Method for preparing regenerated fibers by removing oil stains from waste textile yarns

Abstract

The invention provides a method for preparing regenerated fibers by removing oil stains from textile waste yarns, and relates to the technical field of yarn processing and cleaning, and the method comprises the following steps: collecting material parameters and oil stain parameters of waste yarns as original parameters, and constructing a characteristic parameter set; constructing a case library, and storing a characteristic parameter set and an effective process parameter package of a historical successful case; performing similarity matching on the characteristic parameter set of the current to-be-processed yarn and the case library, and selecting a process parameter packet of an optimal historical case as a reference process parameter packet; performing cleaning according to the reference process parameter packet and detecting the residual oil rate, if the standard is not reached, performing parameter fine adjustment according to the deviation condition of the residual oil rate, and repeating until the standard is reached; and performing optimization management on the case library, and eliminating repeated cases. According to the method, through case matching and parameter self-adaptive adjustment, accurate and efficient decontamination of yarns with different characteristics is achieved, and the quality of regenerated fibers and the process stability are improved.

Description

Technical Field

[0001] This invention relates to the field of yarn processing and cleaning technology, specifically a method for removing oil stains from waste textile yarns to prepare recycled fibers. Background Technology

[0002] Textile recycling is a crucial link in the sustainable cycle of resources. The cleaning and regeneration of waste yarn directly impacts the quality and value of recycled fibers. A major technical bottleneck in the preparation of recycled fibers is the complete removal of stubborn oil stains such as high-viscosity mineral oil and spinning agents adhering to the yarn. Residual oil stains significantly degrade the fiber's openness, spinnability, and dyeing uniformity, resulting in insufficient strength and uneven yarn, making it difficult to apply to mid-to-high-end textiles and affecting the economic benefits of recycling. Existing cleaning processes generally rely on fixed parameter combinations, lacking adaptability to material differences. They cannot accurately match complex conditions with different fiber ratios, yarn counts, initial oil content, and oil stain distribution uniformity, leading to large fluctuations in treatment results. When treatment fails to meet standards, production lines often rely on worker experience for trial and error adjustments, lacking a systematic and quantitative parameter iteration mechanism. This results in low adjustment efficiency and uncontrollable effects. Furthermore, many historical success stories have not been effectively integrated into reusable process knowledge, requiring repeated experimentation each time waste yarn is processed. This hinders the continuous optimization of the overall process level and restricts the development of high-value recycling of waste textiles.

[0003] The prior art, disclosed in CN109056334A, discloses an easy-to-clean finishing agent for blended fabrics and its preparation method. This method includes: heating a polyurethane emulsion to 80-90°C, adding a pre-emulsion and potassium persulfate dropwise, continuing the reflux reaction for 2-3 hours after the addition is complete, cooling to room temperature, adjusting to neutral, adding water for dilution, sieving, stirring and mixing evenly, and then cooling to room temperature to obtain the easy-to-clean finishing agent for blended fabrics. The easy-to-clean finishing agent of this application is environmentally friendly and harmless to human health. It makes blended fabrics less prone to oil stains, and even if stains do occur, they are easy to remove, exhibiting excellent easy-to-clean properties.

[0004] However, the existing technologies mentioned above use fixed cleaning process parameters, which lack the ability to adapt to different material characteristics and oil stain conditions, resulting in large fluctuations in treatment effects. When the treatment fails to meet the standards, there is an over-reliance on the operator's experience for trial and error adjustments, lacking a systematic and quantitative parameter optimization mechanism, which makes the adjustment process inefficient and the results uncontrollable. At the same time, the successful cases accumulated in the production process have not formed a reusable process knowledge system. Each treatment requires the re-exploration of parameter combinations, resulting in a waste of technical experience and restricting the continuous improvement of the process level and the high-value recycling of waste yarn.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to provide a method for removing oil stains from waste textile yarns to prepare recycled fibers, thereby solving the problems mentioned in the background art. This invention, by constructing a case library and employing a similarity matching mechanism, can adaptively select the optimal process parameters based on the specific characteristics of each batch of waste yarns, overcoming the shortcomings of traditional fixed-parameter processes that suffer from poor adaptability to different materials and unstable treatment effects. By establishing a quantitative parameter iterative adjustment mechanism, the system can automatically fine-tune when processing fails to meet standards, effectively solving the problems of low adjustment efficiency and uncontrollable effects caused by relying on worker experience and trial and error. Simultaneously, the system transforms each successful processing case into reusable process knowledge, realizing the systematic accumulation and optimization of historical experience, avoiding repeated trial and error, and significantly improving the stability of the process level.

[0007] To achieve the above objectives, the present invention provides the following technical solution: A method for removing oil stains from waste textile yarns to prepare recycled fibers, comprising the following steps: S1: Collect the material parameters and oil stain parameters of waste yarn as raw parameters, and preprocess the collected raw parameters to construct a feature parameter set for subsequent matching analysis; S2: Build a case library, which associates and stores the characteristic parameter set corresponding to each waste yarn treatment case that has achieved the treatment effect in history with the effective process parameter package used in the end, forming a continuously growing successful case library; S3: Compare the current set of feature parameters of the waste yarn to be processed with the set of feature parameters of each historical case in the case library, and select the process parameter package of the historical case with the highest similarity as the benchmark process parameter package for the current cleaning task. S4: Using the baseline process parameter package as the initial setting, execute the cleaning process and detect the actual residual oil rate of the recycled fiber after cleaning. Compare the actual residual oil rate with the preset residual oil rate. When the actual residual oil rate is less than or equal to the preset residual oil rate, the cleaning is qualified. When the actual residual oil rate is greater than the preset residual oil rate, it is judged as unqualified. If it is unqualified, the parameters in the baseline process parameter package are fine-tuned one by one according to the deviation between the actual residual oil rate and the preset residual oil rate. For the characteristics of different types of process parameters, the corresponding adjustment strategy is adopted, and the fine-tuning, processing and verification are repeated until the verification result meets the standard. S5: Optimize the management of historical cases stored in the case library, eliminate duplicate cases, and improve the representativeness of the case library.

[0008] Furthermore, the material parameters include fiber ratio and yarn count, and the oil stain parameters include initial oil content and oil stain distribution uniformity. The method used to preprocess the feature parameter set includes: detecting outliers and duplicate data for material parameters and oil stain parameters; using statistical methods to identify and delete outlier data and duplicate records that exceed a set threshold; and filling in missing values ​​using the mean of similar parameters. Data normalization uses the min-max normalization method to scale various parameters to the range of [0,1]. The specific formula is as follows:

[0009] in, These are the normalized parameter values. These are the original parameter values. and These are the maximum and minimum values ​​of the same type of parameter, respectively.

[0010] Furthermore, the method for constructing the case library is as follows: the case library is stored in the form of a structured database, and each case entry contains at least one standardized set of feature parameters, as well as a uniquely corresponding package of process parameters that has been verified as effective in practice; The effective process parameters include cleaning agent concentration, cleaning temperature, cleaning time, and mechanical stirring rate.

[0011] Furthermore, the specific method for comparing the feature parameter set of the current yarn to be processed with the feature parameter set of each historical case in the case library is as follows: The similarity between the feature parameter set and the feature parameter sets of historical cases is calculated using the following formula:

[0012] in, The overall similarity between the current waste yarn to be processed and historical cases; , , , These represent the normalized values ​​of the fiber ratio, yarn count, initial oil content, and oil stain distribution uniformity of the current material, respectively. , , , Representing historical cases respectively The normalized value of the corresponding feature; , , , These are weighting coefficients for fiber ratio, yarn count, initial oil content, and oil stain distribution uniformity, respectively. These weighting coefficients are based on the degree of influence of each characteristic on the cleaning effect. , , , The values ​​of all values ​​are in the interval [0,1], and the sum of all weight coefficients is 1, that is... To ensure consistency in similarity calculations; The formula calculates the overall similarity. The value range is [0,1], and the system selects... The process parameter package corresponding to the historical case with the largest value is used as the benchmark process parameter package.

[0013] Furthermore, the specific method for comparing the actual residual oil rate with the preset residual oil rate is as follows: After cleaning using the standard process parameter package, the actual residual oil content of the yarn was measured. For the actual residual oil rate With preset residual oil rate Compare: when ≤ Once the yarn is deemed to have met the standards, it will proceed to the recycled fiber preparation process, and the characteristic parameter set and process parameter package of this case will be stored as a new case in the case library. when > The baseline process parameter package is fine-tuned based on the deviation between the actual residual oil rate and the preset residual oil rate.

[0014] Furthermore, the specific method for determining the deviation between the actual residual oil rate and the preset residual oil rate is as follows: The formula used to calculate the ratio of the actual residual oil rate to the preset residual oil rate is as follows:

[0015] According to the difference ratio Determine the number of adjustments , To The integer value after rounding up.

[0016] Furthermore, the specific methods for adopting corresponding adjustment strategies for different types of process parameters are as follows: linear parameters This includes cleaning time and mechanical stirring rate, which are adjusted by linearly superimposing them with the current values. proportional parameters This includes the cleaning temperature and cleaning agent concentration, which are adjusted by scaling the current values ​​proportionally.

[0017] Furthermore, the formula used to fine-tune each parameter in the baseline process parameter package is as follows: For any linear parameter Its adjustment formula is:

[0018] in, This linear parameter was before this round of adjustments. The value; This is the linear parameter after this round of adjustments. The new value; The preset fixed adjustment step size for this parameter; For any proportional parameter The adjustment formula is:

[0019] in, This specific ratio parameter was in place prior to this round of adjustments. The value; This is the specific ratio parameter after this round of adjustments. The new value; The preset proportional adjustment coefficient for this parameter.

[0020] Furthermore, the specific steps for repeatedly performing fine-tuning, processing, and verification are as follows: Based on the ratio of the actual residual oil rate to the preset residual oil rate Determine the number of adjustments required. ; Based on the number of adjustments After fine-tuning each parameter in the baseline process parameter package, a new process parameter package is generated. The cleaning process was performed using a new set of process parameters, and the actual residual oil content of the regenerated fibers was retested after completion. ; The actual residual oil rate in this round With preset residual oil rate A comparison is made; if the verification results meet the standards, the cleaning process ends; if the verification results do not meet the standards, the process parameter package used and the corresponding actual residual oil rate are compared. As a new baseline state, and based on the new gap ratio, a new number of adjustments is determined, and then fine-tuning, processing and verification are repeated until the residual oil rate meets the standard.

[0021] Furthermore, the specific method for eliminating duplicate cases is as follows: Calculate the similarity between the feature parameter sets of any two cases in the case study. For cases with a similarity of more than 99%, further compare the core parameters in their process parameter packages. The core parameters include cleaning agent concentration and cleaning temperature. When the absolute difference in cleaning agent concentration between two cases is less than 0.5% and the absolute difference in cleaning temperature is no more than 2 degrees, they are determined to be duplicate cases and deleted from the list. Only the single case with the lowest final residual oil rate is retained.

[0022] Compared with the prior art, the beneficial effects of the present invention are: The method for removing oil stains from waste textile yarns to prepare recycled fibers provided by this invention has the following beneficial effects: By constructing a process parameter matching mechanism based on historical successful cases, this invention can intelligently recommend and dynamically adjust the cleaning process according to the specific material and oil stain characteristics of the waste yarns, significantly improving the accuracy of oil stain removal and the consistency of recycled fiber quality, and effectively solving the problem of large fluctuations in the treatment effect of traditional fixed parameter processes; This method greatly reduces the dependence on manual experience in production, and quickly achieves processing standards through a systematic parameter fine-tuning and verification process, improving the efficiency of production line debugging and operation; At the same time, the system has self-learning capabilities, can continuously accumulate and optimize the process knowledge base, avoid case redundancy, and provide a practical and feasible technical solution for improving the technological level and economic benefits of waste textile recycling. Attached Figure Description

[0023] Figure 1 A schematic diagram of the overall process for removing oil stains from waste textile yarns to prepare recycled fibers; Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0025] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0026] Example: Please see Figure 1 The present invention provides a technical solution: A method for removing oil stains from waste textile yarns to prepare recycled fibers S1: First, material parameters and oil stain parameters of waste yarn are collected as raw parameters. These raw parameters cover the basic physical properties and pollution status information of the yarn to ensure a comprehensive reflection of its actual condition. The collected raw parameters are preprocessed to eliminate outliers and inconsistencies in the data, improving the reliability and usability of the data. Through preprocessing, the raw parameters are integrated and transformed into a standardized set of feature parameters. This set of feature parameters not only retains the key characteristics of the yarn but also has good representativeness and comparability, providing an accurate data foundation for subsequent case matching and process parameter analysis. The material parameters include fiber ratio and yarn count, and the oil stain parameters include initial oil content and oil stain distribution uniformity. The method used to preprocess the feature parameter set includes: detecting outliers and duplicate data for material parameters and oil stain parameters; using statistical methods to identify and delete outlier data and duplicate records that exceed a set threshold; and filling in missing values ​​using the mean of similar parameters. Data normalization uses the min-max normalization method to scale various parameters to the range of [0,1]. The specific formula is as follows:

[0027] in, These are the normalized parameter values. These are the original parameter values. and These are the maximum and minimum values ​​of the same type of parameter, respectively.

[0028] S2: Build a case library, which associates and stores the characteristic parameter set corresponding to each waste yarn treatment case that has achieved the treatment effect in history with the effective process parameter package used in the end, forming a continuously growing successful case library; The method used to build the case library is as follows: the case library is stored in the form of a structured database. Each case entry contains at least one standardized set of feature parameters and a unique corresponding process parameter package that has been verified to be effective in practice. The process parameter package records in detail the various operating parameters that have been actually applied in a specific case and achieved the preset treatment effect. These parameters are all derived from historical successful practices and have repeatability and reliability. The effective process parameters include cleaning agent concentration, cleaning temperature, cleaning time, and mechanical agitation rate. These parameters collectively constitute the core variables affecting the cleaning effect, and the rationality of their value range and combination directly relates to the final residual oil rate control level. Systematically storing and managing these case data provides a reliable data foundation and decision support for the subsequent processing of similar materials.

[0029] S3: The system compares the feature parameter set of the current waste yarn to be processed with the feature parameter sets of each historical case in the case library one by one, and evaluates the degree of matching by calculating the comprehensive similarity between the two. The similarity calculation is based on multiple dimensions of the feature parameter set, using normalized parameter values, and introducing preset weight coefficients to reflect the differences in the impact of each feature on the cleaning effect. After completing the comparison of all historical cases, the system identifies the historical case with the highest comprehensive similarity and uses its associated process parameter package as the benchmark process parameter package for the current cleaning task. This benchmark process parameter package will be used as the initial setting for subsequent cleaning processes. The specific method for comparing the feature parameter set of the current yarn to be processed with the feature parameter set of each historical case in the case library is as follows: The similarity between the feature parameter set and the feature parameter sets of historical cases is calculated using the following formula:

[0030] in, The overall similarity between the current waste yarn to be processed and historical cases; , , , These represent the normalized values ​​of the fiber ratio, yarn count, initial oil content, and oil stain distribution uniformity of the current material, respectively. , , , Representing historical cases respectively The normalized value of the corresponding feature; , , , These are weighting coefficients for fiber ratio, yarn count, initial oil content, and oil stain distribution uniformity, respectively. These weighting coefficients are based on the degree of influence of each characteristic on the cleaning effect. , , , The values ​​of all values ​​are in the interval [0,1], and the sum of all weight coefficients is 1, that is... To ensure consistency in similarity calculations, features with greater influence receive higher weight coefficients. This ensures that key features are prioritized in similarity calculations. These weight coefficients are pre-set based on expert experience. =0.2、 =0.3、 =0.4、 =0.1 The formula calculates the overall similarity. The value range is [0,1], and the system selects... The process parameter package corresponding to the historical case with the largest value is used as the benchmark process parameter package.

[0031] S4: Execute the cleaning process using the baseline process parameter package as the initial setting. After the cleaning process is completed, the actual residual oil rate of the recycled fiber is detected to obtain the actual residual oil rate. This actual residual oil rate is compared with the preset residual oil rate to determine if it meets the preset standard. When the actual residual oil rate meets the standard, the cleaning process terminates, and the yarn is allowed to enter the subsequent recycled fiber preparation process. Simultaneously, the system automatically associates the characteristic parameter set corresponding to this processing task with the finally verified and valid process parameter package, forming a new successful case, which is stored in the case library. When the actual residual oil rate is less than or equal to the preset residual oil rate, the cleaning is considered successful. When the actual residual oil rate is greater than the preset residual oil rate but does not meet the standard, the parameters in the baseline process parameter package are fine-tuned one by one according to the deviation between the actual and preset residual oil rates. During the fine-tuning process, corresponding adjustment strategies are adopted for the characteristics of different types of process parameters. After fine-tuning, the cleaning process is re-executed, and the actual residual oil rate is detected again for verification. If it still does not meet the standard, the above fine-tuning and verification process is repeated until the actual residual oil rate meets the preset requirements. The specific method for comparing the actual residual oil rate with the preset residual oil rate is as follows: After cleaning using the standard process parameter package, the actual residual oil content of the yarn was measured. For the actual residual oil rate With preset residual oil rate Compare: when ≤ Once the yarn is deemed to have met the standards, the cleaning process is terminated, and the process proceeds to the recycled fiber preparation stage. The characteristic parameter set and process parameter package of this case are stored as a new case in the case library. when > If the yarn is deemed substandard, the baseline process parameters are fine-tuned based on the deviation between the actual and preset residual oil rates. It should be noted that the parameter fine-tuning process described in this case is specifically designed to handle situations where the residual oil rate exceeds the standard due to insufficient cleaning intensity. The system will target and enhance the process parameters according to the degree of excess residual oil rate to improve cleaning efficiency.

[0032] The specific method for determining the deviation between the actual residual oil rate and the preset residual oil rate is as follows: The formula used to calculate the ratio of the actual residual oil rate to the preset residual oil rate is as follows:

[0033] According to the difference ratio Determine the number of adjustments , To The integer value after rounding up; in and Inversely proportional and They are directly proportional.

[0034] The specific methods for adopting corresponding adjustment strategies for different types of process parameters are as follows: For linear parameters This includes cleaning time and mechanical stirring rate, which are adjusted by linearly superimposing them with the current values. For proportional parameters This includes the cleaning temperature and cleaning agent concentration, which are adjusted by scaling the current values ​​proportionally.

[0035] The formula used to fine-tune each parameter in the baseline process parameter package is as follows: For any linear parameter Its adjustment formula is:

[0036] in, This linear parameter was before this round of adjustments. The value; This is the linear parameter after this round of adjustments. The new value; The preset fixed adjustment step size for this parameter is based on industrial practice experience, and is specifically as follows: Cleaning time 8 minutes; Mechanical stirring rate 130 revolutions per minute For any proportional parameter The adjustment formula is:

[0037] in, This specific ratio parameter was in place prior to this round of adjustments. The value; This is the specific ratio parameter after this round of adjustments. The new value; The preset proportional adjustment coefficient for this parameter is based on industrial practice experience, and its value is as follows: Cleaning temperature 7%; Cleaning agent concentration 15%.

[0038] The specific steps for repeatedly performing fine-tuning, processing, and verification are as follows: Based on the ratio of the actual residual oil rate to the preset residual oil rate Determine the number of adjustments required. ; Based on the number of adjustments The parameters in the baseline process parameter package are fine-tuned one by one. The fine-tuning process is to make targeted adjustments to each parameter according to its characteristics, thereby generating a new process parameter package. The cleaning process was performed using a new set of process parameters, and the actual residual oil content of the regenerated fibers was retested after completion. ; The actual residual oil rate in this round With preset residual oil rate For comparison, if the verification results meet the standards, the cleaning process ends, and the process proceeds to the regenerated fiber preparation stage. The characteristic parameter set and process parameter package of this case are then stored as a new case in the case library. If the verification results do not meet the standards, the applied process parameter package and the corresponding actual residual oil rate are stored. As a new baseline state, and based on the new gap ratio, a new number of adjustments is determined. Then, fine-tuning, processing, and verification are repeated to form an iterative optimization loop until the residual oil rate reaches the standard. At this point, it is determined that the current cleaning task has been completed, the cleaning process ends, and the process of regenerated fiber preparation begins. The process parameter package that finally reaches the standard for residual oil rate during the cleaning process, along with the characteristic parameter set of the corresponding yarn to be treated, is stored as a new success case.

[0039] S5: Optimize the management of historical cases stored in the case library, eliminate duplicate cases, and improve the representativeness of the case library; The specific method for eliminating duplicate cases is as follows: The similarity between the feature parameter sets of any two cases is calculated to initially screen out potential duplicate cases. For cases with a similarity exceeding 99%, the core parameters in their process parameter packages are further compared. The core parameters include cleaning agent concentration and cleaning temperature. When the absolute difference in cleaning agent concentration between two cases is less than 0.5% and the absolute difference in cleaning temperature does not exceed 2 degrees, they are determined to be duplicate cases and deleted. Only the single case with the lowest final residual oil rate is retained to ensure that each case in the case library has unique reference value and to avoid the impact of case redundancy on subsequent matching efficiency and decision accuracy.

[0040] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0041] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0042] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0043] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for removing oil stains from waste textile yarns to prepare recycled fibers, characterized in that, Includes the following steps: S1: Collect the material parameters and oil stain parameters of waste yarn as raw parameters, and preprocess the collected raw parameters to construct a feature parameter set for subsequent matching analysis; S2: Build a case library, which associates and stores the characteristic parameter set corresponding to each waste yarn treatment case that has achieved the treatment effect in history with the effective process parameter package used in the end, forming a continuously growing successful case library; S3: Compare the current set of feature parameters of the waste yarn to be processed with the set of feature parameters of each historical case in the case library, and select the process parameter package of the historical case with the highest similarity as the benchmark process parameter package for the current cleaning task. S4: Using the baseline process parameter package as the initial setting, execute the cleaning process and detect the actual residual oil rate of the recycled fiber after cleaning. Compare the actual residual oil rate with the preset residual oil rate. When the actual residual oil rate is less than or equal to the preset residual oil rate, the cleaning is qualified. When the actual residual oil rate is greater than the preset residual oil rate, it is judged as unqualified. If it is unqualified, the parameters in the baseline process parameter package are fine-tuned one by one according to the deviation between the actual residual oil rate and the preset residual oil rate. For the characteristics of different types of process parameters, the corresponding adjustment strategy is adopted, and the fine-tuning, processing and verification are repeated until the verification result meets the standard. S5: Optimize the management of historical cases stored in the case library, eliminate duplicate cases, and improve the representativeness of the case library.

2. The method for removing oil stains from waste textile yarns and preparing recycled fibers according to claim 1, characterized in that: The material parameters include fiber ratio and yarn count, and the oil stain parameters include initial oil content and oil stain distribution uniformity. The method used to preprocess the feature parameter set includes: detecting outliers and duplicate data for material parameters and oil stain parameters; using statistical methods to identify and delete outlier data and duplicate records that exceed a set threshold; and filling in missing values ​​using the mean of similar parameters. Data normalization uses the min-max normalization method to scale various parameters to the range of [0,1]. The specific formula is as follows: in, These are the normalized parameter values. These are the original parameter values. and These are the maximum and minimum values ​​of the same type of parameter, respectively.

3. The method for removing oil stains from waste textile yarns and preparing recycled fibers according to claim 1, characterized in that: The method for constructing the case library is as follows: the case library is stored in the form of a structured database, and each case entry contains at least one standardized set of feature parameters, as well as a uniquely corresponding package of process parameters that has been verified as effective in practice; The effective process parameters include cleaning agent concentration, cleaning temperature, cleaning time, and mechanical stirring rate.

4. The method for removing oil stains from waste textile yarns and preparing recycled fibers according to claim 1, characterized in that: The specific method for comparing the feature parameter set of the current yarn to be processed with the feature parameter set of each historical case in the case library is as follows: The similarity between the feature parameter set and the feature parameter sets of historical cases is calculated using the following formula: in, The overall similarity between the current waste yarn to be processed and historical cases; , , , These represent the normalized values ​​of the fiber ratio, yarn count, initial oil content, and oil stain distribution uniformity of the current material, respectively. , , , Representing historical cases respectively The normalized value of the corresponding feature; , , , These are weighting coefficients for fiber ratio, yarn count, initial oil content, and oil stain distribution uniformity, respectively. These weighting coefficients are based on the degree of influence of each characteristic on the cleaning effect. , , , The values ​​of all values ​​are in the interval [0,1], and the sum of all weight coefficients is 1, that is... To ensure consistency in similarity calculations; The formula calculates the overall similarity. The value range is [0,1], and the system selects... The process parameter package corresponding to the historical case with the largest value is used as the benchmark process parameter package.

5. The method for removing oil stains from waste textile yarns and preparing recycled fibers according to claim 1, characterized in that: The specific method for comparing the actual residual oil rate with the preset residual oil rate is as follows: After cleaning using the standard process parameter package, the actual residual oil content of the yarn was measured. For the actual residual oil rate With preset residual oil rate Compare: when ≤ Once the yarn is deemed to have met the standards, it will proceed to the recycled fiber preparation process, and the characteristic parameter set and process parameter package of this case will be stored as a new case in the case library. when > If the yarn is deemed substandard, the baseline process parameters are fine-tuned based on the deviation between the actual residual oil rate and the preset residual oil rate.

6. The method for removing oil stains from waste textile yarns and preparing recycled fibers according to claim 5, characterized in that: The specific method for determining the deviation between the actual residual oil rate and the preset residual oil rate is as follows: The formula used to calculate the ratio of the actual residual oil rate to the preset residual oil rate is as follows: According to the difference ratio Determine the number of adjustments , To The integer value after rounding up.

7. The method for removing oil stains from waste textile yarns and preparing recycled fibers according to claim 6, characterized in that: The specific methods for adopting corresponding adjustment strategies for different types of process parameters are as follows: linear parameters This includes cleaning time and mechanical stirring rate, which are adjusted by linearly superimposing them with the current values. proportional parameters This includes the cleaning temperature and cleaning agent concentration, which are adjusted by scaling the current values ​​proportionally.

8. The method for removing oil stains from waste textile yarns and preparing recycled fibers according to claim 7, characterized in that: The formula used to fine-tune each parameter in the baseline process parameter package is as follows: For any linear parameter Its adjustment formula is: in, This linear parameter was before this round of adjustments. The value; This is the linear parameter after this round of adjustments. The new value; The preset fixed adjustment step size for this parameter; For any proportional parameter Its adjustment formula is: in, This specific ratio parameter was in place prior to this round of adjustments. The value; This is the specific ratio parameter after this round of adjustments. The new value; The preset proportional adjustment coefficient for this parameter.

9. The method for removing oil stains from waste textile yarns and preparing recycled fibers according to claim 8, characterized in that: The specific steps for repeatedly performing fine-tuning, processing, and verification are as follows: Based on the ratio of the actual residual oil rate to the preset residual oil rate Determine the number of adjustments required. ; Based on the number of adjustments After fine-tuning each parameter in the baseline process parameter package, a new process parameter package is generated. The cleaning process was performed using a new set of process parameters, and the actual residual oil content of the regenerated fibers was retested after completion. ; The actual residual oil rate in this round With preset residual oil rate Compare the results, and once the verification results meet the standards, end the cleaning process. If the verification results do not meet the standards, the process parameter package used in this application and the corresponding actual residual oil rate will be used. As a new baseline state, and based on the new gap ratio, a new number of adjustments is determined, and then fine-tuning, processing and verification are repeated until the residual oil rate meets the standard.

10. The method for removing oil stains from waste textile yarns and preparing recycled fibers according to claim 1, characterized in that: The specific method for eliminating duplicate cases is as follows: Calculate the similarity between the feature parameter sets of any two cases in the case study. For cases with a similarity of more than 99%, further compare the core parameters in their process parameter packages. The core parameters include cleaning agent concentration and cleaning temperature. When the absolute difference in cleaning agent concentration between two cases is less than 0.5% and the absolute difference in cleaning temperature is no more than 2 degrees, they are determined to be duplicate cases and deleted. Only the single case with the lowest final residual oil rate is retained.

Images