Intelligent manufacturing method for improving production quality of lining cloth

Abstract

The invention relates to the technical field of lining cloth production and manufacturing, in particular to an intelligent manufacturing method for improving lining cloth production quality, which comprises the following steps: acquiring a lining cloth processing sample and processing control parameters, and dividing according to quality grades to obtain M parameter sets; establishing associated influence indexes of cutting-sewing, sewing-ironing and ironing-whole stack; establishing a quality tolerance competition framework, and setting an energy efficiency balance model; according to the method, the quality grade is predicted in real time, the technical problem that the consistency and stability of the lining cloth quality are difficult to guarantee due to lack of lining cloth processing control parameters with dynamic precision adaptation is solved through model optimization analysis and sending of a regulation and control instruction, accurate control and optimization of production parameters are realized through establishment of correlation influence analysis among the processing parameters, and the production efficiency is improved. The method has the technical effects of ensuring optimal parameter matching among the procedures, reducing the influence of error accumulation of the front procedure on the rear procedure, and ensuring the consistency and stability of the quality of the lining cloth.

Description

Technical Field

[0001] The present invention relates to the technical field related to lining cloth production and manufacturing, and in particular to an intelligent manufacturing method for improving the production quality of lining cloth. Background Art

[0002] As a key auxiliary material in the garment manufacturing industry, the production quality of interlining directly affects the structural stability and wearing comfort of finished garments. The conventional interlining production process relies on empirical model judgment, resulting in unstable quality control. However, with the widespread application of technologies such as the Internet of Things, big data, and artificial intelligence, interlining production is gradually shifting towards intelligence, automation, and digitalization.

[0003] In summary, the prior art has the technical problem of lacking precise and dynamically adaptive lining cloth processing control parameters, making it difficult to ensure the consistency and stability of the lining cloth quality. Summary of the invention

[0004] The present application provides an intelligent manufacturing method for improving the production quality of interlining cloth, aiming to solve the technical problems in the prior art of lacking precise and dynamically adaptive interlining cloth processing control parameters and making it difficult to ensure the consistency and stability of the interlining cloth quality.

[0005] In view of the above problems, the technical solution to implement this application is:

[0006] The present application provides an intelligent manufacturing method for improving the production quality of interlining cloth, wherein the method comprises: obtaining an interlining cloth processing sample and corresponding processing control parameters, wherein the processing control parameters include cutting parameters, sewing parameters, ironing parameters, and stacking parameters;

[0007] According to the interlining quality grade, the interlining processing samples and the corresponding processing control parameters are divided to obtain M processing control parameter sets;

[0008] Based on the M processing control parameter sets, establishing a correlation impact analysis of cutting parameters and sewing parameters, and determining a cutting-sewing correlation impact index;

[0009] Based on the M processing control parameter sets, establishing a correlation influence analysis between sewing parameters and ironing parameters, and determining a sewing-ironing correlation influence index;

[0010] Based on the M processing control parameter sets, establishing the correlation influence analysis between the ironing parameters and the stacking parameters, and determining the ironing-stacking correlation influence index;

[0011] Through the cutting-sewing related impact index, sewing-ironing related impact index, ironing-stacking related impact index, combined with the interlining quality grade, a quality tolerance competition framework is established, based on the processing control parameters, the power consumption distribution and the power consumption utilization rate of each interlining production equipment in different time periods are calculated for feedback adjustment, and a heuristic algorithm is used to set an energy efficiency balanced quality tolerance competition model;

[0012] The real-time control parameters of the lining cloth production line are obtained, and the quality grade of the lining cloth under the current production conditions corresponding to the real-time control parameters is predicted, the lining cloth production quality optimization analysis is performed through the energy efficiency balanced quality tolerance competition model, and control instructions are sent to the lining cloth production line. The production balanced optimization control of the lining cloth product quality and the lining cloth production power consumption is performed with the control instructions.

[0013] In summary, one or more technical solutions provided in this application achieve precise control and optimization of production parameters by establishing correlation influence analysis between various processing parameters, ensure optimal parameter matching between various processes, reduce the impact of accumulated errors in the previous processes on the subsequent processes, and ensure the consistency and stability of the lining cloth quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A schematic flow chart of an intelligent manufacturing method for improving the production quality of lining cloth is provided for this application;

[0015] Figure 2 The present application provides a flow chart of obtaining cutting-sewing correlation influencing indicators in an intelligent manufacturing method for improving the production quality of interlining cloth. DETAILED DESCRIPTION

[0016] The present application is described in detail below with reference to the accompanying drawings. Figure 1 As shown, the present application provides an intelligent manufacturing method for improving the production quality of lining cloth, wherein the method comprises:

[0017] S1: Obtain interlining processing samples and corresponding processing control parameters, wherein the processing control parameters include cutting parameters, sewing parameters, ironing parameters, and folding parameters; S2: Divide the interlining processing samples and corresponding processing control parameters according to interlining quality grades to obtain M processing control parameter sets.

[0018] Based on the use of automated equipment and intelligent control systems corresponding to empirical models in interlining production, long-term monitoring has found that although this has improved production efficiency and product quality to a certain extent, there are still some inherent limitations. For example, although the empirical model is based on long-term production practice, it is often difficult to cope with complex and changeable production environments and material properties. When encountering special process requirements, the empirical model cannot provide accurate and effective control parameters, resulting in product quality fluctuations or low production efficiency.

[0019] In order to overcome the limitations of the intelligent control system corresponding to the empirical model and further improve the production quality of interlining cloth, this application realizes the optimization of the whole process from raw material processing, cutting, sewing, ironing to final stacking and packaging to better adapt to the actual situation of the production process. Specifically, the preparation stage includes clarifying the goal of improving the production quality of interlining cloth, defining the type and range of processing samples to be collected, such as the size and material of the samples; designing data recording forms to ensure that all processing control parameters of the four key links of cutting, sewing, ironing and stacking can be fully collected.

[0020] The data collection stage includes randomly selecting a certain number of interlining processing samples from the actual production line or according to specific standards to ensure that the samples are representative; recording the cutting method (manual / automatic), cutting size (length, width), cutting tolerance, cutting speed, etc. to obtain cutting parameters; recording the type, color, density, sewing needle model, sewing speed, pressure, sewing style, etc. of sewing thread to obtain sewing parameters; recording the ironing temperature, time, pressure, speed, etc. to obtain ironing parameters; recording the finishing method (manual / automatic), folding size, packaging method, etc. to obtain the whole stacking parameters.

[0021] According to GB / T 28465-2024 "Inspection Rules for Garment Interlinings" or other applicable standards, quality inspection and grade classification are performed on the processed samples, and the quality grade of each sample is paired with its corresponding processing control parameter. Then, the processing control parameter data set is divided into M different sets according to the interlining quality grade, and each set represents one or more parameter combinations at similar quality grades, forming the M processing control parameter sets.

[0022] Implement intelligent management of interlining production quality, continuously optimize the production process, and improve product quality and production efficiency.

[0023] S3: Based on the M processing control parameter sets, an association influence analysis between cutting parameters and sewing parameters is established to determine the cutting-sewing association influence index; S4: Based on the M processing control parameter sets, an association influence analysis between sewing parameters and ironing parameters is established to determine the sewing-ironing association influence index; S5: Based on the M processing control parameter sets, an association influence analysis between ironing parameters and folding parameters is established to determine the ironing-folding association influence index.

[0024] Obtain data from M sets of processing control parameters on the production line, including detailed parameters for each link of cutting, sewing, ironing and folding; remove outliers and missing values, unify the formats of data from different sources, and ensure data accuracy and consistency.

[0025] Build a parameter association analysis framework and define specific analysis indicators for the relationship between each process, such as cutting-sewing association impact indicators, sewing-ironing association impact indicators, and ironing-folding association impact indicators.

[0026] Cutting-sewing correlation impact analysis, based on the set of cutting parameters and sewing parameters, subdivides the cutting process and sewing process, sets the monitoring points of cutting size errors, and collects cutting size error data sets; sorts and screens the cutting size error data, sets the error threshold according to the inspection standard, and distinguishes the qualified and unqualified parts of the error data; combines sewing parameters, such as sewing thread density, sewing speed, etc., to analyze the impact of different cutting size errors on sewing effects, such as stitch uniformity, seam strength, etc., and determine the cutting-sewing correlation impact indicators.

[0027] Sewing-ironing correlation impact analysis, similarly, the sewing process is segmented, and the sewing stitch error data set is collected, considering factors such as the type, color, and density of the sewing thread; combined with ironing parameters such as temperature, time, and pressure, the impact of sewing stitch error on the flatness and appearance quality after ironing is evaluated, and the sewing-ironing correlation impact index is determined.

[0028] Analysis of the impact of ironing-stacking correlation: In the ironing process, collect the ironing flatness error data set, pay attention to the impact of ironing temperature, pressure and speed on the fabric; combine the stacking parameters, such as folding size and finishing method, analyze how the ironing effect affects the subsequent folding neatness and packaging aesthetics, and determine the ironing-stacking correlation impact indicators.

[0029] Then, statistical methods or machine learning algorithms, such as regression analysis and neural networks, are used to establish a mathematical model of the above-mentioned correlation effects; heuristic algorithms, such as genetic algorithms and simulated annealing algorithms, are used to optimize the model and find the best parameter combination to maximize production efficiency and product quality.

[0030] In actual applications, it also includes real-time monitoring and feedback adjustment. Further, a real-time monitoring system is deployed on the production line to continuously track the parameters and quality data of each process; based on the model prediction and analysis results, control instructions are automatically or manually issued to adjust the processing parameters in real time to achieve the best production status and quality balance; result verification and iteration, further, production data is regularly analyzed to verify the optimization effect, including the improvement of production efficiency, energy consumption and product quality; based on the verification results, the optimization model and parameter settings are continuously adjusted to form a closed loop of continuous improvement.

[0031] Systematically analyze and optimize each key link of interlining production to improve overall production quality and efficiency.

[0032] S6: Establish a quality tolerance competition framework through the cutting-sewing related influence index, sewing-ironing related influence index, and ironing-stacking related influence index in combination with the interlining quality grade, calculate the power consumption distribution based on the processing control parameters and the power consumption utilization rate of each interlining production equipment in different time periods for feedback adjustment, and use a heuristic algorithm to set an energy efficiency balanced quality tolerance competition model; S7: Obtain the real-time control parameters of the interlining production line, and predict the interlining quality grade under the current production conditions corresponding to the real-time control parameters, perform interlining production quality optimization analysis through the energy efficiency balanced quality tolerance competition model, send control instructions to the interlining production line, and use the control instructions to perform production balanced optimization control of interlining product quality and interlining production power consumption.

[0033] Data integration and model establishment, further, collect and integrate the processing control parameters of cutting, sewing, ironing and folding processes, including cutting size, sewing thread density, ironing temperature, etc.; based on the existing cutting-sewing, sewing-ironing, ironing-folding related influencing indicators, combined with the lining quality grade, establish a mapping relationship between these indicators and actual production conditions; build a quality tolerance competition framework to ensure that the equipment and process can operate most efficiently within the allowable quality fluctuation range; analyze the power consumption of each production equipment in different time periods, calculate the average power consumption and peak power consumption of the equipment, and provide basic data for subsequent optimization.

[0034] Preferably, the heuristic algorithm further selects a suitable heuristic algorithm, such as a genetic algorithm, a simulated annealing algorithm or a particle swarm optimization algorithm, according to the production environment and problem characteristics; according to the selected algorithm, set parameters such as the initial population, crossover rate, and mutation rate to ensure that the algorithm can effectively explore the solution space; use the selected algorithm, combined with the quality tolerance competition framework, to optimize the processing control parameters to achieve the target state of the lowest energy consumption and the most stable quality; verify the model effect through simulation or small-scale experiments, adjust the algorithm parameters according to the feedback results, and perform multiple iterations until a satisfactory effect is achieved.

[0035] Real-time monitoring and prediction. Further, sensors are installed at key nodes of the production line to collect real-time data, such as equipment operating status, material flow speed, energy consumption, etc.; big data technology is used to quickly process real-time data to predict the quality grade of the lining under current production conditions; historical data and current real-time data are combined to use machine learning models to predict production quality and identify potential quality problems in a timely manner.

[0036] Dynamic control and optimization: further, based on the output of the energy efficiency balance quality tolerance competition model, control instructions are automatically generated, and the content of the instructions includes equipment adjustment, process parameter modification, etc.; the control instructions are sent to the control system of the production line in real time, and automatically or manually executed to adjust the equipment operation status and optimize the production process; the production process is continuously monitored, and the instructions are adjusted according to feedback information to ensure that energy consumption is minimized while ensuring product quality; the control effects are regularly evaluated, including improved production efficiency, reduced energy consumption and improved product quality, and the model is further fine-tuned according to the evaluation results.

[0037] Achieve closed-loop management from data integration to real-time optimization control, ensuring that interlining production is efficient and high-quality while achieving optimal energy consumption configuration.

[0038] Furthermore, based on the M processing control parameter sets, an association impact analysis of cutting parameters and sewing parameters is established to determine the cutting-sewing association impact index. The method described in the present application includes:

[0039] Based on the M processing control parameter sets, a plurality of cutting process segments corresponding to the cutting parameters and a plurality of sewing process segments corresponding to the sewing parameters are set;

[0040] Based on the multiple cutting process segments corresponding to the cutting parameters, synchronous monitoring is performed to obtain a cutting size error data set, wherein the cutting size error data set includes multiple cutting size error data subsets, and the multiple cutting process segments correspond to the multiple cutting size error data subsets one by one;

[0041] Based on the cutting size error data set, a sewing effect correlation evaluation is performed in sections in combination with a plurality of sewing process sections corresponding to the sewing parameters to obtain the cutting-sewing correlation impact index.

[0042] Parameter and process segmentation definition: further, extract cutting parameters (such as cutting method, size, tolerance, speed) and sewing parameters (such as thread type, density, needle model, speed, pressure, style) from M processing control parameter sets; according to the actual production process, divide the cutting and sewing processes into multiple segments respectively. For example, the cutting process is divided into automatic cutting segment and manual cutting segment, and the sewing process may be subdivided into flat seam segment, overlock segment, etc., among which each segment should clearly define its corresponding parameter set.

[0043] Implement synchronous monitoring and data collection. Further, install or deploy corresponding size detection equipment, such as laser rangefinders, visual inspection systems, etc., in each cutting process segment to ensure that the cutting size information can be captured in real time; ensure that the monitoring equipment works synchronously with the production line, and record each cutting size error data in real time to form a cutting size error data set. Each data subset corresponds to a specific cutting process segment to ensure accurate data matching.

[0044] Data processing and analysis, further, organizes the collected cutting size error data sets, including data cleaning, removal of outliers, normalization, etc., to ensure the accuracy and availability of the data; sorts them according to the size of the cutting size error, sets the error threshold according to the inspection standard information, and processes the data in segments, such as separating the data subsets whose errors are within the allowable range and the data subsets whose errors exceed the allowable range.

[0045] The correlation impact assessment further combines multiple segments of sewing parameters to analyze the impact of different cutting size errors on sewing effects, involving aspects such as the uniformity, strength, and aesthetics of sewing stitches; statistical methods or machine learning models, such as regression analysis and neural networks, are used to evaluate the specific impact of cutting size errors on sewing effects, thereby determining the cutting-sewing correlation impact index. This index should be able to quantify the degree of impact of the error on the sewing process.

[0046] In actual application, it also includes feeding back the cutting-sewing correlation influencing indicators to the production management system as a basis for optimizing the production process and parameter adjustment; according to the evaluation results, adjusting the cutting parameters and / or sewing parameters to reduce cutting size errors and improve the overall sewing quality. At the same time, the monitoring and analysis processes are continuously optimized to improve the response speed and accuracy of the system.

[0047] The system identifies and solves the correlation problems between cutting and sewing in the production process, and realizes refined management and quality control of intelligent manufacturing.

[0048] Furthermore, if Figure 2 As shown, based on the cutting size error data set, the sewing effect association evaluation is performed in segments in combination with the multiple sewing process segments corresponding to the sewing parameters to obtain the cutting-sewing association impact index. The method described in this application includes:

[0049] Sorting the cropping size error data set from small to large to generate a cropping size error sequence;

[0050] Setting a cutting size error threshold through interlining inspection standard information, and filtering the cutting size error sequence data to obtain cutting size error standard data;

[0051] Based on the cutting size error standard data, a sewing effect correlation evaluation is performed in sections in combination with a plurality of sewing process sections corresponding to the sewing parameters to obtain the cutting-sewing correlation impact index.

[0052] Dataset preparation and sorting,Further, collect the cutting size error data set, collect the size error data generated by all cutting processes on the production line,,including length and width deviations, etc.; sort the collected cutting size error data,according to the error value from small to large, to form a cutting size error sequence,which is helpful for the subsequent segmented analysis and threshold setting of,the error.

[0053] Set and apply cutting size error thresholds. Further, refer to GB / T 28465-2024 "Inspection Rules for Clothing Interlinings" to determine the maximum allowable error range of cutting sizes. According to the inspection standards, set specific cutting size error threshold values ​​as the limit for measuring whether the cutting quality meets the standards. According to the set error thresholds, filter the cutting size error sequence, remove outliers that exceed the threshold, retain data that meet the standards, and form a cutting size error standard data set to ensure that subsequent analysis is based on qualified cutting size data.

[0054] Sewing effect correlation evaluation, further, for the sewing process, according to the parameters such as sewing thread type, needle model, sewing speed, pressure, etc., the sewing process is divided into multiple process segments, each segment represents one or several specific sewing condition combinations; design an evaluation model or use statistical analysis methods, such as regression analysis, correlation analysis, etc., to analyze the relationship between the cutting size error standard data and each sewing process segment, considering how the cutting size error affects the uniformity of the sewing stitches, stitching strength, fabric alignment, etc.; through the model or analysis method, quantify the specific impact of the cutting size error on the sewing effect, form a cutting-sewing correlation impact index, and reflect the direct or indirect effect of the cutting error on the sewing quality.

[0055] In actual application, it also includes, based on the cutting-sewing correlation influence indicators, identifying which cutting size error ranges have the greatest impact on sewing quality, and providing direction for process improvement; feeding back the analysis results to technical personnel to guide the adjustment of cutting equipment parameters or sewing processes to reduce adverse effects and improve overall product quality; establishing a continuous monitoring mechanism to ensure that as production conditions change, the cutting-sewing correlation influence indicators always remain in the optimal state, thereby achieving dynamic optimization of the production process.

[0056] Scientifically analyze the interaction between cutting and sewing, improve the manufacturing process in a targeted manner, and ultimately improve the production quality and efficiency of interlinings.

[0057] Furthermore, the cutting size error threshold is set by using the lining cloth inspection standard information, and the method of the present application further includes:

[0058] Calculating nine-tenths of a cropping size error threshold, and segmenting the cropping size error sequence to obtain a first cropping size error sequence segment and a second cropping size error sequence segment, wherein each cropping size error in the first cropping size error sequence segment satisfies nine-tenths of the cropping size error threshold, and each cropping size error in the second cropping size error sequence segment does not satisfy nine-tenths of the cropping size error threshold;

[0059] Based on the first cutting size error sequence segmentation, combined with the multiple sewing process segments corresponding to the sewing parameters, a sewing effect correlation evaluation is performed to obtain a first cutting-sewing correlation influence index;

[0060] Based on the second cutting size error sequence segmentation, combined with the multiple sewing process segments corresponding to the sewing parameters, a sewing effect correlation evaluation is performed to obtain a second cutting-sewing correlation influence index;

[0061] A similarity comparison is performed on the first cutting-sewing association influence index and the second cutting-sewing association influence index. If the similarity comparison passes, nine-tenths of the cutting size error threshold is used to cover the original cutting size error threshold.

[0062] Calculation and segmentation of the cutting size error threshold. Further, refer to the lining inspection standard information in detail, especially GB / T 28465-2024 "Inspection Rules for Clothing Interlinings" to clarify the allowable error range of the cutting size; based on the cutting size error threshold set by the standard, calculate nine-tenths of the threshold value and use it as a temporary reference standard; perform cutting size error sequence segmentation, and segment and intercept the sorted cutting size error sequence to form two sequence segments, the first cutting size error sequence segment contains all error data less than or equal to the newly calculated nine-tenths threshold, and the second cutting size error sequence segment contains all error data greater than the nine-tenths threshold.

[0063] For the evaluation of the associated influence index, further, for the first cutting size error sequence segment, the relationship between each cutting size error data and the corresponding sewing parameters (such as sewing thread density, needle type, etc.) is analyzed; the first cutting-sewing associated influence index is calculated to evaluate the influence of cutting within a smaller error range on the sewing effect; for the second cutting-sewing associated influence evaluation, similarly, the data in the second cutting size error sequence segment is evaluated in association with the sewing parameters, and the second cutting-sewing associated influence index is calculated to reflect the potential influence of a larger cutting size error on the sewing effect.

[0064] Similarity comparison and threshold adjustment. Further, multiple sets of similarity comparison methods (such as Euclidean distance, Pearson correlation coefficient, etc.) are designed to compare the similarity between the first cutting-sewing association influence index and the second cutting-sewing association influence index. If the similarity comparison results show that the impact difference between the two is not large, it means that even under relatively loose cutting size error conditions, the sewing effect is still controllable, and consider adopting a new cutting size error threshold (that is, nine-tenths of the original threshold); if the difference is significant, the original threshold is maintained unchanged.

[0065] In actual application, it also includes, if it is decided to adopt a new cutting size error threshold, updating the control parameters of the production line, adjusting the precision settings of the cutting equipment, and then continuously monitoring the production process, collecting data, verifying the impact of the new cutting size error threshold on the overall production quality and efficiency, and making further fine-tuning when necessary; the entire process should operate as a closed-loop system to ensure continuous feedback from production practice and iterative optimization of cutting and sewing parameters to achieve the best balance between production quality and efficiency.

[0066] Furthermore, the first cutting-sewing association influence index and the second cutting-sewing association influence index are compared for similarity, and the method of the present application further includes:

[0067] According to the production efficiency influencing index, calculating the norm corresponding to the first cutting-sewing associated influencing index and the norm corresponding to the second cutting-sewing associated influencing index, and establishing a first similarity comparison channel;

[0068] According to the process stability index, calculating the norm corresponding to the first cutting-sewing association influence index and the norm corresponding to the second cutting-sewing association influence index, and establishing a second similarity comparison channel;

[0069] According to the material utilization rate index, calculating the norm corresponding to the first cutting-sewing association influence index and the norm corresponding to the second cutting-sewing association influence index, and establishing a third similarity comparison channel;

[0070] The first similarity comparison channel, the second similarity comparison channel, and the third similarity comparison channel are connected to obtain a multidimensional comparison model.

[0071] Define indicators and data preparation, further clarify the impact of changes in cutting size errors on the number of finished product output per unit time, including cutting speed, sewing efficiency, etc., and determine indicators affecting production efficiency; evaluate the pass rate and consistency of sewing, ironing, folding and other processes under different cutting size errors, and determine process stability indicators; calculate the amount of waste under different cutting error levels to evaluate material utilization efficiency and determine material utilization indicators.

[0072] Preferably, the norm is calculated, and further, for the first cutting-sewing associated impact index: the specific impact value on the production efficiency when the cutting size error is within the nine-tenths threshold is quantified to obtain the production efficiency norm; the stability of the process flow within the error range is evaluated, quantified into a numerical value, and used as the process stability norm; the measure of the material saving degree of this error interval is calculated to obtain the material utilization norm.

[0073] For the second cutting-sewing correlation influencing index, the norms of production efficiency, process stability and material utilization are calculated respectively, but this time under the condition that the error is greater than the threshold of nine tenths.

[0074] Constructing similarity comparison channels, including: a first similarity comparison channel, specifically, taking into account the two norms affected by production efficiency, and analyzing the similarity or difference between the two indicators through methods such as Euclidean distance or Pearson correlation coefficient; a second similarity comparison channel, specifically, focusing on process stability indicators, also using norms and selected statistical methods to evaluate the consistency changes of the process affected by cutting size errors; a third similarity comparison channel, specifically, analyzing material utilization indicators, establishing comparisons between norms, and evaluating the impact under new material utilization standards.

[0075] A multidimensional comparison model is established. Further, the three comparison channels, namely the first similarity comparison channel, the second similarity comparison channel and the third similarity comparison channel, are integrated to combine the similarity analysis results of the three single dimensions to form a model in a multidimensional space. , involving matrix operations or multivariate analysis, so as to ensure that all influencing factors are comprehensively considered; through the multidimensional model, the comprehensive impact of different cutting size error thresholds on production efficiency, process stability and material utilization is observed, and the optimal threshold value is identified.

[0076] In the actual application process, it also includes, based on the results of the multidimensional comparison model, if the first cutting-sewing related influence index and the second cutting-sewing related influence index show a high degree of similarity under comprehensive consideration, and the new cutting size error threshold brings positive benefits, then consider adopting the new error threshold; update the production process control parameters, adjust the equipment according to the new cutting size error threshold, and closely monitor the changes in production efficiency, process stability and material utilization rate to ensure that the expected optimization effect is achieved. After that, continue to collect data, evaluate the actual production results, and make adjustments when necessary to ensure continuous improvement and optimization of the production process.

[0077] Furthermore, nine-tenths of the cropping size error threshold is used to cover the original cropping size error threshold, and the method of the present application further includes:

[0078] Calculate one third of the initial cropping size error threshold, and when using nine-tenths of the cropping size error threshold to cover the original cropping size error threshold, simultaneously compare the existing cropping size error threshold with one third of the initial cropping size error threshold;

[0079] If the difference between the existing cropping size error threshold and one third of the initial cropping size error threshold satisfies the critical tolerance constraint, a stop instruction is activated, wherein the stop instruction is used to stop the covering operation corresponding to the original cropping size error threshold being covered by nine-tenths of the cropping size error threshold.

[0080] Adjust the cutting size error threshold and ensure that it is controlled within a reasonable range to avoid excessive relaxation or tightening of the standards. Specifically, clarify the currently set cutting size error threshold as the initial value. For example, assume that the initial error threshold is ±1mm; based on the initial cutting size error threshold, calculate one-third of its value. Taking ±1mm as an example, one-third of it is approximately ±0.33mm.

[0081] In the process of using nine-tenths of the cropping size error threshold to cover the original cropping size error threshold, calculation and comparison must be performed first, and adjustment is not directly implemented for the time being. The difference between the nine-tenths of the cropping size error threshold currently being considered and one-third of the initial error threshold (±0.33 mm) is simultaneously compared. For example, if the nine-tenths error threshold is calculated to be ±0.531441 mm (the sixth use of the nine-tenths of the cropping size error threshold to cover the original cropping size error threshold), the difference between ±0.531441 mm and ±0.33 mm is compared;

[0082] Define a critical tolerance value, such as 0.25mm, as a criterion for whether adjustment is allowed. If the calculated difference (for example, the difference between the absolute value of ±0.531441mm and the absolute value of ±0.33mm is less than or equal to 0.25mm) is less than or equal to this critical value, it indicates that the expansion of the error threshold is acceptable; otherwise, it is considered that the expansion is too large and may lead to quality problems.

[0083] On the contrary, if the difference exceeds the critical tolerance constraint, the stop command is immediately activated to prevent the attempt to adjust the cutting size error threshold to nine-tenths of the original threshold, and maintain it on the existing basis to ensure that product quality is not negatively affected. At the same time, multiple comparisons and decision-making processes are recorded, including the original error threshold, calculated value, comparison results and the decision on whether to implement adjustments, which is of reference significance for subsequent production optimization and standard adjustment. In the process of adjusting the cutting size error threshold, production efficiency and quality control are balanced, achieving a balance between production efficiency and quality assurance.

[0084] Furthermore, based on the M processing control parameter sets, an association influence analysis of sewing parameters and ironing parameters is established to determine the sewing-ironing association influence index. The method of the present application includes:

[0085] Based on the multiple sewing process segments corresponding to the sewing parameters, synchronous monitoring is performed to obtain a sewing stitch error data set, wherein the sewing stitch error data set includes multiple sewing stitch error data subsets, and the multiple sewing process segments correspond to the multiple sewing stitch error data subsets one by one;

[0086] Based on the sewing stitch error data set, the ironing effect correlation evaluation is performed in sections in combination with a plurality of ironing process sections corresponding to the ironing parameters to obtain the sewing-ironing correlation influence index.

[0087] Data preparation and segment definition, further, collect and organize M sets of processing control parameters, especially parameters related to sewing and ironing, to ensure the integrity and accuracy of the data; according to the sewing process, the entire sewing process is subdivided into multiple process segments, such as collar sewing, cuff sewing, side seam sewing, etc. Each segment must have a clear start and end point for synchronous monitoring; similarly, the ironing process is divided into several process segments, such as preheating ironing, initial ironing, fine ironing, etc., to ensure that they correspond to the sewing process segments, which is convenient for subsequent data matching and analysis.

[0088] Synchronous monitoring and data collection. Further, monitoring equipment such as sensors or cameras are deployed at key positions of each sewing and ironing process segment to record relevant data of sewing stitches and ironing effects in real time. The stitch errors generated during the sewing process, such as skipped stitches, broken threads, uneven stitches, etc., are continuously recorded through the monitoring equipment to form a sewing stitch error data set, in which the error data of each sewing process segment constitutes a subset to ensure that the data corresponds to the process segment one by one.

[0089] Data analysis and correlation evaluation,further,; perform statistical analysis on the sewing stitch error data set to identify common error types, frequencies and their relationship with specific sewing parameters (such as sewing thread type, sewing speed, etc.); synchronously record data such as flatness, temperature control, and pressure distribution in the ironing process, and combine them with the sewing stitch error data set for analysis to identify how sewing problems affect the ironing effect, such as ironing wrinkles caused by uneven sewing stitches; use statistical methods or machine learning techniques to analyze the interaction between sewing parameters and ironing parameters, such as whether an increase in sewing thread density will result in the need for a higher ironing temperature to achieve ideal flatness, thereby determining the sewing-ironing correlation influencing indicators.

[0090] The associated influence indicators are determined, and further, the above analysis results are quantified into specific indicators, such as the influence coefficient of sewing stitch error on ironing flatness, the dependence index of sewing speed and ironing pressure, etc., to formulate a sewing-ironing associated influence indicator system to provide a basis for optimizing the production process.

[0091] In the actual application process, it also includes applying the determined correlation influence indicators to actual production, optimizing the production process by adjusting sewing parameters or ironing parameters, and improving product quality and efficiency; continuously monitoring production data, and constantly adjusting the optimization model based on feedback results to ensure that the sewing-ironing correlation influence indicators can reflect the latest production status and realize dynamic optimization of intelligent manufacturing.

[0092] Furthermore, based on the M processing control parameter sets, an association impact analysis of the ironing parameters and the stacking parameters is established to determine the ironing-stacking association impact index. The method of the present application includes:

[0093] Based on the multiple ironing process segments corresponding to the ironing parameters, synchronous monitoring is performed to obtain an ironing flatness error data set, wherein the ironing flatness error data set includes multiple ironing flatness error data subsets, and the multiple ironing process segments correspond to the multiple ironing flatness error data subsets one by one;

[0094] Based on the ironing flatness error data set, a stacking effect correlation evaluation is performed in sections in combination with a plurality of stacking process sections corresponding to the stacking parameters to obtain the ironing-stacking correlation influence index.

[0095] Data preparation and segment definition: further, organize M sets of processing control parameters to ensure that they contain all key ironing parameters (such as ironing temperature, time, pressure, speed) and whole stacking parameters (such as folding method, size, packaging method); define ironing process segments: according to the different stages of the ironing process (such as pre-ironing, main ironing, shaping ironing, etc.), subdivide the ironing process into multiple process segments, and set clear monitoring points for each segment; subdivide the whole stacking process into several key steps (such as preliminary folding, precise folding, packaging, etc.) to ensure that they correspond to the ironing process segments to facilitate data association analysis.

[0096] Synchronous monitoring and data collection. Further, corresponding monitoring equipment, such as temperature sensors, pressure sensors, visual inspection systems, etc., are installed or integrated in each ironing and stacking process segment to monitor the key parameters of ironing flatness and stacking in real time; the flatness errors of each ironing process segment, such as wrinkles, deformation, etc., are recorded in real time through the monitoring equipment to form an ironing flatness error data set, ensuring that the data subset matches the corresponding ironing process segment.

[0097] Data integration and analysis: further, synchronously collect data such as the efficiency of the folding process and the appearance quality of the finished product, including but not limited to folding size deviation, packaging integrity, etc., to form a folding effect database; associate the ironing flatness error data set with the folding effect data set, and identify how the ironing parameters affect the folding accuracy in the folding process and the appearance quality of the lining product through statistical analysis or data mining technology.

[0098] Establish related influencing indicators. Further, based on the analysis results, design ironing-stacking related influencing indicators, such as the influence coefficient of ironing temperature on folding dimensional stability, the correlation coefficient between ironing pressure and folding neatness, etc., to quantify the specific impact of changes in ironing parameters on the stacking effect; verify the effectiveness of these indicators through simulation experiments or actual production data, and continuously adjust and improve the indicator system to ensure that it can accurately reflect the interaction between ironing and stacking processes.

[0099] In the actual application process, it also includes adjusting the ironing parameters or stacking strategies according to the determined ironing-stacking correlation impact indicators to reduce flatness errors and improve stacking quality; continuously monitoring relevant parameters during the production process, collecting feedback data, and continuously iterating and optimizing models and parameter settings to achieve closed-loop control and continuous improvement of the production process. Establish a correlation impact analysis mechanism between ironing parameters and stacking parameters to ensure the overall quality and efficiency of interlining production.

[0100] In summary, the beneficial effects of the embodiments of the present application are:

[0101] 1. By establishing the correlation influence analysis between various processing parameters, the correlation influence indicators of each key link of cutting-sewing, sewing-ironing, and ironing-folding are determined. Through the dynamic adjustment strategy of the cutting size error threshold and the multi-dimensional similarity comparison model, a scientific basis is provided for production decision-making, the decision-making efficiency of the production process is enhanced, the precise control and optimization of production parameters are achieved, and the error accumulation is reduced.

[0102] 2. Utilize real-time monitoring and quality tolerance competition model to dynamically adjust control parameters according to current production conditions to ensure that products meet established quality standards, thereby improving production flexibility and response speed.

[0103] 3. By calculating the power consumption distribution and equipment utilization, combined with the heuristic algorithm, production balance optimization control is carried out to achieve a balance between production quality and power consumption.

[0104] 4. Since one-third of the initial cropping size error threshold is used for calculation, when nine-tenths of the cropping size error threshold is used to cover the original cropping size error threshold, the existing cropping size error threshold is synchronously compared with one-third of the initial cropping size error threshold; if the difference between the existing cropping size error threshold and one-third of the initial cropping size error threshold meets the critical tolerance constraint, the stop instruction is activated, and the stop instruction is used to stop the covering operation corresponding to the nine-tenths of the cropping size error threshold covering the original cropping size error threshold. In the process of adjusting the cropping size error threshold, production efficiency and quality control are balanced, and a balance between production efficiency and quality assurance is achieved.

[0105] In summary, any step can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor, and no unnecessary restrictions are made here.

[0106] Furthermore, the above-mentioned technical scheme only reflects the preferred technical scheme of the technical scheme of the embodiment of the present application. Some changes that may be made to some parts thereof by technicians in this technical field all reflect the novel principles of the embodiment of the present application. Obviously, technicians in this field can make various changes and modifications to the present application without departing from the scope of the present application.

Claims

1. An intelligent manufacturing method for improving the production quality of lining cloth, characterized in that: The method comprises: Obtaining interlining processing samples and corresponding processing control parameters, wherein the processing control parameters include cutting parameters, sewing parameters, ironing parameters, and folding parameters; According to the interlining quality grade, the interlining processing samples and the corresponding processing control parameters are divided to obtain M processing control parameter sets; Based on the M processing control parameter sets, establishing a correlation impact analysis of cutting parameters and sewing parameters, and determining a cutting-sewing correlation impact index; Based on the M processing control parameter sets, establishing a correlation influence analysis between sewing parameters and ironing parameters, and determining a sewing-ironing correlation influence index; Based on the M processing control parameter sets, establishing the correlation influence analysis between the ironing parameters and the stacking parameters, and determining the ironing-stacking correlation influence index; Through the cutting-sewing related impact index, sewing-ironing related impact index, ironing-stacking related impact index, combined with the interlining quality grade, a quality tolerance competition framework is established, based on the processing control parameters, the power consumption distribution and the power consumption utilization rate of each interlining production equipment in different time periods are calculated for feedback adjustment, and a heuristic algorithm is used to set an energy efficiency balanced quality tolerance competition model; The real-time control parameters of the lining cloth production line are obtained, and the quality grade of the lining cloth under the current production conditions corresponding to the real-time control parameters is predicted, the lining cloth production quality optimization analysis is performed through the energy efficiency balanced quality tolerance competition model, and control instructions are sent to the lining cloth production line. The production balanced optimization control of the lining cloth product quality and the lining cloth production power consumption is performed with the control instructions.

2. The intelligent manufacturing method for improving the production quality of lining cloth according to claim 1, characterized in that: Based on the M processing control parameter sets, an association influence analysis of cutting parameters and sewing parameters is established to determine a cutting-sewing association influence index, and the method includes: Based on the M processing control parameter sets, a plurality of cutting process segments corresponding to the cutting parameters and a plurality of sewing process segments corresponding to the sewing parameters are set; Based on the multiple cutting process segments corresponding to the cutting parameters, synchronous monitoring is performed to obtain a cutting size error data set, wherein the cutting size error data set includes multiple cutting size error data subsets, and the multiple cutting process segments correspond to the multiple cutting size error data subsets one by one; Based on the cutting size error data set, a sewing effect correlation evaluation is performed in sections in combination with a plurality of sewing process sections corresponding to the sewing parameters to obtain the cutting-sewing correlation impact index.

3. The intelligent manufacturing method for improving the production quality of lining cloth according to claim 2, characterized in that: Based on the cutting size error data set, a sewing effect correlation evaluation is performed in sections in combination with a plurality of sewing process sections corresponding to the sewing parameters to obtain the cutting-sewing correlation impact index, and the method includes: Sorting the cropping size error data set from small to large to generate a cropping size error sequence; Setting a cutting size error threshold through interlining inspection standard information, and filtering the cutting size error sequence data to obtain cutting size error standard data; Based on the cutting size error standard data, a sewing effect correlation evaluation is performed in sections in combination with a plurality of sewing process sections corresponding to the sewing parameters to obtain the cutting-sewing correlation impact index.

4. The intelligent manufacturing method for improving the production quality of lining cloth according to claim 3, characterized in that: The cutting size error threshold is set by using the lining cloth inspection standard information, and the method further comprises: Calculating nine-tenths of a cropping size error threshold, and segmenting the cropping size error sequence to obtain a first cropping size error sequence segment and a second cropping size error sequence segment, wherein each cropping size error in the first cropping size error sequence segment satisfies nine-tenths of the cropping size error threshold, and each cropping size error in the second cropping size error sequence segment does not satisfy nine-tenths of the cropping size error threshold; Based on the first cutting size error sequence segmentation, combined with the multiple sewing process segments corresponding to the sewing parameters, a sewing effect correlation evaluation is performed to obtain a first cutting-sewing correlation influence index; Based on the second cutting size error sequence segmentation, combined with the multiple sewing process segments corresponding to the sewing parameters, a sewing effect correlation evaluation is performed to obtain a second cutting-sewing correlation influence index; A similarity comparison is performed on the first cutting-sewing association influence index and the second cutting-sewing association influence index. If the similarity comparison passes, nine-tenths of the cutting size error threshold is used to cover the original cutting size error threshold.

5. The intelligent manufacturing method for improving the production quality of lining cloth according to claim 4, characterized in that: Performing a similarity comparison on the first cutting-sewing association influence index and the second cutting-sewing association influence index, the method further includes: According to the production efficiency influencing index, calculating the norm corresponding to the first cutting-sewing associated influencing index and the norm corresponding to the second cutting-sewing associated influencing index, and establishing a first similarity comparison channel; According to the process stability index, calculating the norm corresponding to the first cutting-sewing association influence index and the norm corresponding to the second cutting-sewing association influence index, and establishing a second similarity comparison channel; According to the material utilization rate index, calculating the norm corresponding to the first cutting-sewing association influence index and the norm corresponding to the second cutting-sewing association influence index, and establishing a third similarity comparison channel; The first similarity comparison channel, the second similarity comparison channel, and the third similarity comparison channel are connected to obtain a multidimensional comparison model.

6. The intelligent manufacturing method for improving the production quality of lining cloth according to claim 4, characterized in that: Using nine-tenths of the cropping size error threshold to cover the original cropping size error threshold, the method further includes: Calculate one third of the initial cropping size error threshold, and when using nine-tenths of the cropping size error threshold to cover the original cropping size error threshold, simultaneously compare the existing cropping size error threshold with one third of the initial cropping size error threshold; If the difference between the existing cropping size error threshold and one third of the initial cropping size error threshold satisfies the critical tolerance constraint, a stop instruction is activated, wherein the stop instruction is used to stop the covering operation corresponding to the original cropping size error threshold being covered by nine-tenths of the cropping size error threshold.

7. The intelligent manufacturing method for improving the production quality of lining cloth according to claim 1, characterized in that: Based on the M processing control parameter sets, establishing the correlation influence analysis between the sewing parameters and the ironing parameters, and determining the sewing-ironing correlation influence index, the method includes: Based on the multiple sewing process segments corresponding to the sewing parameters, synchronous monitoring is performed to obtain a sewing stitch error data set, wherein the sewing stitch error data set includes multiple sewing stitch error data subsets, and the multiple sewing process segments correspond to the multiple sewing stitch error data subsets one by one; Based on the sewing stitch error data set, the ironing effect correlation evaluation is performed in sections in combination with a plurality of ironing process sections corresponding to the ironing parameters to obtain the sewing-ironing correlation influence index.

8. The intelligent manufacturing method for improving the production quality of lining cloth according to claim 1, characterized in that: Based on the M processing control parameter sets, an association influence analysis of ironing parameters and stacking parameters is established to determine an ironing-stacking association influence index, the method comprising: Based on the multiple ironing process segments corresponding to the ironing parameters, synchronous monitoring is performed to obtain an ironing flatness error data set, wherein the ironing flatness error data set includes multiple ironing flatness error data subsets, and the multiple ironing process segments correspond to the multiple ironing flatness error data subsets one by one; Based on the ironing flatness error data set, a stacking effect correlation evaluation is performed in sections in combination with a plurality of stacking process sections corresponding to the stacking parameters to obtain the ironing-stacking correlation influence index.

Images