Processing method of double-sided tape

Abstract

The invention relates to the technical field of double-sided adhesive tape production, and discloses a double-sided adhesive tape processing method, which comprises the following steps: obtaining base material raw paper and an adhesive raw material, processing to form a pretreatment material set, and outputting an initial process parameter configuration table; generating a processing flow update instruction set according to the dynamic adjustment signal, and determining target processing parameters through hierarchical disassembly classification; and outputting a targeted process execution scheme in combination with the equipment operation information set. According to the method, a multi-dimensional process vector matching historical database is constructed by extracting raw paper gram weight characteristics, adhesive viscosity characteristics and drying temperature characteristics, and accurate parameter configuration is realized. And potential defects are further identified based on a real-time monitoring data curve, the parameter priority is dynamically adjusted, and the optimization process is judged through statistics and time sequence stability. The method solves the problems of parameter curing, defect response lag and insufficient equipment collaboration in a traditional method, and improves the production efficiency and quality stability of the double-sided tape.

Description

Technical Field

[0001] The invention relates to the technical field of double-sided adhesive tape production, in particular to a processing method of a double-sided adhesive tape. Background Art

[0002] In modern industrial production, double-sided tape is a commonly used adhesive material, and its processing quality directly affects the applicability and reliability of subsequent application scenarios. Traditional double-sided tape processing methods face many technical bottlenecks in actual production. The processing of base paper and adhesive raw materials often remains at an extensive stage, with only simple basic processing, failing to fully extract key characteristic parameters such as base paper weight, adhesive viscosity, and drying temperature. As a result, the initial process parameter configuration lacks a scientific basis, making it difficult to accurately match the raw material characteristics, which in turn affects the thickness uniformity and bonding strength of the subsequent tape.

[0003] Traditional process parameters often use preset fixed values and lack a dynamic adjustment mechanism. When raw material batch differences or equipment operating status fluctuations arise during the production process, parameters cannot be optimized promptly based on real-time monitoring data. This can easily lead to the accumulation of potential production defects, such as incomplete adhesive curing and tape thickness deviations outside the allowable range. This not only increases scrap rates but also prolongs production cycles.

[0004] Traditional methods for assessing machining process stability lack a systematic analytical framework. They often rely solely on the operator's experience to subjectively judge parameter adjustment scenarios, failing to establish scientific criteria from multiple dimensions such as statistical stability and temporal stability. This makes it difficult to accurately assess the actual impact of parameter updates on the machining process, making it difficult to ensure production process stability.

[0005] In terms of matching equipment with processing parameters, traditional methods fail to fully utilize equipment operation information and are unable to perform comprehensive cost optimization based on multi-dimensional data such as historical collaboration records, debugging costs, and failure risks. This can easily lead to waste of equipment resources, increase production debugging costs and failure risks, and affect overall production efficiency and economic benefits. Summary of the Invention

[0006] The object of the present invention is to provide a method for processing a double-sided adhesive tape to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solution: a method for processing a double-sided adhesive tape, the method comprising: Obtaining substrate paper and adhesive raw materials, processing the substrate paper and adhesive raw materials to form a pre-processed material set, and determining and outputting an initial process parameter configuration table; Determine the updated instruction set for the machining process based on the dynamic adjustment signal fed back from the initial process parameter configuration table; Analyzing the machining process update instruction set, performing hierarchical decomposition, classification, and aggregation on the machining process update instruction set, and determining target machining parameters; Acquire a set of equipment operation information, and determine and output a targeted process execution plan based on the equipment operation information set and the target processing parameters.

[0008] Preferably, the processing of the substrate paper and the adhesive raw material to form a pre-processed material set, and determining and outputting an initial process parameter configuration table include: Processing the substrate base paper and adhesive raw materials to extract a base paper weight feature set, an adhesive viscosity feature, and a drying temperature feature; Analyze the base paper weight feature set to determine the thickness uniformity weight and the bonding strength score corresponding to each feature point; Determining a critical processing stage based on a curing cycle of the adhesive raw material, and determining a temperature attenuation coefficient based on the curing cycle and the critical processing stage; Constructing a multi-dimensional process vector according to the thickness uniformity weight, the bonding strength score, the temperature attenuation coefficient, and the adhesive viscosity characteristic; According to the multi-dimensional process vector, a matching search is performed on a preset historical production database to determine and output the initial process parameter configuration table.

[0009] Preferably, constructing a multi-dimensional process vector according to the thickness uniformity weight, the bonding strength score, the temperature attenuation coefficient and the adhesive viscosity characteristic specifically includes: The thickness weight parameter is determined according to the thickness deviation range of the base paper weight characteristic, the viscosity weight parameter is determined according to the flow performance of the adhesive viscosity characteristic, and the temperature weight parameter is determined according to the duration of the drying temperature characteristic; The thickness weight parameter, viscosity weight parameter, temperature weight parameter and temperature attenuation coefficient are weighted and fused to form a composite process vector including thickness dimension, viscosity dimension and temperature dimension.

[0010] Preferably, determining the processing flow update instruction set according to the dynamic adjustment signal fed back from the initial process parameter configuration table includes: According to the initial process parameter configuration table, a real-time parameter visualization interface is provided for the production monitoring system, and the parameter space mapping effect is synchronously updated according to the monitoring data curve fed back by the system; Based on the monitoring data curve, identify the characteristics of potential production defects through feature cluster analysis, dynamically adjust the priority ranking of initial parameters, and generate a parameter update plan; Analyze the parameter update plan, evaluate the stability of the processing flow, determine process stability feedback information, and provide corresponding parameter adjustment suggestions to the operator, and receive confirmation instructions from the worker; According to the worker confirmation instruction, a processing flow update instruction set is determined.

[0011] Preferably, analyzing the parameter update scheme, evaluating the stability of the processing flow, and determining process stability feedback information includes: According to the parameter update scheme, the number of parameter dimensions, execution deviation interval, historical execution result distribution and parameter importance ranking of the extraction process are extracted; According to the process significance of each parameter, determine the process deviation tolerance threshold, historical execution qualified ratio and continuous execution consistency rate; Based on the number of parameter dimensions, the execution deviation interval, and the distribution of historical execution results, and according to the parameter importance ranking and the deviation tolerance threshold, a statistical stability determination condition is established; Determine the effective time range for process execution based on the curing cycle and the key processing stages; Based on the historical execution qualified ratio and the effective time range, according to the continuous execution consistency rate and the parameter importance ranking, a timing stability judgment condition is established; According to the statistical stability judgment condition and the temporal stability judgment condition, it is judged whether the statistical stability or temporal stability corresponding to the current parameter update scheme meets the requirements, and a judgment conclusion is determined, which is used as the process stability feedback information.

[0012] Preferably, the statistical stability determination condition is constructed based on the number of parameter dimensions, the execution deviation interval, and the historical execution result distribution, according to the parameter importance ranking and the deviation tolerance threshold, and specifically includes: Calculate the correlation between the number of parameter dimensions and the execution deviation range, analyze the matching degree between the distribution of historical execution results and the parameter importance ranking, and set the critical range of statistical stability based on the deviation tolerance threshold; The timing stability determination condition is constructed based on the historical execution qualified ratio and the effective time range, according to the continuous execution consistency rate and the parameter importance ranking, and specifically includes: Calculate the fluctuation range of the historical execution qualification ratio within the effective time range, analyze the temporal correlation between the continuous execution consistency rate and the parameter importance ranking, and set the critical range of temporal stability.

[0013] Preferably, analyzing the processing flow update instruction set, performing hierarchical decomposition and classification on the processing flow update instruction set, and determining target processing parameters include: Update the instruction set according to the machining process, and count the key parameter adjustment set and the auxiliary parameter correction set; According to the process update cycle set by the factory, according to the curing cycles corresponding to different batches in the processing process update instruction set, a number of update batches are divided to determine the update batch information set; Analyzing the key parameter adjustment set based on the update batch information set, and determining a redundancy adjustment amount corresponding to each parameter in each update batch according to a numerical drift ratio corresponding to each parameter in the key parameter adjustment set in historical update records; The target processing parameters are constructed according to the auxiliary parameter correction set, the updated batch information set, and the redundancy adjustment amount.

[0014] Preferably, determining and outputting a targeted process execution plan based on the equipment operation information set and according to the target processing parameters includes: Analyzing the target processing parameters based on the equipment operation information set, and determining a number of target production equipment corresponding to each parameter adjustment item in the target processing parameters; Extract the historical collaboration records corresponding to each target production equipment based on the equipment operation information set to determine the historical usage count, historical debugging cost, historical qualified execution ratio, and historical failure risk of each parameter adjustment item on the current production line under the corresponding target production equipment; Based on the historical usage times, historical debugging costs, historical qualified execution ratios and historical failure risks of each parameter adjustment item under the corresponding target production equipment, comprehensive cost optimization processing is performed on each parameter adjustment item to determine the optimal production equipment corresponding to each parameter adjustment item, thereby constructing and outputting the targeted process execution plan.

[0015] Preferably, performing comprehensive cost optimization processing on each parameter adjustment item based on the historical usage count, the historical debugging cost, the historical qualified execution ratio, and the historical failure risk of each parameter adjustment item under the corresponding target production equipment specifically includes: Calculate the weighted sum of historical usage times and historical debugging costs as the equipment usage cost indicator, and calculate the weighted sum of historical qualified execution ratio and historical failure risk as the effect risk cost indicator; Comprehensively compare the equipment use cost index with the effect risk cost index, and select the production equipment with the lowest comprehensive cost as the optimal equipment.

[0016] Preferably, the identifying of potential production defect features through feature cluster analysis includes: Dividing the monitoring data curve into time windows and extracting the parameter fluctuation amplitude and frequency within each time window; The initial classification standard of the clustering algorithm is set as the historical defect product feature library, and clustering iteration is performed based on the matching degree between the parameter fluctuation amplitude and frequency and the initial classification standard; The reliability of the clustering results is evaluated by classification purity, and cluster groups whose matching degree with historical defect characteristics exceeds the preset critical value are screened out, and their corresponding parameter combinations are determined as potential production defect characteristics.

[0017] Compared with the prior art, the present invention has the following beneficial effects: The double-sided tape processing method provided by this invention achieves refined processing of base paper and adhesive raw materials through multi-dimensional feature extraction and process vector construction. By extracting a set of base paper weight features, adhesive viscosity characteristics, and drying temperature characteristics, and analyzing the thickness uniformity weight, bonding strength score, and temperature attenuation coefficient corresponding to each feature, this method accurately captures the raw material characteristics, providing a scientific basis for initial process parameter configuration, significantly improving the matching between parameters and raw materials, and thus enhancing the thickness uniformity and bonding strength stability of the tape product.

[0018] Based on a dynamic adjustment mechanism for the initial process parameter configuration table, the production monitoring system's real-time parameter visualization and monitoring data curve analysis enable timely identification of potential production defect characteristics. Using feature cluster analysis to process monitoring data, potential defects in the production process can be predicted in advance, parameter priorities can be dynamically adjusted, and updated plans can be generated. This enables real-time optimization of the production process, effectively reducing scrap rates and shortening production cycles.

[0019] In terms of machining process stability assessment, by constructing statistical stability judgment conditions and temporal stability judgment conditions, a comprehensive assessment is conducted from multiple dimensions such as the number of parameter dimensions, execution deviation range, historical execution result distribution, and effective time range, to ensure the scientific nature and reliability of the parameter update plan, guarantee the continuous and stable operation of the machining process, and improve the controllability of the production process.

[0020] In the matching optimization of equipment and parameters, the target processing parameters are analyzed based on the equipment operation information set, and comprehensive cost optimization processing is performed based on data such as the number of uses, debugging costs, qualified ratios and failure risks in historical collaboration records. The optimal production equipment can be determined for each parameter adjustment item, which significantly reduces equipment debugging costs and failure risks, improves equipment resource utilization efficiency, and thus improves overall production efficiency and economic benefits.

[0021] This method updates the instruction set by hierarchically disassembling the processing flow, and determines the target processing parameters in combination with the curing cycle and updated batch information. This achieves systematic management and dynamic updating of processing parameters, enabling the entire processing process to better adapt to changes in raw materials and production needs, improving production flexibility and adaptability, and providing strong technical support for the mass production of high-quality double-sided tapes. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a working principle diagram of the double-sided tape processing method of the present invention; Figure 2 A flow chart is formed for the pre-processing material set; Figure 3 Flowcharts constructed for multi-dimensional process vectors; Figure 4 Update the flow chart determined by the instruction set for the machining process. DETAILED DESCRIPTION

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0024] See also Figures 1-4 The present invention relates to a method for processing a double-sided adhesive tape, and the specific implementation steps are as follows: Obtain and process the base paper and adhesive raw materials to form a pre-processed material set, and determine and output an initial process parameter configuration table. In this step, the base paper and adhesive raw materials are processed to extract the base paper weight feature set, adhesive viscosity feature set, and drying temperature feature set. The base paper weight feature set is analyzed to determine the thickness uniformity weight and bonding strength score corresponding to each feature point. Based on the curing cycle of the adhesive raw material, the key processing stage is determined, and the temperature attenuation coefficient is determined based on the curing cycle and key processing stage. A multi-dimensional process vector is constructed based on the thickness uniformity weight, bonding strength score, temperature attenuation coefficient, and adhesive viscosity feature. Based on the multi-dimensional process vector, a matching search is performed on the preset historical production database to determine and output the initial process parameter configuration table.

[0025] Based on the dynamic adjustment signals fed back from the initial process parameter configuration table, the processing process update instruction set is determined. Specifically, based on the initial process parameter configuration table, a real-time parameter visualization interface is provided for the production monitoring system. Based on the monitoring data curve fed back by the system, the parameter space mapping effect is synchronously updated. Based on the monitoring data curve, feature clustering analysis is used to identify potential production defect characteristics, dynamically adjust the priority ranking of initial parameters, and generate a parameter update plan. The parameter update plan is analyzed to evaluate the stability of the processing process, determine process stability feedback information, and feedback the corresponding parameter adjustment suggestions to the operator, who then receives confirmation instructions from the worker. Based on the worker's confirmation instructions, the processing process update instruction set is determined.

[0026] Analyze the machining process update instruction set, perform a hierarchical breakdown and classification of the machining process update instruction set, and determine the target machining parameters. Specifically, based on the machining process update instruction set, calculate the key parameter adjustment set and auxiliary parameter correction set. Based on the factory-set process update cycle and the curing cycles corresponding to different batches in the machining process update instruction set, divide the update batches into several batches and determine the update batch information set. Based on the update batch information set, analyze the key parameter adjustment set and determine the redundant adjustment amount for each parameter in each update batch based on the numerical drift ratio of each parameter in the key parameter adjustment set in the historical update records. Target machining parameters are constructed based on the auxiliary parameter correction set, the update batch information set, and the redundant adjustment amount.

[0027] Obtain the equipment operation information set, and based on the equipment operation information set and the target processing parameters, determine and output a targeted process execution plan. Specifically, based on the equipment operation information set, analyze the target processing parameters and determine the target production equipment corresponding to each parameter adjustment item in the target processing parameters; extract the historical collaboration records corresponding to each target production equipment based on the equipment operation information set to determine the historical usage count, historical debugging cost, historical execution qualified ratio, and historical failure risk of each parameter adjustment item in the current production line under the corresponding target production equipment; based on the historical usage count, historical debugging cost, historical execution qualified ratio, and historical failure risk of each parameter adjustment item under the corresponding target production equipment, perform comprehensive cost optimization processing on each parameter adjustment item to determine the optimal production equipment corresponding to each parameter adjustment item, and thus construct and output a targeted process execution plan.

[0028] Example 1: In the double-sided tape manufacturing process, processing the base paper and adhesive raw materials to form a pre-processed material set, and determining and outputting the initial process parameter configuration table are key initial steps. Specific implementation methods are as follows: After obtaining the base paper and adhesive raw materials, these two types of raw materials need to be processed. For the base paper, its grammage feature set needs to be extracted. The extraction of this set needs to be based on specific testing standards and methods. For example, multi-point sampling is performed at different positions of the base paper, and each sampling point corresponds to a base paper grammage feature point, thereby forming a base paper grammage feature set containing multiple feature points. At the same time, the adhesive raw materials are processed to extract their viscosity characteristics. The extraction of this feature is usually carried out with the help of professional measuring instruments such as viscometers, and is carried out according to standard measurement procedures to ensure that the obtained adhesive viscosity characteristics are accurate and reliable. In addition, the drying temperature characteristics need to be extracted. The extraction of the drying temperature characteristics needs to take into account the temperature changes during the drying process, including the temperature set value, the actual fluctuation range, the duration and other related information.

[0029] The extracted base paper weight feature set is analyzed in depth. For each feature point in the set, its corresponding thickness uniformity weight and bonding strength score are determined. When determining the thickness uniformity weight, it is necessary to comprehensively consider the thickness deviation of the base paper at the feature point. For example, by measuring the thickness at multiple positions near the feature point, the thickness deviation range is calculated, and then the thickness uniformity weight of the feature point is determined based on the correspondence between the deviation range and the thickness uniformity. This weight is used to measure the degree of influence of the feature point on the overall thickness uniformity of the base paper. To determine the bonding strength score, it is necessary to simulate the actual bonding process, conduct a bonding strength test on the base paper at the feature point, and give a corresponding score based on the test results. The score reflects the strength performance of the feature point in the bonding operation.

[0030] Determine the key processing stages based on the curing cycle of the adhesive raw materials. The curing process of adhesives usually includes multiple stages, and the temperature, pressure and other conditions in each stage have different effects on the curing effect. Through the study and analysis of the curing mechanism of adhesives, combined with previous production experience, the stage that plays a decisive role in the formation of adhesive performance in the curing cycle is determined, namely the key processing stage. After determining the key processing stage, the temperature attenuation coefficient is determined based on the curing cycle and these key processing stages. The determination of the temperature attenuation coefficient needs to consider the change pattern of temperature over time in the key processing stage, as well as the effect of temperature change on the curing reaction rate of the adhesive. For example, by establishing a mathematical model between temperature and curing reaction rate, combined with the time nodes of the curing cycle and key processing stages, the temperature attenuation coefficient is calculated. This coefficient is used to describe the degree of influence of temperature changes on the process during the processing.

[0031] After obtaining the thickness uniformity weight, bonding strength score, temperature attenuation coefficient, and adhesive viscosity characteristics, the multidimensional process vector is constructed. During this construction, the thickness weight parameter is first determined based on the thickness deviation range of the base paper weight characteristic. The larger the thickness deviation range, the greater the impact of this feature point on thickness uniformity, and the corresponding thickness weight parameter will also be larger. This determination can be done by pre-setting a table that maps thickness deviation ranges to thickness weight parameters. Based on the actual measured thickness deviation range, the corresponding thickness weight parameter is searched in the table. Next, the viscosity weight parameter is determined based on the flow properties of the adhesive viscosity characteristic. The flow properties of the adhesive can be reflected by the viscosity value; the lower the viscosity value, the better the flow properties. The corresponding viscosity weight parameter may be set based on process requirements. For example, in some processes, adhesives with good flow properties may be assigned a higher viscosity weight parameter to highlight their importance in the process. Next, the temperature weight parameter is determined based on the duration of the drying temperature characteristic. Different drying temperature durations will have different effects on the properties of the base paper and adhesive. The longer the duration, the more significant the impact on certain properties may be. Therefore, the size of the temperature weight parameter needs to be determined based on the actual duration.

[0032] After determining the thickness, viscosity, and temperature weight parameters, these parameters are weighted and fused with the temperature attenuation coefficient. This weighted fusion process requires assigning different weights to each parameter based on its importance in the process. For example, thickness uniformity plays a crucial role in the quality of double-sided tape, so the thickness weight parameter may be assigned a larger weight. The temperature attenuation coefficient, on the other hand, significantly impacts the curing effect of the adhesive and is therefore also assigned a corresponding weight. Through weighted calculation, these parameters are fused into a composite process vector encompassing the thickness, viscosity, and temperature dimensions. This vector comprehensively reflects the characteristics of the current processing materials and process conditions.

[0033] After completing the construction of the multi-dimensional process vector, a matching search is performed on the preset historical production database based on the vector. The preset historical production database stores a large amount of process parameters, raw material characteristics and product quality data from previous production processes. During the matching search, the constructed composite process vector is compared with the records in the database to find historical records with a high degree of similarity to the vector. Through a specific matching algorithm, the similarity between vectors is calculated, and historical records with a similarity exceeding the set threshold are screened out. From these screened historical records, the corresponding process parameters are extracted, and after comprehensive analysis and evaluation, the initial process parameter configuration table is determined and output. The initial process parameter configuration table contains various processing parameters for the current substrate paper and adhesive raw materials, such as temperature, pressure, speed, etc., which provides specific parameter guidance for the subsequent double-sided tape processing and production, ensuring that the production process can be carried out in accordance with the preset process requirements, thereby ensuring the quality and performance of the product.

[0034] Throughout the entire implementation process, every step requires strict adherence to relevant operating specifications and standards to ensure data accuracy and reliability. For example, when extracting raw material characteristics, the accuracy of the measuring instruments and the correctness of the measurement methods must be guaranteed; when analyzing characteristics and determining parameters, sufficient theoretical basis and practical experience must be relied upon; and when constructing process vectors and searching databases, scientific and reasonable algorithms and methods must be employed. Only in this way can the scientific nature and effectiveness of the initial process parameter configuration table be ensured, laying a solid foundation for subsequent processing steps. Furthermore, in actual production, the initial process parameter configuration table must be dynamically adjusted and optimized based on real-time data feedback from the production monitoring system to adapt to varying production conditions and requirements, further improving product quality and production efficiency.

[0035] Example 2: During the double-sided tape processing, determining the processing flow update instruction set based on the dynamic adjustment signal fed back from the initial process parameter configuration table is a key step in achieving dynamic optimization of the production process. The specific implementation method is as follows: Based on the initial process parameter configuration table, a real-time parameter visualization interface is provided for the production monitoring system. This interface must present key process parameters such as temperature, pressure, and adhesive coating amount in intuitive forms such as charts and numerical values, facilitating real-time monitoring by operators and technicians. The interface design must meet real-time refresh requirements, such as updating parameter data once a second to ensure that monitoring information is synchronized with actual production status. When production equipment is operating, the system collects monitoring data for each parameter in real time and generates curves, such as temperature versus time curves and adhesive viscosity fluctuation curves. At this time, the parameter space mapping effect must be updated synchronously based on these monitoring data curves. That is, through data visualization technology, the correlation between multidimensional parameters in the spatial dimension can be graphically displayed. For example, a three-dimensional coordinate graph can be used to display the interactive influence area of the three parameters of temperature, pressure, and curing time, so that operators can intuitively understand the comprehensive impact of parameter changes on the production process.

[0036] Perform feature cluster analysis on the monitoring data curve to identify potential production defect characteristics. The first step is to divide the curve into time windows. The setting of the time window needs to be combined with the production process cycle. For example, every 30 minutes is divided into a time window to ensure that the data in each window can reflect a relatively complete production stage. Within each time window, the parameter fluctuation amplitude and frequency are extracted. The fluctuation amplitude is obtained by calculating the difference between the maximum and minimum values of the parameter, and the frequency is the number of fluctuations of the parameter per unit time. For example, within a certain time window of the temperature monitoring curve, the fluctuation amplitude is ±5°C, and the frequency is once every 10 minutes.

[0037] The initial classification standard of the clustering algorithm is set to the historical defective product feature library. This feature library needs to collect parameter data from previous production when defective products appeared, such as the temperature and adhesive viscosity corresponding to insufficient tape peel strength, to form a standard feature vector. During the clustering iteration process, the parameter fluctuation amplitude and frequency data within the current time window are compared with the initial classification standard for matching, and methods such as Euclidean distance or cosine similarity are commonly used. For example, the Euclidean distance between the current parameter vector and a feature vector in the historical defect feature library is calculated. The smaller the distance, the higher the matching degree. The cluster center is adjusted through multiple iterations to maximize the similarity of data points of the same type and the difference of data points of different types.

[0038] After clustering is completed, the reliability of the results is evaluated through classification purity. The classification purity is calculated as the ratio of the number of data points in a certain class that belong to the true defect characteristics of that class to the total number of data points in that class. For example, if a cluster group has a total of 100 data points, 80 of which match the historical defect characteristics, then the classification purity is 80%. Cluster groups with a matching degree exceeding the preset critical value (such as 70%) are screened out, and their corresponding parameter combinations are determined as potential production defect characteristics. For example, when the parameter combination of a cluster group is a temperature fluctuation in the range of 60-65°C and an adhesive viscosity that is 15% lower than the standard value, and the matching degree with "insufficient peel strength" in the historical defect feature library reaches 75%, then this parameter combination is determined as a potential defect characteristic.

[0039] After identifying potential defect characteristics, dynamically adjust the priority ranking of the initial parameters. Priority ranking needs to comprehensively consider factors such as the degree of influence of parameters on product quality and the scope of influence of parameter fluctuations on production stability. For example, the temperature parameter has a significant impact on the curing effect of the adhesive, and its priority should be higher than the equipment operating speed parameter. During adjustment, if a potential defect characteristic is related to the temperature parameter, the priority of the temperature parameter is increased so that it is adjusted first in the parameter update. A parameter update plan is generated based on the adjusted priority. The plan must clearly define the adjustment direction and adjustment range of each parameter, such as adjusting the temperature from the current 62°C to 68°C and increasing the adhesive viscosity from 1200cP to 1500cP.

[0040] Analyze the parameter update plan and evaluate the stability of the processing flow. First, analyze the number of parameter dimensions in the plan (e.g., involving temperature, viscosity, and pressure), the execution deviation range (e.g., a temperature adjustment allows a ±2°C deviation), the distribution of historical execution results (e.g., the distribution of product pass rates after similar parameter adjustments), and the parameter importance ranking (e.g., temperature > viscosity > pressure). Based on the process significance of each parameter, determine the deviation tolerance threshold (e.g., ±3°C for temperature and ±5% for viscosity). Also, calculate the historical execution pass rate (e.g., the product pass rate under the same parameter adjustment was 92%) and the consistency rate of consecutive executions (e.g., the consistency of 10 consecutive executions of the parameter adjustment was 95%).

[0041] Based on the number of parameter dimensions, execution deviation interval and historical execution result distribution, combined with parameter importance ranking and deviation tolerance threshold, statistical stability judgment conditions are constructed. For example, when the number of parameter dimensions exceeds 3 and the execution deviation interval exceeds 1.5 times the deviation tolerance threshold, it is determined that there is a risk in statistical stability. At the same time, based on the curing cycle and key processing stages, the effective time range of process execution is determined. For example, the key stage of adhesive curing is the 1st to 2nd hour, and the effective time range is set to this period. Based on the historical execution qualified ratio and effective time range, combined with the continuous execution consistency rate and parameter importance ranking, a timing stability judgment condition is constructed. For example, when the historical execution qualified ratio fluctuates by more than 10% within the effective time range and the continuous execution consistency rate is less than 90%, it is determined that the timing stability does not meet the requirements.

[0042] According to the statistical stability judgment conditions and the timing stability judgment conditions, determine whether the current parameter update plan meets the requirements. If the statistical stability or timing stability does not meet the requirements, return to adjust the parameter update plan; if it meets the requirements, form process stability feedback information, such as "the statistical stability of the parameter update plan is good, and the timing stability needs to be continuously monitored." Feedback this feedback information and parameter adjustment suggestions to the operation end, which is presented to the worker in the form of a pop-up window or message prompt. The worker confirms according to the actual production situation, such as clicking the "Confirm Execution" or "Reject Update" button. After the system receives the worker's confirmation instruction, if it is confirmed to be executed, the processing flow update instruction set is determined according to the instruction. The instruction set contains specific parameter adjustment values, execution equipment, time nodes and other information, such as "adjust the coating machine temperature to 68°C at 14:00, and execute by equipment number A-001."

[0043] Throughout the implementation process, it is necessary to ensure the real-time and accuracy of data collection. For example, the sampling frequency of monitoring data must be no less than 1 time per minute, and the collection equipment must be calibrated regularly. During cluster analysis, the historical defect product feature library must be continuously updated to incorporate newly emerging defect features to improve identification accuracy. During the stability assessment process, the threshold setting of each judgment condition must be combined with the actual production conditions of the factory and the product quality requirements. For example, the deviation tolerance threshold of high-precision tape should be lower than that of ordinary tape. In addition, a reasonable response time must be set for the worker confirmation link. If there is no response within 30 minutes, an automatic reminder will be issued to ensure the continuity of the production process.

[0044] Example 3: During the double-sided tape processing, analyzing the processing flow, updating the instruction set, and performing hierarchical decomposition and classification to determine the target processing parameters is an important step in ensuring accurate adjustment of production parameters. The specific implementation method is as follows: After obtaining the processing flow update instruction set, it is necessary to systematically count the parameters in the instruction set to distinguish between the key parameter adjustment set and the auxiliary parameter correction set. The key parameter adjustment set usually includes parameters that play a decisive role in the performance of double-sided tape products and the stability of the processing flow, such as the curing temperature of the adhesive, the coating speed of the base paper, the coating amount of the adhesive, etc. Slight changes in these parameters may directly affect the core performance indicators of the tape such as peel strength and holding power. The auxiliary parameter correction set covers parameters that play an auxiliary role in key parameters, such as the pressure during equipment operation and the ventilation volume in the drying process. Although they do not directly determine the core performance of the product, they will affect the execution effect and stability of the key parameters. During the statistical process, it is necessary to clarify the role and importance of each parameter in the processing flow based on process knowledge and production experience, and use this as a standard for classification to ensure that the division of key parameters and auxiliary parameters is accurate and reasonable.

[0045] Based on the factory's pre-set process update cycle and the curing cycles corresponding to different product batches within the process update instruction set, the entire process is divided into several update batches, and the update batch information set is determined. The factory-set process update cycle is typically determined based on a combination of factors such as equipment maintenance needs, product changeover plans, and production management experience. For example, it may be set to update process parameters every eight hours. However, the curing cycles for different product batches may vary depending on factors such as adhesive type and product specifications. For example, one batch may use a fast-curing adhesive with a 30-minute curing cycle, while another batch may use a slow-curing adhesive with a 60-minute curing cycle. When dividing the update batches, batches with the same or similar curing cycles should be grouped together to ensure a certain degree of consistency in production conditions within each update batch. The update batch information set should record detailed information such as the start and end time of each batch, the corresponding curing cycle, and the product specifications produced, to facilitate targeted management of parameter adjustments.

[0046] Based on the update batch information set, an in-depth analysis of the key parameter adjustment set is performed. For each parameter in the key parameter adjustment set, it is necessary to check its corresponding numerical drift ratio in the historical update record. The numerical drift ratio refers to the statistical value of the degree of deviation between the actual execution value and the set value of the parameter in the previous multiple updates. For example, in the historical update of a certain temperature parameter, the actual execution value drifted an average of ±2°C relative to the set value, and its numerical drift ratio can be expressed as 2%. By analyzing the numerical drift ratio, the stability of each parameter in the long-term production process can be understood. For parameters with a large drift ratio, more attention and a larger amount of redundant adjustment are required in subsequent adjustments.

[0047] When determining the redundant adjustment amount for each parameter in each update batch, it is necessary to comprehensively consider the numerical drift ratio of the parameter, its importance in the current batch, and the requirements of the production process. For example, for a critical temperature parameter with a numerical drift ratio of 3%, in the current batch, since the product is more sensitive to temperature, its redundant adjustment amount may need to be set to ±3°C to compensate for possible drift and ensure that the temperature is controlled within a reasonable range. The setting of the redundant adjustment amount must follow certain principles. It must be able to effectively compensate for parameter drift, but it must not be excessively adjusted and cause production instability. It usually requires repeated verification and optimization based on historical data and process experience.

[0048] The target processing parameters are constructed based on the auxiliary parameter correction set, the update batch information set, and the redundant adjustment amount. During the construction process, the auxiliary parameter correction set needs to be matched with the corresponding update batch to ensure that the auxiliary parameter correction of each batch can be coordinated with the key parameter adjustment. For example, in a certain update batch, the key parameter adjustment set requires the curing temperature to be increased by 5°C. Then the corresponding auxiliary parameter correction set may need to increase the ventilation volume in the drying process by 10% to match the temperature adjustment and ensure the curing effect of the adhesive. At the same time, the redundant adjustment amount is incorporated into the setting of the key parameters and auxiliary parameters to form the final target processing parameters.

[0049] When establishing target processing parameters, a separate parameter plan should be developed for each batch, following the order in which the batch information sets are updated, to ensure precise parameter guidance for each batch's production. For example, for the first updated batch, the target processing parameters might be: a curing temperature of 65°C (with a ±3°C margin adjustment), a coating speed of 10 m / min, and a drying ventilation volume of 500 m3 / h. For the second updated batch, based on its curing cycle and parameter drift, the target processing parameters might be adjusted to: a curing temperature of 68°C (with a ±3°C margin adjustment), a coating speed of 10.5 m / min, and a drying ventilation volume of 550 m3 / h.

[0050] Throughout the implementation process, a comprehensive parameter management system needs to be established to centrally store and manage data such as key parameter adjustment sets, auxiliary parameter correction sets, updated batch information sets, and redundant adjustment amounts to ensure data traceability and consistency. At the same time, the parameter analysis and construction process requires the joint participation of professional process engineers and production management personnel, who, combined with their professional knowledge and practical experience, can improve the scientific nature and feasibility of the target processing parameters. Furthermore, it is necessary to regularly evaluate and summarize the execution effects of the target processing parameters, optimize and improve the parameter classification standards, updated batch division methods, and redundant adjustment amount settings based on actual production conditions, and continuously improve the accuracy and effectiveness of production parameter adjustments, thereby enhancing the production quality and efficiency of double-sided tape.

[0051] Example 4: In the double-sided tape processing process, determining and outputting a targeted process execution plan based on the equipment operation information set and the target processing parameters is a key step in achieving optimal allocation of production resources. The specific implementation method is as follows: Analyze the target processing parameters based on the equipment operation information set, and identify the target production equipment corresponding to each parameter adjustment item in the target processing parameters. For example, when the target processing parameters include the parameter adjustment item "adjust the adhesive curing temperature to 68°C", it is necessary to determine the target production equipment that can achieve this temperature adjustment, which may include coating machines, curing ovens and other equipment. The equipment operation information set contains the basic information, operating status, maintenance records, etc. of all production equipment in the factory. By retrieving and analyzing this information, it can be determined which equipment has the ability to perform this parameter adjustment item. When determining the target production equipment, factors such as the equipment model, specifications, and accuracy need to be considered to ensure that the equipment can meet the requirements of the parameter adjustment.

[0052] Based on the equipment operation information set, the historical collaboration records corresponding to each target production equipment are extracted. These historical collaboration records detail how the equipment collaborated with other equipment during previous production processes and how it performed in executing various parameter adjustments. For example, for a specific target production equipment, model A-100 coating machine, the historical collaboration records for the parameter adjustment item "Adhesive Coating Amount Adjustment" are extracted. These records include the number of times the equipment was used to execute this parameter adjustment item over different time periods, the historical commissioning costs, the historical compliance rate, and the historical failure risk. The historical number of uses reflects how frequently the equipment processes the parameter adjustment item. For example, the coater executed "adhesive coating amount adjustment" 50 times in the past month. The historical debugging cost refers to the cost of debugging the equipment each time to meet the parameter adjustment requirements, including labor costs, material costs, etc. For example, the cost of each debugging is about 500 yuan. The historical qualified execution ratio indicates the qualified status of the products produced by the equipment after executing the parameter adjustment item. For example, the qualified rate of products after executing the parameter adjustment item is 90%. The historical failure risk is the possibility of failure of the equipment when executing the parameter adjustment item, assessed based on the equipment's failure record and operating status. For example, by analyzing the equipment's maintenance record and current operating parameters, it is assessed that the failure risk of the equipment when executing the parameter adjustment item is 5%.

[0053] Comprehensive cost optimization is performed for each parameter adjustment item based on its historical usage count, historical commissioning costs, historical qualified execution rate, and historical failure risk for the corresponding target production equipment. For example, the parameter adjustment item "Adjusting the adhesive coating amount to 150g / m²" corresponds to coater A-100 and coater B-200. For coater A-100, the weighted sum of its historical usage count and historical commissioning costs is calculated as the equipment usage cost indicator. Assuming a weight of 0.4 for the historical usage count and 0.6 for the historical commissioning cost, 50 historical usages, and a commissioning cost of 500 yuan per time, the equipment usage cost indicator is 50 × 0.4 + 500 × 0.6 = 20 + 300 = 320. The weighted sum of the historical qualified execution ratio and the historical failure risk is calculated as the effect risk cost indicator. Assuming the weight of the historical qualified execution ratio is 0.7, the weight of the historical failure risk is 0.3, the historical qualified execution ratio is 90%, and the historical failure risk is 5%, then the effect risk cost indicator is 90% × 0.7 + 5% × 0.3 = 0.63 + 0.015 = 0.645. For the coating machine B-200, assuming it has been used 30 times in history, the cost of each commissioning is 800 yuan, the historical qualified execution ratio is 95%, and the historical failure risk is 3%, then the equipment use cost indicator is 30 × 0.4 + 800 × 0.6 = 12 + 480 = 492, and the effect risk cost indicator is 95% × 0.7 + 3% × 0.3 = 0.665 + 0.009 = 0.674.

[0054] Compare the equipment cost index with the effect-risk cost index and select the production equipment with the lowest overall cost as the optimal equipment. In the above example, the equipment cost index of coater A-100 is 320, and the effect-risk cost index is 0.645. The overall cost can be calculated by adding the two indexes: 320 + 0.645 = 320.645. Coater B-200 has an equipment cost index of 492 and an effect-risk cost index of 0.674, resulting in an overall cost of 492 + 0.674 = 492.674. Since 320.645 < 492.674, coater A-100 is selected as the optimal equipment for the parameter adjustment "Adhesive coating weight adjusted to 150g / m²."

[0055] Based on the optimal production equipment corresponding to each parameter adjustment item, a targeted process execution plan is constructed and output. The targeted process execution plan needs to list in detail each parameter adjustment item and its corresponding optimal equipment, the specific parameter value of the adjustment, the execution time node, the operation steps, and precautions. For example, for the parameter adjustment item "adjust the adhesive curing temperature to 68°C", the optimal equipment is determined to be the curing oven model C-300. The targeted process execution plan needs to clearly state: this parameter adjustment item is executed by the curing oven C-300, adjusting the temperature from the current 65°C to 68°C, and the adjustment time is set at 2 pm on the same day. The operation steps are to first turn off the heating system of the curing oven, wait for the temperature to drop below 60°C, then reset the temperature to 68°C, start the heating system, and start production after the temperature stabilizes; precautions include real-time monitoring of temperature changes during the adjustment process to ensure that the temperature fluctuation range does not exceed ±2°C, and the need to calibrate the equipment after the adjustment is completed.

[0056] When developing a targeted process execution plan, it's crucial to ensure its completeness and operability. Each step must have clear regulations and instructions to avoid ambiguity or errors during implementation. Furthermore, the interplay between different parameter adjustments must be considered to ensure coordination and consistency across the entire process execution plan. For example, adjusting the adhesive curing temperature might require a corresponding adjustment to the adhesive coating speed to ensure product quality and production efficiency.

[0057] Furthermore, during implementation, a comprehensive equipment management and monitoring system must be established to track equipment operating status and parameter adjustment progress in real time, enabling timely identification and resolution of potential issues. For example, if optimal equipment fails, it is necessary to rapidly switch to a backup device and adjust the process execution plan accordingly to ensure continuous production. Furthermore, the effectiveness of the process execution plan must be evaluated and summarized, with continuous optimization of equipment selection methods and standards to enhance the accuracy and effectiveness of comprehensive cost optimization. This will ensure optimal allocation of production resources, reduce production costs, and improve the quality and efficiency of double-sided tape production.

[0058] Example 5: During the double-sided tape production process, identifying potential production defects through feature cluster analysis is a key step in ensuring product quality. This method requires a systematic approach based on production data and historical experience. Taking the production of a batch of PET-based double-sided tape as an example, the specific implementation method is as follows: The monitoring data curves fed back by the production monitoring system are divided into time windows. Assuming a 4-hour production cycle for this batch of tape, based on the characteristics of the adhesive coating, drying, and curing process, the time windows are set to 20-minute intervals, for a total of 12 time windows. During the first time window (0-20 minutes), real-time data on parameters such as coater temperature, adhesive viscosity, and substrate speed is collected to form a continuous monitoring data curve. For example, the temperature monitoring curve shows that the temperature fluctuated between 65-70°C during this period, the adhesive viscosity curve shows values varying between 1200-1350 cP, and the substrate speed remained stable at 8 m / min.

[0059] Extract the parameter fluctuation amplitude and frequency within each time window. For example, the temperature parameter is calculated by calculating the difference between the maximum temperature of 70°C and the minimum temperature of 65°C within the time window, resulting in a fluctuation amplitude of 5°C. The number of temperature fluctuations within 20 minutes is counted. If the temperature rises from 65°C to 70°C and then falls back to 65°C, it is considered a complete fluctuation. If there are two fluctuations within this period, the frequency is 6 times / hour. Similarly, the fluctuation amplitude of the adhesive viscosity is 150 cP, with a frequency of once every 10 minutes. The substrate running speed has no significant fluctuations, with an amplitude of 0 and a frequency of 0.

[0060] The initial classification criteria for the clustering algorithm are set to a historical defective product feature library. This library stores parameter combinations corresponding to defects such as "insufficient tape peel strength" and "uneven adhesive layer thickness." For example, historical data shows that when the temperature is below 60°C and the adhesive viscosity is below 1200 cP, the defect of insufficient peel strength is more likely to occur. The corresponding feature vector is (temperature < 60°C, viscosity < 1200 cP). When the temperature fluctuation exceeds 8°C and the substrate speed fluctuation exceeds 1 m / min, the adhesive layer thickness is more likely to be uneven. The feature vector is (temperature fluctuation > 8°C, speed fluctuation > 1 m / min).

[0061] Calculate the matching degree between the parameter fluctuation data of the current time window and the initial classification standard. Taking the temperature fluctuation amplitude of 5°C and the viscosity fluctuation amplitude of 150cP in the first time window as an example, calculate the Euclidean distance between it and the "uneven adhesive layer thickness" feature vector. Assuming that the weight of the temperature fluctuation amplitude is 0.6, the weight of the viscosity fluctuation amplitude is 0.4, the temperature fluctuation threshold of the historical feature vector is 8°C, and the viscosity fluctuation threshold is 200cP, then the standardized current data is (5 / 8=0.625, 150 / 200=0.75), the historical feature vector is (1, 1), and the Euclidean distance is , the matching degree is expressed by 1-0.45=0.55.

[0062] During cluster iterations, the cluster center is adjusted based on the matching degree. If the matching degree between the current data and multiple historical defect signatures falls below a preset threshold (e.g., 0.6), it is considered a new cluster candidate and the cluster center is recalculated. For example, if the parameter fluctuation data from the first three time windows all match the existing defect signatures with a matching degree of 0.5-0.55, the system merges these data into a new cluster group and iteratively calculates the central parameter value for that group, such as an average temperature fluctuation amplitude of 6°C or an average viscosity fluctuation amplitude of 160 cP.

[0063] The reliability of clustering results is assessed using classification purity. Classification purity is calculated based on the consistency of the matching between data within the same cluster group and historical defect signatures. For example, if a cluster group contains data from five time windows, and four of these data have a matching degree greater than 0.6 with the "uneven adhesive layer thickness" feature, and one has a matching degree of 0.5, the classification purity is 4 / 5 = 80%. When the classification purity exceeds 75%, the cluster group's results are considered reliable.

[0064] Filter out cluster groups whose matching degree with historical defect features exceeds a preset critical value (such as 0.6). For example, in the 5th time window, the temperature fluctuation amplitude reaches 7°C and the viscosity fluctuation amplitude is 180cP. The matching degree with the "uneven adhesive layer thickness" feature is calculated as follows: the normalized value of temperature fluctuation is 7 / 8=0.875, the normalized value of viscosity fluctuation is 180 / 200=0.9, and the Euclidean distance is 0. , the matching degree 1-0.16=0.84>0.6, and the cluster group is screened out.

[0065] The parameter combinations corresponding to the selected cluster groups are identified as potential production defect characteristics. For example, the parameter combination in the fifth time window (temperature fluctuation of 7°C and viscosity fluctuation of 180 cP) is identified as a potential defect characteristic because historical data shows that when these two parameters fluctuate beyond a certain range, the probability of uneven adhesive layer thickness increases.

[0066] During subsequent production, preventive measures were implemented to address this potential defect. For example, the coating machine's temperature control system was adjusted to increase the accuracy of the temperature sensor, keeping temperature fluctuations within ±3°C. The adhesive storage tank's agitation was optimized to reduce viscosity fluctuations. Furthermore, the monitoring frequency for this parameter combination was increased from data collection every 20 minutes to every 10 minutes, ensuring real-time monitoring of parameter changes.

[0067] Throughout the implementation process, the feature library for historical defective products needs to be continuously updated. For example, if subsequent production reveals that substrate speed fluctuations exceeding 0.5 m / min and temperature fluctuations exceeding 5°C can also lead to uneven adhesive layer thickness, this new parameter combination (speed fluctuation > 0.5 m / min, temperature fluctuation > 5°C) needs to be incorporated into the feature library, and the initial classification criteria of the clustering algorithm needs to be adjusted.

[0068] Furthermore, the time window division needs to be dynamically adjusted based on different product specifications and process requirements. For example, when producing double-sided tape with high-viscosity adhesives, fluctuations in adhesive viscosity have a greater impact on product quality. Therefore, the time window can be shortened to 10 minutes to more promptly detect abnormal viscosity fluctuations. The matching calculation weights used in the clustering algorithm also need to be adjusted based on process priorities. If the current batch of products requires higher peel strength, the weights for temperature and viscosity parameters should be increased, while the weight for substrate speed parameters should be reduced.

[0069] This feature clustering analysis method enables timely identification of abnormal parameter combinations that could lead to product defects during the production process, enabling proactive intervention and preventing the mass production of defective products. For example, in one production batch, cluster analysis identified a parameter combination in which the temperature consistently fluctuated between 60-62°C and the adhesive viscosity was below 1100 cP. Promptly adjusting the temperature to 65-70°C and adding adhesive additives to increase the viscosity prevented the entire batch from being scrapped due to insufficient peel strength. This process does not rely on specific experimental data verification, but rather relies on statistical analysis of historical data and dynamic matching of real-time production data, ensuring the reliability and practicality of the identification results.

[0070] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0071] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for processing a double-sided adhesive tape, characterized in that: include: Obtaining substrate paper and adhesive raw materials, processing the substrate paper and adhesive raw materials to form a pre-processed material set, and determining and outputting an initial process parameter configuration table; Determine the updated instruction set for the machining process based on the dynamic adjustment signal fed back from the initial process parameter configuration table; Analyzing the machining process update instruction set, performing hierarchical decomposition, classification, and aggregation on the machining process update instruction set, and determining target machining parameters; Acquire a set of equipment operation information, and determine and output a targeted process execution plan based on the equipment operation information set and the target processing parameters.

2. The method for processing a double-sided tape according to claim 1, characterized in that: The processing of the substrate base paper and the adhesive raw material to form a pre-processed material set, and determining and outputting an initial process parameter configuration table include: Processing the substrate base paper and adhesive raw materials to extract a base paper weight feature set, an adhesive viscosity feature, and a drying temperature feature; Analyze the base paper weight feature set to determine the thickness uniformity weight and the bonding strength score corresponding to each feature point; Determining a critical processing stage based on a curing cycle of the adhesive raw material, and determining a temperature attenuation coefficient based on the curing cycle and the critical processing stage; Constructing a multi-dimensional process vector according to the thickness uniformity weight, the bonding strength score, the temperature attenuation coefficient, and the adhesive viscosity characteristic; According to the multi-dimensional process vector, a matching search is performed on a preset historical production database to determine and output the initial process parameter configuration table.

3. The method for processing a double-sided adhesive tape according to claim 2, wherein: The multi-dimensional process vector is constructed according to the thickness uniformity weight, the bonding strength score, the temperature attenuation coefficient, and the adhesive viscosity characteristic, specifically including: The thickness weight parameter is determined according to the thickness deviation range of the base paper weight characteristic, the viscosity weight parameter is determined according to the flow performance of the adhesive viscosity characteristic, and the temperature weight parameter is determined according to the duration of the drying temperature characteristic; The thickness weight parameter, viscosity weight parameter, temperature weight parameter and temperature attenuation coefficient are weighted and fused to form a composite process vector including thickness dimension, viscosity dimension and temperature dimension.

4. The method for processing a double-sided tape according to claim 2, wherein: The step of determining a processing flow update instruction set based on the dynamic adjustment signal fed back from the initial process parameter configuration table includes: According to the initial process parameter configuration table, a real-time parameter visualization interface is provided for the production monitoring system, and the parameter space mapping effect is synchronously updated according to the monitoring data curve fed back by the system; Based on the monitoring data curve, identify the characteristics of potential production defects through feature cluster analysis, dynamically adjust the priority ranking of initial parameters, and generate a parameter update plan; Analyze the parameter update plan, evaluate the stability of the processing flow, determine process stability feedback information, and provide corresponding parameter adjustment suggestions to the operator, and receive confirmation instructions from the worker; According to the worker confirmation instruction, a processing flow update instruction set is determined.

5. The method for processing a double-sided adhesive tape according to claim 4, characterized in that: The analyzing the parameter updating scheme, evaluating the stability of the processing flow, and determining process stability feedback information includes: According to the parameter update scheme, the number of parameter dimensions, execution deviation interval, historical execution result distribution and parameter importance ranking of the extraction process are extracted; According to the process significance of each parameter, determine the process deviation tolerance threshold, historical execution qualified ratio and continuous execution consistency rate; Based on the number of parameter dimensions, the execution deviation interval, and the distribution of historical execution results, and according to the parameter importance ranking and the deviation tolerance threshold, a statistical stability determination condition is established; Determine the effective time range for process execution based on the curing cycle and the key processing stages; Based on the historical execution qualified ratio and the effective time range, according to the continuous execution consistency rate and the parameter importance ranking, a timing stability judgment condition is established; According to the statistical stability judgment condition and the temporal stability judgment condition, it is judged whether the statistical stability or temporal stability corresponding to the current parameter update scheme meets the requirements, and a judgment conclusion is determined, which is used as the process stability feedback information.

6. The method for processing a double-sided adhesive tape according to claim 5, characterized in that: The statistical stability determination condition is constructed based on the number of parameter dimensions, the execution deviation interval, and the historical execution result distribution, according to the parameter importance ranking and the deviation tolerance threshold, and specifically includes: Calculate the correlation between the number of parameter dimensions and the execution deviation range, analyze the matching degree between the distribution of historical execution results and the parameter importance ranking, and set the critical range of statistical stability based on the deviation tolerance threshold; The timing stability determination condition is constructed based on the historical execution qualified ratio and the effective time range, according to the continuous execution consistency rate and the parameter importance ranking, and specifically includes: Calculate the fluctuation range of the historical execution qualification ratio within the effective time range, analyze the temporal correlation between the continuous execution consistency rate and the parameter importance ranking, and set the critical range of temporal stability.

7. The method for processing a double-sided adhesive tape according to claim 6, characterized in that: The analyzing the processing flow update instruction set, performing hierarchical decomposition, classification, and aggregation on the processing flow update instruction set, and determining target processing parameters includes: Update the instruction set according to the machining process, and count the key parameter adjustment set and the auxiliary parameter correction set; According to the process update cycle set by the factory, according to the curing cycles corresponding to different batches in the processing process update instruction set, a number of update batches are divided to determine the update batch information set; Analyzing the key parameter adjustment set based on the update batch information set, and determining a redundancy adjustment amount corresponding to each parameter in each update batch according to a numerical drift ratio corresponding to each parameter in the key parameter adjustment set in historical update records; The target processing parameters are constructed according to the auxiliary parameter correction set, the updated batch information set, and the redundancy adjustment amount.

8. The method for processing a double-sided adhesive tape according to claim 7, characterized in that: The step of determining and outputting a targeted process execution plan based on the equipment operation information set and according to the target processing parameters includes: Analyzing the target processing parameters based on the equipment operation information set, and determining a number of target production equipment corresponding to each parameter adjustment item in the target processing parameters; Extract the historical collaboration records corresponding to each target production equipment based on the equipment operation information set to determine the historical usage count, historical debugging cost, historical qualified execution ratio, and historical failure risk of each parameter adjustment item on the current production line under the corresponding target production equipment; Based on the historical usage times, historical debugging costs, historical qualified execution ratios and historical failure risks of each parameter adjustment item under the corresponding target production equipment, comprehensive cost optimization processing is performed on each parameter adjustment item to determine the optimal production equipment corresponding to each parameter adjustment item, thereby constructing and outputting the targeted process execution plan.

9. The method for processing a double-sided adhesive tape according to claim 8, characterized in that: The comprehensive cost optimization process is performed on each parameter adjustment item based on the historical usage count, the historical debugging cost, the historical qualified execution ratio, and the historical failure risk of each parameter adjustment item under the corresponding target production equipment, specifically including: Calculate the weighted sum of historical usage times and historical debugging costs as the equipment usage cost indicator, and calculate the weighted sum of historical qualified execution ratio and historical failure risk as the effect risk cost indicator; Comprehensively compare the equipment use cost index with the effect risk cost index, and select the production equipment with the lowest comprehensive cost as the optimal equipment.

10. The method for processing a double-sided adhesive tape according to claim 4, characterized in that: The identification of potential production defect features through feature cluster analysis includes: Dividing the monitoring data curve into time windows and extracting the parameter fluctuation amplitude and frequency within each time window; The initial classification standard of the clustering algorithm is set as the historical defect product feature library, and clustering iteration is performed based on the matching degree between the parameter fluctuation amplitude and frequency and the initial classification standard; The reliability of the clustering results is evaluated by classification purity, and cluster groups whose matching degree with historical defect characteristics exceeds the preset critical value are screened out, and their corresponding parameter combinations are determined as potential production defect characteristics.

Images