Wet tissue quality control system based on artificial intelligence

Through the artificial intelligence-based wet wipe quality control system, we can identify abnormal indicators of production lines and make automated adjustments. Combined with the visual evaluation module to improve wet wipe quality control, the problem of traditional systems' response delay and insufficient deep learning capabilities is solved, and efficient and accurate Wet wipe production line control and product quality assurance.

CN118938847AInactive Publication Date: 2024-11-12SHANDONG GREEN ENERGY TECH CO LTD

Patent Information

Application Number
CN202411433065.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-15
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional wet wipe quality control systems respond to delays when dealing with quality problems on high-speed production lines, lack of deep learning and real-time feedback capabilities, resulting in reduced production efficiency and poor product quality, especially for wet wipe humidity and thickness deviations and product appearance defects. Untimely identification.

Method used

Adopt artificial intelligence-based wipe quality control system to identify abnormal indicators in production line data through the abnormal data analysis module, adjust key control parameters, and combine the visual evaluation module to extract and classify the wet wipe images, optimize the feedback mechanism to improve the Production line control parameters and image analysis parameters to realize real-time data monitoring and automated adjustment.

Benefits of technology

Accurate identification and rapid adjustment of small deviations in the production line are achieved, significantly reducing dependence on manual inspections, improving production efficiency and product consistency, reducing scrap rate and production costs, and ensuring that product quality meets strict standards.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118938847A_ABST
    Figure CN118938847A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of quality control, in particular to a wet tissue quality control system based on artificial intelligence, which comprises an abnormal data analysis module, a production adjustment module, a visual evaluation module and an optimization feedback module, and collects wet tissue quality data and machine operation state data based on a sensor in a wet tissue production line. By continuously collecting production data and analyzing the production data in real time, tiny deviation on a production line can be accurately recognized, adjustment can be rapidly made, the automatic reaction mechanism remarkably reduces dependence on manual inspection, the production efficiency and the product consistency are improved, the quality standard of each batch of products is ensured through anomaly detection and real-time adjustment, and the production efficiency is improved. The rejection rate and the production cost are effectively reduced, control over the appearance quality of products is further enhanced through application of visual evaluation, it is ensured that each piece of wet tissue meets the strict quality requirement, and an accurate basis is provided for continuous improvement of the production process by means of deep data analysis through optimization of a feedback mechanism.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of quality control, and in particular to a wet wipes quality control system based on artificial intelligence. Background Art

[0002] The wet wipes quality control system is a system specifically used to monitor and ensure the quality standards of the wet wipes production process. Its main purpose is to ensure the consistency and safety of the quality of each batch of wet wipes, including multiple indicators such as humidity, fiber density, and sterility. By using sensors and data processing technology, it can detect any deviations on the production line in real time, and adjust the manufacturing process or mark unqualified products in a timely manner to ensure that consumers can obtain high-quality and safe products.

[0003] Traditional systems rely on regular manual inspections and partially automated equipment, which can delay responses when dealing with sudden quality issues on high-speed production lines. For example, the identification of wet wipes’ moisture and thickness deviations is not timely, resulting in the quality of the entire batch of products being affected. Data analysis in traditional systems is limited to simple statistical evaluations and lacks deep learning and real-time feedback capabilities, which limits the ability to make quick decisions during the production process. This technological gap leads to reduced production efficiency, increased production costs and waste of resources. The lack of real-time visual monitoring also often results in product appearance defects not being identified in a timely manner, which in turn affects product quality. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a wet wipes quality control system based on artificial intelligence.

[0005] In order to achieve the above object, the present invention adopts the following technical solution: a wet wipes quality control system based on artificial intelligence, the system comprising: The abnormal data analysis module collects wet wipes quality data and machine operation status data based on sensors in the wet wipes production line. It collects wet wipes humidity and thickness information, and combines production speed and temperature status to identify abnormal indicators in the data and generate abnormal indicator information. The production adjustment module adjusts the key control parameters of the wet wipes production line based on the abnormal indicator information, including the humidity controller, heating controller and speed controller parameters, and evaluates the adjusted control parameters, verifies the adjustment reaction effect by simulating the production situation, and generates adjustment verification results; The visual assessment module uses a camera to capture images of wet wipes on the production line based on the adjustment and verification results, extracts features from the captured images, assesses the texture and folding quality of the wet wipes, and classifies each wet wipe according to the quality standards to generate a quality classification record; The optimization feedback module counts the wet wipes marked as unqualified based on the quality classification records, analyzes the proportion and defect types of unqualified wet wipes, adjusts and optimizes production line control parameters, data monitoring and image analysis parameters according to the analysis results, and generates a control parameter tuning log.

[0006] The present invention is improved in that the step of obtaining the abnormal indicator information is specifically as follows: Based on the sensors in the wet wipes production line, real-time data collection is carried out, including wet wipes humidity, wet wipes thickness, production speed and temperature status, and preliminary data sorting and standardization are carried out to generate a preliminary sensor data set; Based on the preliminary sensor dataset, a Z-score normalization was applied to each data point using the formula: , Determine the degree of bias in the data and generate a standardized set of data points where represents the observed value, is the mean of the data set, is the standard deviation of the data set, is the adjustment factor, used to optimize the standard deviation effect, Represents the Z score of a data point; Outliers are identified on the standardized data point set, and data points with an absolute value of Z score greater than 2 are identified. , mark the data point as abnormal and obtain abnormal indicator information.

[0007] The present invention is improved in that the adjustment steps of the key control parameters are specifically as follows: Analyzing the abnormal indicator information, including humidity, heating and speed data, determining deviations from current production standards, and generating deviation analysis information; Based on the deviation analysis information, the formula is used: , Adjust the parameters of the humidity controller, heating controller and speed controller to obtain new control parameter settings, where: Indicates new parameter settings. It is the old parameter setting. is the sensitivity coefficient of the target humidity, is the standard deviation of the historical deviation, is the target humidity, is the current humidity.

[0008] The present invention is improved in that the step of obtaining the adjustment verification result is specifically as follows: Apply new control parameters to simulate production tests, monitor key production indicators, including wet wipes humidity, heating efficiency and speed, collect real-time data, and obtain production test data; Based on the production test data, statistical analysis is performed to verify the effectiveness of the control parameter adjustment, using the formula: , The adjustment verification effect is obtained, where is the score of the difference between the means before and after adjustment, and Represent the average production indicators before and after adjustment, and represents the corresponding sample variance, and Represents the new and old sample sizes.

[0009] The present invention is improved in that the step of extracting features from the captured image is specifically as follows: Based on the adjustment verification result, configure the camera to capture the wet wipes image on the production line, and adjust the light and camera angle settings to generate the wet wipes original image; Applying image processing technology to process the original wet wipes image, including contrast adjustment, grayscale conversion and noise filtering, to optimize the analysis applicability of the image and generate optimized image data; The optimized image data is subjected to feature extraction using the formula: , Calculate the clarity index of image texture ,in, and is the width and height of the image, and The images are and Directional gradient.

[0010] The present invention is improved in that the steps of obtaining the quality classification record are specifically as follows: Using the feature-extracted data, the texture and folding features of each wet wipe are evaluated, compared with the quality standards and classified to generate a preliminary quality rating result; Based on the preliminary quality rating results, the formula is used: , Calculate the mass fraction of each wipe , get the quality classification record, where, is the score of the texture clarity of the wipes. represents the folding quality score, is the target threshold for quality control, and is the weight coefficient, is a constant used to normalize the result.

[0011] The present invention is improved in that the steps for analyzing the proportion and defect types of unqualified wet wipes are specifically as follows: Based on the quality classification records, extracting information about unqualified wet wipes from production data, including defect information and quality scores of each wet wipe, to obtain a list of unqualified wet wipes; Based on the list of unqualified wipes, the formula is used: , Calculate the ratio of the total number of unqualified wet wipes to the production process to obtain the ratio information of unqualified wet wipes, where: Indicates the percentage of non-conforming products, is the number of substandard wipes, is the total number of wipes produced; Based on the unqualified wet wipes ratio information, the defect types are analyzed, including the distribution of texture and folding defects and the occurrence rate in the unqualified wet wipes, to generate defect type analysis results.

[0012] The present invention is improved in that the steps of obtaining the control parameter tuning log are specifically as follows: Based on the analysis results, determine the key control parameters that affect product quality, including the operating speed of the production line, heating temperature and humidity level, collect the current settings and performance of the parameters, and obtain a list of parameters to be adjusted; Based on the list of parameters to be adjusted, detailed adjustments are made using the formula: , Get the optimal parameter settings, where is the optimized parameter value, is the current parameter setting, is the target quality, Indicates the deviation between the current product quality and the target quality; Based on the optimal parameter settings, the adjustment effects are tracked through real-time data monitoring, and it is analyzed whether each parameter change optimizes product quality. Each adjusted data is continuously recorded to obtain a control parameter tuning log.

[0013] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by continuously collecting production data and analyzing it in real time, it is possible to accurately identify slight deviations on the production line and make rapid adjustments. This automated response mechanism significantly reduces reliance on manual inspections, improves production efficiency and product consistency, and anomaly detection and real-time adjustments ensure the quality standards of each batch of products, effectively reducing scrap rates and production costs. The application of visual evaluation further enhances control over product appearance quality, ensuring that each wet wipe meets strict quality requirements, while the optimized feedback mechanism uses deep data analysis to provide an accurate basis for continuous improvement of production processes, fundamentally improving control efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a system flow chart of the present invention; Figure 2 This is a flowchart for obtaining abnormal indicator information in the present invention; Figure 3 This is a flow chart for adjusting key control parameters in the present invention; Figure 4 A flowchart for obtaining the adjustment verification result in the present invention; Figure 5 A flow chart of feature extraction for a captured image in the present invention; Figure 6 A flowchart for obtaining quality classification records in the present invention; Figure 7 It is a flow chart for analyzing the proportion and defect types of unqualified wet wipes in the present invention; Figure 8 This is a flow chart for obtaining the control parameter tuning log in the present invention. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with 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.

[0016] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0017] See also Figure 1The present invention provides a technical solution: a wet wipes quality control system based on artificial intelligence includes: The abnormal data analysis module collects wet wipes quality data and machine operation status data based on sensors in the wet wipes production line. It collects wet wipes humidity and thickness information, and combines production speed and temperature status to identify abnormal indicators in the data and generate abnormal indicator information. The production adjustment module adjusts the key control parameters of the wet wipes production line based on abnormal indicator information, including humidity controller, heating controller and speed controller parameters, and evaluates the adjusted control parameters. The evaluation verifies the adjustment response effect by simulating production conditions and generates adjustment verification results. Based on the adjustment and verification results, the visual assessment module uses a camera to capture images of wet wipes on the production line, extracts features from the captured images, evaluates the texture and folding quality of the wet wipes, and classifies each wet wipe against the quality standards to generate quality classification records; The optimization feedback module counts the wet wipes marked as unqualified based on the quality classification records, analyzes the proportion and defect types of unqualified wet wipes, adjusts and optimizes the production line control parameters, data monitoring and image analysis parameters according to the analysis results, and generates a control parameter tuning log.

[0018] The adjustment verification results specifically include parameter adjustment effect, production stability, and adjustment response time. The quality classification records include texture qualification rating, folding integrity inspection, qualified product identification results, and unqualified product screening results. The control parameter tuning log includes parameter adjustment records, defect type analysis results, and optimization effect evaluation results.

[0019] See also Figure 2 ,The specific steps for obtaining abnormal indicator information are: Based on the sensors in the wet wipes production line, real-time data collection is carried out, including wet wipes humidity, wet wipes thickness, production speed and temperature status, and preliminary data sorting and standardization are carried out to generate a preliminary sensor data set; Data collection is carried out based on the sensor devices on the wet wipes production line. The deployment of sensors involves various key production nodes, including humidity control, thickness measurement points, speed monitoring points and temperature sensing areas. The sensors at each point are used to capture specific types of data. For example, the humidity sensor is installed near the discharge port to ensure that the humidity of the product meets the standard specifications. The thickness measurement is carried out immediately after the cutting machine to confirm the consistency of each batch of products. The speed sensor records the running speed of the material to ensure the continuity and efficiency of the production process. The temperature sensor is arranged in the drying area and the cooling area to monitor the key heat treatment process. The collected data will be sorted and standardized in format to ensure the consistency and availability of all data, thereby generating a preliminary sorted sensor data set.

[0020] Based on the preliminary sensor dataset, a Z-score was applied to normalize each data point using the formula: , Determine the degree of bias in the data and generate a standardized set of data points where represents the observed value, is the mean of the data set, is the standard deviation of the data set, is the adjustment factor, used to optimize the standard deviation effect, is a constant to prevent division by zero errors, Represents the Z score of a data point; A set of data is collected: , calculate its average value and standard deviation ,set up and , the calculation process is as follows: calculate , Apply a Z-score to each data point, right The Z score is: ; right The Z score is: ; right The Z score is: ; right The Z score is: ; right The Z score is: ; The results show that there are no data points , all data points are not identified as abnormal, effectively helping to identify behaviors within the normal fluctuation range of the data.

[0021] Perform outlier identification on the standardized data point set and identify data points with an absolute value of Z score greater than 2, that is, , identify the data point as abnormal and obtain abnormal indicator information; According to the outlier identification process of the standardized data point set, the data is processed by the aforementioned standardization. As a criterion for anomaly detection, the Z score here refers to the deviation of a data point from the collective data mean after standard deviation adjustment. In this process, each data point is calculated individually and compared with the threshold. The identified outliers are marked and recorded. The records are then used for further analysis, such as quality control and production adjustments, to ensure consistent product quality and optimized production efficiency.

[0022] See also Figure 3 , the adjustment steps of key control parameters are as follows: Analyze abnormal indicator information, including humidity, heating and speed data, determine deviations from current production standards, and generate deviation analysis information; Analyze the abnormal indicator information, focusing on the data of humidity, heating and speed. The data shows the deviation from the set production standards. Through statistical analysis of the centralization and dispersion trends of the data, confirm which control parameters deviate greatly. For example, the humidity controller may have inaccurate readings due to sensor failure or environmental changes, and the speed controller may have its accuracy affected by mechanical wear. Generate a deviation analysis report, which lists in detail the differences between the current value and the target value of each control parameter, providing a basis for the next parameter adjustment.

[0023] Based on the deviation analysis information, the formula is used: , Adjust the parameters of the humidity controller, heating controller and speed controller to obtain new control parameter settings, where: Indicates new parameter settings. It is the old parameter setting. is the sensitivity coefficient of the target humidity, is the standard deviation of the historical deviation, is the target humidity, is the current humidity.

[0024] Monitor the current humidity controller parameters The target humidity is 50. The current humidity is 30%. is 35%, the standard deviation of historical deviation is 3%, is 5; Calculate the ratio of sensitivity to standard deviation: ; Calculate the adjustment value for the difference between target and current humidity: ; Calculate new control parameters: ; This result indicates that the adjusted control parameter of 41.65 will help the humidity controller get closer to the target setting and reduce product error.

[0025] See also Figure 4 , the specific steps for obtaining the adjustment verification results are as follows: Apply new control parameters to simulate production tests, monitor key production indicators, including wet wipes humidity, heating efficiency and speed, collect real-time data, and obtain production test data; A simulated production test was conducted, which mainly targeted the newly adjusted control parameters, with special attention paid to the performance of the humidity controller, heating controller and speed controller. Data on key performance indicators were collected, which will be used to evaluate the influence and applicability of the new parameters. The changes in each indicator were recorded through real-time monitoring to ensure the accuracy and completeness of the data. At the same time, data collection equipment was used to ensure that the data obtained could reflect the actual production status. A data report containing humidity level, heating efficiency and machine speed adjustment response was generated, which will serve as the basis for evaluating the effect of the new control parameters and provide the necessary input information for the next step of data analysis.

[0026] Based on the production test data, statistical analysis is performed to verify the effectiveness of the control parameter adjustment, using the formula: , The adjustment verification effect is obtained, where is the score of the difference between the means before and after adjustment, and Represent the average production indicators before and after adjustment, and represents the corresponding sample variance, and Represents the new and old sample sizes.

[0027] The average production speeds before and after adjustment are / hour and / hour, and the sample variances are and The sample sizes are and ; Calculate the variance of each group of data divided by the sample size: , ; Calculate the denominator: ; Calculate the final value: ; The results show that the production speed after adjustment has been significantly improved compared with that before adjustment, indicating that the setting of new control parameters has effectively improved production efficiency.

[0028] See also Figure 5 , the steps for feature extraction of the captured image are as follows: Based on the adjustment and verification results, configure the camera to capture the wet wipes images on the production line, and adjust the light and camera angle settings to generate the original wet wipes images; Configuring a high-resolution camera to capture images of wet wipes on the production line ensures image clarity, lays the foundation for subsequent feature extraction, and generates high-quality original images. By adjusting the camera's light and angle, the image capture conditions are optimized to ensure that the details of the image are fully displayed, which is crucial for subsequent image processing and analysis. The image data obtained will directly affect the effect and accuracy of feature extraction, thereby determining the next step of image preprocessing strategies and methods.

[0029] Apply image processing technology to process the original wet wipes image, including contrast adjustment, grayscale and noise filtering, to optimize the analysis applicability of the image and generate optimized image data; Image processing technology is applied to the original image, including contrast adjustment, grayscale processing and noise removal. The processing optimizes the quality of the image data, making it more suitable for detailed feature analysis and obtaining optimized image data. The application of processing technology is to enhance important features in the image, such as edges and textures, which is critical for machine learning algorithms to recognize and classify objects in the image. The optimized image will be used for more accurate feature extraction, thereby improving the efficiency and accuracy of the entire quality inspection.

[0030] The optimized image data is subjected to feature extraction using the formula: , Calculate the clarity index of image texture ,in, and is the width and height of the image, and The images are and Directional gradient.

[0031] The following data was collected: The image size is Pixel width and Pixel height, the gradient of a point is calculated and , substitute into the formula: Calculate the square root of the sum of the squared gradients for each pixel: ; Compute the average of the total gradients: ; The results show that the texture clarity score of the image is 25, which represents the average clarity level of the image texture and provides a quantitative method to evaluate the texture and surface quality of wet wipes.

[0032] See also Figure 6 , the specific steps for obtaining quality classification records are as follows: Using the feature-extracted data, the texture and folding features of each wet wipe are evaluated, compared with the quality standards and classified to generate preliminary quality rating results; After extracting texture and folding feature data from the wet wipes, the data is processed to ensure that each feature is quantified, providing the necessary basis for quality assessment. By comparing with the quality standards, the machine learning model can effectively classify each wet wipe, including scoring each feature data and comparing the score with the set quality threshold. The scoring includes calculating texture clarity, folding uniformity and other relevant quality indicators. Each wet wipe is assigned a quality grade based on the indicators. The grade reflects the overall quality of the wet wipe, ensuring that only products that meet the standards can enter the next step of sales or further processing, generating preliminary quality rating results.

[0033] Based on the preliminary quality rating results, the formula is used: , Calculate the mass fraction of each wipe , get the quality classification record, where, is the score of the texture clarity of the wipes. represents the folding quality score, is the target threshold for quality control, and is the weight coefficient, reflecting the importance of the difference feature in quality assessment, is a constant used to normalize the results to prevent the scores from being too high or too low; The following data was collected: ; ; ; and ; ; Compute the weighted sum of texture and fold scores: ; Calculate the quality score: ; The results showed that the comprehensive quality score was 8.3, reflecting the performance of the wipes in terms of texture and folding quality, and the degree of matching with the quality standards, providing a basis for quality classification and ensuring the effectiveness of product quality control and improvement.

[0034] See also Figure 7 The specific steps for analyzing the proportion and defect types of unqualified wet wipes are as follows: Based on the quality classification records, extract the information of unqualified wet wipes from the production data, including the defect information and quality score of each wet wipe, and obtain the list of unqualified wet wipes; Based on the existing quality classification records, all wet wipes data marked as unqualified are extracted, including the defect information and rating results of each wet wipe. The data extraction process involves data query and data screening to ensure that detailed information of all unqualified products is accurately obtained from a large amount of production data, generating a data set containing specific defect types and quantities.

[0035] Based on the list of unqualified wipes, the formula is used: , Calculate the ratio of the total number of unqualified wet wipes to the production process to obtain the ratio information of unqualified wet wipes, where: Indicates the percentage of non-conforming products, is the number of substandard wipes, is the total number of wipes produced; The following data were collected, the total number of production 5000 wet wipes, of which unqualified wet wipes is 300; Calculate the unqualified ratio: , The results indicate that 6% of the wipes in the current production batches do not meet quality standards, pointing out quality control issues that require attention during the production process.

[0036] Based on the information on the proportion of unqualified wet wipes, analyze the defect types, including the distribution of texture and folding defects and their occurrence rate in unqualified wet wipes, and generate defect type analysis results; Using the obtained unqualified proportion data, we further analyzed the defect types in the unqualified wet wipes. The frequency of occurrence of each defect type was analyzed through classification and statistical methods, including unclear texture, incorrect folding and other types. The statistics of each defect were not only based on the quantity, but also took into account its proportion in the unqualified wet wipes, thereby revealing the main production problems. The analysis process relies on data processing and analysis technology to ensure the accuracy and reliability of the results, and generate an analysis log including the main defect types and descriptions.

[0037] See also Figure 8 , the specific steps for obtaining the control parameter tuning log are: Based on the analysis results, determine the key control parameters that affect product quality, including the production line's operating speed, heating temperature, and humidity level, collect the current settings and performance of the parameters, and obtain a list of parameters to be adjusted; Based on the analysis of unqualified wipes, we collect control parameter data related to quality defects, such as humidity setting, temperature control and line speed adjustment. The parameters directly affect the product qualification rate. Through systematic data collection methods, we integrate the current control parameters, record the set value and real-time performance of each parameter, provide basic information for subsequent adjustments, and generate a list of parameters to be optimized.

[0038] Based on the list of parameters to be adjusted, make detailed adjustments using the formula: , Get the optimal parameter settings, where is the optimized parameter value, is the current parameter setting, is the target quality, Indicates the deviation between the current product quality and the target quality; The following data was collected: is 50; 90%; is -10%; Calculate the new parameters: , The results show that through adjustment, the new control parameters should be adjusted to 55.55 in order to improve the production quality.

[0039] Based on the optimal parameter settings, the adjustment effect is tracked through real-time data monitoring, and each parameter change is analyzed to see whether it optimizes product quality. Each adjusted data is continuously recorded to obtain a control parameter tuning log; After adjusting the control parameters, implement control tests to verify the effectiveness of the new parameter settings, continuously track the parameter adjustment effects through data monitoring to ensure that each adjustment has a significant improvement in product quality, adjust the strategy through real-time data feedback, and form a control parameter tuning log. The log records the entire process from parameter analysis to optimization implementation, providing support for continuous improvement of production line efficiency and product quality.

[0040] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. Wet wipes quality control system based on artificial intelligence, It is characterized in that The system comprises: The abnormal data analysis module collects wet wipes quality data and machine operation status data based on sensors in the wet wipes production line. It collects wet wipes humidity and thickness information, and combines production speed and temperature status to identify abnormal indicators in the data and generate abnormal indicator information. The production adjustment module adjusts the key control parameters of the wet wipes production line based on the abnormal indicator information, including the humidity controller, heating controller and speed controller parameters, and evaluates the adjusted control parameters, verifies the adjustment reaction effect by simulating the production situation, and generates adjustment verification results; The visual assessment module uses a camera to capture images of wet wipes on the production line based on the adjustment and verification results, extracts features from the captured images, assesses the texture and folding quality of the wet wipes, and classifies each wet wipe according to the quality standards to generate a quality classification record; The optimization feedback module counts the wet wipes marked as unqualified based on the quality classification records, analyzes the proportion and defect types of unqualified wet wipes, adjusts and optimizes production line control parameters, data monitoring and image analysis parameters according to the analysis results, and generates a control parameter tuning log.

2. According to the artificial intelligence-based wet wipes quality control system of claim 1, It is characterized in that The steps for obtaining the abnormal indicator information are specifically as follows: Based on the sensors in the wet wipes production line, real-time data collection is carried out, including wet wipes humidity, wet wipes thickness, production speed and temperature status, and preliminary data sorting and standardization are carried out to generate a preliminary sensor data set; Based on the preliminary sensor dataset, a Z-score normalization was applied to each data point using the formula: , Determine the degree of bias in the data and generate a standardized set of data points where represents the observed value, is the mean of the data set, is the standard deviation of the data set, is the adjustment factor used to optimize the standard deviation effect, represents the Z score of a data point; Outliers are identified on the standardized data point set, and data points with an absolute value of Z score greater than 2 are identified. , mark the data point as abnormal and obtain abnormal indicator information.

3. According to the artificial intelligence-based wet wipes quality control system of claim 1, It is characterized in that The adjustment steps of the key control parameters are specifically as follows: Analyzing the abnormal indicator information, including humidity, heating and speed data, determining deviations from current production standards, and generating deviation analysis information; Based on the deviation analysis information, the formula is used: , Adjust the parameters of the humidity controller, heating controller and speed controller to obtain new control parameter settings, where: Indicates new parameter settings. It is the old parameter setting. is the sensitivity coefficient of the target humidity, is the standard deviation of the historical deviation, is the target humidity, is the current humidity.

4. The wet wipes quality control system based on artificial intelligence according to claim 1, It is characterized in that The steps for obtaining the adjustment verification result are specifically as follows: Apply new control parameters to simulate production tests, monitor key production indicators, including wet wipes humidity, heating efficiency and speed, collect real-time data, and obtain production test data; Based on the production test data, statistical analysis is performed to verify the effectiveness of the control parameter adjustment, using the formula: , The adjustment verification effect is obtained, where is the score of the difference between the means before and after adjustment, and Represent the average production indicators before and after adjustment, and represents the corresponding sample variance, and Represents the new and old sample sizes.

5. The wet wipes quality control system based on artificial intelligence according to claim 1, It is characterized in that The step of extracting features from the captured image is specifically as follows: Based on the adjustment verification result, configure the camera to capture the wet wipes image on the production line, and adjust the light and camera angle settings to generate the wet wipes original image; Applying image processing technology to process the original wet wipes image, including contrast adjustment, grayscale conversion and noise filtering, to optimize the analysis applicability of the image and generate optimized image data; The optimized image data is subjected to feature extraction using the formula: , Calculate the clarity index of image texture ,in, and is the width and height of the image, and The images are and Directional gradient.

6. The wet wipes quality control system based on artificial intelligence according to claim 1, It is characterized in that The steps for obtaining the quality classification record are specifically as follows: Using the feature-extracted data, the texture and folding features of each wet wipe are evaluated, compared with the quality standards and classified to generate a preliminary quality rating result; Based on the preliminary quality rating results, the formula is used: , Calculate the mass fraction of each wet wipe , get the quality classification record, where, is the score of the texture clarity of the wipes. represents the folding quality score, is the target threshold for quality control, and is the weight coefficient, is a constant used to normalize the result.

7. The wet wipes quality control system based on artificial intelligence according to claim 1, It is characterized in that The specific steps for analyzing the proportion and defect types of unqualified wet wipes are as follows: Based on the quality classification records, extracting information about unqualified wet wipes from production data, including defect information and quality scores of each wet wipe, to obtain a list of unqualified wet wipes; Based on the list of unqualified wipes, the formula is used: , Calculate the ratio of the total number of unqualified wet wipes to the production process to obtain the ratio information of unqualified wet wipes, where: Indicates the percentage of non-conforming products, is the number of substandard wipes, is the total number of wipes produced; Based on the unqualified wet wipes ratio information, the defect types are analyzed, including the distribution of texture and folding defects and the occurrence rate in the unqualified wet wipes, to generate defect type analysis results.

8. The wet wipes quality control system based on artificial intelligence according to claim 1, It is characterized in that The steps for obtaining the control parameter tuning log are specifically as follows: Based on the analysis results, determine the key control parameters that affect product quality, including the operating speed of the production line, heating temperature and humidity level, collect the current settings and performance of the parameters, and obtain a list of parameters to be adjusted; Based on the list of parameters to be adjusted, detailed adjustments are made using the formula: , Get the optimal parameter settings, where is the optimized parameter value, is the current parameter setting, is the target quality, Indicates the deviation between the current product quality and the target quality; Based on the optimal parameter settings, the adjustment effects are tracked through real-time data monitoring, and it is analyzed whether each parameter change optimizes product quality. Each adjusted data is continuously recorded to obtain a control parameter tuning log.

Citation Information

Patent Citations

  • Paper product production quality intelligent inspection method and system

    CN112557406A

  • Textile detection method and system based on machine vision

    CN117115147A

  • Control system and method for silicone sealant production

    CN118550263A

  • Method and system for upgrading and optimizing production parameters of plastic pin gun

    CN118707908A

  • Digital twin object processing system and method

    CN118747479A

Cited By

  • Dynamic production line measurement and control method and system based on visual identification

    CN119169010A

  • Dynamic production line measurement and control method and system based on visual recognition

    CN119169010B

  • Food safety detection management and control method and system based on artificial intelligence

    CN119691637A

  • Intelligent control system for feed production

    CN119717729A

  • Sanitary napkin comfort optimization system based on AI intelligent analysis

    CN119845824A