Control management method and system for bedding article production process

Abstract

The invention provides a control management method and system for a bedding article production process, and relates to the technical field of bedding article production, potential defects are found and prevented in time by collecting and analyzing cloth parameters in the production process in real time, and meanwhile the types and numerical values of the possible defects are predicted by means of a correlation prediction model, so that the production efficiency is improved. Therefore, production parameters are adjusted in advance, and product quality stability is ensured. In addition, the method can dynamically adjust the detection threshold according to the associated estimated data, improves the detection efficiency, reduces manual intervention and human errors through intelligent production equipment, and improves the production efficiency and reliability. Under the combined action of the measures, the number of defective products is remarkably reduced, the reworking and scrapping cost is reduced, and meanwhile the resource utilization rate and the production efficiency are improved; and finally, through analysis and early warning of production data, timely and accurate information support is provided for production managers, and scientific production decision making is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of bedding production, and in particular to a control and management method and system for a bedding production process. Background Art

[0002] As an important part of the home textile industry, the control and management of bedding production process is directly related to product quality, production efficiency and cost-effectiveness. However, in the actual production process, the bedding production process faces many challenges.

[0003] In the production process of bedding, the control of fabric parameters (such as textile density, color difference, size, etc.) is crucial. However, due to the lack of precise monitoring and control methods in traditional production processes, the control of fabric parameters is inaccurate, affecting the quality and stability of the product. During the production process, due to the influence of various factors, bedding may have potential defects, such as uneven sewing and excessive color difference. These defects are often difficult to detect in time by naked eyes or traditional detection methods, resulting in a decrease in product qualification rate and increased rework and scrap costs. In traditional production processes, the adjustment of production parameters often depends on manual experience and judgment. However, due to the subjectivity and uncertainty of manual judgment, the adjustment of production parameters is often untimely or inaccurate, affecting production efficiency and product quality.

[0004] Therefore, it is necessary to provide a control and management method and system for the bedding production process to solve the above-mentioned technical problems. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a control and management method and system for a bedding production process for solving the problems of inaccurate control of fabric parameters and difficulty in discovering potential defects in the production process of bedding.

[0006] The present invention provides a control and management method for a bedding production process, the management method comprising the following steps: Obtain historical data on the bedding production process, and use data association analysis methods to analyze the correlation between fabric parameters in the historical data and the corresponding defects, as well as the correlation between the defects, and establish a correlation prediction model; According to the preset collection cycle, the data of the current bedding production process is collected, wherein the data of the bedding production process specifically includes fabric weaving density, color difference, size and pattern alignment; Based on the data collected during the current bedding production process, the current cycle detection defect data is determined according to the preset initial detection threshold; The current cycle detection defect data is input into the associated prediction model. The associated prediction model outputs associated prediction data based on the input current cycle detection defect data, wherein the associated prediction data specifically includes defect type and defect value; Based on the associated estimated data, determine whether to dynamically adjust the initial detection threshold. If it is determined that the initial detection threshold is to be dynamically adjusted, detect the data collected in the bedding production process in a subsequent collection cycle according to the adjusted detection threshold to obtain the detection defect data of the subsequent collection cycle. The defect data detected in the current cycle and the defect data detected in the subsequent acquisition cycle are analyzed to obtain analysis results, and early warning notifications are issued based on the analysis results, and parameter adjustment suggestions are generated at the same time.

[0007] Preferably, the historical data of the bedding production process is obtained, and the correlation between the fabric parameters in the historical data and the corresponding defects, as well as the correlation between the defects, is analyzed by a data correlation analysis method to establish a correlation prediction model, and the specific steps are: Collect information on fabric parameters and defects that occur during the production process from the historical records of bedding production, where fabric parameters specifically include fabric weaving density, color difference, size and pattern alignment, and defects specifically include poor sewing, stains, color difference and holes; Preprocess the collected information on fabric parameters and defect information that occurs during the production process, remove outliers and missing values, and organize the data set; Through the data association analysis method, the association relationship between each fabric parameter and defect in the data set is identified to obtain the association analysis results; Based on the association analysis results, the association prediction model is obtained by training the neural network model.

[0008] Preferably, the data in the current bedding production process is collected according to a preset collection cycle, wherein the data in the bedding production process specifically includes fabric weaving density, color difference, size and pattern alignment, and the specific steps are: Set the collection level for the speed and output of the production line in the production process, including low level and high level, and set the corresponding collection cycle for low level and high level respectively; Through sensors and camera intelligent devices, fabric parameters in the production process are automatically collected according to the set collection cycle. The fabric parameters specifically include fabric textile density, color difference, size and pattern alignment.

[0009] Preferably, the method of determining the current cycle detection defect data based on the collected data in the current bedding production process according to a preset initial detection threshold value comprises the following specific steps: Set initial detection thresholds for fabric weave density, color difference, size, and pattern alignment; The collected fabric parameters during the production process are compared with the initial detection thresholds of fabric textile density, color difference, size and pattern alignment to obtain comparison results; The fabric parameters exceeding the initial detection threshold in the comparison results are identified and marked as the defect data of the current cycle detection.

[0010] Preferably, based on the associated estimated data, it is determined whether to dynamically adjust the initial detection threshold. If it is determined that the initial detection threshold is dynamically adjusted, the data collected in the bedding production process in a subsequent collection cycle is detected according to the adjusted detection threshold to obtain the detection defect data of the subsequent collection cycle. The specific steps are: Preset an adjustment threshold and set an adjustment strategy, wherein the adjustment strategy is specifically that if it is determined that the value of each defect in the associated estimated data does not exceed the adjustment threshold, the adjustment of the detection threshold will not be triggered; and if it is determined that the associated estimated data reaches the adjustment threshold or exceeds the preset adjustment threshold, the adjustment of the detection threshold will be triggered; When it is determined that the associated estimated data reaches the adjustment threshold or exceeds the preset adjustment threshold, the adjustment strategy is triggered, that is, the detection threshold is adjusted up or down to obtain the adjusted detection threshold; The data collected during the bedding production process in a subsequent collection cycle is tested according to the adjusted detection threshold value to obtain detection defect data for a subsequent collection cycle.

[0011] Preferably, the analysis obtains the current cycle detection defect data and the subsequent acquisition cycle detection defect data, obtains the analysis result, and issues an early warning notification based on the analysis result, and generates parameter adjustment suggestions, and the specific steps are: Combining the obtained defect data detected in the current cycle with the defect data detected in the subsequent acquisition cycle, identifying the change trend of the defect data through a data analysis method, and obtaining an analysis result of the change trend; Based on the analysis results of the change trend, it is identified that the defect data exceeds the preset warning data section, and a warning notification is issued in time; Based on the analysis results of the changing trends, specific parameter adjustment suggestions are estimated and generated, including adjusting the fabric parameters.

[0012] A control and management system for a bedding production process, the management system comprising: The model building module is used to obtain historical data of the bedding production process, analyze the correlation between the fabric parameters in the historical data and the corresponding defects, as well as the correlation between the defects, and establish a correlation prediction model through data correlation analysis methods; A data collection module is used to collect data in the current bedding production process according to a preset collection cycle, wherein the data in the bedding production process specifically includes fabric textile density, color difference, size and pattern alignment; A data detection module is used to determine the current cycle detection defect data based on the collected data in the current bedding production process and according to a preset initial detection threshold; The estimation analysis module is used to input the current cycle detection defect data into the associated estimation model. The associated estimation model outputs associated estimation data based on the input current cycle detection defect data, wherein the associated estimation data specifically includes defect type and defect value; An adjustment and detection module, which is used to determine whether to dynamically adjust the initial detection threshold based on the associated estimated data. If it is determined that the initial detection threshold is to be dynamically adjusted, the data collected in the bedding production process in a subsequent collection cycle is detected according to the adjusted detection threshold to obtain the detection defect data of the subsequent collection cycle; The early warning and generation module is used to analyze the current cycle detection defect data and the subsequent collection cycle detection defect data, obtain analysis results, and issue early warning notifications based on the analysis results, while generating parameter adjustment suggestions.

[0013] Compared with the related art, the control and management method and system of the bedding production process provided by the present invention have the following beneficial effects: The present invention timely discovers and prevents potential defects by real-time collection and analysis of fabric parameters in the production process, and predicts the types of defects and their values ​​that may occur with the help of the associated prediction model, so as to adjust the production parameters in advance and ensure the stability of product quality. In addition, the method can also dynamically adjust the detection threshold according to the associated prediction data to improve the detection efficiency, and reduce manual intervention and human errors through intelligent production equipment, thereby improving production efficiency and reliability; these measures work together to significantly reduce the number of defective products, reduce rework and scrap costs, and improve resource utilization and production efficiency; finally, through the analysis and early warning of production data, it provides timely and accurate information support for production managers, which helps to make scientific production decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a flow chart of a control and management method of a bedding production process of the present invention; Figure 2 This is a system block diagram of a control and management system for a bedding production process of the present invention. DETAILED DESCRIPTION

[0015] The present invention will be further described below in conjunction with the accompanying drawings and implementation modes.

[0016] Embodiment 1: like Figure 1 As shown, a control and management method for a bedding production process specifically comprises the following steps: S100, obtaining historical data of the bedding production process, analyzing the correlation between fabric parameters in the historical data and corresponding defects, as well as the correlation between the defects, through a data correlation analysis method, and establishing a correlation prediction model; S200, collecting data in the current bedding production process according to a preset collection cycle, wherein the data in the bedding production process specifically includes fabric weaving density, color difference, size, and pattern alignment; S300, based on the data collected in the current bedding production process, according to the preset initial detection threshold, determine the current cycle detection defect data; S400, inputting the current cycle detection defect data into the associated prediction model, and the associated prediction model outputs associated prediction data according to the input current cycle detection defect data, wherein the associated prediction data specifically includes defect type and defect value; S500: Based on the associated estimated data, determine whether to dynamically adjust the initial detection threshold; if it is determined that the initial detection threshold is to be dynamically adjusted, detect the data collected in the bedding production process in a subsequent collection cycle according to the adjusted detection threshold to obtain the detection defect data of the subsequent collection cycle; S600: Analyze the obtained current cycle detection defect data and the subsequent acquisition cycle detection defect data to obtain analysis results, issue an early warning notification based on the analysis results, and generate parameter adjustment suggestions.

[0017] In the specific implementation process, the specific steps of step S100 are: S101. Collecting information on fabric parameters and defect information occurring during the production process from the historical records of bedding production, wherein the fabric parameters specifically include fabric weaving density, color difference, size, and pattern alignment, and the defects specifically include poor sewing, stains, color difference, and holes; Specifically, by consulting production records, quality inspection reports, and consumer feedback, we collect information on fabric parameters and defects that occur during the production process, and classify and organize them to form a structured data set for subsequent analysis; S102, preprocessing the collected information on fabric parameters and defect information occurring during the production process, removing abnormal values ​​and missing values, and arranging to obtain a data set; Specifically, the collected information on fabric parameters and defect information that occurred during the production process are preprocessed, and statistical methods or machine learning algorithms are used to detect outliers in the data set and mark or delete them. Missing values ​​are processed by interpolation, mean filling, or deletion of samples containing missing values ​​to ensure the accuracy and completeness of the data set. It should be noted that outliers may be caused by equipment failure, operational errors, or measurement errors, which will interfere with subsequent data analysis; and missing values ​​may be caused by incomplete records or data loss, which also need to be processed; S103, identifying the correlation between each fabric parameter and the defect in the data set through a data correlation analysis method, and obtaining a correlation analysis result; Specifically, in this embodiment, the association rules between the fabric parameters and the defects are identified by using the association rule mining algorithm, specifically the Apriori algorithm, and the Pearson correlation coefficient or the Spearman rank correlation coefficient in the correlation analysis is used to quantify the correlation between the fabric parameters and the defects, thereby obtaining the association analysis result; For example, in this embodiment, through association rule mining, it is found that when the fabric textile density is lower than 160 threads / inch, the probability of poor sewing and holes increases significantly. At the same time, through correlation analysis, it is found that there is a significant positive correlation between the color difference value and the stain defect, that is, the larger the color difference value, the higher the probability of the stain defect; S104, based on the association analysis results, using a neural network model to train and obtain an association prediction model; Specifically, in this embodiment, a multi-layer perceptron (MLP) neural network model is selected for training. During the training process, fabric parameters (such as textile density, color difference, etc.) are used as input features, and defect types and their values ​​are used as output targets. After multiple iterative trainings, an associated prediction model is finally obtained.

[0018] In the specific implementation process, the specific steps of step S200 are: S201, setting a collection level for the speed and output of the production line in the production process, specifically including a low level and a high level, and setting corresponding collection cycles for the low level and the high level respectively; Specifically, based on the product production standards of the production line, the collection level is set for the speed and output of the production line in the production process, respectively: the low-level collection level is used for the situation where the production line speed is slow and the output is low. At this time, a long collection cycle is set to reduce the frequency of data collection and reduce interference with the production process; the high-level collection level is used for the situation where the production line speed is fast and the output is high. At this time, a short collection cycle is set to ensure the real-time and accuracy of the data; For example, during the production process, the system identifies that the production line is fast and has a high output, so it decides to set a high level of collection level and a short collection cycle, specifically collecting data every 5 minutes, to ensure the real-time and accuracy of the data, and provide strong support for subsequent quality control and optimization; while if the production line is slow and has a low output, a long collection cycle is set, specifically collecting data every 20 minutes; S202, automatically collecting fabric parameters in the production process according to a set collection cycle through sensors and camera intelligent devices, where the fabric parameters specifically include fabric weaving density, color difference, size, and pattern alignment; Specifically, intelligent devices such as sensors and cameras are configured in advance according to the actual situation of the production line and the requirements of the collection level. Then, the fabric parameter data is automatically collected through intelligent devices such as sensors and cameras according to the set collection cycle, and the collected data is stored in the database for subsequent analysis and processing.

[0019] In the specific implementation process, the specific steps of step S300 are: S301, setting initial detection thresholds for fabric textile density, color difference, size and pattern alignment; Specifically, based on historical data and customer standards, an initial detection threshold is set. For example, in this embodiment, the initial detection threshold of textile density is set to 180 strands / inch, the initial detection threshold of color difference is set to 0.5, the initial detection threshold of size is set to allow a deviation of ±2%, and the initial detection threshold of pattern alignment is set to allow a deviation of ±1 mm. S302, comparing the collected fabric parameters in the production process with the initial detection thresholds of fabric weaving density, color difference, size and pattern alignment to obtain comparison results; Specifically, the fabric parameters are monitored in real time using automated testing equipment and software, and compared with the initial testing thresholds. The comparison results are presented in the form of data tables, charts or alarm messages, and the comparison results are recorded for reference in subsequent quality analysis and optimization. For example, during the production process, the automated detection equipment and software monitor in real time that the textile density of a batch of fabrics is 175 strands / inch, the color difference is 0.6, the size is 2.18 meters x 2.38 meters, and the pattern alignment has a deviation of ±2 mm; after comparing these fabric parameters with the initial detection threshold, it is found that the textile density and color difference both exceed the initial detection threshold, so it is judged as unqualified; at the same time, although the size and pattern alignment are close, they are still within the allowable range, so they are judged as qualified; S303, identifying the fabric parameters exceeding the initial detection threshold in the comparison results, and marking them as the current cycle detection defect data; Specifically, by checking the comparison results and data tables, the fabric parameters that exceed the initial detection threshold are identified. Then, the quality inspection software is used to mark and record the fabric parameters that exceed the initial detection threshold. This data is used as the inspection defect data for the current cycle and will be used for subsequent quality analysis and improvement to ensure continuous improvement in product quality and production efficiency.

[0020] In the specific implementation process, the specific steps of step S500 are: S501, presetting an adjustment threshold and setting an adjustment strategy, wherein the adjustment strategy is specifically that if it is determined that the value of each defect in the associated estimated data does not exceed the adjustment threshold, then the adjustment of the detection threshold is not triggered; and if it is determined that the associated estimated data reaches the adjustment threshold or exceeds the preset adjustment threshold, then the adjustment of the detection threshold is triggered; S502: When it is determined that the associated estimated data reaches an adjustment threshold or exceeds a preset adjustment threshold, an adjustment strategy is triggered, that is, the detection threshold is adjusted upward or downward to obtain an adjusted detection threshold; Specifically, when the associated estimated data reaches or exceeds the adjustment threshold, the adjustment strategy is triggered to increase or decrease the detection threshold. It should be noted that the detection threshold is dynamically adjusted according to the changes in the current production status to ensure the continuous improvement of product quality and production efficiency. Secondly, the adjustment range and direction are determined based on the situation of the associated estimated data in the production process; Exemplarily, in this embodiment, when the textile density deviation in the associated estimated data exceeds 5%, the estimated product quality will be greatly reduced. Therefore, the adjustment threshold of the textile density deviation is set to 5%. At the same time, an adjustment strategy is formulated: when the textile density deviation in the associated estimated data reaches or exceeds 5%, the adjustment strategy is triggered, and the detection threshold is lowered by 1% to strengthen the monitoring of the textile density; S503, testing the data collected in the bedding production process in a subsequent collection cycle according to the adjusted detection threshold, and obtaining detection defect data in a subsequent collection cycle; Specifically, automated testing equipment and software are used to test data collected during the bedding production process in a subsequent collection cycle based on the adjusted detection threshold.

[0021] In the specific implementation process, the specific steps of step S600 are: S601, combining the obtained current cycle detection defect data and the subsequent acquisition cycle detection defect data, identifying the change trend of the defect data through a data analysis method, and obtaining an analysis result of the change trend; Specifically, using the data analysis software or analysis tools in the data analysis method, the defect data detected in the current cycle and the defect data detected in the subsequent acquisition cycle are processed and analyzed to identify the change trend of the defect data, and the analysis results of the change trend are presented in the form of charts, reports, etc. for reference and use in subsequent steps; S602, based on the analysis result of the change trend, it is identified that the defect data exceeds the preset warning data section, and a warning notification is issued in time; Specifically, based on customer needs or industry standards, set warning data segments; when defect data reaches or exceeds the preset threshold or data interval, the warning mechanism is automatically triggered to send a warning notice to relevant personnel. The warning notice is sent through various means such as email, SMS or instant messaging software to ensure that relevant personnel can receive it in time and take corresponding measures; In this embodiment, the warning data section of the fabric is set, that is, the number of scratches does not exceed 100 per week, and the color difference area does not exceed 5% of the total area; For example, through comparative analysis, when it is found that the number of scratches in the current cycle in the defect data has decreased but still exceeds 100, an early warning notification can be immediately issued to the person in charge of the production line; S603, based on the analysis results of the change trend, generate specific parameter adjustment suggestions, including adjusting fabric parameters; Specifically, according to the analysis results of the change trend, the relationship between the defect data and the production parameters is analyzed using data analysis software or tools to identify the key factors affecting product quality. Then, based on the key factors affecting product quality, specific parameter adjustment suggestions are estimated and generated; For example, if, based on the analysis results of the changing trend, it is identified that the number of scratches in the current cycle in the defect data exceeds the warning data segment, and it is identified that the scratch positions are fixed and the cause is the friction with machine parts during the transmission process, then the specific parameter adjustment suggestions are estimated to be: increase the thickness of the fabric and increase the gap parameters of the conveying device.

[0022] Embodiment 2: like Figure 2 As shown, a control and management system for a bedding production process specifically includes: The model building module is used to obtain historical data of the bedding production process, analyze the correlation between the fabric parameters in the historical data and the corresponding defects, as well as the correlation between the defects, and establish a correlation prediction model through data correlation analysis methods; A data collection module is used to collect data in the current bedding production process according to a preset collection cycle, wherein the data in the bedding production process specifically includes fabric textile density, color difference, size and pattern alignment; A data detection module is used to determine the current cycle detection defect data based on the collected data in the current bedding production process and according to a preset initial detection threshold; The estimation analysis module is used to input the current cycle detection defect data into the associated estimation model. The associated estimation model outputs associated estimation data based on the input current cycle detection defect data, wherein the associated estimation data specifically includes defect type and defect value; An adjustment and detection module, which is used to determine whether to dynamically adjust the initial detection threshold based on the associated estimated data. If it is determined that the initial detection threshold is to be dynamically adjusted, the data collected in the bedding production process in a subsequent collection cycle is detected according to the adjusted detection threshold to obtain the detection defect data of the subsequent collection cycle; The early warning and generation module is used to analyze the current cycle detection defect data and the subsequent collection cycle detection defect data, obtain analysis results, and issue early warning notifications based on the analysis results, while generating parameter adjustment suggestions.

[0023] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0024] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0025] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. A control and management method for a bedding production process, characterized in that: The management method comprises the following steps: Obtain historical data on the bedding production process, and use data association analysis methods to analyze the correlation between fabric parameters in the historical data and the corresponding defects, as well as the correlation between the defects, and establish a correlation prediction model; According to the preset collection cycle, data in the current bedding production process is collected, wherein the data in the bedding production process specifically includes fabric textile density, color difference, size and pattern alignment; Based on the data collected during the current bedding production process, the current cycle detection defect data is determined according to the preset initial detection threshold; The current cycle detection defect data is input into the associated prediction model. The associated prediction model outputs associated prediction data based on the input current cycle detection defect data, wherein the associated prediction data specifically includes defect type and defect value; Based on the associated estimated data, determine whether to dynamically adjust the initial detection threshold. If it is determined that the initial detection threshold is to be dynamically adjusted, detect the data collected in the bedding production process in a subsequent collection cycle according to the adjusted detection threshold to obtain the detection defect data of the subsequent collection cycle. The defect data detected in the current cycle and the defect data detected in the subsequent acquisition cycle are analyzed to obtain analysis results, and early warning notifications are issued based on the analysis results, and parameter adjustment suggestions are generated at the same time.

2. A control and management method for a bedding production process according to claim 1, characterized in that: The historical data of the bedding production process is obtained, and the correlation between the fabric parameters in the historical data and the corresponding defects, as well as the correlation between the defects, is analyzed by a data correlation analysis method to establish a correlation prediction model. The specific steps are as follows: Collect information on fabric parameters and defects that occur during the production process from the historical records of bedding production, where fabric parameters specifically include fabric weaving density, color difference, size and pattern alignment, and defects specifically include poor sewing, stains, color difference and holes; Preprocess the collected information on fabric parameters and defect information that occurs during the production process, remove outliers and missing values, and organize the data set; Through the data association analysis method, the association relationship between each fabric parameter and defect in the data set is identified to obtain the association analysis results; Based on the association analysis results, the association prediction model is obtained by training the neural network model.

3. A control and management method for a bedding production process according to claim 1, characterized in that: The data of the current bedding production process is collected according to the preset collection cycle, wherein the data of the bedding production process specifically includes fabric weaving density, color difference, size and pattern alignment, and the specific steps are: Set the collection level for the speed and output of the production line in the production process, including low level and high level, and set the corresponding collection cycle for low level and high level respectively; Through sensors and camera intelligent devices, fabric parameters in the production process are automatically collected according to the set collection cycle. The fabric parameters specifically include fabric textile density, color difference, size and pattern alignment.

4. A method for controlling and managing a bedding production process according to claim 1, characterized in that: Based on the data collected in the current bedding production process, according to the preset initial detection threshold, the current cycle detection defect data is judged, and the specific steps are as follows: Set initial detection thresholds for fabric weave density, color difference, size, and pattern alignment; The collected fabric parameters during the production process are compared with the initial detection thresholds of fabric textile density, color difference, size and pattern alignment to obtain comparison results; The fabric parameters exceeding the initial detection threshold in the comparison results are identified and marked as the defect data of the current cycle detection.

5. The control and management method for a bedding production process according to claim 1, characterized in that: Based on the associated estimated data, it is determined whether to dynamically adjust the initial detection threshold. If it is determined that the initial detection threshold is dynamically adjusted, the data collected in the bedding production process in a subsequent collection cycle is detected according to the adjusted detection threshold to obtain the detection defect data of the subsequent collection cycle. The specific steps are: Preset an adjustment threshold and set an adjustment strategy, wherein the adjustment strategy is specifically that if it is determined that the value of each defect in the associated estimated data does not exceed the adjustment threshold, the adjustment of the detection threshold will not be triggered; and if it is determined that the associated estimated data reaches the adjustment threshold or exceeds the preset adjustment threshold, the adjustment of the detection threshold will be triggered; When it is determined that the associated estimated data reaches the adjustment threshold or exceeds the preset adjustment threshold, the adjustment strategy is triggered, that is, the detection threshold is adjusted up or down to obtain the adjusted detection threshold; The data collected during the bedding production process in a subsequent collection cycle is tested according to the adjusted detection threshold value to obtain detection defect data for a subsequent collection cycle.

6. A method for controlling and managing a bedding production process according to claim 1, characterized in that: The defect data of the current cycle detected and the defect data of the subsequent acquisition cycle detected obtained by the analysis are analyzed to obtain analysis results, and an early warning notification is issued according to the analysis results, and a parameter adjustment suggestion is generated at the same time. The specific steps are as follows: Combining the obtained defect data detected in the current cycle with the defect data detected in the subsequent acquisition cycle, identifying the change trend of the defect data through a data analysis method, and obtaining an analysis result of the change trend; Based on the analysis results of the change trend, it is identified that the defect data exceeds the preset warning data section, and a warning notification is issued in time; Based on the analysis results of the changing trends, specific parameter adjustment suggestions are estimated and generated, including adjusting the fabric parameters.

7. A control and management system for a bedding production process, applied to a control and management method for a bedding production process according to any one of claims 1 to 6, characterized in that: The management system comprises: The model building module is used to obtain historical data of the bedding production process, analyze the correlation between the fabric parameters in the historical data and the corresponding defects, as well as the correlation between the defects, and establish a correlation prediction model through data correlation analysis methods; A data collection module is used to collect data in the current bedding production process according to a preset collection cycle, wherein the data in the bedding production process specifically includes fabric textile density, color difference, size and pattern alignment; A data detection module is used to determine the current cycle detection defect data based on the collected data in the current bedding production process and according to a preset initial detection threshold; The estimation analysis module is used to input the current cycle detection defect data into the associated estimation model. The associated estimation model outputs associated estimation data based on the input current cycle detection defect data, wherein the associated estimation data specifically includes defect type and defect value; An adjustment and detection module, which is used to determine whether to dynamically adjust the initial detection threshold based on the associated estimated data. If it is determined that the initial detection threshold is dynamically adjusted, the data collected in the bedding production process in a subsequent collection cycle is detected according to the adjusted detection threshold to obtain the detection defect data of the subsequent collection cycle; The early warning and generation module is used to analyze the current cycle detection defect data and the subsequent collection cycle detection defect data, obtain analysis results, and issue early warning notifications based on the analysis results, while generating parameter adjustment suggestions.

Images