at the production line level, taken from the average dwell time of historical qualified batches or the value specified in the process specification, used to eliminate the dimension of time and establish a relative duration benchmark; Represented by natural constant An exponential function with base 0.

[0047] It should be noted that the safety correction coefficient is used to adaptively suppress and adjust the theoretical sizing parameter output according to the actual operating conditions of the equipment and the boundary risk level, so as to achieve a precise match between the parameter output and the equipment operating cycle and the material safety limit. Its core construction lies in: adopting a standard exponential decay structure to explicitly couple the physical residence time of the fabric in the drying zone with the boundary risk level, forming an adaptive correction weight that has both physical meaning and control stability.

[0048] In other words, the actual residence time of the fabric in the drying zone under the current operating conditions is directly obtained by using the ratio of the effective length of the drying zone to the linear velocity of the fabric. The longer the residence time, the more significant the penetration and spreading of the slurry on the fabric surface and the cumulative effect of material thermal deformation. Under the same boundary risk, parameter overshoot and fabric thermal deformation are more likely to occur, thus requiring a corresponding increase in parameter suppression strength; a reference time is introduced. This converts absolute dwell time into a dimensionless relative dwell time multiple, making exponential operations dimensionless.

[0049] By using the exponential decay function, the time-weighted boundary risk signal can be smoothly mapped to... Within the interval, that is, when the actual dwell time is equal to the baseline dwell time and the boundary risk level is high, the input term of the exponential decay function is 1. According to the characteristics of the natural exponential function, the safety correction coefficient is about 0.37 at this time, which achieves moderate intensity suppression of the theoretical pulp parameter output. Under high-risk conventional working conditions, it can take into account both parameter safety and output continuity, avoid insufficient or excessive suppression, and obtain the safety correction coefficient.

[0050] Conventional process models directly output theoretical slurry parameters without considering the material's critical abrupt change characteristics and equipment operating constraints. When approaching the safety critical range, these parameters are prone to abrupt changes and exceeding boundaries, leading to problems such as uneven slurry distribution, ink edge diffusion, and localized thermal deformation of the fabric. Directly using a hard cutoff limiting method would cause parameter jumps and process condition oscillations, affecting production stability and product consistency. Therefore, a safety correction coefficient is needed to smooth and dampen the theoretical parameters. The specific steps are as follows: S5: Apply a safety correction coefficient to the sizing parameters output by the conventional model to perform smooth damping correction, obtain the safe sizing parameters, and send them out for execution to complete the configuration of the critical region parameters.

[0051] Using the process safety benchmark value as the safety boundary for parameter correction, the corrected parameters are limited to not exceeding the material's physical tolerance limit. The safety correction coefficient is used as an adaptive adjustment weight to perform damped interpolation calculations on the theoretical sizing parameters output by the conventional model. Gradual slope constraints are adopted during the correction process to strictly control the single adjustment range of parameters, maintain continuous and smooth parameter iteration, and prevent abrupt changes. After the correction is completed, safe sizing parameters that adapt to the material's sensitive characteristics, critical risk level, and equipment operating conditions are obtained and sent to the inkjet sizing equipment for execution, thus completing the adaptive safety configuration of process parameters in the critical region.

[0052] Specifically, the safe sizing parameters satisfy the following relationship: ; In the formula, This indicates the final issued safety process parameter configuration values; Indicates the theoretical recommended value; The process safety baseline value is taken as the lower limit of the safety range or the average value of historical stable operation of the same batch, which serves as the safety boundary of the critical state. This represents the safety correction factor.

[0053] The steps to obtain the theoretical recommended value are as follows: Obtain the operating parameters of the current production scenario (such as fabric properties, ambient temperature, etc.), organize them into a standardized input vector, and substitute them into a preset conventional parameter mapping model. Specifically, conventional industrial control models such as quadratic polynomials and process regression formulas can be used. At the same time, construct a comprehensive quality objective function with core optimization objectives such as slurry uniformity, color reproduction accuracy, and coating efficiency to clarify the direction of parameter optimization. Then, call the standard numerical optimization solution process to solve for the extreme points of the objective function within the preset process parameter range. The resulting optimal parameter combination is the theoretical recommended value.

[0054] The process safety baseline values ​​are based on the thermal stability tolerance limit and slurry saturation adhesion limit of the bio-based nylon fabric itself as core constraints. Combined with multi-batch mass production process test data, the safe operating boundaries of key process parameters such as drying temperature and slurry coating amount are pre-defined. These process safety baseline values ​​are not fixed constants but can be dynamically adjusted adaptively according to production conditions: the system adaptively fine-tunes based on the differences in the physical properties of different production batches of fabric and real-time fluctuations in workshop ambient temperature, combined with the boundary risk index; when the workshop ambient temperature is too high and the critical risk of fabric heating increases, the temperature-related process safety baseline values ​​are automatically lowered to reserve greater safety redundancy to avoid the risk of thermal deformation; when the concentration of slurry physical properties fluctuates, the safety baseline boundary corresponding to the coating amount is simultaneously and adaptively corrected, ensuring that the process safety baseline always matches the current material characteristics and actual on-site conditions, guaranteeing the rationality and applicability of parameter constraints.

[0055] It should be noted that bio-based nylon polymer fabrics have unique physical properties and are highly sensitive to sudden changes in process parameters such as drying temperature, slurry concentration, and coating rate when approaching the critical process safety range. If conventional hard thresholds are used to directly cut off parameters or make large-scale jumps in adjustment, it is very easy to cause sudden changes in the load on the equipment, violent fluctuations in temperature control and slurry pump output, and induce sudden changes in internal stress of the fabric, resulting in quality defects such as local thermal deformation and uneven slurry adhesion.

[0056] Throughout the entire process of issuing safety sizing parameters to the digital inkjet printing sizing equipment and commencing production, the system simultaneously initiates a real-time online monitoring process for the equipment's operating conditions. This enables dynamic adaptive adjustment of process parameters. The specific implementation steps are as follows: During the entire process of issuing safety sizing parameters to the digital inkjet printing sizing equipment and commencing production, the system simultaneously initiates a real-time online monitoring process for the equipment's operating conditions, operating continuously alongside the sizing process. The system continuously collects core operating data of the digital inkjet printing sizing equipment through on-site deployed online sensors, equipment encoders, frequency converters, and industrial control acquisition terminals, with a collection frequency set to 1-5 times / second. The collected data includes: actual fabric linear speed, real-time temperature of the drying zone, sizing liquid flow rate, coating roller speed, equipment traction tension, and workshop ambient temperature and humidity, among other comprehensive operating condition data. Simultaneously, the system also captures the actual parameter execution values ​​fed back from the equipment's electrical control system and compares them item by item with the currently issued safety sizing parameters.

[0057] Based on the physical properties of the same batch of fabrics, the rated operating parameters of the equipment, and the process safety thresholds, the system pre-defines an independent allowable operating condition range for each process parameter. The system performs difference calculations on the real-time collected equipment operating condition data and the current safe sizing parameters item by item, calculating the deviation of individual parameters and the overall deviation. If all operating condition data fall within the preset allowable operating condition range, the current operating condition and process parameters are considered to be properly matched, and the existing material sensitivity index, boundary risk index, safety correction coefficient, and safe sizing parameters are kept unchanged, with the equipment continuing to produce stably according to the current parameters. If any one or more operating condition data exceed the preset allowable operating condition range, the operating condition is considered to have deviated, and the parameter iteration update process is immediately triggered.

[0058] When a deviation from the operating condition is triggered, the system temporarily freezes the original parameter output logic, calls the latest real-time collected fabric property data and equipment operating condition data, and strictly follows the calculation logic of steps S2 to S4 of this invention to recalculate the material sensitivity index A, boundary risk index B, and safety correction coefficient C in real time. The specific calculation process is as follows: combining the latest collected fiber moisture absorption tendency value, surface spreading characteristic value, and real-time drying temperature, the fluid characteristic terms and thermal characteristic terms are updated to obtain a new material sensitivity index; based on the updated material sensitivity index, the current process safety critical threshold, and real-time parameter trial values, the safety margin is recalculated, and a new boundary risk index is obtained through hyperbolic tangent function mapping operation; combining the effective length of the drying zone, real-time fabric running linear speed, baseline process time, and the updated boundary risk index, a new safety correction coefficient is obtained through exponential decay function operation.

[0059] After completing the iteration of core indicators, the system uses the updated safety correction coefficients to interpolate and correct the theoretical sizing parameters output by the conventional model, generating a new generation of safe sizing parameters adapted to the current field conditions. The system converts the updated parameters into control commands that the equipment can recognize and sends them to each execution unit of the digital inkjet printing sizing equipment in real time, completing the dynamic switching of process parameters. The entire parameter iteration, updating, and sending process adopts a smooth and gradual change mode, strictly prohibiting abrupt parameter changes, ensuring continuous and stable equipment operation and sizing process, enabling process parameters to adapt dynamically to fluctuations in field conditions, and providing complete real-time monitoring, deviation judgment, parameter iteration, and dynamic adaptation functions.

[0060] By using a safety correction coefficient as a continuously adjustable weighting factor, the quantified critical approach risk level can be smoothly and continuously transformed into the correction ratio of process parameters. When the critical approach risk level is high, the process configuration parameters are automatically guided to converge smoothly towards the safety benchmark range, constraining the model output amplitude and avoiding the risk of parameters exceeding the limit. When the critical approach risk level is low and the operating condition is far from the safety boundary, the parameter optimization potential of the conventional optimization model is fully preserved, taking into account both process quality and production efficiency.

[0061] The optimal process configuration parameter sequence obtained after smoothing and damping correction is converted into standardized control commands that conform to the communication protocol of digital sizing equipment. These commands are then directly sent to the underlying execution units of the digital inkjet printing sizing equipment, including functional components such as the slurry conveying pump frequency converter, the drying air duct temperature control adjustment module, and the coating traction tension roller, to achieve precise execution of the process parameters.

[0062] After the digital inkjet printing and sizing process is completed in a single batch, the actual sizing layer adhesion uniformity, surface coating status and pattern color reproduction of the finished fabric are collected online, and the measured quality indicators are compared and analyzed with the preset process target threshold.

[0063] If the measured quality deviation falls within the preset allowable tolerance range, the process parameter configuration scheme for the current batch is deemed valid. The entire set of physical property datasets, index calculation parameters, and process configuration parameters are archived and stored as a benchmark reference for subsequent batches of the same material. If the measured quality deviation exceeds the preset allowable tolerance range, the physical property anomaly characteristic parameters and operating condition deviation characteristic parameters corresponding to this production are extracted. The safety boundary threshold of the previous data standardization dataset is iteratively corrected in reverse, and the damping response adjustment curve in the material sensitivity index calculation process is updated simultaneously.

[0064] The revised and optimized baseline rules are then incorporated into the process parameter configuration process for the next batch of bio-based nylon fabrics, enabling process self-learning and adaptive iterative optimization under multiple production conditions. This forms a complete closed-loop control system encompassing data acquisition, indicator modeling, parameter correction, quality feedback, and iterative optimization.

[0065] It should be noted that those skilled in the art can make various modifications and improvements without departing from the inventive concept, and these all fall within the scope of protection of this invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A method for configuring parameters for digital inkjet printing and sizing of bio-based nylon fabrics, characterized in that, include: The fiber moisture absorption tendency value, surface spreading characteristic value, thermal response baseline reference value, process safety critical threshold and equipment operation limit value of bio-based nylon fabric are obtained, and an initial dataset is constructed. The fiber moisture absorption tendency value is used to characterize the adsorption and penetration ability of bio-based nylon fibers to slurry, the surface spreading characteristic value is used to characterize the diffusion and spreading ability of slurry on the surface of bio-based nylon fabric, and the thermal response baseline value is the inherent thermal characteristic parameter of bio-based nylon fabric, corresponding to the critical temperature reference for the fabric to undergo thermal deformation and thermal shrinkage. Based on the fiber moisture absorption tendency value, surface spreading characteristic value and thermal response basic reference value, multi-physical characteristic coupling calculation is performed to construct a material sensitivity index for quantifying the sensitivity of bio-based nylon fabrics to parameter fluctuations during the sizing process. Based on the safety margin between the material sensitivity index and the process safety critical threshold, a boundary risk index is constructed to quantify the risk of approaching the critical zone, wherein the process safety critical threshold is a preset upper limit benchmark value of the process, which is calibrated in advance based on the thermal deformation and slurry coating limit characteristics of bio-based nylon fabrics. The boundary risk index is dynamically coupled with the equipment operating parameters to obtain a safety correction coefficient for suppressing parameter overshoot in the critical zone. The safety correction coefficient is used to adaptively suppress and adjust the theoretical slurry parameter output according to the actual operating conditions of the equipment and the boundary risk level, so as to achieve precise matching between the parameter output and the equipment operating cycle and material safety limit. The safety correction coefficient is used to smooth and damp the sizing parameters output by the conventional model to obtain safe sizing parameters, which are then sent out for execution to complete the configuration of critical region parameters.

2. The parameter configuration method for digital inkjet printing and sizing of bio-based nylon fabric according to claim 1, characterized in that, The material sensitivity index is calculated as follows: Based on the fiber moisture absorption tendency value, surface spreading characteristic value, and thermal response baseline reference value, the results are obtained through coupling calculation of fluid characteristic terms and thermal characteristic terms. The fluid characteristic term is the ratio of the fiber moisture absorption tendency value to the surface spreading characteristic value, and the thermal characteristic term is the difference between the actual drying temperature and the thermal response baseline reference value.

3. The parameter configuration method for digital inkjet printing and sizing of bio-based nylon fabrics according to claim 1, characterized in that, The boundary risk index is calculated as follows: The ratio of the material sensitivity index to the process safety critical threshold and the current parameter trial value is calculated; The calculation results are smoothed using the hyperbolic tangent function to obtain the boundary risk index, which is used to quantify the risk level of parameters approaching the critical region.

4. The parameter configuration method for digital inkjet printing and sizing of bio-based nylon fabric according to claim 1, characterized in that, The safety correction factor is calculated as follows: The actual dwell time of the fabric is calculated based on the effective length of the drying zone and the linear speed of the fabric movement. The actual dwell time is then normalized to the reference time to obtain the relative dwell multiple. The relative dwell time multiple is coupled and weighted with the boundary risk index, and then mapped using an exponential decay function to obtain the safety correction coefficient.

5. The parameter configuration method for digital inkjet printing and sizing of bio-based nylon fabric according to claim 1, characterized in that, The process of applying the safety correction coefficient to smooth and damp the sizing parameters output by the conventional model includes: Set process safety benchmark values ​​as safety boundaries for parameter correction to ensure that the corrected parameters do not exceed the physical tolerance limits of bio-based nylon fabrics; The safety correction coefficient is used as the parameter adjustment weight to perform damped interpolation calculation on the sizing parameters output by the conventional process model. During the correction process, parameter step changes are eliminated, taking into account both the safety and continuity of parameter adjustment, and outputting safe sizing parameters that meet the process requirements and material properties.

6. The parameter configuration method for digital inkjet printing and sizing of bio-based nylon fabrics according to claim 1, characterized in that, The process of issuing safety sizing parameters to the equipment also includes: real-time online monitoring of the actual operating conditions of the digital inkjet printing sizing equipment, and comparing the degree of deviation between the actual operating conditions and the current safety sizing parameters; When the actual operating conditions are detected to deviate from the preset allowable operating conditions range, the material sensitivity index, boundary risk index and safety correction coefficient are recalculated and updated in real time, and the safety sizing parameters are refreshed simultaneously, so that the process parameters can be dynamically adapted to the fluctuations of the on-site operating conditions.

7. The parameter configuration method for digital inkjet printing and sizing of bio-based nylon fabrics according to claim 1, characterized in that, The construction of the initial dataset specifically includes: The fiber moisture absorption tendency value and surface spreading characteristic value were normalized to eliminate absolute value deviation; the normalized data were checked for range and outliers were removed, and out-of-range data were replaced with stable verification data of the same batch. Using the production batch index as the time axis benchmark, the effective physical property data, critical thresholds and equipment limits are combined to form an initial dataset that binds material status and process constraints by batch; among them, the effective physical property data are the fiber moisture absorption tendency value, surface spreading characteristic value and thermal response basic reference value after normalization and outlier removal processing.

8. The parameter configuration method for digital inkjet printing and sizing of bio-based nylon fabrics according to claim 1, characterized in that, After the safety sizing parameters are issued and executed, a closed-loop feedback control step is also included: Obtain the sizing uniformity, adhesion strength, and printing color reproduction index of the actual fabric, and compare the deviation with the preset quality target. If the deviation is within the allowable tolerance, the current configuration is confirmed to be effective and archived as historical stable data. If the deviation exceeds the limit, extract the abnormal feature parameters, reverse the response curve of the boundary threshold and safety correction coefficient of the initial dataset, and complete the cross-batch process adaptive iterative optimization.

Images