Detection Method for Durable Antibacterial Performance of Antibacterial Nonwoven Fabric

Abstract

The present invention discloses a method for detecting the persistent antibacterial performance of antibacterial non-woven fabrics, which relates to the technical field of antibacterial performance detection. The method includes: collecting multi-dimensional data of the antibacterial non-woven fabric to obtain a multi-dimensional data set; extracting multiple colony image features; performing antibacterial analysis on the surface of the antibacterial non-woven fabric for multiple environmental data to generate multiple antibacterial correlation coefficients; performing antibacterial performance decay modeling, constructing an antibacterial decay model, performing trend analysis of antibacterial performance, and plotting an antibacterial performance decay trend curve; calculating the antibacterial contribution according to the antibacterial performance decay trend curve to obtain the antibacterial contribution degree, performing antibacterial persistence analysis on the antibacterial non-woven fabric to obtain the persistent antibacterial analysis result, and generating antibacterial suggestions. It solves the technical problem of insufficient accuracy of the detection result due to the single evaluation dimension in the detection process of the persistent antibacterial performance of antibacterial non-woven fabrics in the prior art, and achieves the technical effect of improving the comprehensiveness and accuracy of antibacterial performance detection.

Description

Technical Field

[0001] The present invention relates to the technical field of antibacterial performance detection, and particularly to a method for detecting the persistent antibacterial performance of antibacterial non-woven fabrics. Background Art

[0002] With the continuous improvement of people's requirements for health and hygiene, antibacterial non-woven fabrics, as a material with both antibacterial performance and practicality, are widely used in the medical, daily life, and industrial fields. However, in the prior art, the detection methods for the antibacterial performance of antibacterial non-woven fabrics mostly focus on the evaluation of initial performance, lacking the dynamic evaluation of their antibacterial performance with time and environmental changes. This not only leads to insufficient accuracy in the analysis of antibacterial performance persistence but also makes it difficult to provide a scientific basis for the improvement and optimization of materials. In addition, multi-dimensional data (such as environmental parameters, colony distribution characteristics, etc.) are not effectively integrated during the detection process for comprehensive analysis, and the attenuation law of antibacterial performance cannot be fully revealed. Summary of the Invention

[0003] The present application provides a method for detecting the persistent antibacterial performance of antibacterial non-woven fabrics, which solves the technical problem of insufficient accuracy of detection results caused by a single evaluation dimension during the detection of the persistent antibacterial performance of antibacterial non-woven fabrics in the prior art.

[0004] In view of the above problems, the present application provides a method for detecting the persistent antibacterial performance of antibacterial non-woven fabrics.

[0005] The present application provides a method for detecting the persistent antibacterial performance of antibacterial non-woven fabrics, and the method includes:

[0006] Collecting multi-dimensional data of the antibacterial non-woven fabric through a data sensing network to obtain a multi-dimensional data set, where the multi-dimensional data set includes multiple environmental data and multiple surface colony image data of the antibacterial non-woven fabric; traversing and analyzing the multiple surface colony image data based on the multiple environmental data to extract multiple colony image features; performing antibacterial analysis on the multiple environmental data on the surface of the antibacterial non-woven fabric according to the multiple colony image features to generate multiple antibacterial correlation coefficients; performing antibacterial performance attenuation modeling based on the multiple antibacterial correlation coefficients to construct an antibacterial attenuation model, performing trend analysis of antibacterial performance through the antibacterial attenuation model, and drawing an antibacterial performance attenuation trend curve; calculating the antibacterial contribution according to the antibacterial performance attenuation trend curve to obtain the antibacterial contribution degree, performing antibacterial persistence analysis on the antibacterial non-woven fabric according to the antibacterial contribution degree to obtain a persistent antibacterial analysis result, and generating antibacterial suggestions.

[0007] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0008] First, multi-dimensional data of the antibacterial non-woven fabric is collected through a data sensing network to obtain a multi-dimensional data set, which includes multiple environmental data and multiple surface colony image data of the antibacterial non-woven fabric. Next, based on the multiple environmental data, the multiple surface colony image data is traversed and analyzed to extract multiple colony image features. Further, antibacterial analysis of the multiple environmental data on the surface of the antibacterial non-woven fabric is performed according to the multiple colony image features to generate multiple antibacterial correlation coefficients. Then, an antibacterial performance decay model is constructed based on the multiple antibacterial correlation coefficients, and a trend analysis of the antibacterial performance is performed through the antibacterial decay model to draw an antibacterial performance decay trend curve. Finally, antibacterial contribution calculation is performed according to the antibacterial performance decay trend curve to obtain the antibacterial contribution degree. Antibacterial durability analysis of the antibacterial non-woven fabric is carried out based on the antibacterial contribution degree to obtain the durable antibacterial analysis result, and antibacterial suggestions are generated. This solves the technical problem of insufficient accuracy of the detection results caused by the single evaluation dimension in the detection process of the antibacterial durability of antibacterial non-woven fabrics in the prior art, and achieves the technical effect of improving the comprehensiveness and accuracy of antibacterial performance detection. Description of the Drawings

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0010] Figure 1 Schematic flowchart of the method for detecting the durable antibacterial performance of the antibacterial non-woven fabric provided by the embodiment of the present application;

[0011] Figure 2 Schematic flowchart of extracting multiple colony image features in the method for detecting the durable antibacterial performance of the antibacterial non-woven fabric provided by the embodiment of the present application. Detailed Embodiments

[0012] By providing a method for detecting the durable antibacterial performance of antibacterial non-woven fabrics, the present application solves the technical problem of insufficient accuracy of the detection results caused by the single evaluation dimension in the detection process of the antibacterial durability of antibacterial non-woven fabrics in the prior art.

[0013] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0014] It should be noted that the terms "include" and "have" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units need not be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products, or devices.

[0015] Examples are as follows Figure 1 As shown, an embodiment of the present application provides a method for detecting the persistent antibacterial performance of antibacterial non-woven fabrics. The method includes:

[0016] Collect multi-dimensional data of the antibacterial non-woven fabric through a data sensing network to obtain a multi-dimensional data set, where the multi-dimensional data set includes multiple environmental data and multiple surface colony image data of the antibacterial non-woven fabric.

[0017] According to the application scenario of the antibacterial non-woven fabric, select appropriate sensors for deployment. These sensors may include temperature sensors, humidity sensors, light sensors, gas sensors, etc., to monitor key parameters such as temperature, humidity, light intensity, and gas composition of the environment where the antibacterial non-woven fabric is located; use image acquisition devices such as high-resolution cameras or microscopes to regularly photograph the surface of the antibacterial non-woven fabric to obtain colony image data; integrate the collected environmental data and surface colony image data to construct a multi-dimensional data set. The multi-dimensional data set contains various data of the antibacterial non-woven fabric at different times and under different environmental conditions, providing a rich information basis for subsequent analysis and evaluation.

[0018] Perform a traversal analysis of the multiple surface colony image data based on the multiple environmental data to extract multiple colony image features.

[0019] Based on the multiple collected environmental data, perform a one-by-one traversal analysis of the surface colony image data, and combine the changes in the environmental data to extract multiple colony image features. These colony image features include, but are not limited to, the area, morphology, distribution density, color change, etc. of the colonies, which are used to comprehensively characterize the growth state of the colonies and their response laws to environmental conditions, providing key support for antibacterial performance analysis.

[0020] Furthermore, as Figure 2 shown, perform a traversal analysis of the multiple surface colony image data based on the multiple environmental data to extract multiple colony image features. The method includes:

[0021] Performing clustering analysis on the multiple surface colony image data according to the multiple environmental data to determine multiple colony image groups, where each of the multiple colony image groups corresponds to an environmental data; traversing the multiple colony image groups based on the multiple environmental data for morphological analysis to determine the colony distribution morphological characteristics; traversing the multiple colony image groups based on the multiple environmental data for density analysis to determine the colony density characteristics; performing image enhancement on the multiple surface colony image data according to the colony distribution morphological characteristics and the colony density characteristics to generate multiple surface colony enhanced images; traversing the multiple surface colony enhanced images for feature analysis to obtain multiple feature vectors, and performing dimensionality reduction and integration on the colony distribution morphological characteristics and the colony density characteristics based on the multiple feature vectors to generate the multiple colony image characteristics.

[0022] Specifically, according to the multiple environmental data collected (such as temperature, humidity, light, etc.), using clustering algorithms (such as K-means, hierarchical clustering, etc.) to perform clustering analysis on the multiple surface colony image data, grouping the colony images according to different conditions of the environmental data (such as grouping the colony images according to environmental data such as temperature, humidity, etc.) to generate multiple colony image groups, where each colony image group corresponds to a specific environmental data. Exemplarily, grouping the colony images according to humidity, dividing them into high humidity (humidity > 80%), medium humidity (humidity 50% - 80%), and low humidity (humidity < 50%). Traversing the multiple colony image groups, performing morphological analysis on the colony images through image processing algorithms (such as edge detection) to extract the colony distribution morphological characteristics, including but not limited to the boundary morphology, irregularity, ductility, etc. of the colonies, to quantify the morphological changes of the colonies; performing density analysis on the multiple colony image groups after clustering, and determining the colony density characteristics in the image by statistics, such as the number of colonies per unit area, colony overlap degree, etc., to evaluate the aggregation degree of the colonies; according to the extracted colony distribution morphological characteristics and colony density characteristics, performing image enhancement processing on the multiple surface colony image data, and using enhancement algorithms (such as edge detection, contrast adjustment, etc.) to generate multiple surface colony enhanced images, enhancing the detail features of the images to make them more suitable for subsequent feature analysis; traversing the multiple surface colony enhanced images, extracting key features to form multiple feature vectors; through feature dimensionality reduction algorithms (such as principal component analysis or t-SNE), performing dimensionality reduction and integration on the extracted colony distribution morphological characteristics and colony density characteristics, removing redundant information, retaining important features, and finally generating the multiple colony image characteristics for subsequent antibacterial performance analysis.

[0023] Furthermore, traversing the multiple surface colony enhanced images for feature analysis to obtain multiple feature vectors, and performing dimensionality reduction and integration on the colony distribution morphological characteristics and the colony density characteristics based on the multiple feature vectors to generate the multiple colony image characteristics, the method includes:

[0024] Traverse the multiple surface colony enhanced images for edge detection, segment the multiple surface colony enhanced images according to the edge detection results, and determine multiple colony region images; perform colony feature combination transformation on the multiple colony region images to generate multiple feature vectors; perform normalization processing on the multiple feature vectors to generate standard feature vectors; use the principal component analysis method to combine the standard feature vectors to reduce the dimensions of the colony distribution morphology features and the colony density features, and generate a colony distribution morphology reduced-dimension feature matrix and a colony density reduced-dimension feature matrix; screen and determine the principal component features according to the standard feature vectors, and based on the principal component features, perform correlation integration on the colony distribution morphology reduced-dimension feature matrix and the colony density reduced-dimension feature matrix to obtain the multiple colony image features.

[0025] Specifically, traverse multiple surface colony enhanced images, apply an edge detection algorithm (such as the Canny or Sobel algorithm) to each image to extract the colony edge features, that is, identify the boundary between the colony and the background; according to the edge detection results, segment the surface colony enhanced images to generate multiple colony region images, and clarify the independent regions and distribution boundaries of the colonies; for the multiple colony region images, extract key features (such as morphological features, texture features, color features, etc.), and perform combination transformation on the extracted multiple features to generate multiple feature vectors, and these feature vectors represent the feature information of each colony region in numerical form; perform normalization processing on the generated multiple feature vectors to map the feature values to a standardized range (such as [0,1] or [-1,1]) to generate standard feature vectors.

[0026] Use principal component analysis (PCA) to perform dimensionality reduction on the standard feature vectors. Specifically, calculate the covariance matrix of the feature vectors; extract the eigenvalues and eigenvectors, and screen the principal components with larger contribution rates; based on the principal components, reduce the dimensions of the colony distribution morphology features and the colony density features to generate a colony distribution morphology reduced-dimension feature matrix and a colony density reduced-dimension feature matrix respectively. According to the principal component features generated by dimensionality reduction, combined with the contribution rates of the standard feature vectors, screen the principal component features with high representational ability; based on the screened principal component features, perform correlation integration on the colony distribution morphology reduced-dimension feature matrix and the colony density reduced-dimension feature matrix; generate multiple colony image features through the integration operation to comprehensively reflect the distribution morphology and density features of the colonies.

[0027] Perform antibacterial analysis on the multiple environmental data on the surface of the antibacterial non-woven fabric according to the multiple colony image features to generate multiple antibacterial correlation coefficients.

[0028] Match the extracted multiple colony image features with the corresponding environmental data (such as temperature, humidity, light intensity, etc.) to establish a mapping relationship between colony features and environmental conditions; through statistical analysis methods (such as regression analysis, correlation analysis, etc.), evaluate the response law of colony image features (such as colony density, morphological distribution, etc.) with the change of environmental data, and quantify the impact of environmental conditions on colony changes; based on the mapping relationship between colony image features and environmental data, use a correlation calculation method (such as Pearson correlation coefficient or Spearman correlation coefficient) to generate multiple antibacterial correlation coefficients to characterize the influence intensity of environmental conditions on the antibacterial performance of antibacterial non-woven fabrics.

[0029] Furthermore, perform antibacterial analysis on the surface of the antibacterial non-woven fabric for the multiple environmental data according to the multiple colony image features to generate multiple antibacterial correlation coefficients. The method includes:

[0030] Perform multiple regression analysis on the multiple environmental data according to the dimensionality-reduced feature matrix of colony distribution morphology and the dimensionality-reduced feature matrix of colony density to obtain multiple regression coefficients; based on the multiple regression coefficients, perform antibacterial evaluation on the surface of the antibacterial non-woven fabric for the multiple environmental data to obtain characteristic influence scores; arrange the multiple environmental data in descending order according to the characteristic influence scores to generate an environmental influence sequence; based on the environmental influence sequence, perform variable screening on the multiple environmental data, determine the environmental influence variables for antibacterial calculation, and generate the multiple antibacterial correlation coefficients.

[0031] Preferably, use a multiple regression analysis method (such as linear regression, ridge regression, lasso regression, etc.), take the dimensionality-reduced feature matrix of colony distribution morphology and the dimensionality-reduced feature matrix of colony density as independent variables, and the environmental data as the dependent variable, perform regression analysis, calculate the influence of each environmental variable on colony features, obtain multiple regression coefficients to quantify the explanatory ability of environmental data on colony feature changes; based on the multiple regression coefficients, evaluate the contribution of each environmental variable to the antibacterial performance on the surface of the antibacterial non-woven fabric, that is, by calculating the absolute value of the regression coefficient or the standardized regression coefficient of each variable, obtain the influence degree of each environmental variable on the antibacterial performance on the surface of the antibacterial non-woven fabric, that is, the characteristic influence score; arrange the multiple environmental data in descending order according to the characteristic influence scores to generate an environmental influence sequence; based on the environmental influence sequence, perform variable screening on the environmental data, and determine the environmental influence variables that have a significant impact on antibacterial performance by setting a threshold (such as the characteristic influence score reaches a certain level).

[0032] Using the selected environmental impact variables and combining with colony characteristics, antibacterial performance calculation is carried out. Specifically, the selected environmental variables (such as temperature, humidity, etc.) are matched with colony characteristics (such as the dimensionality reduction feature matrix of colony distribution morphology, the dimensionality reduction feature matrix of colony density) to form an environmental variable - colony characteristic combination; define antibacterial performance indicators according to actual needs, such as the inhibition rate (the reduction ratio of colony area or density); construct an antibacterial performance calculation model based on the environmental variable - colony characteristic combination, and a linear regression method can be used to quantify the impact of environmental variables on the change of colony characteristics. Exemplarily, where P is the antibacterial performance value, and x i is the environmental variable - colony characteristic combination, and β i is the linear regression coefficient; use the antibacterial performance value to conduct a correlation analysis (such as Pearson correlation coefficient or Spearman correlation coefficient) on the results of each pair of environmental variables and colony characteristics to quantify the impact of environmental variables on colony changes and generate antibacterial correlation coefficients.

[0033] Based on the multiple antibacterial correlation coefficients, conduct antibacterial performance decay modeling, construct an antibacterial decay model, and through the antibacterial decay model, conduct a trend analysis of antibacterial performance and draw an antibacterial performance decay trend curve.

[0034] According to the antibacterial correlation coefficients, construct an antibacterial decay model. Specifically, assume that the antibacterial performance decays over time (or with the change of environmental conditions), which can usually be expressed as P(t) = P0e -kt , where P(t) is the antibacterial performance value at time t, P0 is the initial antibacterial performance value, and k is the decay coefficient. After constructing the antibacterial decay model, conduct a trend analysis of antibacterial performance; calculate the trend of antibacterial performance change over time or with the environment by simulating the antibacterial performance decay in different time periods or different environmental conditions; according to the results of the antibacterial decay model and trend analysis, draw an antibacterial performance decay trend curve, and the antibacterial performance decay trend curve reflects the change trend of antibacterial performance over time or with environmental conditions.

[0035] Furthermore, through the antibacterial decay model, conduct a trend analysis of antibacterial performance and draw an antibacterial performance decay trend curve. The method includes:

[0036] Perform short-term analysis on the antibacterial performance according to the multiple antibacterial correlation coefficients through the antibacterial decay model to determine multiple short-term antibacterial groups; perform long-term analysis on the antibacterial performance according to the multiple antibacterial correlation coefficients through the antibacterial decay model to determine multiple long-term antibacterial groups; perform decay analysis on the multiple short-term antibacterial groups based on the half-life time, and generate a short-term antibacterial performance decay trend curve according to the first analysis result; perform decay analysis on the multiple long-term antibacterial groups based on the half-life time, and generate a long-term antibacterial performance decay trend curve according to the second analysis result; perform cross-validation on the short-term antibacterial performance decay trend curve and the long-term antibacterial performance decay trend curve, and draw the antibacterial performance decay trend curve according to the validation result.

[0037] Perform short-term analysis on the antibacterial performance according to the multiple antibacterial correlation coefficients through the antibacterial decay model. Specifically, according to the short-term changes in environmental data and colony characteristics, determine multiple short-term antibacterial groups, which represent the changes in antibacterial performance within a short period of time. The short-term analysis can focus on the decay process of antibacterial performance in the initial stage.

[0038] Perform long-term analysis on the antibacterial performance according to the multiple antibacterial correlation coefficients through the antibacterial decay model. At this time, considering the long-term stability of environmental data and colony characteristics and their long-term impact on antibacterial performance, determine multiple long-term antibacterial groups, which represent the trends and laws of antibacterial performance decay under long-term environmental conditions.

[0039] Perform decay analysis on the multiple short-term antibacterial groups based on the half-life time; the half-life time represents the time required for the antibacterial performance to decay to half of the initial value; by analyzing the decay process of the short-term antibacterial groups, generate a short-term antibacterial performance decay trend curve according to the first analysis result to show the change trend of antibacterial performance within a short period of time.

[0040] Similarly, perform decay analysis on the multiple long-term antibacterial groups based on the half-life time; under long-term conditions, the decay of antibacterial performance may be affected by other factors (such as environmental changes, material aging, etc.); generate a long-term antibacterial performance decay trend curve according to the second analysis result to show the decay characteristics of antibacterial performance during long-term use.

[0041] Perform cross-validation on the short-term antibacterial performance decay trend curve and the long-term antibacterial performance decay trend curve. Cross-validation can ensure the consistency of short-term and long-term analysis results, and evaluate the accuracy of the antibacterial performance decay model by comparing the differences between the two. Finally, based on the validation result, draw the final antibacterial performance decay trend curve to present the overall trend of antibacterial performance change over time or environmental conditions.

[0042] Calculate the antibacterial contribution according to the antibacterial performance decay trend curve to obtain the antibacterial contribution degree. Analyze the antibacterial persistence of the antibacterial non-woven fabric based on the antibacterial contribution degree to obtain the persistent antibacterial analysis result, and generate antibacterial suggestions.

[0043] The antibacterial contribution degree represents the contribution of the antibacterial performance to the antibacterial effect within a specific time period, and can be calculated by integration or accumulation of the changes in antibacterial performance under different environmental conditions and time periods.

[0044] Based on the antibacterial contribution degree, analyze the antibacterial persistence of the antibacterial non-woven fabric to evaluate the duration and decay rate of the antibacterial performance of the antibacterial non-woven fabric in actual applications; determine the persistence of the antibacterial performance and predict the decay cycle of the antibacterial performance by analyzing the changes in the antibacterial contribution degree; based on the results of the antibacterial persistence analysis, generate antibacterial suggestions, such as material optimization, improvement of environmental adaptability, etc.

[0045] Furthermore, calculate the antibacterial contribution according to the antibacterial performance decay trend curve to obtain the antibacterial contribution degree. The method includes:

[0046] Retrieve the historical colony data record log, traverse the historical colony data record log for time series identification to determine the colony generation time series; extract the initial bacteriostatic rate based on the antibacterial performance decay trend curve, and perform colony accumulation calculation according to the initial bacteriostatic rate combined with the colony generation time series to determine the colony cumulative area data; perform time segment calculation according to the colony cumulative area data combined with the antibacterial performance decay trend curve to obtain the antibacterial efficiency in multiple time periods; integrate according to the colony generation time series based on the antibacterial efficiency in the multiple time periods to generate the antibacterial contribution degree of the antibacterial non-woven fabric.

[0047] Specifically, retrieve the historical colony data record log to obtain the colony growth data at different times. These data usually include information such as colony area and density, and record the specific time of each colony generation; traverse the historical colony data record log and perform time series identification to determine the colony generation time series, that is, the specific time nodes of each colony growth and the corresponding antibacterial performance; based on the antibacterial performance decay trend curve, extract the initial bacteriostatic rate (i.e., the antibacterial ability of the antibacterial non-woven fabric at the initial moment), and then perform colony accumulation calculation according to the initial bacteriostatic rate combined with the colony generation time series; perform time segment calculation according to the colony cumulative area data combined with the antibacterial performance decay trend curve. By dividing into multiple time periods, calculate the antibacterial efficiency in each time period (i.e., the change in antibacterial performance during this period). The antibacterial efficiency reflects the degree of inhibition of the antibacterial performance on colony growth in each period of time; integrate according to the colony generation time series based on the antibacterial efficiency in multiple time periods to calculate the antibacterial contribution degree. The antibacterial contribution degree can be obtained by integrating the antibacterial efficiency in each time period.

[0048] Furthermore, the antibacterial durability analysis of the antibacterial non-woven fabric is carried out according to the antibacterial contribution degree to obtain a durable antibacterial analysis result. The method includes:

[0049] Perform durability calculation based on the antibacterial contribution degree of the antibacterial non-woven fabric and the antibacterial efficiency in the multiple time periods to obtain the durable antibacterial efficiency; perform performance calculation according to the durable antibacterial efficiency to obtain the proportion of long-term performance. Set multiple durable performance indicators according to the proportion of long-term performance; classify the performance of the antibacterial non-woven fabric according to the multiple durable performance indicators to generate multiple performance levels; based on the multiple performance levels, perform durable antibacterial determination to generate an antibacterial determination result, and add the antibacterial determination result to the durable antibacterial analysis result.

[0050] Perform durability calculation based on the antibacterial contribution degree of the antibacterial non-woven fabric and the antibacterial efficiency in multiple time periods to obtain the durable antibacterial efficiency. Specifically, the durable antibacterial efficiency reflects the change of antibacterial performance during long-term use. By integrating and averaging the antibacterial efficiency over the entire use cycle, the continuous effect of antibacterial performance can be quantified. According to the durable antibacterial efficiency, calculate the proportion of long-term performance, which represents the proportion of the antibacterial non-woven fabric having a high antibacterial effect over the entire use cycle; according to the proportion of long-term performance, set multiple durable performance indicators, such as antibacterial duration, antibacterial effect stability, and antibacterial efficiency maintenance rate, etc., to evaluate the durable performance of the antibacterial non-woven fabric; based on these durable performance indicators, classify the performance of the antibacterial non-woven fabric to generate different performance levels (such as excellent, good, poor) to reflect the strength of its antibacterial durability; based on the generated performance levels, perform durable antibacterial determination to determine whether the durable antibacterial ability of the antibacterial non-woven fabric meets the predetermined standard, and add the antibacterial determination result to the durable antibacterial analysis result.

[0051] Furthermore, the method for generating the antibacterial suggestion includes:

[0052] Perform antibacterial analysis based on the historical colony data record log and set the expected antibacterial performance threshold; judge whether the multiple performance levels are greater than or equal to the expected antibacterial performance threshold. If the multiple performance levels are less than the expected antibacterial performance threshold, then generate the antibacterial determination result, and the antibacterial determination result includes a heat map of the spatial distribution of antibacterial performance; calculate the surface antibacterial uniformity data of the antibacterial non-woven fabric according to the heat map of the spatial distribution of antibacterial performance; generate a warning signal according to the surface antibacterial uniformity data, trigger an antibacterial improvement instruction through the warning signal, and perform optimization analysis according to the antibacterial improvement instruction combined with the multiple performance levels to generate the antibacterial suggestion.

[0053] Based on the historical colony data record log, antibacterial performance analysis is carried out. By analyzing the historical data, an expected antibacterial performance threshold is set, which is the minimum standard that the antibacterial performance should reach. It is judged whether multiple performance levels are greater than or equal to the expected antibacterial performance threshold. If the performance level is lower than the expected threshold, an antibacterial determination result is generated. The antibacterial determination result includes a heat map of the spatial distribution of antibacterial performance, showing the distribution of antibacterial effects in different regions. According to the heat map of the spatial distribution of antibacterial performance, the antibacterial uniformity data on the surface of the antibacterial non-woven fabric is calculated. The antibacterial uniformity data can reflect whether the distribution of antibacterial performance on the surface of the non-woven fabric is uniform, ensuring that effective antibacterial effects can be obtained in different parts. Based on the surface antibacterial uniformity data, a warning signal is generated. When the antibacterial effects in some regions do not meet the standards or there are large fluctuations, the warning signal will be triggered. According to the warning signal, an antibacterial improvement instruction is triggered, and optimization analysis is carried out in combination with multiple performance levels. Through the optimization analysis, an improvement plan is determined, such as adjusting the distribution of the bacteriostatic agent, improving the antibacterial characteristics of the material, etc., to obtain antibacterial suggestions, so as to guide the optimization and improvement of the antibacterial non-woven fabric and improve the persistence and uniformity of its antibacterial performance.

[0054] In summary, the embodiments of the present application at least have the following technical effects:

[0055] First, multi-dimensional data of the antibacterial non-woven fabric is collected through a data sensing network to obtain a multi-dimensional data set. The multi-dimensional data set includes multiple environmental data and multiple surface colony image data of the antibacterial non-woven fabric. Then, based on the multiple environmental data, the multiple surface colony image data is traversed and analyzed to extract multiple colony image features. Further, based on the multiple colony image features, antibacterial analysis of the surface of the antibacterial non-woven fabric is carried out on the multiple environmental data to generate multiple antibacterial correlation coefficients. Then, an antibacterial performance decay model is constructed based on the multiple antibacterial correlation coefficients. Through the antibacterial decay model, trend analysis of the antibacterial performance is carried out, and an antibacterial performance decay trend curve is drawn. Finally, antibacterial contribution calculation is carried out according to the antibacterial performance decay trend curve to obtain the antibacterial contribution degree. According to the antibacterial contribution degree, antibacterial persistence analysis of the antibacterial non-woven fabric is carried out to obtain a persistent antibacterial analysis result, and antibacterial suggestions are generated. This solves the technical problem of insufficient accuracy of the detection results caused by the single evaluation dimension in the detection process of the antibacterial performance persistence of the antibacterial non-woven fabric in the prior art, and achieves the technical effect of improving the comprehensiveness and accuracy of the antibacterial performance detection.

[0056] It should be noted that the above sequence of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above specific embodiments of the present specification have been described. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-tasking and parallel processing are also possible or may be advantageous.

[0057] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0058] This specification and the drawings are merely exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A method for detecting the durable antibacterial properties of antibacterial nonwoven fabrics, characterized in that: The method comprises: Performing multi-dimensional data collection on the antibacterial non-woven fabric through a data sensor network to obtain a multi-dimensional data set, wherein the multi-dimensional data set includes a plurality of environmental data and a plurality of surface colony image data of the antibacterial non-woven fabric; Performing traversal analysis on the plurality of surface colony image data based on the plurality of environmental data to extract a plurality of colony image features; Performing antibacterial analysis on the surface of the antibacterial non-woven fabric on the plurality of environmental data according to the plurality of colony image features, and generating a plurality of antibacterial correlation coefficients; Based on the multiple antibacterial correlation coefficients, antibacterial performance attenuation modeling is performed to construct an antibacterial attenuation model, and antibacterial performance trend analysis is performed through the antibacterial attenuation model to draw an antibacterial performance attenuation trend curve; Calculating the antibacterial contribution according to the antibacterial performance attenuation trend curve to obtain the antibacterial contribution degree, analyzing the antibacterial durability of the antibacterial non-woven fabric according to the antibacterial contribution degree to obtain a durable antibacterial analysis result, and generating an antibacterial recommendation; The method of traversing and analyzing the plurality of surface colony image data based on the plurality of environmental data to extract a plurality of colony image features includes: Performing cluster analysis on the plurality of surface colony image data according to the plurality of environmental data to determine a plurality of colony image groups, wherein each of the plurality of colony image groups corresponds to one environmental data; Based on the multiple environmental data, multiple colony image groups are traversed to perform morphological analysis to determine the morphological characteristics of colony distribution; Based on the multiple environmental data, multiple colony image groups are traversed to perform density analysis to determine colony density characteristics; Performing image enhancement on the plurality of surface colony image data according to the colony distribution morphology characteristics and the colony density characteristics to generate a plurality of surface colony enhanced images; The plurality of surface colony enhanced images are traversed to perform feature analysis to obtain a plurality of feature vectors, and based on the plurality of feature vectors, the colony distribution morphological features and the colony density features are integrated by dimensionality reduction to generate the plurality of colony image features.

2. The method for detecting the durable antibacterial performance of the antibacterial nonwoven fabric according to claim 1, characterized in that: Traversing the plurality of surface colony enhanced images for feature analysis to obtain a plurality of feature vectors, and performing dimension reduction integration on the colony distribution morphological features and the colony density features based on the plurality of feature vectors to generate the plurality of colony image features, the method comprising: Traversing the plurality of surface colony enhanced images to perform edge detection, segmenting the plurality of surface colony enhanced images according to the edge detection results, and determining a plurality of colony region images; Perform colony feature combination transformation according to the multiple colony region images to generate multiple feature vectors; Normalizing the multiple feature vectors to generate a standard feature vector; The colony distribution morphology characteristics and the colony density characteristics are reduced in dimension by using the principal component analysis method in combination with the standard feature vector to generate a colony distribution morphology reduction feature matrix and a colony density reduction feature matrix; The principal component features are determined by screening according to the standard feature vectors, and the colony distribution morphology dimension reduction feature matrix and the colony density dimension reduction feature matrix are associated and integrated based on the principal component features to obtain the multiple colony image features.

3. The method for detecting the durable antibacterial performance of the antibacterial nonwoven fabric according to claim 2, characterized in that: According to the multiple colony image features, the multiple environmental data are subjected to antibacterial analysis on the surface of the antibacterial non-woven fabric to generate multiple antibacterial correlation coefficients, and the method includes: Performing a multivariate regression analysis on the plurality of environmental data according to the colony distribution morphology dimension reduction feature matrix and the colony density dimension reduction feature matrix to obtain a multivariate regression coefficient; Based on the multiple regression coefficients, the plurality of environmental data are subjected to an antibacterial evaluation on the surface of the antibacterial nonwoven fabric to obtain a characteristic impact score; Arrange the plurality of environmental data in descending order according to the feature impact scores to generate an environmental impact sequence; The plurality of environmental data are screened for variables based on the environmental impact sequence, environmental impact variables are determined for antibacterial calculation, and the plurality of antibacterial correlation coefficients are generated.

4. The method for detecting the durable antibacterial performance of the antibacterial nonwoven fabric according to claim 1, characterized in that: The antibacterial performance trend analysis is performed by using the antibacterial attenuation model to draw an antibacterial performance attenuation trend curve, and the method includes: Performing short-term analysis according to the multiple antibacterial correlation coefficients using the antibacterial attenuation model to determine multiple short-term antibacterial groups; Performing a long-term analysis according to the multiple antibacterial correlation coefficients using the antibacterial attenuation model to determine multiple long-term antibacterial groups; Performing attenuation analysis on the multiple short-term antibacterial groups based on half-life time, and generating a short-term antibacterial performance attenuation trend curve according to the first analysis result; Performing attenuation analysis on the multiple long-term antibacterial groups based on half-life time, and generating a long-term antibacterial performance attenuation trend curve according to the second analysis result; The short-term antibacterial performance attenuation trend curve is cross-validated with the long-term antibacterial performance attenuation trend curve, and the antibacterial performance attenuation trend curve is drawn according to the validation result.

5. The method for detecting the durable antibacterial performance of the antibacterial nonwoven fabric according to claim 1, characterized in that: The antibacterial contribution is calculated according to the antibacterial performance attenuation trend curve to obtain the antibacterial contribution degree, and the method includes: Retrieving historical colony data record logs, traversing the historical colony data record logs for time sequence identification, and determining the colony generation time sequence; Extracting the initial inhibition rate based on the antibacterial performance attenuation trend curve, performing colony accumulation calculation according to the initial inhibition rate combined with the colony generation time series, and determining the colony accumulation area data; Perform time segment calculation based on the colony cumulative area data combined with the antibacterial performance attenuation trend curve to obtain the antibacterial efficiency in multiple time periods; The antibacterial efficiency in the plurality of time periods is integrated according to the colony generation time series to generate the antibacterial contribution of the antibacterial nonwoven fabric.

6. The method for detecting the durable antibacterial performance of the antibacterial nonwoven fabric according to claim 5, characterized in that: The method of performing antibacterial persistence analysis on the antibacterial non-woven fabric according to the antibacterial contribution to obtain a persistent antibacterial analysis result comprises: Performing a durable calculation based on the antibacterial contribution of the antibacterial non-woven fabric and the antibacterial efficiency in the multiple time periods to obtain a durable antibacterial efficiency; Performing performance calculation according to the long-lasting antibacterial efficiency to obtain a long-lasting performance ratio, and setting a plurality of long-lasting performance indicators according to the long-lasting performance ratio; Classifying the antibacterial nonwoven fabrics according to the multiple durable performance indicators to generate multiple performance grades; A durable antibacterial determination is performed based on the plurality of performance levels, an antibacterial determination result is generated, and the antibacterial determination result is added to the durable antibacterial analysis result.

7. The method for detecting the durable antibacterial performance of the antibacterial nonwoven fabric according to claim 6, characterized in that: Generating the antimicrobial recommendation, the method comprising: Performing antimicrobial analysis based on the historical colony data record log and setting an expected antimicrobial performance threshold; Determine whether the multiple performance levels are greater than or equal to the expected antibacterial performance threshold, and if the multiple performance levels are less than the expected antibacterial performance threshold, generate the antibacterial determination result, wherein the antibacterial determination result includes a heat map of the spatial distribution of antibacterial performance; Calculating surface antibacterial uniformity data of the antibacterial nonwoven fabric according to the antibacterial performance spatial distribution heat map; An early warning signal is generated according to the surface antibacterial uniformity data, an antibacterial improvement instruction is triggered by the early warning signal, and an optimization analysis is performed according to the antibacterial improvement instruction in combination with the multiple performance levels to generate the antibacterial recommendation.

Images