Fabric one-step pretreatment method based on biological enzyme

Abstract

The invention discloses a one-step fabric pretreatment method based on bio-enzyme, which comprises the following steps: acquiring fabric surface slurry component and grease impurity distribution data, detecting optimal matching parameters of cellulase activity and protease activity through a spectral analysis technology, and determining an initial set value of bio-enzyme concentration according to fabric density and thickness information; if the qualified state shows that the quality index does not reach the standard, returning to adjust the activity proportion of each component in the compound enzyme formula, if the quality index reaches the standard, recording the current process parameter as an optimization template, and meanwhile, carrying out statistics on water consumption and energy consumption data in the treatment process; a resource consumption analysis module is adopted to process the water consumption and energy consumption data, the saving rate is calculated by comparing the resource consumption reference value of traditional chemical pretreatment, and the environmental protection benefit index is evaluated according to the wastewater neutralization degree to obtain comprehensive treatment effect evaluation.

Description

Technical Field

[0001] This invention relates to the field of textile technology based on bio-enzymes, and more particularly to a one-step pretreatment method for fabrics based on bio-enzymes. Background Technology

[0002] Textile pretreatment processes are a crucial link in the textile industry, directly affecting the quality and efficiency of subsequent dyeing and finishing processes, and occupying an important position in the entire textile industry chain.

[0003] Traditional textile pretreatment mainly relies on chemical methods, using desizing and refining processes under strongly alkaline conditions to remove sizing, grease and impurities from fabrics, but this method has obvious drawbacks.

[0004] Chemical pretreatment requires large quantities of highly alkaline chemicals such as caustic soda, which not only consumes significant amounts of energy and water resources but also generates highly concentrated alkaline wastewater, necessitating additional neutralization steps and increasing environmental pressure and production costs. Currently, the core challenges facing the textile pretreatment field lie in two interrelated technical factors: process integration and environmental requirements. Traditional processes require separate desizing and refining steps, making one-step integration impossible. This process separation complicates the treatment flow, increasing equipment investment and operating costs. Insufficient process integration further exacerbates the complexity of environmental treatment, as multi-step processing inevitably generates more diverse types of wastewater, particularly alkaline wastewater, making subsequent neutralization a necessary step. This environmental treatment requirement not only increases additional chemical consumption but also extends the entire treatment cycle, creating a technical contradiction between process efficiency and environmental requirements.

[0005] Therefore, how to develop a bio-enzyme treatment method that can complete desizing and refining in one step, while avoiding the generation of alkaline wastewater that requires neutralization, and achieving the goals of energy and water conservation and environmental pollution reduction while ensuring key quality indicators such as fabric desizing rate, capillary effect and whiteness, has become a key issue in the development of textile pretreatment technology. Summary of the Invention

[0006] This invention provides a one-step pretreatment method for fabrics based on biological enzymes, mainly comprising: Data on the composition of sizing agents and distribution of oil impurities on the fabric surface were obtained. The optimal ratio of cellulase and protease activities was detected by spectral analysis. The initial set value of the biological enzyme concentration was determined based on the fabric density and thickness information. The initial set values ​​are processed using a bio-enzyme optimization algorithm. If the sizing content of the fabric exceeds a preset threshold, the proportion of cellulase is increased. If the oil content exceeds a preset threshold, the proportion of lipase is increased, thereby obtaining a compound enzyme formulation combination tailored to the current fabric characteristics. A temperature and time control model for the enzymatic hydrolysis reaction was established based on the compound enzyme formulation. The reaction process status was judged by real-time monitoring of the enzyme activity change curve. When the enzyme activity reached its peak, dynamic data on desizing rate and refining effect were recorded. The pH value change trend in the dynamic data is analyzed using a wastewater neutralization control algorithm. If the pH value remains within the neutral range, the enzymatic hydrolysis treatment continues. If the pH value deviates from the neutral range, the amount of buffer solution added is adjusted to obtain a stable neutral wastewater output. The surface characteristic parameters of the enzymatically hydrolyzed fabric are processed by a fabric quality assessment algorithm to obtain quantitative indicators of capillary effect, whiteness and strength retention rate. The current treatment effect is judged to be qualified based on the degree of deviation between the quantitative indicators and the standard values. If the qualified status shows that the quality indicators do not meet the standards, then return to adjust the activity ratio of each component in the compound enzyme formula. If the quality indicators meet the standards, then record the current process parameters as an optimization template, and at the same time, collect the water consumption and energy consumption data during the processing. The water and energy consumption data are processed using a resource consumption analysis module. The savings rate is calculated by comparing the resource consumption benchmark value of traditional chemical pretreatment. The environmental benefit index is evaluated based on the degree of neutralization of wastewater to obtain a comprehensive treatment effect evaluation. Based on the comprehensive treatment effect evaluation, an adaptive adjustment mechanism for process parameters is established. When processing a new batch of fabric, the historical optimized template with similar characteristics is automatically matched, and a stable one-step pretreatment effect is obtained by fine-tuning the enzyme ratio and reaction conditions.

[0007] As a further preferred technical solution of the present invention, step S1 includes: Data on the distribution of sizing components and oil impurities on the fabric surface were obtained by using spectral analysis technology. The spatial distribution map of the chemical components on the fabric surface was obtained by using Fourier transform infrared spectroscopy. Concentration characteristics of slurry components and oil impurities were extracted from the spatial distribution map, and the content ratio of the main components was determined by principal component analysis algorithm. The activities of cellulase and protease were determined based on their content ratios, and enzyme activity data were obtained using ultraviolet-visible spectrophotometry. If the enzyme activity data deviates from the preset threshold range, the ratio of cellulase and protease is adjusted by linear regression algorithm to determine the optimal ratio. Based on the fabric density and thickness data, the initial concentration setting value of the bio-enzyme is calculated using a preset mapping function; The actual amount of biological enzyme applied was adjusted from the initial concentration setting value, and real-time spectral monitoring technology was used to obtain the trend of changes in the fabric surface after enzyme treatment; The treatment effect is judged based on the trend of change. If the residual slurry components or oil impurities exceed the preset threshold, the concentration of biological enzymes is adjusted by iterative optimization algorithm to obtain the final treatment parameters.

[0008] As a further preferred technical solution of the present invention, step S2 includes: Initial characteristic data of fabric samples are obtained, and the sizing and oil content are detected by spectral analysis to obtain fabric characteristic parameters; If the slurry content exceeds the preset threshold, the cellulase addition ratio is predicted by a linear regression algorithm, and the cellulase adjustment amount is determined by combining the initial characteristic data. If the oil content exceeds the preset threshold, the support vector machine algorithm is used to analyze the oil characteristics, and the amount of lipase to be adjusted is determined in combination with the initial characteristic data. Based on the adjustment amounts of cellulase and lipase, the initial proportions of the compound enzyme formulation are calculated using a weighted average method to obtain the preliminary enzyme formulation combination. A genetic algorithm was used to optimize the initial enzyme formulation combination, and the proportion of each enzyme was iteratively adjusted to obtain the optimized compound enzyme formulation. The optimized compound enzyme formula was verified by simulation technology, and the removal rates of sizing and grease from the treated fabric were analyzed to determine the formula's effectiveness. If the removal rate does not meet the preset standard, the process returns to the step of adjusting the enzyme ratio, re-optimizes the formula, and obtains the final compound enzyme formula.

[0009] As a further preferred technical solution of the present invention, step S3 includes: By constructing a preset temperature and time control model, the initial parameter data of the enzymatic hydrolysis reaction are obtained, and the parameters are calibrated according to the characteristics of the compound enzyme formulation to obtain the preliminary reaction condition configuration. Based on the initial reaction conditions, data on changes in enzyme activity are collected in real time, and sensor technology is used to monitor the fluctuations of the change curve to determine whether the enzyme activity is close to its peak state. If the enzyme activity change curve shows that it is close to the peak state, the peak recording mechanism is triggered to obtain the corresponding time point and temperature data and determine whether the peak is stable. By collecting the dynamic changes in desizing rate data after the peak value stabilizes, and comparing them with preset thresholds, a preliminary evaluation result of the desizing effect is obtained. Based on the preliminary evaluation results of the desizing effect, the dynamic data of the refining effect are recorded simultaneously, and the fluctuation of the refining effect is analyzed in real time to determine whether the effect meets the expected standard. If the analysis results of the refining effect do not meet the expected standards, adjust the temperature control and time control parameters, re-acquire the enzymatic hydrolysis reaction operation data, and judge whether the adjusted effect meets the requirements. By adjusting the effect data, the final optimized configuration of the enzymatic hydrolysis reaction is generated, and the parameters are saved according to the characteristics of the compound enzyme formula, resulting in a complete record of the reaction process. Beneficial effects

[0010] This invention discloses a method that obtains fabric surface characteristics through spectral analysis, determines a composite enzyme formulation using a bio-enzyme optimization algorithm, and establishes an enzymatic reaction control model to monitor the treatment process in real time. Simultaneously, a wastewater neutralization control algorithm is used to maintain pH stability, and a fabric quality assessment algorithm is used to determine the treatment effect. If quality indicators fail to meet standards, the enzyme formulation is adjusted; if standards are met, it is recorded as an optimization template. This invention also includes resource consumption analysis and environmental benefit assessment, establishing an adaptive adjustment mechanism for process parameters that can automatically match historical optimization templates of similar fabrics. This method achieves high efficiency, energy saving, and environmental protection in fabric pretreatment, improving production efficiency and product quality. Attached Figure Description

[0011] Figure 1 This is a flowchart of the present invention. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0013] like Figure 1 This embodiment of a one-step fabric pretreatment method based on bio-enzymes may specifically include the following steps: S1. Obtain data on the composition of sizing agents and the distribution of oil and grease impurities on the fabric surface. Detect the optimal ratio of cellulase activity and protease activity using spectral analysis technology. Determine the initial set value of the biological enzyme concentration based on the fabric density and thickness information.

[0014] Data on the distribution of sizing components and oil impurities on the fabric surface were obtained using spectral analysis. Fourier transform infrared spectroscopy was employed to obtain a spatial distribution map of the chemical components on the fabric surface. Concentration characteristics of sizing components and oil impurities were extracted from the spatial distribution map. Principal component analysis was used to determine the content ratio of the main components. Based on the content ratio, the activities of cellulase and protease were detected, and enzyme activity data were obtained using ultraviolet-visible spectrophotometry. If the enzyme activity data deviated from the preset threshold range, the ratio of cellulase and protease was adjusted using a linear regression algorithm to determine the optimal ratio. Based on the fabric density and thickness data, a preset mapping function was used to calculate the initial concentration setpoint of the bioenzymes. The actual amount of bioenzymes applied was adjusted from the initial concentration setpoint. Real-time spectral monitoring technology was used to obtain the trend of changes in the fabric surface after enzyme treatment. The treatment effect was judged based on the trend. If the residual sizing components or oil impurities exceeded the preset threshold, the bioenzyme concentration was adjusted using an iterative optimization algorithm to obtain the final treatment parameters.

[0015] For example, when obtaining data on the composition of sizing agents and the distribution of oil impurities on the surface of fabrics through spectral analysis, Fourier transform infrared spectroscopy can be used.

[0016] Specifically, this technology uses infrared light to irradiate the surface of a fabric and records the absorption spectra at different wavelengths, thereby analyzing the chemical bond characteristics of starchy substances and oily impurities in the sizing. Suppose that the characteristic absorption peaks of starch slurry are detected on the surface of a cotton fabric, concentrated around 1080 cm⁻¹, while the characteristic peaks of oily impurities are around 1740 cm⁻¹. A spatial distribution map can visually show that starch is mainly concentrated at the fabric edges, while oily impurities are distributed in the central region. This distribution map provides precise targeting for subsequent processing. When extracting concentration characteristics and using principal component analysis (PCA), the spectral data can be converted into a matrix form to analyze the content ratio of starch and oil. For example, suppose the analysis results show that starch accounts for 70% and oily impurities account for 30%, this provides data support for subsequent enzyme selection and formulation. PCA can also effectively reduce dimensionality, decrease data redundancy, and improve computational efficiency. For enzyme activity detection, UV-Vis spectrophotometry is a commonly used method. Suppose that cellulase activity is measured by detecting the absorbance of substrate degradation products, and the obtained value is 120 U / mL, while the preset threshold is 100-150 U / mL, which is within the normal range. However, if the protease activity is only 50 U / mL, below the threshold of 60-80 U / mL, it indicates a potential problem. If the concentration is too low (U / mL), the ratio needs to be adjusted. Linear regression algorithms can be used to analyze the relationship between enzyme ratio and activity, deriving an adjustment scheme requiring a 20% increase in protease concentration. When calculating the initial enzyme concentration, based on fabric density and thickness data, assuming a density of 0.5 g / cm³ and a thickness of 0.2 cm, a preset mapping function yields an initial cellulase concentration of 5 g / L. This method ensures the matching of enzyme quantity with fabric characteristics, avoiding waste or insufficiency. Real-time spectral monitoring technology is used to track the enzyme treatment effect. For example, if starch residue decreases from the initial 10% to 2% during treatment, but is still above the 1% threshold, an iterative optimization algorithm can gradually increase the cellulase concentration to 6 g / L, ultimately achieving the required residue level. This dynamic adjustment significantly improves treatment accuracy and efficiency. Specifically, the above-mentioned technical links support each other, from spectral analysis to enzyme activity detection to concentration optimization, forming a closed-loop control that ensures efficient removal of sizing agents and impurities from the fabric surface, while reducing resource waste and optimizing treatment costs, demonstrating high industrial application value.

[0017] S2. The initial set values ​​are processed using a bio-enzyme optimization algorithm. If the sizing content of the fabric exceeds a preset threshold, the proportion of cellulase is increased. If the oil content exceeds a preset threshold, the proportion of lipase is increased, thereby obtaining a compound enzyme formula combination for the current fabric characteristics.

[0018] Initial characteristic data of the fabric sample is obtained. Sizing and oil content are detected using spectral analysis to obtain fabric characteristic parameters. If the sizing content exceeds a preset threshold, the cellulase addition ratio is predicted using a linear regression algorithm. Combined with the initial characteristic data, the cellulase adjustment amount is determined. If the oil content exceeds a preset threshold, the oil characteristics are analyzed using a support vector machine algorithm. Combined with the initial characteristic data, the lipase adjustment amount is determined. Based on the cellulase and lipase adjustment amounts, the initial ratio of the compound enzyme formulation is calculated using a weighted average method to obtain a preliminary enzyme formulation combination. A genetic algorithm is used to optimize the preliminary enzyme formulation combination, iteratively adjusting the ratio of each enzyme to obtain an optimized compound enzyme formulation. The optimized compound enzyme formulation is verified using simulation technology. The sizing and oil removal rates of the treated fabric are analyzed to determine the formulation effect. Based on the judgment results, if the removal rate does not meet the preset standard, the process returns to the enzyme ratio adjustment step, and the formulation is re-optimized to obtain the final compound enzyme formulation.

[0019] For example, when acquiring initial characteristic data of fabric samples, near-infrared spectroscopy can be used to scan the fabric surface to obtain spectral signals reflecting the content of sizing agents and oils. Let's assume that a cotton fabric sample shows a sizing agent content of 5.2% and an oil content of 3.8%. These data will serve as the basis for subsequent analysis. The advantage of spectral analysis technology lies in its non-destructive detection, enabling rapid acquisition of chemical information from the fabric surface, providing a reliable basis for subsequent enzyme formulation adjustments. For instance, if the sizing agent content exceeds a preset threshold (e.g., 4.0%), a linear regression algorithm can be used to predict the proportion of cellulase to be added. Assuming historical data... Data analysis revealed that for every 1.0% increase in sizing content, a 0.5 unit increase in cellulase concentration is required. Therefore, for the current sample, a preliminary increase of 2.5 units of cellulase can be determined. This method allows for precise adjustment of enzyme dosage based on fabric characteristics, avoiding resource waste. For instance, if the oil content exceeds a preset threshold (e.g., 3.0%), a support vector machine algorithm can be used to analyze oil characteristics. Assuming the algorithm identifies the oil as primarily composed of long-chain fatty acids, a suitable lipase for decomposing such substances can be selected. Combined with initial characteristic data, an increase of 1.2 units in lipase concentration can be determined. This approach improves enzyme targeting and processing efficiency. For example, when calculating the initial ratio of a compound enzyme formulation, a weighted average method can be used, assigning weights to the adjustment amounts of cellulase and lipase according to their importance. Assuming a weight of 0.6 for cellulase and 0.4 for lipase, a preliminary ratio of 6:4 can be determined in the compound enzyme formulation. This method balances the effects of different enzymes, ensuring the rationality of the formulation. Furthermore, when optimizing the initial enzyme formulation using a genetic algorithm, multiple generations of iterative adjustments can be simulated to gradually select a better ratio. Assuming an initial ratio of 6:4, after 10 generations of optimization, adjusting it to 6.5:3.5 revealed even better treatment results. This optimization method can find a better solution under multivariate conditions, improving the adaptability of the formulation. For example, when verifying the optimized formulation using simulation technology, the fabric treatment process can be simulated under laboratory conditions. Assuming the sizing removal rate is 92% and the oil removal rate is 88% after treatment, close to the preset standard, this verification method can intuitively reflect the formulation effect and provide data support for subsequent adjustments. For example, if the removal rate does not meet the standard, the enzyme ratio adjustment step can be returned to, and the formulation can be optimized again. Assuming that by increasing the cellulase ratio to 7.0 units, the final removal rate is increased to over 95%, this iterative adjustment method can continuously approach the ideal effect, ensuring the practicality of the final formulation.

[0020] S3. Establish a temperature and time control model for the enzymatic hydrolysis reaction based on the compound enzyme formula combination. Determine the reaction process status by real-time monitoring of the enzyme activity change curve. When the enzyme activity reaches its peak, start recording dynamic data on desizing rate and refining effect.

[0021] By constructing a pre-defined temperature and time control model, initial parameter data for the enzymatic hydrolysis reaction are obtained. Parameter calibration is performed based on the characteristics of the compound enzyme formulation to obtain a preliminary reaction condition configuration. Based on this preliminary configuration, data on enzyme activity changes are collected in real time. Sensor technology is used to monitor the fluctuations of the change curve to determine if the enzyme activity is close to its peak state. If the enzyme activity change curve shows that it is close to its peak state, a peak recording mechanism is triggered to obtain the corresponding time point and temperature data, and to determine if the peak is stable. Using the data after the peak has stabilized, the dynamic changes in desizing rate are collected and compared with a pre-defined threshold to obtain a preliminary evaluation result of the desizing effect. Based on the preliminary evaluation result of the desizing effect, dynamic data on the refining effect are recorded simultaneously. The fluctuations in the refining effect are analyzed in real time to determine if the effect meets the expected standard. If the refining effect analysis result does not meet the expected standard, the temperature and time control parameters are adjusted, and the enzymatic hydrolysis reaction operation data is re-acquired to determine if the adjusted effect meets the requirements. Based on the adjusted effect data, the final optimized configuration for the enzymatic hydrolysis reaction is generated. Parameters are saved based on the characteristics of the compound enzyme formulation, resulting in a complete reaction process record.

[0022] In one possible implementation, constructing a pre-defined temperature and time control model requires considering the characteristics of the enzymatic reaction and designing a reasonable parameter range. For example, for the enzymatic reaction of a compound enzyme formulation in fabric treatment, the temperature range could be set to 40-60°C and the time range to 30-120 minutes, establishing an initial model using laboratory data. The model will preset different temperature and time combinations based on the type of enzyme, such as cellulase and lipase, to ensure enzyme activity remains within a suitable range. For instance, cellulase exhibits higher activity at 50°C, while lipase may perform better at 45°C. Such a model provides a basis for subsequent parameter calibration and reduces the number of experiments. For example, when acquiring real-time enzyme activity data, a high-precision sensor can be used to monitor enzyme activity fluctuations in the reaction solution. Specifically, the sensor records enzyme activity data every 5 seconds, forming a continuous activity curve. For instance, in a certain experiment, enzyme activity reached its peak 40 minutes after the reaction began, at a temperature of 48°C, with an activity value of 200 U / mL. This data acquisition method can accurately capture the dynamic changes in enzyme activity, providing a reliable basis for subsequent peak determination. In one embodiment, when the peak recording mechanism is triggered, the system automatically records the temperature and time point at which enzyme activity reaches its peak and continuously monitors it for 5 minutes to confirm peak stability. For example, if the peak occurs at 48°C and 40 minutes, and the activity fluctuation is less than 5% in the subsequent 5 minutes, the peak is considered stable. This mechanism ensures that the reaction conditions are optimal, avoiding a decrease in enzyme activity due to temperature or time deviations. For instance, when collecting dynamic changes in desizing rate data, the residual sizing content on the fabric surface can be detected every 10 minutes using a spectrometer. Assuming the initial sizing content is 8% and the preset desizing rate threshold is 90%, in one experiment, the desizing rate reached 92% after 60 minutes of reaction, indicating good results. Such dynamic monitoring can provide timely feedback on the enzymatic hydrolysis effect, providing data support for subsequent optimization. Specifically, when recording the refining effect simultaneously, residual oil in the fabric can be analyzed using an oil content analyzer. For example, if the initial oil content is 5% and the target refining effect is an oil removal rate of 85%, in one experiment, the oil removal rate is 88% after 80 minutes of reaction, indicating that the refining effect meets the standard. This simultaneous monitoring method can comprehensively evaluate the overall performance of the compound enzyme formula. In one possible implementation, if the refining effect does not meet the standard, the temperature can be adjusted to 52°C or the reaction time can be extended to 100 minutes, and the enzymatic reaction data can be collected again. For example, in one adjustment, after the temperature is increased by 2°C, the desizing rate increases from 88% to 93%, and the refining effect is also improved simultaneously.This dynamic adjustment method can quickly optimize reaction conditions and improve enzymatic hydrolysis efficiency. For example, when generating the final optimized configuration for the enzymatic hydrolysis reaction, parameters such as temperature 48°C and time 90 minutes can be saved as a standard configuration for subsequent production reference. In one application, this configuration stabilized the desizing rate at over 94% and achieved a refining effect of 90%, significantly improving the quality of fabric treatment. This parameter saving method facilitates the standardization and repeatability of the production process. The applicant wants to explain that the above steps, through technologies such as sensors and spectral analysis, form a complete closed loop from data acquisition to parameter optimization, which can effectively improve the applicability and stability of the compound enzyme formula in fabric treatment. Real-time monitoring and dynamic adjustment of each link ensure that the reaction conditions are always close to the optimal activity state of the enzyme, providing reliable technical support for industrial production.

[0023] S4. The pH value change trend in the dynamic data is analyzed using a wastewater neutralization control algorithm. If the pH value remains within the neutral range, the enzymatic hydrolysis treatment continues. If the pH value deviates from the neutral range, the amount of buffer solution added is adjusted to obtain a stable neutral wastewater output.

[0024] Dynamic data of wastewater pH value is acquired in real time by sensors to generate a time series dataset. The time series dataset is analyzed using a moving average algorithm to obtain the pH value change trend. If the change trend shows that the pH value is within the neutral range, the enzymatic hydrolysis treatment parameters are kept constant by the control module, and an enzymatic hydrolysis treatment command is generated. If the change trend shows that the pH value deviates from the neutral range, the buffer addition amount is predicted by a linear regression algorithm to obtain the buffer adjustment parameters. Based on the buffer adjustment parameters, the buffer addition amount is adjusted by a flow controller to generate adjusted wastewater pH value data. The adjusted wastewater pH value data is reacquired by sensors to verify whether it is within the neutral range, and the verification result is obtained. Based on the verification result, the pH value analysis and adjustment steps are repeated to generate a stable neutral wastewater output.

[0025] For example, in wastewater treatment, real-time acquisition of dynamic pH data from sensors is crucial for ensuring a stable enzymatic hydrolysis environment. pH directly affects enzyme activity; excessive acidity or alkalinity leads to decreased hydrolysis efficiency. Suppose that in a textile wastewater treatment scenario, sensors collect pH data every 5 minutes, creating a time-series dataset over 24 hours, with the data fluctuating between 5.5 and 8.5. This real-time monitoring provides a foundation for subsequent analysis. For instance, in analyzing time-series datasets, moving average algorithms can smooth short-term fluctuations and highlight long-term trends. Suppose the collected pH data shows a gradual downward trend in the first 6 hours, from 7.2 to 6.5. The moving average algorithm calculates the hourly average, concluding that the overall trend is slightly acidic. This analytical method directly reflects changes in the wastewater environment, providing a basis for subsequent adjustments. For example, after judging the pH trend, if the data stabilizes within the neutral range of 6.8 to 7.2, the control module will maintain the current enzymatic hydrolysis parameters unchanged, such as keeping the temperature at 40 degrees Celsius and the stirring speed at 200 rpm. This stable state helps the enzymatic hydrolysis reaction to continue and avoids unnecessary parameter adjustments. For example, if the trend shows that the pH value deviates from the neutral range, such as dropping to 6.0, a linear regression algorithm can be used to predict the amount of buffer solution to add. Based on historical data analysis, assuming that 100 ml of buffer solution needs to be added for every 0.5 unit decrease in pH value, the algorithm will predict the specific amount to be added as 120 ml based on the current deviation. This prediction method improves the accuracy of adjustment. For example, when adjusting the amount of buffer solution added, the flow controller gradually injects the buffer solution according to the predicted parameters. Assuming the initial flow rate is set to 10 ml / min and the addition is completed over 12 minutes, the sensor then detects that the pH value has risen back to 6.9. This dynamic adjustment ensures that the wastewater environment gradually approaches the ideal state. For example, after adjustment, the pH data is re-verified via sensors. If it still doesn't reach 7.0, the system records the current value as 6.9 and triggers a new round of analysis and adjustment until it stabilizes within the target range. This cyclical mechanism ensures the stability of wastewater treatment. For instance, after cyclically performing pH analysis and adjustment, the system ultimately produces stable neutral wastewater output with a pH value maintained at around 7.0. This stable output environment provides a reliable guarantee for subsequent enzymatic hydrolysis treatment, while also reducing the risk of wastewater corrosion to equipment and improving the overall efficiency and sustainability of the treatment system.

[0026] S5. Process the surface characteristic parameters of the enzymatically hydrolyzed fabric using a fabric quality assessment algorithm to obtain quantitative indicators of capillary effect, whiteness, and strength retention rate. Determine the qualification status of the current treatment effect based on the degree of deviation between the quantitative indicators and the standard values.

[0027] Digital images of the fabric surface after enzymatic hydrolysis are acquired using an image acquisition device to generate first image data. Image processing algorithms are used to denoise and enhance edges in the first image data to obtain second image data. Feature parameters of the fabric surface, including texture roughness and color distribution, are extracted from the second image data to generate a feature parameter set. The feature parameter set is classified using a support vector machine algorithm to calculate quantitative indicators for capillary effect, whiteness, and strength retention rate, resulting in a set of quantitative indicators. Based on the deviation between the quantitative indicator set and preset standard values, the Euclidean distance algorithm is used to calculate the degree of deviation, generating a deviation value. If the deviation value is less than a preset threshold, the processing effect is determined to be acceptable, and a qualified label is generated; if the deviation value is greater than or equal to the preset threshold, an unacceptable label is generated. Based on the acceptable or unacceptable label, a fabric quality assessment result is generated to determine the final processing status.

[0028] For example, when acquiring digital images of the fabric surface after enzymatic hydrolysis using image acquisition equipment, a high-resolution industrial camera can be used to ensure the capture of subtle textures and color changes on the fabric surface. Suppose that in the enzymatic hydrolysis process of a textile factory, the camera captures 1000×1000 pixel images at a frequency of 10 frames per second, generating the first image data; this data reflects the surface state of the fabric after enzymatic hydrolysis, such as fiber smoothness or color uniformity (it should be noted that image acquisition must be performed under a constant light source to avoid light variations interfering with subsequent analysis).

[0029] In one embodiment of the applicant's work, when the image processing algorithm performs denoising and edge enhancement on the first image data, it can use Gaussian filtering to remove noise and then use the Canny edge detection algorithm to enhance the boundaries of the fabric texture. Assuming that there are noise points caused by dust in the original image, Gaussian filtering can smooth these interferences, while edge enhancement highlights the outline of the fibers, generating clear second image data. This processing ensures the accuracy of subsequent feature extraction. For example, when extracting feature parameters from the second image data, texture roughness can be calculated using the gray-level co-occurrence matrix, and chromaticity distribution can be analyzed using the HSV color space. Suppose that the texture roughness value of a batch of fabric samples is 0.85 and the standard deviation of chromaticity distribution is 0.03. These parameters reflect the surface smoothness and color consistency of the fabric. The feature parameter set provides a quantitative basis for subsequent classification. In one embodiment, when the support vector machine algorithm classifies the feature parameter set, the model can be pre-trained to distinguish between qualified and unqualified fabrics. Suppose that the training data contains 1000 samples, and the model divides the fabrics into two categories according to the capillary effect value, whiteness value, and strength retention rate. If a fabric has a capillary effect value of 0.9, a whiteness value of 85, and a strength retention rate of 95%, the model outputs a set of quantitative indicators, indicating that it is close to the high-quality standard. This classification method improves the objectivity of the evaluation. For example, when using the Euclidean distance algorithm to calculate the degree of deviation, the set of quantitative indicators can be compared with the standard values. Suppose that the standard gross efficiency value is 0.95, the whiteness value is 90, and the strength retention rate is 98%, while the deviation value of the sample is calculated to be 0.07. If the preset threshold is 0.1, then the deviation value is less than the threshold, and a qualified mark is generated. This method ensures the accuracy of the evaluation results.

[0030] In one embodiment, when generating fabric quality assessment results based on pass / fail indicators, the results can be fed back to the production system. If a pass indicator is generated, the system continues with the current enzymatic hydrolysis parameters; if a fail indicator is generated, it prompts adjustments to the hydrolysis time or solution concentration. For example, if the whiteness value of a certain fail-quality fabric is too low, the system suggests extending the hydrolysis time by 10 minutes. This feedback mechanism optimizes the production process. The applicant wishes to clarify that the above process, along with wastewater pH control, falls within the field of textile enzymatic hydrolysis, but focuses on fabric quality assessment and does not directly overlap with pH treatment. Image analysis technology ensures product quality traceability, while feature classification and deviation calculation improve the automation level of the assessment. These methods collectively support the refined management of the enzymatic hydrolysis process.

[0031] S6. If the qualified status shows that the quality indicators do not meet the standards, return to adjust the activity ratio of each component in the compound enzyme formula. If the quality indicators meet the standards, record the current process parameters as an optimization template, and at the same time, collect the water consumption and energy consumption data during the processing.

[0032] If the quality indicators fail to meet the standards, the activity data of each component in the compound enzyme formulation is obtained, and the correlation between component activity and quality indicators is analyzed using a linear regression algorithm to obtain an activity ratio adjustment plan. Based on the activity ratio adjustment plan, the proportions of each component in the compound enzyme formulation are updated, and the adjusted quality indicators are calculated by simulating the process flow to determine whether they meet the standards. If the adjusted quality indicators meet the standards, the current process parameters, including temperature, pressure, and stirring speed, are obtained, and an optimization template is generated by storing them in a database and identifying the template. Process parameters are extracted from the optimization template, and water consumption and energy consumption data during the processing are obtained in conjunction with sensor data. The average value is calculated using a data statistics module to obtain consumption statistics results. A time series analysis algorithm is used to predict the trend of consumption statistics results, generating trends in water consumption and energy consumption, and determining whether they exceed preset thresholds. If the trend exceeds the preset threshold, the process parameters are optimized using a gradient descent algorithm, the optimization template is updated, and the adjusted process parameters are obtained. Based on the adjusted process parameters, the compound enzyme formulation ratio is updated, and the process flow is re-executed to obtain new quality indicators and determine whether they continue to meet the standards.

[0033] For example, in the enzymatic hydrolysis of textiles, if quality indicators fail to meet standards, it is necessary to analyze the activity data of the components in the compound enzyme formulation. Assuming the capillary effect value is detected to be 10% lower than the standard value, the activity data of cellulase, protease, and pectinase in the compound enzyme can be collected and recorded as 1000 U / g, 800 U / g, and 600 U / g, respectively. Using a linear regression algorithm, the relationship between the activity of each component and the capillary effect value is analyzed. It is found that cellulase activity and capillary effect value have a strong positive correlation, with a correlation coefficient of 0.9. Based on this, the proportion of cellulase is adjusted from 30% to 40%, generating a new formulation. This adjustment, driven by data, ensures the scientific validity of the formulation.

[0034] In one possible implementation, the updated compound enzyme formulation needs to be validated through a simulated process flow. Assuming the simulation shows that the adjusted gross efficiency value increases to within the standard range, such as from 80% to 95%, while the whiteness value and strength retention rate also reach 90% and 85% respectively, both meeting the standards, the simulation process is completed using virtual simulation software. Parameters such as temperature 40°C, pressure 1.2 bar, and stirring speed 200 rpm are input to calculate quality indicators and verify the formulation's effectiveness. This approach improves the efficiency of process adjustments. Specifically, after achieving the target, process parameters need to be stored to generate an optimization template. The database can record parameters such as temperature (40°C), pressure (1.2 bar), and stirring speed (200 rpm), generating template identifiers such as "T20250608". Water consumption data (e.g., 2.5 m³ / hour) and energy consumption data (e.g., 300 kWh / hour) are collected in real time by sensors, calculating daily averages of 2.4 m³ and 290 kWh respectively. This data storage method facilitates subsequent retrieval and optimization, ensuring process stability. For example, consumption statistics need to be analyzed using time series analysis to predict trends. Suppose the analysis shows that water consumption is expected to increase from 2.4 m³ to 2.8 m³ in the next week, exceeding the threshold of 2.6 m³. Therefore, the gradient descent algorithm is used to optimize process parameters, reducing the temperature to 38°C and adjusting the stirring speed to 180 rpm. The water consumption is then recalculated to 2.5 m³, meeting the threshold requirement. This combination of prediction and optimization effectively controls resource consumption.

[0035] In one possible implementation, the adjusted process parameters need to be re-executed to verify continued compliance. Assuming that after the new process is run, the gross efficiency value stabilizes at 94%, and the whiteness and strength retention rates are 91% and 86% respectively, both consistently meeting standards, and sensor data further confirms that water and energy consumption remain within 2.5 m³ and 290 kWh respectively, this cyclical verification mechanism ensures long-term process stability and reduces the risk of quality fluctuations. The applicant aims to demonstrate that the above method, through data-driven and real-time monitoring, achieves highly efficient optimization of enzymatic hydrolysis. Adjusting the activity ratio improves the compliance rate of quality indicators, optimizing template storage facilitates process reproducibility, and trend prediction and parameter adjustment effectively control resource consumption. This multi-stage collaborative approach not only improves the fabric processing pass rate but also optimizes production efficiency and resource utilization.

[0036] S7. The water consumption and energy consumption data are processed using a resource consumption analysis module. The savings rate is calculated by comparing the resource consumption benchmark value of traditional chemical pretreatment. The environmental benefit index is evaluated based on the degree of neutralization of wastewater to obtain a comprehensive treatment effect evaluation.

[0037] The data processing module extracts real-time monitoring values ​​from water consumption and energy consumption data to obtain a resource consumption dataset. Using a benchmark comparison method, the resource consumption dataset is compared with a preset benchmark value for traditional chemical pretreatment resource consumption to calculate the resource saving rate. If the resource saving rate is greater than a preset threshold, a linear regression algorithm is used to predict the resource consumption trend, obtaining the consumption change trend. Based on the consumption change trend and combined with wastewater neutralization data, a cluster analysis algorithm is used to classify environmental benefit levels, obtaining environmental benefit indicators. A weighted average method is used to integrate the resource saving rate and environmental benefit indicators to generate a comprehensive treatment effect score. If the comprehensive treatment effect score is lower than a preset threshold, a decision tree algorithm is used to analyze outliers in the water and energy consumption data to obtain optimization adjustment parameters. Based on these optimization adjustment parameters, the processing strategy of the resource consumption analysis module is updated, generating a new resource consumption dataset.

[0038] For example, in the field of enzyme treatment process optimization in the textile industry, the application of data processing modules is crucial. Real-time monitoring of water and energy consumption data can be achieved by collecting data hourly using sensor devices, forming a dataset containing timestamps and specific consumption values. For instance, in a monitoring session, water consumption was 5.2 tons per ton of fabric processed, and energy consumption was 120 kWh per ton of fabric processed. This data will be integrated into a resource consumption dataset for subsequent analysis. For example, in the implementation of the benchmark comparison method, the above resource consumption dataset can be compared with the benchmark values ​​of traditional chemical pretreatment. Assuming the benchmark for water consumption in traditional processes is 8 tons per ton of fabric, and the benchmark for energy consumption is 150 kWh per ton of fabric, the comparison calculation shows a water saving rate of 35% and an energy saving rate of 20%. This saving rate reflects the advantage of enzyme treatment in resource utilization. If the saving rate exceeds a preset threshold, such as 15%, further trend prediction analysis is triggered. For example, when using linear regression algorithms to predict resource consumption trends, the changing patterns of water and energy consumption data from the past 30 days can be analyzed. Assuming the prediction results show that the next 7... Water consumption may gradually rise to 5.5 tons per ton of fabric, while energy consumption remains stable. This trend will provide a basis for subsequent environmental benefit assessments and help determine the sustainability of resource utilization. For example, when performing cluster analysis based on wastewater neutralization data, indicators such as wastewater pH and COD concentration can be correlated with consumption trends. Assuming a batch of wastewater has a pH of 7.2 and a COD concentration of 200 mg / L, a clustering algorithm can classify it as a medium-level environmental benefit indicator. This indicator reflects the process's performance in environmental protection. For instance, when using a weighted average method to integrate resource saving rate and environmental benefit indicators, a weight of 0.6 for the saving rate and 0.4 for the environmental benefit can be set. Assuming a saving rate of 30% and an environmental benefit score of 70, the final comprehensive treatment effect score would be 46. If the score is below the preset threshold of 50, further analysis of outliers is needed to optimize the process. For example, when using a decision tree algorithm to analyze outliers, focus can be placed on instances where water consumption suddenly rises to 6 tons per ton of fabric. The data showed that the problem might be related to excessively high equipment cleaning frequency. The proposed optimization parameters could be to reduce the cleaning frequency or adjust the water consumption for cleaning, thereby reducing unnecessary resource waste. For example, when updating the processing strategy of the resource consumption analysis module, the cleaning frequency could be adjusted based on these parameters, changing it from once a day to once every two days, and a new resource consumption dataset could be generated. Assuming that the water consumption drops to 5.0 tons per ton of fabric after the adjustment, it shows a significant resource saving effect and also provides data support for subsequent process optimization. This method helps to continuously improve the process flow and enhance overall efficiency.

[0039] S8. Based on the comprehensive treatment effect evaluation, establish an adaptive adjustment mechanism for process parameters. When processing a new batch of fabric, automatically match historical optimized templates with similar characteristics, and obtain a stable one-step pretreatment effect by fine-tuning the enzyme ratio and reaction conditions.

[0040] By analyzing the characteristic data of the new batch of fabric, optimized template data similar to the current batch's characteristics are obtained from a pre-established historical template library to determine the preliminary process parameter configuration scheme. Based on the obtained optimized template data, a support vector machine model is used to classify the characteristics of the new batch of fabric and determine whether the similarity to historical templates reaches a preset threshold. If the similarity is insufficient, suboptimal template data is extracted from the historical template library to obtain a more suitable preliminary parameter configuration. For the preliminary parameter configuration, the initial treatment data of the new batch of fabric is obtained. Combined with the enzyme ratio and reaction conditions in the historical templates, the differences between historical data and current data are compared and analyzed to determine the range of process parameters that need to be fine-tuned. Based on the determined fine-tuning range, the enzyme ratio and reaction conditions are dynamically adjusted. If the deviation between the current processing data and the target pretreatment effect exceeds a preset threshold, the parameter values ​​are iteratively calculated to obtain an optimized combination of enzyme ratio and reaction conditions. Using this optimized parameter combination, a one-step pretreatment operation is performed on a new batch of fabric, acquiring real-time processing effect data to determine if the standard for stable effect has been met. If not, the current deviation data is recorded and fed back to the adjustment mechanism module. Based on the feedback deviation data, combined with the adaptive adjustment mechanism, the causes of the deviation are re-analyzed and the fine-tuning strategy is updated. Parameter correction is performed using similar feature data from the historical template library to determine the final process parameter configuration scheme. After obtaining the final configuration scheme, for subsequent batches of fabric, the optimized data in the historical template library is updated, and the automatic matching module continuously learns from similar features to obtain a more accurate matching and adjustment basis.

[0041] In one possible implementation, by analyzing the characteristic data of a new batch of fabric, an optimized template is obtained from a historical template library to ensure the accuracy of process parameters. For example, for characteristic data such as fiber length, density, and hygroscopicity of a batch of cotton fabric, the system extracts template data matching these characteristics from the historical template library to initially determine process parameters of 2.5 g / L enzyme dosage, 45 minutes reaction time, and 50°C. This method, by reusing historical data, can quickly generate reliable initial configurations and reduce experimental costs. For example, when using a support vector machine model to classify fabric features, the system calculates the similarity between the new batch and historical templates based on feature vectors such as fiber length and density. If the similarity is lower than a preset threshold of 80%, a suboptimal template is extracted from the library, such as a template with an enzyme dosage adjusted to 2.7 g / L and a reaction time of 50 minutes. This classification method, through data-driven judgment, ensures a higher degree of matching in parameter configuration and reduces processing failures caused by feature deviations. Specifically, for fine-tuning the initial parameter configuration, the system will compare the initial treatment data of the new batch of fabric with the differences in historical templates. For example, if the whiteness value of the fabric after initial treatment is 5% lower than the target value, by analyzing the whiteness data of the enzyme ratio in the historical template when it is 2.5 g / L, it will be determined that the enzyme dosage needs to be increased by 0.2 g / L, and the reaction time should be extended by 5 minutes.

[0042] This fine-tuning, based on data comparison, can accurately pinpoint the range of parameters requiring adjustment, improving the stability of the treatment effect. In one possible implementation, when dynamically adjusting the enzyme ratio and reaction conditions, if the whiteness deviation still exceeds 3%, the system iteratively calculates and attempts to gradually increase the enzyme dosage from 2.7 g / L to 2.9 g / L, increasing by 0.1 g / L each time, while monitoring the reaction temperature change. This method, through small-step iterations, gradually approaches the target effect, avoiding the waste of resources caused by large adjustments. For example, after the one-step pretreatment operation is completed, the whiteness and softness data of the fabric are monitored in real time. If the whiteness does not meet the standard, the deviation data, such as a whiteness value that is 4% lower, will be recorded and fed back to the adjustment mechanism module. This real-time feedback mechanism can promptly detect problems and ensure that the parameters for subsequent batches are more optimized. Specifically, the adaptive adjustment mechanism analyzes the causes of deviations, such as insufficient enzyme activity or too short a reaction time, and combines similar feature data from the historical template library to correct the parameters to an enzyme dosage of 3.0 g / L and a reaction time of 55 minutes. This correction method continuously optimizes the accuracy of parameter configuration through data accumulation and learning. In one possible implementation, when updating the historical template library, the system stores the final parameter configurations, such as enzyme dosage of 3.0 g / L and reaction time of 55 minutes, into the library. It also continuously learns the characteristics of new batches through an automatic matching module. For example, for subsequent batches of cotton fabrics, the system automatically recommends more precise enzyme ratios and reaction conditions based on the updated template library. This continuous learning mechanism can improve the coverage and matching efficiency of the template library, providing a reliable basis for long-term production.

[0043] Those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A one-step pretreatment method for fabrics based on bio-enzymes, characterized in that, The method includes: S1. Obtain data on the composition of sizing agents and the distribution of oil and grease impurities on the fabric surface. Detect the optimal ratio of cellulase activity and protease activity using spectral analysis technology. Determine the initial set value of the biological enzyme concentration based on the fabric density and thickness information. S2. The initial set value is processed using a bio-enzyme optimization algorithm. If the sizing content of the fabric exceeds the preset threshold, the proportion of cellulase is increased. If the oil content exceeds the preset threshold, the proportion of lipase is increased to obtain a compound enzyme formula combination for the current fabric characteristics. S3. Establish a temperature and time control model for the enzymatic hydrolysis reaction based on the compound enzyme formula combination. Determine the reaction process status by real-time monitoring of the enzyme activity change curve. Start recording dynamic data of desizing rate and refining effect after the enzyme activity reaches its peak. S4. The pH value change trend in the dynamic data is analyzed using a wastewater neutralization control algorithm. If the pH value remains within the neutral range, the enzymatic hydrolysis treatment continues. If the pH value deviates from the neutral range, the amount of buffer solution added is adjusted to obtain a stable neutral wastewater output. S5. Process the surface characteristic parameters of the enzymatically hydrolyzed fabric using a fabric quality assessment algorithm to obtain quantitative indicators of capillary effect, whiteness, and strength retention rate. Determine the pass / fail status of the current treatment effect based on the degree of deviation between the quantitative indicators and the standard values. S6. If the qualified status shows that the quality indicators do not meet the standards, return to adjust the activity ratio of each component in the compound enzyme formula. If the quality indicators meet the standards, record the current process parameters as an optimization template, and at the same time, collect the water consumption and energy consumption data during the processing. S7. The water consumption and energy consumption data are processed by the resource consumption analysis module. The saving rate is calculated by comparing the resource consumption benchmark value of traditional chemical pretreatment. The environmental benefit index is evaluated based on the degree of neutralization of wastewater to obtain a comprehensive treatment effect evaluation. S8. Based on the comprehensive treatment effect evaluation, establish an adaptive adjustment mechanism for process parameters. When processing a new batch of fabric, automatically match historical optimized templates with similar characteristics, and obtain a stable one-step pretreatment effect by fine-tuning the enzyme ratio and reaction conditions.

2. The one-step pretreatment method for fabrics based on bio-enzymes according to claim 1, characterized in that, Step S1 includes: Data on the distribution of sizing components and oil impurities on the fabric surface were obtained by using spectral analysis technology. The spatial distribution map of the chemical components on the fabric surface was obtained by using Fourier transform infrared spectroscopy. Concentration characteristics of slurry components and oil impurities were extracted from the spatial distribution map, and the content ratio of the main components was determined by principal component analysis algorithm. The activities of cellulase and protease were determined based on their content ratios, and enzyme activity data were obtained using ultraviolet-visible spectrophotometry. If the enzyme activity data deviates from the preset threshold range, the ratio of cellulase and protease is adjusted by linear regression algorithm to determine the optimal ratio. Based on the fabric density and thickness data, the initial concentration setting value of the bio-enzyme is calculated using a preset mapping function; The actual amount of biological enzyme applied was adjusted from the initial concentration setting value, and real-time spectral monitoring technology was used to obtain the trend of changes in the fabric surface after enzyme treatment; The treatment effect is judged based on the trend of change. If the residual slurry components or oil impurities exceed the preset threshold, the concentration of biological enzymes is adjusted by iterative optimization algorithm to obtain the final treatment parameters.

3. The one-step pretreatment method for fabrics based on bio-enzymes according to claim 1, characterized in that, Step S2 includes: Initial characteristic data of fabric samples are obtained, and the sizing and oil content are detected by spectral analysis to obtain fabric characteristic parameters; If the slurry content exceeds the preset threshold, the cellulase addition ratio is predicted by a linear regression algorithm, and the cellulase adjustment amount is determined by combining the initial characteristic data. If the oil content exceeds the preset threshold, the support vector machine algorithm is used to analyze the oil characteristics, and the amount of lipase to be adjusted is determined in combination with the initial characteristic data. Based on the adjustment amounts of cellulase and lipase, the initial proportions of the compound enzyme formulation are calculated using a weighted average method to obtain the preliminary enzyme formulation combination. A genetic algorithm was used to optimize the initial enzyme formulation combination, and the proportion of each enzyme was iteratively adjusted to obtain the optimized compound enzyme formulation. The optimized compound enzyme formula was verified by simulation technology, and the removal rates of sizing and grease from the treated fabric were analyzed to determine the formula's effectiveness. If the removal rate does not meet the preset standard, the process returns to the step of adjusting the enzyme ratio, re-optimizes the formula, and obtains the final compound enzyme formula.

4. The one-step pretreatment method for fabrics based on bio-enzymes according to claim 1, characterized in that, Step S3 includes: By constructing a preset temperature and time control model, the initial parameter data of the enzymatic hydrolysis reaction are obtained, and the parameters are calibrated according to the characteristics of the compound enzyme formulation to obtain the preliminary reaction condition configuration. Based on the initial reaction conditions, data on changes in enzyme activity are collected in real time, and sensor technology is used to monitor the fluctuations of the change curve to determine whether the enzyme activity is close to its peak state. If the enzyme activity change curve shows that it is close to the peak state, the peak recording mechanism is triggered to obtain the corresponding time point and temperature data and determine whether the peak is stable. By collecting the dynamic changes in desizing rate data after the peak value stabilizes, and comparing them with preset thresholds, a preliminary evaluation result of the desizing effect is obtained. Based on the preliminary evaluation results of the desizing effect, the dynamic data of the refining effect are recorded simultaneously, and the fluctuation of the refining effect is analyzed in real time to determine whether the effect meets the expected standard. If the analysis results of the refining effect do not meet the expected standards, adjust the temperature control and time control parameters, re-acquire the enzymatic hydrolysis reaction operation data, and judge whether the adjusted effect meets the requirements. By adjusting the effect data, the final optimized configuration of the enzymatic hydrolysis reaction is generated, and the parameters are saved according to the characteristics of the compound enzyme formula, resulting in a complete record of the reaction process.

5. A one-step pretreatment method for fabrics based on bio-enzymes according to claim 1, 2, 3, or 4, characterized in that, The S4 step includes: Dynamic data of wastewater pH value are acquired in real time using sensors to generate a time series dataset. The moving average algorithm was used to analyze the time series dataset to obtain the trend of pH value changes; If the trend shows that the pH value is in the neutral range, the enzymatic hydrolysis parameters are kept constant by the control module, and an enzymatic hydrolysis instruction is generated. If the trend shows that the pH value deviates from the neutral range, the amount of buffer solution to be added is predicted by a linear regression algorithm to obtain the buffer solution adjustment parameters; Based on the buffer adjustment parameters, the amount of buffer added is adjusted through the flow controller to generate adjusted wastewater pH data. The pH value of the adjusted wastewater was reacquired by the sensor to verify whether it was within the neutral range, and the verification results were obtained. Based on the verification results, the pH analysis and adjustment steps were repeated cyclically to generate a stable neutral wastewater output.

6. The one-step pretreatment method for fabrics based on bio-enzymes according to claim 5, characterized in that, Step S5 includes: Digital images of the fabric surface after enzymatic hydrolysis are acquired using an image acquisition device to generate the first image data. The first image data is denoised and edge-enhanced using an image processing algorithm to obtain the second image data. Feature parameters of the fabric surface, including texture roughness and color distribution, are extracted from the second image data to generate a feature parameter set; The feature parameter set is classified by the support vector machine algorithm, and the quantitative indicators of gross value, whiteness value and strength retention rate are calculated to obtain the quantitative indicator set. Based on the deviation between the quantitative index set and the preset standard value, the Euclidean distance algorithm is used to calculate the degree of deviation and generate the deviation value. If the deviation value is less than the preset threshold, the processing effect is judged to be qualified and a qualified label is generated. If the deviation value is greater than or equal to the preset threshold, a non-compliance mark is generated; Based on the qualified or unqualified labels, a fabric quality assessment result is generated to determine the final processing status.

7. The one-step pretreatment method for fabrics based on bio-enzymes according to claim 5, characterized in that, Step S6 includes: If the quality indicators do not meet the standards, the activity data of each component in the compound enzyme formula are obtained, and the correlation between the component activity and the quality indicators is analyzed by linear regression algorithm to obtain an activity ratio adjustment plan. Based on the activity ratio adjustment plan, the proportions of each component in the compound enzyme formula are updated, and the adjusted quality indicators are calculated by simulating the process flow to determine whether they meet the standards. If the adjusted quality indicators meet the standards, the current process parameters, including temperature, pressure and stirring speed, are obtained, and an optimization template is generated by storing them in the database and the template identifier is determined. Process parameters are extracted from the optimized template, and water and energy consumption data during the processing are obtained by combining sensor data. The average value is calculated through the data statistics module to obtain the consumption statistics results. By using time series analysis algorithms to predict trends in consumption statistics, the changing trends of water and energy consumption are generated, and it is determined whether they exceed preset thresholds. If the trend of change exceeds the preset threshold, the process parameters are optimized by the gradient descent algorithm, the optimization template is updated, and the adjusted process parameters are obtained. Based on the adjusted process parameters, update the compound enzyme formulation ratio and re-execute the process flow to obtain new quality indicators and determine whether the standards are continuously met.

8. The one-step pretreatment method for fabrics based on bio-enzymes according to claim 5, characterized in that, Step S7 includes: The data processing module extracts real-time monitoring values ​​from water consumption data and energy consumption data to obtain a resource consumption dataset. By comparing the resource consumption dataset with the preset traditional chemical pretreatment resource consumption benchmark value using the benchmark comparison method, the resource saving rate is calculated. If the resource saving rate is greater than the preset threshold, the linear regression algorithm is used to predict the resource consumption trend and obtain the consumption change trend. Based on the consumption change trend and combined with the wastewater neutralization data, a cluster analysis algorithm was used to classify the environmental benefit level and obtain the environmental benefit index. By using a weighted average method, resource conservation rate and environmental benefit indicators are integrated to generate a comprehensive treatment effect score; If the overall processing effect score is lower than the preset threshold, the decision tree algorithm is used to analyze the outliers in the water consumption and energy consumption data to obtain the optimization adjustment parameters. Based on the optimized and adjusted parameters, the processing strategy of the resource consumption analysis module is updated, and a new resource consumption dataset is generated.

9. The one-step pretreatment method for fabrics based on bio-enzymes according to claim 8, characterized in that, Step S8 includes: By analyzing the characteristic data of the new batch of fabrics, optimized template data with similar characteristics to the current batch are obtained from the pre-established historical template library to determine the preliminary process parameter configuration scheme. Based on the obtained optimized template data, the support vector machine model is used to classify the features of the new batch of fabrics and determine whether the similarity features with the historical templates reach the preset threshold. If the similarity is insufficient, the suboptimal template data is extracted from the historical template library to obtain a more matching preliminary parameter configuration.

10. The one-step pretreatment method for fabrics based on bio-enzymes according to claim 9, characterized in that, In step S8: For the initial parameter configuration, the initial treatment data of the new batch of fabric is obtained. Combined with the enzyme ratio and reaction conditions in the historical template, the range of process parameters that need to be fine-tuned is determined by comparing and analyzing the differences between the historical data and the current data. Based on the determined fine-tuning range, the enzyme ratio and reaction conditions are dynamically adjusted. If the deviation between the current processing data and the target pretreatment effect exceeds the preset threshold, the parameter values ​​are adjusted through iterative calculation to obtain the optimized enzyme ratio and reaction condition combination. By optimizing the parameter combination, a one-step pretreatment operation is performed on the new batch of fabrics to obtain real-time processing effect data and determine whether the standard of stable effect has been met. If not, the current deviation data is recorded and fed back to the adjustment mechanism module. Based on the feedback deviation data, combined with the adaptive adjustment mechanism, the causes of deviation are re-analyzed and the fine-tuning strategy is updated. Parameter correction is performed using similar feature data from the historical template library to determine the final process parameter configuration scheme. After obtaining the final configuration scheme, for subsequent batches of fabric processing, the optimized data in the historical template library is updated, and the automatic matching module is used to continuously learn similar features to obtain a more accurate basis for matching and adjustment.

Images