Preparation method, system and device of fresh-keeping packaging bag for cold-chain food and storage medium

Abstract

The invention relates to a preparation method, system and device of a fresh-keeping packaging bag for cold-chain food and a storage medium, and the method comprises the following steps: obtaining historical performance parameters of packaging bags in historical batches, and carrying out batch quality identification to obtain packaging bag quality data; performing hyperspectral imaging monitoring on the coating area to obtain coating monitoring data, and performing coating analysis on the historical performance parameters to obtain a coating processing result; performing film performance analysis on the packaging bag quality data and the coating treatment result to obtain film performance parameters and initial process parameters; carrying out heat sealing position measurement on the coating treatment result, and carrying out sealing analysis according to the film performance to obtain a sealing performance analysis result; and performing packaging bag optimization on the packaging bag quality data according to the initial process parameters and the sealing performance analysis result to obtain a packaging bag preparation optimization scheme. According to the method, the preparation strategy can be flexibly adjusted, so that the package adapts to diversified cold chain application scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of fresh-keeping packaging bags, and in particular to a preparation method, system, device and storage medium for fresh-keeping packaging bags for cold chain food. Background Art

[0002] Existing cold chain food packaging bag manufacturing technologies often focus solely on single material performance indicators, such as the mechanical strength of the substrate or simple barrier properties, while ignoring the material's adaptability to low-temperature environments and the impact of the overall bag's performance coordination on preservation. This one-sided manufacturing approach can lead to performance failures in actual cold chain environments, such as low-temperature embrittlement, reduced sealing performance, or poor barrier properties, which in turn impacts the preservation quality and shelf life of cold chain foods. Summary of the Invention

[0003] The main purpose of the present invention is to provide a method, system, device and storage medium for preparing fresh-keeping packaging bags for cold chain food, which can flexibly adjust the preparation strategy to make the packaging adapt to various cold chain application scenarios.

[0004] To achieve the above object, the present invention provides a method for preparing a fresh-keeping packaging bag for cold chain food, comprising: Obtain historical performance parameters of historical batches of packaging bags, perform batch quality identification, and obtain packaging bag quality data; Performing hyperspectral imaging monitoring on the coating area to obtain coating monitoring data, and performing coating analysis on the historical performance parameters to obtain coating treatment results; Performing film performance analysis on the packaging bag quality data and the coating treatment results to obtain film performance parameters and initial process parameters; measuring the heat sealing position of the coating treatment result, and performing sealing analysis based on the film performance to obtain a sealing performance analysis result; The packaging bag quality data is prepared and optimized based on the initial process parameters and the sealing performance analysis results to obtain a packaging bag preparation optimization plan.

[0005] Furthermore, the acquisition of historical performance parameters of historical batches of packaging bags, performing quality identification, and generating packaging bag quality characteristic data includes: Extracting elongation at break from the historical performance parameters to obtain tensile strength data; Performing thickness oxygen permeability analysis on the historical performance parameters to obtain oxygen permeability parameters; Extracting heat deformation temperature based on the historical performance parameters to obtain temperature adaptability data; performing batch-to-batch dispersion calculation on the tensile strength data, the oxygen permeability parameter, and the temperature adaptability data to obtain batch stability data; The packaging bag quality data is obtained by dynamically matching the batch stability data with a preset quality threshold.

[0006] Furthermore, the coating area is subjected to hyperspectral imaging monitoring to obtain coating monitoring data, and the historical performance parameters are subjected to coating analysis to obtain coating treatment results, including: Performing hyperspectral imaging scanning on the coating area during the coating process to obtain hyperspectral imaging data; Extracting spectral features from the hyperspectral imaging data to obtain coating spectral feature data; Dividing the region into uniformity regions according to the coating spectrum characteristic data to obtain coating thickness distribution data; Performing coating process matching on the historical performance parameters to obtain coating process correlation data; Positioning defects in the coating area according to the coating process correlation data to obtain coating defect distribution data; A coating quality assessment is performed on the coating thickness distribution data and the coating defect distribution data to obtain the coating processing result.

[0007] Furthermore, the film performance analysis is performed on the packaging bag quality data and the coating treatment results to obtain film performance parameters and initial process parameters, including: Performing a low-temperature oxygen permeability bending test on the packaging bag quality data to obtain low-temperature adaptability data of the packaging bag; Measuring the coating thickness of the coating treatment result according to the low temperature adaptation data of the packaging bag to obtain coating distribution characteristic parameters; Performing a coating peel strength test on the packaging bag quality data according to the coating distribution characteristic parameters to obtain a bonding performance evaluation result; Performing coating compounding on the packaging bag quality data according to the combined performance evaluation results to obtain composite film data; Performing tensile modulus and tear strength tests on the composite film data to obtain film performance parameters; Film preparation parameters are identified based on the film performance parameters to obtain the initial process parameters.

[0008] Furthermore, the heat sealing position of the coating treatment result is measured, and a sealing analysis is performed based on the film performance to obtain a sealing performance analysis result, including: Performing surface temperature field scanning measurement on the coating treatment result to obtain heat sealing position positioning data; Perform heat seal area shape recognition based on the heat seal position positioning data to obtain heat seal geometric parameters; performing stress analysis on the heat seal geometric parameters to obtain heat seal stress analysis data; Measuring the sealing adhesive strength and airtightness of the film according to the heat sealing stress analysis data to obtain sealing strength test data and airtightness performance evaluation data; A performance evaluation is performed based on the sealing strength test data and the airtight performance evaluation data to obtain the sealing performance analysis result.

[0009] Furthermore, the packaging bag quality data is optimized based on the initial process parameters and the sealing performance analysis results to obtain a packaging bag preparation optimization plan, including: Matching the initial process parameters to the molding equipment to obtain equipment control parameters; Optimizing the sealing process by adjusting the equipment control parameters according to the sealing performance analysis results to obtain sealing process control parameters; Cutting and positioning the packaging bag quality data, and setting the film thickness according to the sealing process control parameters to obtain packaging bag film parameters; Perform coating uniformity compensation according to the sealing process control parameters and the packaging bag film parameters to obtain coating compensation parameters; Dynamically adjusting the coating compensation parameters and the packaging bag film parameters to obtain a process adjustment sequence; The initial process parameters are iteratively optimized according to the process adjustment sequence to obtain an optimized solution for packaging bag preparation.

[0010] The present invention further provides a system for preparing a fresh-keeping packaging bag for cold chain food, which is applied to any of the above-mentioned methods for preparing a fresh-keeping packaging bag for cold chain food, comprising: An acquisition module, which is used to obtain historical performance parameters of historical batches of packaging bags, perform batch quality identification, and obtain packaging bag quality data; An analysis module, the analysis module is used to perform hyperspectral imaging monitoring on the coating area to obtain coating monitoring data, perform coating analysis on the historical performance parameters, and obtain coating treatment results; a correlation module, the correlation module being used to perform film performance analysis on the packaging bag quality data and the coating treatment results to obtain film performance parameters and initial process parameters; a processing module, the processing module being configured to measure the heat sealing position of the coating processing result and perform sealing analysis based on the film performance to obtain a sealing performance analysis result; A control module is used to optimize the packaging bag quality data according to the initial process parameters and the sealing performance analysis results to obtain an optimization plan for packaging bag preparation.

[0011] The present invention also provides a device for preparing a fresh-keeping packaging bag for cold chain food, comprising: Memory, used to store programs; The processor is used to execute the program to implement each step of the method for preparing a fresh-keeping packaging bag for cold chain food as described in any one of the above.

[0012] The present invention also provides a storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any of the above methods.

[0013] The present invention provides a method, system, device and storage medium for preparing a fresh-keeping packaging bag for cold chain food, which has the following beneficial effects: Through comprehensive analysis of quality identification and coating monitoring data from historical batches of packaging bags, the performance stability of packaging bags can be more comprehensively evaluated, avoiding the problem of insufficient low-temperature adaptability caused by relying solely on a single material indicator, thereby improving packaging reliability in cold chain environments. Combined with hyperspectral imaging monitoring and coating analysis, it is possible to accurately identify the uniformity and defects of the coating process, optimize the coating process, reduce the risk of barrier performance degradation or sealing failure due to uneven coating, and improve the overall preservation effect of the packaging bag. Based on film performance analysis and optimization of initial process parameters, the mechanical strength, low-temperature toughness and barrier properties of the packaging bag can be coordinated, avoiding low-temperature embrittlement or poor sealing problems caused by performance imbalance in traditional preparation methods, and enhancing the adaptability of packaging bags in cold chain environments. Through heat seal position measurement and sealing performance analysis, the heat sealing process can be accurately controlled, reducing air leakage or water seepage caused by loose sealing, ensuring the sealing reliability of the packaging bag during long-term low-temperature storage and transportation, and extending the shelf life of food. Based on the optimized adjustment of process parameters and sealing performance, the preparation plan can be dynamically optimized so that the packaging bags can maintain stable performance under different cold chain conditions, reduce quality fluctuations caused by process deviations, and improve production consistency and product yield. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a flow chart of a method for preparing a fresh-keeping packaging bag for cold chain food provided by the present invention; Figure 2 This is a structural diagram of a system for preparing fresh-keeping packaging bags for cold chain food provided by the present invention; Figure 3 This is a structural diagram of a device for preparing fresh-keeping packaging bags for cold chain food provided by the present invention.

[0015] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0018] Reference Figure 1 As shown, the present invention provides a method for preparing a fresh-keeping packaging bag for cold chain food, comprising: Step S1: Obtain historical performance parameters of historical batches of packaging bags, perform batch quality identification, and obtain packaging bag quality data; Step S2: performing hyperspectral imaging monitoring on the coating area to obtain coating monitoring data, performing coating analysis on the historical performance parameters to obtain coating treatment results; Step S3: performing film performance analysis on the packaging bag quality data and coating treatment results to obtain film performance parameters and initial process parameters; Step S4: measuring the heat sealing position of the coating treatment result, and performing sealing analysis based on the film performance to obtain a sealing performance analysis result; Step S5: Optimizing the packaging bag quality data based on the initial process parameters and the sealing performance analysis results to obtain an optimized packaging bag preparation solution.

[0019] Based on the above steps, the detailed steps are as follows: Step S1: The performance parameters of historical batches of packaging bags serve as the foundation for quality identification. These parameters include physical and chemical indicators such as mechanical strength, thickness uniformity, air permeability, and heat resistance. By collecting this historical data, a baseline for packaging bag quality can be established for subsequent analysis. The quality identification process involves data cleaning, outlier removal, and statistical analysis to ensure data accuracy and representativeness. Statistical methods such as mean, standard deviation, and coefficient of variation can be used to assess quality fluctuations between batches.

[0020] Performance parameters for historical batches are extracted from the production database, including metadata such as production date, raw material batch, and process conditions. This data is standardized to eliminate dimensional differences and facilitate subsequent comparisons. Visualization tools such as boxplots or scatterplots are used to visually display the quality distribution of different batches and identify outliers. Integrating domain knowledge, outlier batches are investigated in depth to determine whether they represent measurement errors or true quality issues. The resulting bag quality data includes not only the raw performance parameters but also the analyzed quality scores or classification labels, providing structured input for subsequent steps.

[0021] Step S2: Hyperspectral imaging technology captures the spectral characteristics of the coated area, providing detailed information in both spatial and spectral dimensions. A hyperspectral camera scans the coated area, acquiring the reflectance spectrum of each pixel and generating coating monitoring data. This data reveals coating uniformity, thickness distribution, and defects such as bubbles, cracks, or uncovered areas. The core of coating analysis is correlating hyperspectral data with historical performance parameters to explore the relationship between coating characteristics and packaging bag performance.

[0022] The hyperspectral imaging system scans the coated area under standard lighting conditions to ensure data consistency. Spectral preprocessing methods such as denoising, baseline correction, and normalization are used to improve data quality. Chemometric methods such as partial least squares regression or support vector machines are used to develop predictive models linking spectral features with coating properties (such as adhesion and barrier properties). Furthermore, the impact of coating process conditions (such as temperature, speed, and formulation) on coating quality is analyzed by integrating them with historical performance parameters. Coating results, including coating quality scores, defect distribution maps, and optimization recommendations, provide key input for thin film performance analysis.

[0023] Step S3: Film Performance Analysis comprehensively evaluates the composite material's mechanical, barrier, thermal, and optical properties. Mechanical performance testing includes tensile strength, elongation at break, tear strength, and puncture strength, reflecting the film's durability during the packaging process. Barrier performance, characterized by parameters such as oxygen transmission rate, carbon dioxide transmission rate, and water vapor transmission rate, is directly related to food preservation. Thermal performance analysis includes heat deformation temperature, Vicat softening point, and heat seal strength temperature curve to determine the film's operating temperature range and heat seal process window.

[0024] Film performance parameters are obtained using standardized testing methods. Tensile testing is performed according to ASTM D882, gas permeability testing follows ASTM D3985, and heat seal strength is determined according to ASTM F88. The testing environment maintains strict temperature and humidity conditions to ensure data reproducibility and reliability. The performance parameter database is established by statistically analyzing the results of multiple parallel tests to calculate mean values, standard deviations, and confidence intervals.

[0025] Initial process parameters are determined based on film performance analysis, including key parameters such as heat sealing temperature, pressure, time, and molding temperature. Orthogonal experimental design is used to optimize process parameter combinations and establish a mathematical model linking process parameters and product quality. The process window is determined by balancing equipment capacity, production efficiency, and product quality. These initial process parameters provide operational guidance for subsequent sealing analysis and packaging molding, and their accuracy directly impacts the consistency and reliability of the final product.

[0026] Step S4: Heat seal position measurement: Precision measuring equipment is used to determine the heat seal area distribution and geometric parameters on the film surface. An infrared thermal imager monitors the temperature distribution during the heat seal process in real time, ensuring uniformity across the entire seal width. A laser displacement sensor measures thickness variations in the heat seal area to assess the material's fluidity and deformation characteristics during the heat seal process. Precise control of the heat seal position is crucial to the packaging bag's sealing reliability and appearance quality, requiring measurement accuracy of ±0.1mm.

[0027] Sealing analysis is based on the film's rheological behavior and interfacial adhesion mechanisms under heat-sealing conditions. During the heat-sealing process, the coated film undergoes complex physicochemical changes between the surface coating and the substrate. Heating causes the montmorillonite nanosheets to rearrange their orientation, affecting molecular diffusion and mechanical interlocking at the sealing interface. Differential scanning calorimetry (DSC) analyzes the enthalpy changes during the heat-sealing process to determine the optimal heat-sealing temperature range. Scanning electron microscopy (SEM) is used to observe the micromorphology of the heat-sealing interface and evaluate the seal quality.

[0028] The seal performance analysis covers key indicators such as heat seal strength, seal integrity, and pressure resistance. The heat seal strength test utilizes a 180-degree peel test and a T-peel test to simulate the stresses experienced by the packaging bag during transportation and storage. The seal integrity test uses the bubble method to detect microporous defects, ensuring the airtightness of the package. The pressure resistance test evaluates the deformation and failure behavior of the packaging bag under internal and external pressure differentials. These analysis results provide a scientific basis for the final determination of the packaging molding process, ensuring the safety and effectiveness of cold chain food packaging.

[0029] Step S5: Initial process parameters provide the foundation for producing high-quality film, while the sealing performance analysis results identify areas for improvement in the heat-sealing process. The goal of manufacturing optimization is to integrate these two types of data and adjust production parameters to ensure the optimal balance between mechanical properties, sealing reliability, and production efficiency. This optimization process involves adjusting the coating process, optimizing heat-sealing parameters, or refining the material formulation, ultimately resulting in an actionable manufacturing plan.

[0030] Design of Experiments (DOE) methods, such as orthogonal experiments or response surface optimization, are used to explore the impact of different process parameter combinations on packaging bag performance. Benchmark experiments are conducted based on the initial process parameters, and key variables (such as coating speed, drying temperature, and heat sealing pressure) are adjusted based on the sealing performance analysis results. The feasibility of the optimization plan is verified through simulation (such as finite element analysis) or small-scale pilot production. The final output of the optimized packaging bag production plan includes a table of adjusted process parameters, quality control standards, and exception handling strategies to ensure stability and consistency in large-scale production. This plan can be directly applied to the production line to improve the overall performance and yield rate of the packaging bags.

[0031] The present invention provides a method for preparing fresh-keeping packaging bags for cold chain food. Through comprehensive analysis of the quality identification and coating monitoring data of historical batches of packaging bags, it is possible to more comprehensively evaluate the performance stability of the packaging bags, avoid the problem of insufficient low-temperature adaptability caused by relying solely on a single material indicator, and thus improve the packaging reliability in the cold chain environment. Combined with hyperspectral imaging monitoring and coating analysis, it is possible to accurately identify the uniformity and defects of the coating process, optimize the coating process, reduce the risk of barrier performance degradation or sealing failure due to uneven coating, and improve the overall fresh-keeping effect of the packaging bag. Based on film performance analysis and optimization of initial process parameters, it is possible to coordinate the mechanical strength, low-temperature toughness and barrier properties of the packaging bag, avoid low-temperature embrittlement or poor sealing problems caused by performance imbalance in traditional preparation methods, and enhance the adaptability of the packaging bag in the cold chain environment. Through heat seal position measurement and sealing performance analysis, the heat sealing process can be accurately controlled, air leakage or water seepage caused by lax sealing can be reduced, and the sealing reliability of the packaging bag during long-term low-temperature storage and transportation can be ensured, extending the shelf life of food. Based on the optimized adjustment of process parameters and sealing performance, the preparation plan can be dynamically optimized so that the packaging bags can maintain stable performance under different cold chain conditions, reduce quality fluctuations caused by process deviations, and improve production consistency and product yield.

[0032] In one embodiment, historical performance parameters of historical batches of packaging bags are obtained, quality identification is performed, and packaging bag quality characteristic data is generated, including: Elongation at break is a key indicator for measuring the ductility and fracture resistance of packaging bag materials during stretching, directly impacting the durability and impact resistance of packaging bags in actual use. Historical performance parameters include tensile test data of materials from different batches and under different production conditions, which records the material's deformation behavior during stress. The process of extracting elongation at break involves analyzing the original tensile curve and identifying the maximum elongation percentage of the material before fracture. This parameter reflects the material's ability to plastically deform when stretched to fracture. Higher values ​​indicate greater toughness and the ability to withstand greater deformation without breaking.

[0033] Generating tensile strength data relies not only on a single value for elongation at break but also on the stress-strain relationship during stretching. The tensile test data in historical performance parameters includes test results from multiple samples, each with different performance at different stretching rates and under different environmental conditions. Statistical analysis of these sample data allows the calculation of the average elongation at break, standard deviation, and extreme value range, forming a comprehensive data set reflecting the material's tensile properties. The accuracy of tensile strength data depends on the completeness of the historical data and the coverage of the test conditions to ensure that the data represents the material's performance in actual applications.

[0034] Extracting elongation at break is closely related to the subsequent calculation of batch-to-batch dispersion. As one of the foundations of batch stability assessment, the fluctuation range of tensile strength data directly impacts the reliability of batch stability data. If the elongation at break of a particular batch deviates significantly from the historical average, it indicates anomalies in raw materials or process parameters during the production process. Extracting tensile strength data provides mechanical performance support for the subsequent integration of oxygen permeability parameters and temperature adaptability data. Together, these three elements constitute the core elements of packaging bag quality characteristic data.

[0035] Oxygen permeability is a key indicator for evaluating the barrier properties of packaging bags, directly impacting the freshness and shelf life of the contents. The thickness and oxygen permeability data in the historical performance parameters are obtained through laboratory testing, recording the oxygen transmission rates of different batches of packaging bags at different thicknesses. The core of thickness oxygen permeability analysis lies in establishing a correlation between thickness and oxygen permeability, revealing the stability of the material's barrier properties. The oxygen permeability parameter not only reflects the inherent properties of the material but is also affected by thickness uniformity during the production process, resulting in variations in oxygen permeability at different locations within the same batch.

[0036] Generating oxygen permeability parameters requires stratifying historical test data. Based on the thickness distribution of the packaging bags, the data is divided into several intervals, and the average oxygen permeability and its fluctuation range are calculated within each interval. This process can identify areas where thickness is sensitive to oxygen permeability. For example, when the thickness falls below a certain critical value, the oxygen permeability increases sharply. Oxygen permeability parameters also include temporal trends. Some materials exhibit barrier performance degradation after long-term storage. If such a phenomenon is observed in historical data, it must be noted in the parameters. The comprehensiveness of oxygen permeability parameters provides a basis for the barrier performance dimension for subsequent batch stability assessments.

[0037] Thickness oxygen permeability analysis and tensile strength data extraction are synergistic. Mechanical and barrier properties of packaging bags often trade off against each other; for example, increasing thickness improves barrier properties but reduces flexibility. Combining oxygen permeability parameters with tensile strength data can reveal the balance point in material design and provide guidance for quality optimization. The thermal stability of oxygen permeability parameters is also correlated with subsequent temperature adaptability data. The oxygen permeability of certain materials increases significantly in high-temperature environments. This coupling effect must be reflected in quality characteristic data.

[0038] Heat deformation temperature (HDT) is a core parameter for evaluating the heat resistance of packaging bag materials, determining their shape stability and ability to retain functionality in high-temperature environments. The heat deformation test data within the historical performance parameters records the material's deformation behavior under varying temperature gradients and is obtained using standard thermomechanical analysis methods. The key to extracting the HDT is identifying the critical point in the temperature-deformation curve where the material begins to soften significantly. The temperature corresponding to this point is the HDT. Temperature adaptability data must include not only this critical value but also the material's deformation rate below and above the critical temperature to fully reflect its thermal stability.

[0039] The generation of temperature adaptability data needs to consider the consistency of historical test conditions. Different batches of thermal deformation tests have differences in parameters such as heating rate and load size, and these interfering factors need to be eliminated through data normalization. For packaging bags made of composite materials, it is also necessary to analyze the synergistic effect of the thermal properties of each component material. For example, some barrier layers degrade before the substrate softens. Such special phenomena should be noted in the temperature adaptability data to avoid a single thermal deformation temperature value covering up the complex behavior of the material. The time dimension of the temperature adaptability data also needs to be paid attention to. Some materials show performance degradation after multiple thermal cycles. If there is such a long-term thermal aging record in the historical data, it needs to be reflected in the parameters.

[0040] Heat deformation temperature extraction is inherently correlated with oxygen permeability parameters. Under high-temperature conditions, the oxygen permeability of packaging bags increases due to material softening. This coupling effect needs to be revealed through cross-analysis of temperature adaptability data and oxygen permeability parameters. Temperature adaptability data also provides thermal performance support for batch stability assessments. A significant deviation of a batch's heat deformation temperature from the historical average indicates an anomaly in the additive ratio or curing process. The combination of temperature adaptability data and tensile strength data can also assess the degradation of mechanical properties of materials under temperature fluctuations, such as low-temperature embrittlement or high-temperature creep. These multi-dimensional correlations together constitute the integrity of the quality characteristic data of packaging bags.

[0041] Batch stability data is a core indicator for measuring the consistency of packaging bag production quality. Its calculation relies on the distribution characteristics of tensile strength data, oxygen permeability parameters, and temperature adaptability data across multiple batches. Calculating dispersion is not a simple statistical variance or range, but rather a comprehensive assessment of the fluctuation patterns of each performance parameter within and between batches. The dispersion of tensile strength data reflects the stability of the material's mechanical properties. If the elongation at break distribution of certain batches deviates significantly from historical benchmarks, it indicates uneven raw material mixing or inaccurate control of the stretching process. The dispersion of oxygen permeability parameters reflects the controllability of barrier properties. Differences in oxygen permeability between different areas of the same batch can be attributed to uneven thickness or coating defects. The dispersion of temperature adaptability data is related to the reliability of thermal stability. Abnormally high fluctuations in heat deformation temperature suggest batch-specific deviations in the curing process.

[0042] The calculation of dispersion requires a multi-dimensional comparison strategy. The performance parameters of each sample within the same batch are first calculated for intra-group dispersion to identify local fluctuations in the production process; the same parameters between different batches are then calculated for inter-group dispersion to evaluate the long-term stability of the production system. The coupled dispersion of tensile strength and oxygen permeability also requires attention. For example, a batch has both high tensile dispersion and low oxygen permeability dispersion, revealing the special influence of the material modification process. Cross-discrete analysis of temperature adaptability data and the other two parameters can reveal the role of environmental factors. For example, batches produced in high temperature seasons show systematic thermal deformation temperature offsets. Batch stability data ultimately integrates these discrete features to form a structured data set containing longitudinal fluctuation trends and lateral anomalies.

[0043] The dynamic matching of batch stability data and subsequent quality thresholds forms a closed loop. The discreteness calculation results must retain the units and dimensions of the original parameters to avoid normalization processing that obscures the actual engineering significance. For composite packaging bags, the discreteness of each functional layer needs to be calculated in layers and then weighted and integrated. For example, the temperature adaptability discreteness of the inner heat-sealing material should be given a higher weight. Special batches in historical data (such as pilot production batches and process verification batches) need to be marked when calculating discreteness to prevent them from interfering with the stability benchmark. Time series analysis of batch stability data can also reveal potential influencing factors such as equipment wear or changes in raw material suppliers. These in-depth information provides a basis for the dynamic adjustment of quality thresholds.

[0044] The preset quality thresholds are not fixed numerical boundaries, but rather a flexible evaluation system based on historically optimal batch performance. The dynamic matching process employs a progressive comparison strategy: the tensile strength dispersion in the batch stability data is first compared with the mechanical performance module within the threshold range. If the dispersion falls within the yellow warning range, a review of the impact resistance of the packaging bags for that batch is triggered. The oxygen permeability dispersion is then compared with the barrier performance threshold. Batches exceeding the red warning line are directly identified as at risk of barrier failure. The temperature adaptability dispersion is ultimately matched with the thermal stability threshold, incorporating a seasonal correction factor (e.g., a 5% relaxation of the temperature variation tolerance for summer production batches). This hierarchical matching mechanism avoids misjudgments caused by single parameter rejection and maintains the systematic nature of quality evaluation.

[0045] The core of dynamic matching lies in the threshold self-learning mechanism. When the tensile strength dispersion of three consecutive batches consistently exceeds the historical benchmark by 15%, the mechanical module of the quality threshold will automatically adjust upward to the premium standard. Conversely, if the oxygen permeability parameter dispersion continuously exceeds the threshold, the system will generate a recommendation for testing the raw material moisture content. The packaging bag quality data output includes three judgment results: basic compliance (whether it meets industry standards), process stability (whether it meets production control requirements), and excellence rating (whether it meets customer customization requirements). For food and pharmaceutical-grade packaging bags, dynamic matching also introduces derived thresholds for microbial barrier performance. Even if the oxygen permeability parameter is qualified, if the batch stability data shows a surge in surface roughness dispersion, a hygiene performance warning will still be triggered.

[0046] The generation of quality data forms a closed-loop verification process with all the aforementioned steps. If unusual fluctuations in tensile strength data are determined to be random errors during batch stability calculations, dynamic matching will utilize supplemental test data from the same batch for secondary verification. If the interaction between oxygen permeability parameters and temperature adaptability data is significant during the dispersion calculation, the coupling correction factor will be mandatory during quality threshold matching. The final output of packaging bag quality data includes three dimensions: original parameter value, dispersion level, and threshold compliance, along with a timestamp and process version number. This structured data format not only meets the immediate decision-making needs of factory inspection, but also provides a traceable analytical foundation for subsequent process optimization, achieving a complete closed-loop quality control process from detection to improvement.

[0047] This example constructs a multi-dimensional data system for packaging bag quality characteristics by extracting key indicators such as elongation at break, oxygen permeability, and heat deformation temperature from historical performance parameters, enabling a comprehensive quantitative assessment of packaging bag performance. By calculating inter-batch dispersion, it accurately identifies quality fluctuations during the production process and promptly detects anomalies in raw materials or process parameters, effectively improving the accuracy of quality control. A dynamic matching mechanism compares batch stability data against preset quality thresholds, ensuring the objectivity of quality assessments while automatically adjusting evaluation criteria based on actual production conditions, significantly enhancing the adaptability of quality management.

[0048] In one embodiment, hyperspectral imaging monitoring is performed on the coating area to obtain coating monitoring data, and coating analysis is performed on the historical performance parameters to obtain coating treatment results, including: Hyperspectral imaging is a key step in obtaining optical information about the coated surface. The coating process presents potential challenges, such as material distribution and thickness variations. Hyperspectral imaging captures reflected or transmitted spectral data across different wavelengths to generate multidimensional image information. In practice, a hyperspectral camera continuously scans the coated area, covering the entire spectral range from visible light to near-infrared and even wider. During the scanning process, the coated area is divided into a number of pixels, each corresponding to a set of continuous spectral curves.

[0049] These curves reflect the optical properties of the coating material at different wavelengths, such as absorption peaks and reflectivity. Hyperspectral imaging data is stored in the form of a three-dimensional data cube, which includes spatial and spectral dimensions. The spatial dimension records the geometric distribution of the coating area, and the spectral dimension records the spectral characteristics of each pixel. During scanning, it is necessary to ensure stable lighting conditions to avoid interference from ambient light, while controlling the scanning speed and resolution to ensure data accuracy. Dynamic changes in the coating area affect the imaging quality, so it is necessary to simultaneously record the coating process parameters such as temperature, humidity, and coating speed to provide contextual support for subsequent analysis. The quality of hyperspectral imaging data directly determines the reliability of subsequent feature extraction and analysis.

[0050] Spectral feature extraction is a core step in extracting valuable information from hyperspectral imaging data. The spectral characteristics of coating materials are closely related to their chemical composition and physical state. Raw hyperspectral data contains a large amount of redundant information, requiring preprocessing to remove noise and correct for baseline drift. After preprocessing, key spectral features are extracted using feature selection or transformation methods. For example, specific functional groups in coating materials exhibit absorption or reflection properties at specific wavelengths, and these wavelengths can be used as characteristic bands.

[0051] Coating spectral feature data not only contains the intensity information of a single band, but also involves derived features such as band combinations, derivative spectra, and normalized indices. Feature extraction must be combined with the known optical properties of the coating material. For example, the absorption peak of polymer films in the near-infrared region is related to molecular vibrations. Overfitting must be avoided during the extraction process to ensure that the features have physical meaning and distinguishability. Coating spectral feature data is usually represented in the form of a two-dimensional matrix, with each row corresponding to a spatial pixel and each column corresponding to a characteristic variable. This data provides input for subsequent uniformity classification and defect detection, and the completeness of its features directly affects the accuracy of coating quality assessment.

[0052] Uniformity region segmentation is a key step in inferring the spatial distribution of coating thickness based on spectral signatures. Within the coating spectral signature data, the spectral similarity of pixels at different locations reflects coating uniformity. Using clustering or classification algorithms, the coating area is divided into several subregions, each with consistent spectral signatures but distinct differences between them. This segmentation should take into account the desired coating process objectives, such as the ideal uniform coating thickness distribution.

[0053] Coating thickness distribution data is obtained by establishing a spectral feature and thickness calibration model based on calibration samples measured in the laboratory. The thickness distribution data is presented in the form of a spatial map, with the estimated thickness value of each pixel or sub-area marked. Edge effects and transition areas need to be processed during the segmentation process to avoid human-introduced errors. Thickness distribution data not only reveals overall uniformity, but also identifies local areas that are too thick or too thin, providing a basis for process adjustments. This step is synergistic with defect location. Areas with abnormal thickness correspond to potential defects and need to be further verified in subsequent steps. The accuracy of thickness distribution data depends on the correlation between spectral features and thickness, so the accuracy of early feature extraction is crucial.

[0054] Coating process correlation data is generated by analyzing the relationship between historical performance parameters and the current coating process. The goal is to establish a mapping relationship between process parameters and coating quality. Historical performance parameters include coating speed, temperature, humidity, material ratio, coating equipment status, etc. These parameters affect coating results in different batches or under different production conditions. The core of coating process matching lies in identifying which historical parameter combinations produce the optimal coating quality and comparing them with the current coating process to see if there are any deviations.

[0055] Collect historical coating data, including coating process parameters and corresponding quality inspection results for both successful and failed batches. Through data mining or statistical analysis, identify patterns in the impact of key process parameters. For example, higher coating speeds lead to uneven thickness, while specific temperature ranges improve material flow. Coating process-related data can be presented as optimized parameter combinations, threshold limits for key parameters, or process adjustment recommendations. This data not only explains potential issues in the current coating process but also provides a reference for subsequent defect location.

[0056] Defect location is the process of identifying anomalies or defective areas within a coating area based on coating process correlation data and coating thickness distribution data. Coating defects can manifest as localized thickness anomalies, missing material, bubbles, cracks, or contamination. Coating defect distribution data is presented as a spatial map or coordinate table, indicating the location, type, and severity of the defect.

[0057] Combined with data related to the coating process, it is possible to analyze which process deviations lead to specific defects. For example, excessive coating speeds can lead to material accumulation at the edge, while excessively low temperatures can cause uneven curing. Subsequently, coating thickness distribution data can be used to identify areas where thickness exceeds the expected range. Furthermore, anomalous spectral features in hyperspectral imaging data, such as localized reflectivity spikes, can also aid defect detection. Defect localization can employ threshold segmentation, pattern recognition, or machine learning methods to distinguish between properly coated areas and defective regions.

[0058] Coating defect distribution data is not only used for quality assessment but also provides feedback for coating process adjustments, such as optimizing the coating path or adjusting the material ratio. This step is closely linked to coating quality assessment, as the severity and distribution density of defects directly influence the final coating process outcome.

[0059] Coating quality assessment is the process of quantitatively evaluating the overall effectiveness of a coating process by combining coating thickness distribution data with defect distribution data. Coating process results typically include a quality grade determination (e.g., acceptable, unacceptable, or requiring rework), an analysis of key issues, and recommendations for improvement.

[0060] Coating quality evaluation criteria are set, such as the allowable thickness fluctuation range, maximum defect size, or defect density threshold. The coating thickness distribution data is then compared with the standard to assess overall uniformity. Defect coverage or severity index is calculated, combined with the defect distribution data. If the coating thickness is uniform and defects are minimal, the coating is considered acceptable. If there are severe local defects or large areas of uneven thickness, the coating is considered unacceptable and process adjustments may be required.

[0061] The generation of coating process results relies not only on objective data but also on industry standards or customer requirements. For example, food packaging requires higher coating uniformity than industrial packaging. The conclusion of this step directly influences production decisions, such as whether to release the current batch, whether process optimization is required, or whether equipment maintenance is needed.

[0062] This embodiment uses hyperspectral imaging technology to monitor the coating area in real time, which can fully obtain the spatial distribution and spectral characteristic information of the coating material, and realize precise control of the coating quality. The method based on spectral feature extraction and uniformity area division can accurately identify the coating thickness distribution, effectively avoiding the subjectivity and limitations of traditional manual inspection. Combined with historical process parameters for matching analysis, it is possible to quickly locate coating defects and trace the root causes of process problems, significantly improving the diagnostic efficiency of quality problems. By establishing a comprehensive evaluation system for coating thickness distribution and defect distribution, a quantitative evaluation of coating quality is achieved, providing a reliable basis for production process optimization. This technical solution not only improves the stability and consistency of the coating process, but also reduces the defective product rate, while reducing the cost of manual inspection, and has significant economic benefits and application value.

[0063] In one embodiment, film performance analysis is performed on the packaging bag quality data and coating process results to obtain film performance parameters and initial process parameters, including: Oxygen permeability testing utilizes a coulometric oxygen permeability tester. The packaging bag quality data sample is secured in a test chamber. Pure oxygen is introduced into one side, while a carrier gas is introduced into the other. An electrochemical sensor measures the amount of oxygen transmitted. The test temperature is set within the cold chain storage range of 2-8°C, with relative humidity controlled at 75%. The test lasts for 24 hours to ensure data stability. Thickness uniformity is strictly controlled during sample preparation to prevent edge effects from affecting test results. The oxygen permeability value directly reflects the substrate's ability to block oxygen. Modification with low-temperature plasticizers enhances the mobility of the substrate's molecular chains, and changes in intermolecular free volume affect the diffusion path of gas molecules.

[0064] The low-temperature bending test is carried out in accordance with the GB / T1043 standard. The packaging bag quality data samples are prepared into standard specimens and placed in a low-temperature environmental chamber for pretreatment for 2 hours. The test temperature is set to three gradients of -18°C, -10°C, and 0°C to simulate the temperature changes during freezing, refrigeration, and thawing. The bending test adopts a three-point bending method, the span is set to 16 times the thickness of the specimen, and the loading speed is controlled at 2mm / min. The bending stress-strain curves of the specimens at different temperatures are recorded, and the bending modulus and fracture strain are calculated. The addition of low-temperature plasticizers significantly improves the low-temperature toughness of the substrate, and the reduction of the glass transition temperature enables the material to maintain flexibility in a cold chain environment.

[0065] Low-temperature performance data for packaging bags combines information on oxygen permeability and low-temperature flexural properties to establish a performance characterization system for materials in cold chain environments. Oxygen permeability data reflects how barrier properties change with temperature, while low-temperature flexural data reveals the temperature dependence of mechanical properties. This data provides a basis for optimizing coating thickness, ensuring that composite films maintain optimal overall performance throughout the cold chain.

[0066] Coating thickness measurement determines the target design value for coating thickness based on the changing trends in oxygen permeability and mechanical properties of the packaging bag during low-temperature adaptation. When the substrate's oxygen permeability is high, the coating thickness is increased to compensate for the lack of barrier properties. When low-temperature flexural properties are poor, the coating thickness is appropriately reduced to prevent excessive rigidification of the composite film. Coating thickness is measured using a non-contact laser thickness gauge. Measurement points are evenly distributed across the film surface, creating a two-dimensional thickness distribution map to identify both regular and random variations in thickness.

[0067] Coating distribution characteristic parameters include statistical indicators such as average thickness, thickness standard deviation, thickness gradient, and local maximum thickness difference. Average thickness reflects the accuracy of the coating process setpoints, standard deviation indicates thickness uniformity, thickness gradient reveals the fluid dynamics of the coating process, and local maximum thickness difference identifies defective areas. Laser thickness measurement results are verified through scanning electron microscopy cross-sectional analysis to observe the topography of the coating-substrate interface and evaluate the coating's continuity and integrity.

[0068] Statistical methods are used to determine coating distribution characteristic parameters by processing large amounts of measurement data. This method establishes a probability density function for the thickness distribution and identifies outliers and systematic deviations. These parameters directly impact the barrier uniformity and mechanical consistency of the composite film, guiding the selection of sampling locations for subsequent peel strength testing. The spatial distribution of coating thickness reflects the process stability of the coating equipment and the rationality of parameter settings, providing valuable feedback for optimizing the coating process.

[0069] The sampling strategy for coating peel strength testing is based on statistical analysis of coating distribution characteristic parameters. Samples are prepared at locations representative of different thickness ranges. The peel test utilizes a 180-degree peeling method with a controlled peeling speed of 25 mm / min. The test environment is maintained at a temperature of 23°C ± 2°C and a relative humidity of 50% ± 5%. During sample preparation, standard adhesive tape is applied to the coating surface to ensure that the peeling interface is located at the junction of the coating and the substrate. The peel force-displacement curve records the mechanical response throughout the peeling process, identifying the peak, average, and fluctuation characteristics of the peel force.

[0070] The combined performance evaluation results cover three aspects: interfacial adhesion strength, peel mode analysis, and failure mechanism identification. Interfacial adhesion strength is calculated by dividing the peel force by the sample width and reflects the strength of the bond between the coating and the substrate. Peel mode analysis distinguishes between cohesive failure, adhesive failure, and mixed failure types by observing the surface morphology after peeling. Cohesive failure indicates insufficient internal strength of the coating, adhesive failure reflects weak interfacial bonding, and mixed failure indicates a good match between the interface and coating strength. Failure mechanism identification combines scanning electron microscopy analysis and chemical composition testing to reveal the interaction mechanism at the molecular level.

[0071] The dispersion state of nano-montmorillonite significantly influences the cohesive strength of the coating and its interfacial bonding with the substrate. Well-dispersed nanosheets enhance interfacial adhesion through physical entanglement and chemical bonding, while agglomerated particles form stress concentration points that reduce peel strength. Modification with low-temperature plasticizers alters the surface energy of the substrate, affecting wettability and diffusion penetration with the coating material. The results of the bonding performance evaluation provide a quantitative assessment of the interlayer bonding quality of the composite film, guiding the optimization of subsequent composite process parameters.

[0072] The determination of coating composite process parameters is based on an analysis of interfacial adhesion strength and failure modes from the bonding performance evaluation results. When peel strength is low and adhesion failure is predominant, increasing the composite temperature and pressure enhances interfacial bonding. When peel strength is moderate but cohesive failure is predominant, adjusting the coating formulation to enhance cohesive strength. When peel strength is high and mixed failure is observed, maintaining the existing process parameters. The composite process utilizes hot pressing, with the composite temperature controlled at 10-20°C below the substrate's softening point to prevent excessive deformation. The composite pressure is determined based on the coating viscosity and substrate hardness, and is set within the range of 0.2-0.8 MPa.

[0073] The lamination data collection process strictly controls the stability of process conditions and maintains a constant lamination speed to ensure uniform interfacial bonding. The lamination roller temperature is monitored in real time by an infrared thermometer, with temperature fluctuations controlled within ±2°C. Lamination pressure is precisely controlled by an air pressure regulation system, with pressure fluctuations less than ±0.05 MPa. The film tension changes during the lamination process are monitored to prevent cracking or delamination of the coating caused by excessive stretching. After lamination, monitoring is conducted under standard conditions for 24 hours to eliminate the effects of internal stress and solvent residue.

[0074] Verification of composite film data includes visual inspection, thickness measurement, and preliminary performance testing. Visual inspection identifies surface defects such as bubbles, wrinkles, and color variations, recording their location, size, and distribution. Thickness measurement verifies the impact of the composite process on film thickness and evaluates compression set and rebound properties. Preliminary performance testing includes simple tensile and peel tests to verify the effectiveness of the composite process.

[0075] Tensile modulus testing was performed using a universal testing machine equipped with a high-precision extensometer. Specimens were prepared according to ASTM D882, with specimen dimensions of 150 mm x 15 mm and thickness measurement accuracy of ±0.001 mm. The test environment was maintained at a temperature of 23°C ± 2°C and a relative humidity of 50% ± 5%. Specimens were preconditioned for at least 4 hours. The tensile speed was set at 5 mm / min, and the strain range was controlled within the linear elastic region of 0.1%-0.5%. The tensile modulus was calculated from the initial slope of the stress-strain curve, reflecting the stiffness characteristics of the composite film.

[0076] Tear strength testing utilizes the Elmendorf tear test method. Specimens are prepared in a specified geometry with a strictly controlled pre-cut depth. This tear test simulates the tear damage experienced by packaging bags during use and evaluates the material's resistance to tear propagation. Tear strength is calculated by dividing the tear force by the specimen thickness, eliminating the influence of thickness variations. The tear behavior of composite films is significantly influenced by the interfacial bond strength between the coating and the substrate. Good interfacial bonding effectively prevents crack propagation along the interface and improves overall tear strength.

[0077] Film performance parameters are obtained through multiple parallel tests to ensure data reliability, with no fewer than 10 valid specimens per test item. Statistical methods are used to calculate the mean, standard deviation, and coefficient of variation for tensile modulus and tear strength data, establishing confidence intervals for these performance parameters. The performance parameter database includes test results for various coating thicknesses and lamination processes, providing data support for process optimization. These performance parameters are directly related to the performance of the packaging bag. Tensile modulus influences deformation during packaging, while tear strength determines the durability and safety of the bag.

[0078] Film preparation parameter identification establishes a quantitative relationship between film performance parameters and preparation process conditions, and a mathematical model is constructed using multiple regression analysis. Tensile modulus and tear strength are used as dependent variables, and coating thickness, lamination temperature, lamination pressure, and lamination speed are used as independent variables. A regression equation is fitted using the least squares method. The model's validity is evaluated using correlation coefficients and significance tests. A correlation coefficient greater than 0.85 and a significance level less than 0.05 are considered reliable. The parameter identification process considers interactions between process parameters, establishing a polynomial regression model with interaction terms to improve prediction accuracy.

[0079] Initial process parameters are determined based on a comprehensive optimization of performance targets and process constraints. Performance targets are determined based on the requirements for cold chain food packaging. The tensile modulus ensures dimensional stability during packaging, and the tear strength ensures integrity during transportation and storage. Process constraints include equipment capacity limitations, production efficiency requirements, and energy consumption control targets. The optimization algorithm utilizes a multi-objective genetic algorithm, simultaneously considering the dual objectives of optimal performance and minimal cost to find a Pareto optimal solution.

[0080] Initial process parameters include substrate modification parameters, coating process parameters, and lamination process parameters. Substrate modification parameters involve the type, dosage, and mixing temperature of the plasticizer; coating process parameters include coating thickness, coating speed, and drying temperature; and lamination process parameters encompass lamination temperature, pressure, and speed. The coordinated configuration of these parameters determines the overall performance of the final product, and parameter identification results provide process guidance for large-scale production. The accuracy of initial process parameters directly impacts product quality stability and production efficiency, and is a key technical foundation for the industrialized production of cold chain food packaging bags.

[0081] This embodiment can accurately obtain the performance characteristics of the substrate in a cold chain environment by conducting a low-temperature oxygen permeability bending test on the quality data of the packaging bag, providing a scientific basis for subsequent coating design and avoiding the performance mismatch problem caused by traditional empirical design. By measuring the coating thickness based on the low-temperature adaptation data of the packaging bag, precise control of the coating thickness and quantitative characterization of the distribution characteristics are achieved, ensuring that the composite film has consistent barrier properties and mechanical properties in different areas. The bonding performance evaluation results are obtained by the coating peel strength test, which can identify the failure mode of the interface bonding, provide clear guidance for the optimization of the composite process parameters, and effectively improve the bonding strength between the coating and the substrate. The film performance parameters are obtained by tensile modulus and tear strength testing, and a quantitative standard for performance evaluation is established to provide reliable data support for the prediction of the performance of the packaging bag. The initial process parameters are obtained by identifying the film preparation parameters, which achieves a precise match between the performance requirements and the process conditions, and provides an optimized process route for the large-scale production of cold chain food packaging bags.

[0082] In one embodiment, heat seal position measurement is performed on the coating process result, and sealing analysis is performed based on film performance to obtain sealing performance analysis results, including: Surface temperature field scanning and measurement is a key technical step in ensuring the heat seal quality of cold chain food packaging bags. Film materials after coating have varying thermal conductivity properties. Using infrared thermal imaging equipment to scan the entire film surface in all directions accurately captures the temperature distribution. During the scanning process, the thermal imaging probe moves along a pre-set trajectory across the entire film surface, recording the temperature value at each location. Temperature data is collected at a frequency of at least 50 frames per second, ensuring that even the slightest temperature changes are captured.

[0083] Scanning measurements cover all areas of the film surface, including edges, center areas, and designated heat-seal locations. Temperature sensors detect subtle temperature variations caused by variations in material thickness and coating uniformity. The ambient temperature remains constant during the measurement process, preventing external interference from affecting the results. Scanning data is stored in a digital matrix format, with each matrix element corresponding to the temperature value at a specific coordinate on the film surface.

[0084] Heat seal positioning is achieved by analyzing temperature gradients. Coating materials exhibit different thermal response characteristics at varying thicknesses and densities, and these differences create distinct characteristic patterns in the temperature field. Data processing algorithms identify areas with the most dramatic temperature variations, which correspond to the optimal heat seal locations. Positioning accuracy reaches millimeters, providing an accurate reference for subsequent heat sealing operations.

[0085] Temperature field data also contains information about the thermal stability of film materials. By continuously monitoring temperature changes at the same location, the consistency of the material's thermal response can be assessed. Positioning data includes not only spatial coordinate information but also thermal characteristic parameters at each location, providing a scientific basis for optimizing heat sealing process parameters. The entire scanning and measurement process is highly automated, reducing human error and improving the reliability of positioning data.

[0086] Heat-seal area shape recognition is based on in-depth analysis of the positional data obtained in the previous step. The spatial coordinate information contained in this positioning data provides the foundational data for shape recognition. Image processing technology performs boundary detection on the temperature field data, identifying continuous regions with similar thermal characteristics. The boundary contours of these regions reflect the actual shape characteristics of the heat-seal area.

[0087] The shape recognition algorithm uses contour tracing to extract the complete area outline along the temperature gradient boundary. The contour data is represented as a sequence of coordinate points, with each point corresponding to a specific location on the area boundary. By analyzing the geometric characteristics of the contour, the basic shape types of the heat-sealed area, such as rectangle, circle, or irregular, are identified. The shape classification results provide a basis for subsequent geometric parameter calculations.

[0088] The calculation of heat seal geometric parameters covers basic dimensions such as the length, width, area, and perimeter of the region. For rectangular heat seal regions, the long and short sides are calculated; for circular regions, the diameter and radius are calculated; for irregular shapes, the equivalent diameter and form factor are calculated. The actual area is calculated by counting the number of pixels within the region and converting the pixel size.

[0089] Perimeter calculation is based on the cumulative distance between contour coordinate points. Shape regularity is assessed by comparing the deviation between the actual contour and the ideal geometry. Geometric parameters also include higher-order parameters describing shape characteristics, such as the region's center coordinates, principal axis orientation, and eccentricity. These parameters comprehensively describe the geometric characteristics of the heat-sealed area, providing detailed geometric information for stress analysis and process optimization. Parameter accuracy reaches micron levels, meeting the requirements of precision packaging applications.

[0090] Heat seal stress analysis uses geometric parameters as input to assess the mechanical stress state experienced by film materials during the heat seal process. The dimensional information in these geometric parameters directly influences the stress distribution pattern, with varying aspect ratios and shape characteristics leading to significant differences in stress concentration. Stress analysis employs the finite element method, discretizing the heat seal area into numerous small cells, with each cell performing a localized stress calculation.

[0091] Material properties include physical characteristics such as elastic modulus, Poisson's ratio, and yield strength. These parameters, combined with geometric information, determine the stress distribution. Temperature changes during the heat sealing process cause thermal expansion of the material, generating thermal stress. Simultaneously, mechanical pressure generates mechanical stress. These two stresses combine to form a composite stress state. The analysis considers the material's nonlinear properties, including plastic deformation and creep effects.

[0092] Stress analysis data includes various stress descriptions, including stress components, principal stresses, and equivalent stresses. Stress components include normal stress and shear stress, which reflect tensile, compressive, and shear deformation states, respectively. Principal stresses represent the maximum and minimum stress values ​​within a material and are important indicators for assessing material failure risk. Equivalent stress comprehensively considers the impact of each stress component and provides a unified stress evaluation standard.

[0093] The spatial characteristics of stress distribution reveal the location and extent of stress concentration. Corners, edges, and locations of geometric abrupt changes are high-risk areas for stress concentration. Stress gradient information reflects the severity of stress changes, with high-gradient areas corresponding to vulnerable points in the material. Time history analysis reveals the evolution of stress during the heat sealing process, identifying the timing and duration of stress peaks. These results provide theoretical guidance for the selection and optimization of heat sealing process parameters, ensuring heat seal strength while avoiding material damage.

[0094] Seal bond strength measurements are performed at key test locations identified by stress analysis data. High stress areas and stress concentrations revealed by stress analysis serve as key areas for strength testing. A tensile testing machine applies a gradually increasing tensile load to the heat-sealed joint, recording a load-displacement curve. The load application rate is maintained constant throughout the test to minimize the impact of dynamic effects on the test results.

[0095] Strength testing includes two modes: peel strength and tensile strength. The peel strength test evaluates the heat-sealed joint's resistance to tearing. During the test, one end is fixed while the other is peeled at a constant speed. The tensile strength test evaluates the joint's ultimate ability to withstand tensile loads. Tension is applied simultaneously to both ends in opposite directions. Test data includes information such as the maximum load, failure location, and deformation characteristics. Statistical analysis of the results from multiple test samples is performed to obtain the mean and standard deviation of the strength data.

[0096] Airtightness measurement utilizes a combination of the pressure decay method and the tracer gas method. The pressure decay method involves filling a sealed package with gas at a constant pressure and monitoring the pressure change over time. The pressure decay rate reflects the seal's quality; a lower decay rate indicates better airtightness. The tracer gas method uses a special gas, such as helium, as a tracer, and measures the concentration of leaked gas using a mass spectrometer.

[0097] Airtightness performance evaluation data includes leakage rate, sealing grade, and service life prediction. Leakage rate, expressed as the volume of gas leaked per unit time, is a direct indicator of airtightness performance. Sealing grades are categorized based on leakage rate, providing a basis for product quality grading. Service life prediction is based on accelerated aging test data, using the Arrhenius equation to estimate the seal failure time under normal operating conditions. The accuracy of test data is verified through repeatability and comparative testing to ensure data reliability and consistency.

[0098] Sealing performance analysis results are obtained through a comprehensive evaluation of strength test data and airtightness data. Strength data reflects the mechanical properties of the heat-sealed joint, while airtightness data reflects the seal's barrier properties. The combination of the two provides a comprehensive performance picture. A multi-index evaluation system is established during the evaluation process, with each index weighted according to actual application requirements. The evaluation results are presented as a comprehensive score, which directly reflects the quality of the sealing performance.

[0099] Performance analysis utilizes a comparative analysis method, comparing test results with industry standards and design requirements. Strength data is compared with actual loads in packaging applications to assess safety margins. Airtightness data is compared with the barrier properties required for food preservation to determine whether shelf life requirements are met. Comparative analysis results are quantified using metrics such as compliance rate and excess multiple.

[0100] Failure mode analysis identifies the primary causes and influencing factors of seal failure. By analyzing the damage location, morphology, and failure mechanism, weak links in the heat sealing process are identified. Common failure modes include interfacial delamination, substrate tearing, and inadequate heat sealing. Each failure mode corresponds to different improvement measures and prevention plans.

[0101] Performance trend analysis identifies changing patterns and trends in seal performance by comparing historical data. Statistical analysis processes large amounts of test data to identify key factors and patterns that influence performance. Trend analysis results guide process improvements and drive continuous optimization of packaging technology.

[0102] The analysis results ultimately form a detailed performance evaluation report, including test data, evaluation conclusions, and improvement suggestions. The report provides a scientific basis for product quality control, process parameter optimization, and technical improvements, ensuring that the sealing performance of cold chain food preservation packaging bags meets actual application requirements.

[0103] This embodiment can accurately identify the position and shape of the heat-sealed area by scanning and measuring the surface temperature field of the coating treatment results and obtaining heat-sealing position positioning data, thereby avoiding sealing failure caused by position deviation. By identifying the shape of the heat-sealed area and analyzing the geometric parameters, not only the accuracy of the heat-sealing process is optimized, but also the size and shape of the heat-sealed area can be adjusted according to actual needs to improve the sealing performance of the package. By performing stress analysis on the heat-sealing geometric parameters, the stress state of the film material during the heat-sealing process can be evaluated in real time to ensure that the material will not be excessively deformed or ruptured during the heat-sealing process, thereby greatly improving the stability and reliability of the heat seal. The sealing strength test and airtightness evaluation based on the stress analysis data further optimize the sealing performance of the packaging bag, ensuring that the packaging bag can effectively prevent the entry of external gas and moisture, and extend the shelf life of cold chain food.

[0104] In one embodiment, the packaging bag quality data is optimized based on the initial process parameters and the sealing performance analysis results to obtain a packaging bag preparation optimization plan, including: Initial process parameters are the theoretical guiding data for bag production, covering key variables such as heat-sealing temperature, pressure, speed, and cooling time. The key to matching molding equipment lies in translating these theoretical parameters into executable instructions for specific equipment, while also ensuring the equipment's stability and accuracy during actual operation. This process first requires collecting equipment performance data, including the heat sealer's temperature control accuracy, the pressure system's response speed, and the synchronization of the transmission mechanism. Equipment calibration experiments are then conducted to determine the executable range of each process parameter on the equipment, such as the actual fluctuation range of the heat-sealing temperature, the linear error compensation value of the pressure sensor, and the stability threshold of the conveyor belt speed.

[0105] During the matching process, matching is performed based on the dynamic response characteristics of the equipment. For example, the heating rate of the heat sealing head affects the uniformity of heating of the film, so the equipment control parameters need to introduce preheating time compensation to ensure that the temperature reaches the set value before sealing. At the same time, when multiple processes are produced in a collaborative manner, timing matching between equipment is crucial. The connection between processes such as cutting, sealing, and coating requires synchronous optimization of equipment control parameters to avoid uneven film tension or sealing misalignment due to equipment response delays. The generated equipment control parameters include not only basic set values, but also cover the dynamic adjustment strategies of the equipment, such as temperature PID control parameters, pressure real-time feedback compensation mechanism, etc., to ensure the accuracy and repeatability of process execution.

[0106] The results of the sealing performance analysis reflect the seal quality of the packaging bag during actual testing, including indicators such as heat seal strength, airtightness, and tear resistance. The goal of sealing process optimization is to improve the mechanical properties and seal reliability of the sealing area by adjusting equipment control parameters. This process begins by analyzing the cause of sealing defects. For example, insufficient seal strength may be caused by low temperature or uneven pressure distribution, while leakage may be related to insufficient sealing time or uneven film heating.

[0107] Optimizing sealing process control parameters requires a combination of material properties and equipment capabilities. For example, for multilayer composite films, the varying melting temperatures of different material layers necessitates a gradient control strategy for heat-sealing temperatures to prevent overheating of the outer layer and insufficient fusion of the inner layer. Pressure optimization, on the other hand, requires considering the film's elastic deformation characteristics, ensuring uniform pressure across the sealing surface through dynamic pressure regulation. Furthermore, matching sealing time with cooling rate also impacts seal quality; excessively rapid cooling can lead to internal stress concentration, reducing seal strength.

[0108] Sealing process control parameters encompass not only static setpoints but also dynamic adjustment strategies, such as fine-tuning the heat-sealing temperature in real time based on film thickness or adjusting the pressure distribution based on online measurement feedback. These optimized parameters directly influence subsequent film thickness settings, ensuring a perfect match between the sealing process and material properties.

[0109] Packaging bag quality data includes key indicators such as cutting accuracy, dimensional tolerance, and edge smoothness. The cutting positioning process uses high-precision sensors or machine vision systems to monitor the film's position on the production line in real time, ensuring geometric alignment between the cutting blade and the sealing area. For example, photoelectric encoders or CCD cameras can be used to detect film edges and dynamically adjust the cutting mechanism's trajectory to avoid cutting deviations caused by film tension fluctuations.

[0110] Film thickness settings require dynamic adjustment in conjunction with sealing process control parameters. Sealing temperature and pressure affect the film's melt flow behavior, necessitating pre-compensation for thickness distribution during the extrusion or blown film stages. For example, in high-temperature sealing areas, the film may shrink due to heat, leading to thinning. Therefore, the initial thickness must be increased in these locations to ensure overall uniformity after sealing. Furthermore, the thickness ratios of the individual layers in multilayer composite films must be optimized to balance mechanical properties and cost.

[0111] The packaging film parameters include not only the nominal thickness but also the thickness distribution curve, material interlayer ratio, and other data, providing precise input for subsequent coating uniformity compensation. The output of this step directly affects the adhesion of the coating process, ensuring that the film surface properties meet the requirements of subsequent processing.

[0112] The coating process is a critical step in the packaging bag production process, and its quality directly affects the product's barrier properties, printability, and subsequent processing performance. Compensating for coating uniformity requires a deep understanding of the sealing process and film properties, enabling precise control through multi-dimensional parameter regulation. During implementation, the first step is to establish a database mapping the sealing process parameters to the film's characteristic parameters. This database must include key parameters such as the change in wetting angle of the film surface under different sealing temperature ranges, the microscopic morphology of the film surface under different pressure conditions, and the variation patterns of surface energy in areas with different thickness distributions.

[0113] The actual compensation process begins with testing the film's surface condition. A high-precision surface profilometer is used to perform three-dimensional topographic scanning of the sealed film surface, capturing key indicators such as surface roughness and waviness. A contact angle meter is also used to measure the surface wetting characteristics of different areas and create a surface energy distribution map. This test data is then correlated with the sealing process control parameters to identify the corresponding relationship between process parameters and surface properties. For example, high-temperature sealing areas often exhibit a decrease in surface energy, necessitating adjustments to the coating solution formulation or coating process parameters in these areas.

[0114] When calculating coating process parameters, factors such as the coating fluid's rheological properties, surface tension, and solvent evaporation rate must be comprehensively considered. For water-based coating fluids, special attention should be paid to the impact of ambient humidity on the coating effect; for solvent-based coating fluids, the ventilation conditions in the coating room must be controlled. The coating amount is calculated using a partitioning compensation algorithm, which divides the film surface into several functional areas. Each area is matched with the optimal coating parameters based on its surface characteristics. For example, in the area near the sealing line, due to the thermal history effect, the coating amount needs to be appropriately increased and the coating speed needs to be reduced; in the main film area, standard coating parameters can be used.

[0115] The parameters of the coating equipment must be dynamically matched to the film's operating speed. Key parameters such as the coating head's installation angle, distance from the film surface, and atomizing air pressure require real-time adjustment based on the film's characteristics. For multi-component coating systems, the stability of the components' proportions during mixing and spraying must also be ensured. The final output of the coating compensation parameters includes control instructions from multiple dimensions: the base coating volume setpoint, the partition compensation coefficient, the coating head's motion trajectory, and drying condition parameters. Together, these parameters constitute a complete coating process control solution.

[0116] Dynamic process adjustment is the critical conversion process that transforms static parameters into executable production instructions. This phase of work requires the establishment of a complete digital twin model of the production line, verifying the feasibility of the process plan through virtual simulation. The simulation model must include key modules such as the coating unit, drying unit, and tension control unit, each of which requires a precise mathematical model. For example, the coating unit model must simulate the spreading of the coating liquid on the film surface, and the drying unit model must be able to predict the curing behavior of the coating under different temperature gradients.

[0117] The process sequence must adhere to the closed-loop control principle of "detection-decision-execution." A high-precision sensor network is deployed at key nodes on the production line to collect real-time process parameters such as film temperature, thickness, and tension. This data is transmitted to the central control system via industrial Ethernet and compared and analyzed against pre-set process standards. When parameter deviations are detected, the system automatically generates adjustment instructions, which are sorted by process priority to form a complete process adjustment sequence.

[0118] The adjustment sequence within the coating process requires careful consideration of its synergy with other processes. For example, when increasing the coating speed, the drying oven temperature profile and conveyor speed must be adjusted simultaneously to ensure adequate coating curing. The impact on the subsequent slitting process must also be considered to avoid burrs caused by incompletely cured coating surfaces. The process adjustment sequence also needs to include emergency response plans. For example, if uneven coating is detected, the system can automatically reduce the line speed and initiate a compensatory coating procedure.

[0119] Dynamic changes in film parameters are a key focus of process adjustments. As production progresses, film parameters such as thickness and tension may fluctuate, necessitating an adaptive process adjustment sequence. The system continuously monitors statistical process control (SPC) charts of film parameters. When parameter drift trends are detected, it automatically fine-tunes relevant process parameters to maintain optimal production control. For multi-layer composite films, dimensional changes caused by differences in the thermal expansion coefficients of the various layers must also be considered, requiring appropriate compensation measures to be incorporated into the process adjustment sequence.

[0120] The process adjustment sequence is a multi-dimensional control matrix, encompassing process scheduling on the time axis, parameter distribution on the spatial axis, and control standards on the quality axis. This sequence is converted into control instructions that the equipment can recognize and transmit to each execution unit via the fieldbus, ensuring the coordinated operation of the entire production system.

[0121] The iterative optimization process employs a "design-verify-improve" cycle, gradually approaching the optimal process solution through repeated experiments. The first iteration uses initial process parameters as the foundation, and a small-batch trial production is conducted according to the process adjustment sequence. During the trial production process, a comprehensive data collection system is established to record key parameters and product quality data for each production batch.

[0122] Quality assessment utilizes a comprehensive, multi-index evaluation system. In addition to conventional physical property testing (such as seal strength and air permeability), microstructural analysis is also performed. Electron microscopy is used to observe the interface between the coating and the substrate, and infrared spectroscopy is used to analyze changes in the coating's chemical structure. These test data are then correlated with process parameters to identify key process factors influencing product quality.

[0123] Parameter optimization utilizes experimental design methods such as the response surface methodology (RSM). Key process parameters serve as input variables, and product quality indicators serve as response variables. Through a scientifically designed experimental plan, a mathematical model linking process parameters and product quality is established. This model can be used to identify the optimal combination of process parameters in a multidimensional parameter space. For example, analysis revealed an interaction between sealing temperature and coating speed, necessitating readjustment of the matching relationship between these two parameters.

[0124] Each iteration generates new process knowledge, which needs to be promptly updated in the process database. The database uses version control to record the parameter settings, implementation results, and improvement directions for each optimized version. Furthermore, a process knowledge graph should be established to transform dispersed process experience into a systematic knowledge system to support subsequent continuous optimization.

[0125] The packaging bag preparation optimization program is a comprehensive system encompassing multiple dimensions: On the equipment dimension, it defines standard operating parameters and tolerances for each process step; on the material dimension, it defines the process windows for different formulations; on the quality dimension, it establishes detailed product inspection standards and process control methods; and on the management dimension, it establishes comprehensive process documentation and change control procedures. This program not only includes optimal static parameter settings but also defines dynamic adjustment strategies and methods to ensure that it can cope with various changing conditions in actual production.

[0126] This embodiment achieves precise control of the coating process through the coordinated optimization of the sealing process control parameters and the packaging bag film parameters, effectively improving the uniformity and adhesion of the coating, and significantly improving the barrier properties and appearance quality of the packaging bag. The dynamic process adjustment mechanism can respond to parameter fluctuations in the production process in real time, ensure coordinated operation between various processes, and greatly improve production stability and product consistency. The iterative optimization method has been verified through multiple rounds of experiments, and a systematic correlation model between process parameters and product quality has been established, providing reliable process window guidance for different material formulations and production conditions. The complete preparation optimization solution not only includes static parameter settings, but also has dynamic adjustment capabilities, enabling the production line to flexibly respond to various changing conditions, while ensuring product quality and improving production efficiency.

[0127] Reference Figure 2 As shown, a system for preparing a fresh-keeping packaging bag for cold chain food is applied to any of the above-mentioned methods for preparing a fresh-keeping packaging bag for cold chain food, comprising: The acquisition module is used to obtain the base material performance parameters of the composite base material, perform modification treatment with the low-temperature plasticizer, and obtain the packaging bag quality data; An analysis module is used to obtain the dispersion data of the nano-montmorillonite material, perform barrier coating analysis on the quality data of the packaging bag, and obtain the coating treatment results; A correlation module is used to analyze film performance based on packaging bag quality data and coating treatment results to obtain film performance parameters and initial process parameters; A processing module is used to measure the heat sealing position of the coating processing result and perform sealing analysis based on the film performance to obtain a sealing performance analysis result; The control module is used to package and shape the packaging bag quality data according to the initial process parameters and the sealing performance analysis results to obtain a fresh-keeping packaging bag for cold chain food.

[0128] The present invention provides a system for preparing fresh-keeping packaging bags for cold chain food. Through comprehensive analysis of the quality identification and coating monitoring data of historical batches of packaging bags, it can more comprehensively evaluate the performance stability of packaging bags, avoid the problem of insufficient low-temperature adaptability caused by relying solely on a single material indicator, and thus improve the packaging reliability in the cold chain environment. Combined with hyperspectral imaging monitoring and coating analysis, it can accurately identify the uniformity and defects of the coating process, optimize the coating process, reduce the risk of barrier performance degradation or sealing failure due to uneven coating, and improve the overall fresh-keeping effect of the packaging bag. Based on film performance analysis and optimization of initial process parameters, it can coordinate the mechanical strength, low-temperature toughness and barrier properties of the packaging bag, avoid low-temperature embrittlement or poor sealing problems caused by performance imbalance in traditional preparation methods, and enhance the adaptability of packaging bags in cold chain environments. Through heat seal position measurement and sealing performance analysis, the heat sealing process can be accurately controlled, air leakage or water seepage caused by lax sealing can be reduced, and the sealing reliability of the packaging bag during long-term low-temperature storage and transportation can be ensured, extending the shelf life of food. Based on the optimized adjustment of process parameters and sealing performance, the preparation plan can be dynamically optimized so that the packaging bags can maintain stable performance under different cold chain conditions, reduce quality fluctuations caused by process deviations, and improve production consistency and product yield.

[0129] Reference Figure 3 As shown, the present invention also provides a device for preparing a fresh-keeping packaging bag for cold chain food, comprising: Memory, used to store programs; A processor is used to execute a program to implement each step of a method for preparing a fresh-keeping packaging bag for cold chain food as described in any one of claims 1 to 6.

[0130] In this embodiment, the processor and memory may be connected via a bus or other means. The memory may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid-state drive. The processor may be a general-purpose processor, such as a central processing unit, a digital signal processor, an application-specific integrated circuit, or one or more integrated circuits configured to implement the embodiments of the present invention.

[0131] The present invention also provides a storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any of the above methods.

[0132] It should be noted that, those skilled in the art will clearly understand that, for the sake of convenience and brevity of description, the specific working processes of the above-described system and each module can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0133] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for preparing a fresh-keeping packaging bag for cold chain food, characterized in that: include: Obtain historical performance parameters of historical batches of packaging bags, perform batch quality identification, and obtain packaging bag quality data; Performing hyperspectral imaging monitoring on the coating area to obtain coating monitoring data, and performing coating analysis on the historical performance parameters to obtain coating treatment results; Performing film performance analysis on the packaging bag quality data and the coating treatment results to obtain film performance parameters and initial process parameters; measuring the heat sealing position of the coating treatment result, and performing sealing analysis based on the film performance to obtain a sealing performance analysis result; The packaging bag quality data is prepared and optimized based on the initial process parameters and the sealing performance analysis results to obtain a packaging bag preparation optimization plan.

2. The method for preparing a fresh-keeping packaging bag for cold chain food according to claim 1, characterized in that: The method of obtaining historical performance parameters of historical batches of packaging bags, performing quality identification, and generating packaging bag quality characteristic data includes: Extracting elongation at break from the historical performance parameters to obtain tensile strength data; Performing thickness oxygen permeability analysis on the historical performance parameters to obtain oxygen permeability parameters; Extracting heat deformation temperature based on the historical performance parameters to obtain temperature adaptability data; performing batch-to-batch dispersion calculation on the tensile strength data, the oxygen permeability parameter, and the temperature adaptability data to obtain batch stability data; The packaging bag quality data is obtained by dynamically matching the batch stability data with a preset quality threshold.

3. The method for preparing a fresh-keeping packaging bag for cold chain food according to claim 1, characterized in that: The method of performing hyperspectral imaging monitoring on the coating area to obtain coating monitoring data and performing coating analysis on the historical performance parameters to obtain coating treatment results includes: Performing hyperspectral imaging scanning on the coating area during the coating process to obtain hyperspectral imaging data; Extracting spectral features from the hyperspectral imaging data to obtain coating spectral feature data; Dividing the region into uniformity regions according to the coating spectrum characteristic data to obtain coating thickness distribution data; Performing coating process matching on the historical performance parameters to obtain coating process correlation data; Positioning defects in the coating area according to the coating process correlation data to obtain coating defect distribution data; A coating quality assessment is performed on the coating thickness distribution data and the coating defect distribution data to obtain the coating processing result.

4. The method for preparing a fresh-keeping packaging bag for cold chain food according to claim 1, characterized in that: The film performance analysis is performed on the packaging bag quality data and the coating treatment results to obtain film performance parameters and initial process parameters, including: Performing a low-temperature oxygen permeability bending test on the packaging bag quality data to obtain low-temperature adaptability data of the packaging bag; Measuring the coating thickness of the coating treatment result according to the low temperature adaptation data of the packaging bag to obtain coating distribution characteristic parameters; Performing a coating peel strength test on the packaging bag quality data according to the coating distribution characteristic parameters to obtain a bonding performance evaluation result; Performing coating compounding on the packaging bag quality data according to the combined performance evaluation results to obtain composite film data; Performing tensile modulus and tear strength tests on the composite film data to obtain film performance parameters; Film preparation parameters are identified based on the film performance parameters to obtain the initial process parameters.

5. The method for preparing a fresh-keeping packaging bag for cold chain food according to claim 1, characterized in that: The heat sealing position measurement of the coating treatment result and the sealing analysis based on the film performance are performed to obtain the sealing performance analysis result, including: Performing surface temperature field scanning measurement on the coating treatment result to obtain heat sealing position positioning data; Perform heat seal area shape recognition based on the heat seal position positioning data to obtain heat seal geometric parameters; performing stress analysis on the heat seal geometric parameters to obtain heat seal stress analysis data; Measuring the sealing adhesive strength and airtightness of the film according to the heat sealing stress analysis data to obtain sealing strength test data and airtightness performance evaluation data; A performance evaluation is performed based on the sealing strength test data and the airtight performance evaluation data to obtain the sealing performance analysis result.

6. The method for preparing a fresh-keeping packaging bag for cold chain food according to claim 1, characterized in that: The step of optimizing the packaging bag quality data based on the initial process parameters and the sealing performance analysis results to obtain a packaging bag preparation optimization plan includes: Matching the initial process parameters to the molding equipment to obtain equipment control parameters; Optimizing the sealing process by adjusting the equipment control parameters according to the sealing performance analysis results to obtain sealing process control parameters; Cutting and positioning the packaging bag quality data, and setting the film thickness according to the sealing process control parameters to obtain packaging bag film parameters; Perform coating uniformity compensation according to the sealing process control parameters and the packaging bag film parameters to obtain coating compensation parameters; Dynamically adjusting the coating compensation parameters and the packaging bag film parameters to obtain a process adjustment sequence; The initial process parameters are iteratively optimized according to the process adjustment sequence to obtain an optimized solution for packaging bag preparation.

7. A system for preparing fresh-keeping packaging bags for cold chain food, characterized in that: The method for preparing a fresh-keeping packaging bag for cold chain food according to any one of claims 1 to 6 comprises: An acquisition module, which is used to obtain historical performance parameters of historical batches of packaging bags, perform batch quality identification, and obtain packaging bag quality data; An analysis module, the analysis module is used to perform hyperspectral imaging monitoring on the coating area to obtain coating monitoring data, perform coating analysis on the historical performance parameters, and obtain coating treatment results; a correlation module, the correlation module being used to perform film performance analysis on the packaging bag quality data and the coating treatment results to obtain film performance parameters and initial process parameters; a processing module, the processing module being configured to measure the heat sealing position of the coating processing result and perform sealing analysis based on the film performance to obtain a sealing performance analysis result; A control module is used to optimize the packaging bag quality data according to the initial process parameters and the sealing performance analysis results to obtain an optimization plan for packaging bag preparation.

8. A device for preparing fresh-keeping packaging bags for cold chain food, characterized in that: include: Memory, used to store programs; A processor is used to execute the program to implement the various steps of the method for preparing a fresh-keeping packaging bag for cold chain food as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: Computer instructions are stored, and the computer instructions are used to make a computer execute the method according to any one of claims 1 to 6.

Images